diff --git a/.vscode/settings.json b/.vscode/settings.json index fb6b857de..81aeee0e2 100644 --- a/.vscode/settings.json +++ b/.vscode/settings.json @@ -39,6 +39,7 @@ "colocalisation", "contig", "diffpval", + "Ensembl", "eqtl", "finngen", "GCST", diff --git a/docs/python_api/datasets/molecular_complex.md b/docs/python_api/datasets/molecular_complex.md new file mode 100644 index 000000000..492aeafbe --- /dev/null +++ b/docs/python_api/datasets/molecular_complex.md @@ -0,0 +1,5 @@ +--- +title: Molecular Complex +--- + +::: gentropy.dataset.molecular_complex.MolecularComplex diff --git a/docs/python_api/datasources/_datasources.md b/docs/python_api/datasources/_datasources.md index db32e75da..9091414ab 100644 --- a/docs/python_api/datasources/_datasources.md +++ b/docs/python_api/datasources/_datasources.md @@ -14,6 +14,11 @@ This section contains information about the data source harmonisation tools avai 1. [GTEx (eQTL catalogue)](eqtl_catalogue/_eqtl_catalogue.md) 2. [UKB PPP (EUR)](ukb_ppp_eur/_ukb_ppp_eur.md) +3. [deCODE proteomics](deCODE/_decode.md) + +## Protein complexes + +1. [Complex Portal](complex_portal/_complex_portal.md) ## Interaction / Interval-based Experiments @@ -39,5 +44,4 @@ This section contains information about the data source harmonisation tools avai ## Biological samples -1. [Uberon](biosample_ontologies/_uberon.md) -2. [Cell Ontology](biosample_ontologies/_cell_ontology.md) +1. [Uberon and Cell Ontology](biosample_ontologies/_biosample_ontologies.md) diff --git a/docs/python_api/datasources/complex_portal/_complex_portal.md b/docs/python_api/datasources/complex_portal/_complex_portal.md new file mode 100644 index 000000000..56a7e2ab9 --- /dev/null +++ b/docs/python_api/datasources/complex_portal/_complex_portal.md @@ -0,0 +1,14 @@ +--- +title: Complex Portal +--- + +[Complex Portal](https://www.ebi.ac.uk/complexportal/) is a manually curated resource of macromolecular complexes maintained by EMBL-EBI. It provides two complementary datasets: + +- **Experimental** – complexes with direct experimental evidence. +- **Predicted** – computationally predicted complexes. + +Both files are distributed in the **ComplexTAB** flat-file format and are filtered to human complexes (NCBI taxonomy ID 9606) during ingestion. + +The resulting `MolecularComplex` dataset is used downstream in the deCODE proteomics pipeline to annotate multi-protein SomaScan aptamers with a `molecularComplexId`. + +::: gentropy.datasource.complex_portal.ComplexTab diff --git a/docs/python_api/datasources/deCODE/.pages b/docs/python_api/datasources/deCODE/.pages new file mode 100644 index 000000000..79df30837 --- /dev/null +++ b/docs/python_api/datasources/deCODE/.pages @@ -0,0 +1,6 @@ +nav: + - _decode.md + - manifest.md + - aptamer_metadata.md + - study_index.md + - summary_stats.md diff --git a/docs/python_api/datasources/deCODE/_decode.md b/docs/python_api/datasources/deCODE/_decode.md new file mode 100644 index 000000000..611b27073 --- /dev/null +++ b/docs/python_api/datasources/deCODE/_decode.md @@ -0,0 +1,15 @@ +--- +title: deCODE proteomics +--- + +[deCODE proteomics](https://www.nature.com/articles/s41586-023-06563-x) is a large-scale proteomics dataset generated by deCODE genetics, a biopharmaceutical company based in Iceland. The dataset includes measurements of protein levels in blood samples from thousands of individuals (up to ~36,000 Icelandic participants), using the SomaScan aptamer-based platform. + +Two sub-datasets are provided: + +- **RAW** (`deCODE-proteomics-raw`): non-SMP-normalised SomaScan measurements. +- **SMP** (`deCODE-proteomics-smp`): SMP-normalised SomaScan measurements. + +For a full description of the dataset and methods, refer to [Eldjarn et al., 2023](https://www.nature.com/articles/s41586-023-06563-x). + +::: gentropy.datasource.decode.deCODEDataSource +::: gentropy.datasource.decode.deCODEPublicationMetadata diff --git a/docs/python_api/datasources/deCODE/aptamer_metadata.md b/docs/python_api/datasources/deCODE/aptamer_metadata.md new file mode 100644 index 000000000..65c4b2d1a --- /dev/null +++ b/docs/python_api/datasources/deCODE/aptamer_metadata.md @@ -0,0 +1,5 @@ +--- +title: deCODE Aptamer Metadata +--- + +::: gentropy.datasource.decode.aptamer_metadata.AptamerMetadata diff --git a/docs/python_api/datasources/deCODE/manifest.md b/docs/python_api/datasources/deCODE/manifest.md new file mode 100644 index 000000000..3023cd243 --- /dev/null +++ b/docs/python_api/datasources/deCODE/manifest.md @@ -0,0 +1,5 @@ +--- +title: deCODE manifest +--- + +::: gentropy.datasource.decode.manifest.deCODEManifest diff --git a/docs/python_api/datasources/deCODE/study_index.md b/docs/python_api/datasources/deCODE/study_index.md new file mode 100644 index 000000000..152142d07 --- /dev/null +++ b/docs/python_api/datasources/deCODE/study_index.md @@ -0,0 +1,6 @@ +--- +title: deCODE Study Index +--- + +::: gentropy.datasource.decode.study_index.deCODEStudyIdParts +::: gentropy.datasource.decode.study_index.deCODEStudyIndex diff --git a/docs/python_api/datasources/deCODE/summary_stats.md b/docs/python_api/datasources/deCODE/summary_stats.md new file mode 100644 index 000000000..2b9494689 --- /dev/null +++ b/docs/python_api/datasources/deCODE/summary_stats.md @@ -0,0 +1,6 @@ +--- +title: deCODE Summary Statistics +--- + +::: gentropy.datasource.decode.summary_statistics.deCODEHarmonisationConfig +::: gentropy.datasource.decode.summary_statistics.deCODESummaryStatistics diff --git a/docs/python_api/steps/biosample_index_step.md b/docs/python_api/steps/biosample_index_step.md index d8f7abbb4..bbe4864f8 100644 --- a/docs/python_api/steps/biosample_index_step.md +++ b/docs/python_api/steps/biosample_index_step.md @@ -1,5 +1,5 @@ --- -title: biosample_index +title: Biosample Index Generation --- ::: gentropy.biosample_index.BiosampleIndexStep diff --git a/docs/python_api/steps/colocalisation.md b/docs/python_api/steps/colocalisation.md index 76ecf7150..17a0dfd9a 100644 --- a/docs/python_api/steps/colocalisation.md +++ b/docs/python_api/steps/colocalisation.md @@ -1,5 +1,5 @@ --- -title: colocalisation +title: Colocalisation --- ::: gentropy.colocalisation.ColocalisationStep diff --git a/docs/python_api/steps/credible_set_qc_step.md b/docs/python_api/steps/credible_set_qc_step.md index 2999115e7..c7ac08e60 100644 --- a/docs/python_api/steps/credible_set_qc_step.md +++ b/docs/python_api/steps/credible_set_qc_step.md @@ -1,5 +1,5 @@ --- -title: credible_set_qc +title: Credible Set Quality Control --- ::: gentropy.credible_set_qc.CredibleSetQCStep diff --git a/docs/python_api/steps/decode_ingestion.md b/docs/python_api/steps/decode_ingestion.md new file mode 100644 index 000000000..5af577a3a --- /dev/null +++ b/docs/python_api/steps/decode_ingestion.md @@ -0,0 +1,5 @@ +--- +title: deCODE ingestion +--- + +::: gentropy.decode_ingestion diff --git a/docs/python_api/steps/eqtl_catalogue.md b/docs/python_api/steps/eqtl_catalogue.md index 32f2aa257..4f79b9352 100644 --- a/docs/python_api/steps/eqtl_catalogue.md +++ b/docs/python_api/steps/eqtl_catalogue.md @@ -1,5 +1,5 @@ --- -title: eQTL Catalogue +title: eQTL Catalogue ingestion --- ::: gentropy.eqtl_catalogue.EqtlCatalogueStep diff --git a/docs/python_api/steps/finngen_studies.md b/docs/python_api/steps/finngen_studies.md index 1ec4394f4..aa8b2e0c6 100644 --- a/docs/python_api/steps/finngen_studies.md +++ b/docs/python_api/steps/finngen_studies.md @@ -1,5 +1,5 @@ --- -title: finngen_studies +title: FinnGen Study Index generation --- ::: gentropy.finngen_studies.FinnGenStudiesStep diff --git a/docs/python_api/steps/finngen_sumstat_preprocess.md b/docs/python_api/steps/finngen_sumstat_preprocess.md index 57f27658e..988437d9e 100644 --- a/docs/python_api/steps/finngen_sumstat_preprocess.md +++ b/docs/python_api/steps/finngen_sumstat_preprocess.md @@ -1,5 +1,5 @@ --- -title: finngen_sumstat_preprocess +title: Finngen Summary Statistics Ingestion --- ::: gentropy.finngen_sumstat_preprocess.FinnGenSumstatPreprocessStep diff --git a/docs/python_api/steps/finngen_ukbb_mvp_meta_step.md b/docs/python_api/steps/finngen_ukbb_mvp_meta_step.md index b0759c1de..a6ca66208 100644 --- a/docs/python_api/steps/finngen_ukbb_mvp_meta_step.md +++ b/docs/python_api/steps/finngen_ukbb_mvp_meta_step.md @@ -1,5 +1,5 @@ --- -title: FinnGen UKBB MVP Meta Analysis Step +title: FinnGen UKBB MVP Meta Analysis ingestion --- ::: gentropy.finngen_ukb_mvp_meta.FinngenUkbMvpMetaSummaryStatisticsIngestionStep diff --git a/docs/python_api/steps/gwas_catalog_curation.md b/docs/python_api/steps/gwas_catalog_curation.md index 8512e39fc..548a49c7a 100644 --- a/docs/python_api/steps/gwas_catalog_curation.md +++ b/docs/python_api/steps/gwas_catalog_curation.md @@ -1,5 +1,5 @@ --- -title: gwas_catalog_study_curation +title: GWAS Catalog Study Curation --- ::: gentropy.gwas_catalog_study_curation.GWASCatalogStudyCurationStep diff --git a/docs/python_api/steps/gwas_catalog_study_index.md b/docs/python_api/steps/gwas_catalog_study_index.md index 4984de2a0..73a2f00a9 100644 --- a/docs/python_api/steps/gwas_catalog_study_index.md +++ b/docs/python_api/steps/gwas_catalog_study_index.md @@ -1,5 +1,5 @@ --- -title: gwas_catalog_study_inclusion +title: GWAS Catalog Study Inclusion --- ::: gentropy.gwas_catalog_study_index.GWASCatalogStudyIndexGenerationStep diff --git a/docs/python_api/steps/gwas_catalog_sumstat_preprocess.md b/docs/python_api/steps/gwas_catalog_sumstat_preprocess.md index 3b0422050..8af7a3ee4 100644 --- a/docs/python_api/steps/gwas_catalog_sumstat_preprocess.md +++ b/docs/python_api/steps/gwas_catalog_sumstat_preprocess.md @@ -1,5 +1,5 @@ --- -title: gwas_catalog_sumstat_preprocess +title: GWAS Catalog Summary Statistics ingestion --- ::: gentropy.gwas_catalog_sumstat_preprocess.GWASCatalogSumstatsPreprocessStep diff --git a/docs/python_api/steps/gwas_catalog_top_hits.md b/docs/python_api/steps/gwas_catalog_top_hits.md index 03d81eafb..260b6c18e 100644 --- a/docs/python_api/steps/gwas_catalog_top_hits.md +++ b/docs/python_api/steps/gwas_catalog_top_hits.md @@ -1,5 +1,5 @@ --- -title: GWAS Catalog Top Hits Ingestion Step +title: GWAS Catalog Top Hits ingestion --- ::: gentropy.gwas_catalog_top_hits.GWASCatalogTopHitIngestionStep diff --git a/docs/python_api/steps/ld_clump.md b/docs/python_api/steps/ld_clump.md index fea44f807..d3b46a972 100644 --- a/docs/python_api/steps/ld_clump.md +++ b/docs/python_api/steps/ld_clump.md @@ -1,5 +1,5 @@ --- -title: ld_based_clumping +title: Linkage Disequilibrium Based Clumping --- ::: gentropy.ld_based_clumping.LDBasedClumpingStep diff --git a/docs/python_api/steps/ld_index.md b/docs/python_api/steps/ld_index.md index d8f61a528..46b860e16 100644 --- a/docs/python_api/steps/ld_index.md +++ b/docs/python_api/steps/ld_index.md @@ -1,5 +1,5 @@ --- -title: GnomAD Linkage data ingestion +title: GnomAD Linkage Disequilibrium Index generation --- ::: gentropy.gnomad_ingestion.LDIndexStep diff --git a/docs/python_api/steps/locus_breaker_clumping.md b/docs/python_api/steps/locus_breaker_clumping.md index 1e49234e3..5b0fa5ac9 100644 --- a/docs/python_api/steps/locus_breaker_clumping.md +++ b/docs/python_api/steps/locus_breaker_clumping.md @@ -1,5 +1,5 @@ --- -title: locus_breaker_clumping +title: Locus Breaker Clumping --- ::: gentropy.locus_breaker_clumping.LocusBreakerClumpingStep diff --git a/docs/python_api/steps/molecular_complex.md b/docs/python_api/steps/molecular_complex.md new file mode 100644 index 000000000..b95554fb6 --- /dev/null +++ b/docs/python_api/steps/molecular_complex.md @@ -0,0 +1,5 @@ +--- +title: Molecular complex ingestion +--- + +::: gentropy.molecular_complex diff --git a/docs/python_api/steps/pics.md b/docs/python_api/steps/pics.md index aacc6fbaf..5654489f6 100644 --- a/docs/python_api/steps/pics.md +++ b/docs/python_api/steps/pics.md @@ -1,5 +1,5 @@ --- -title: pics +title: PICS --- ::: gentropy.pics.PICSStep diff --git a/docs/python_api/steps/pqtl_study.md b/docs/python_api/steps/pqtl_study.md new file mode 100644 index 000000000..24a856553 --- /dev/null +++ b/docs/python_api/steps/pqtl_study.md @@ -0,0 +1,5 @@ +--- +title: pQTL study index transformation +--- + +::: gentropy.pqtl_study diff --git a/docs/python_api/steps/summary_statistics_qc.md b/docs/python_api/steps/summary_statistics_qc.md index a9fea12b9..efad2685f 100644 --- a/docs/python_api/steps/summary_statistics_qc.md +++ b/docs/python_api/steps/summary_statistics_qc.md @@ -1,5 +1,5 @@ --- -title: summary_statistics_qc +title: Summary Statistics QC --- ::: gentropy.sumstat_qc_step.SummaryStatisticsQCStep diff --git a/docs/python_api/steps/ukb_ppp_eur_sumstat_preprocess.md b/docs/python_api/steps/ukb_ppp_eur_sumstat_preprocess.md index 4dd74f1df..28be1f6f5 100644 --- a/docs/python_api/steps/ukb_ppp_eur_sumstat_preprocess.md +++ b/docs/python_api/steps/ukb_ppp_eur_sumstat_preprocess.md @@ -1,5 +1,5 @@ --- -title: ukb_ppp_eur_sumstat_preprocess +title: UKB PPP EUR Summary Statistics ingestion --- ::: gentropy.ukb_ppp_eur_sumstat_preprocess.UkbPppEurStep diff --git a/docs/python_api/steps/variant_annotation_step.md b/docs/python_api/steps/variant_annotation_step.md index 2b5582df4..f5184b3f1 100644 --- a/docs/python_api/steps/variant_annotation_step.md +++ b/docs/python_api/steps/variant_annotation_step.md @@ -1,5 +1,5 @@ --- -title: GnomAD variant data ingestion +title: GnomAD Variant Index generation --- ::: gentropy.gnomad_ingestion.GnomadVariantIndexStep diff --git a/docs/python_api/steps/variant_index_step.md b/docs/python_api/steps/variant_index_step.md index 8a36f097f..3e54a6539 100644 --- a/docs/python_api/steps/variant_index_step.md +++ b/docs/python_api/steps/variant_index_step.md @@ -1,5 +1,5 @@ --- -title: variant_index +title: Variant Index generation --- ::: gentropy.variant_index.VariantIndexStep diff --git a/docs/python_api/steps/window_based_clumping.md b/docs/python_api/steps/window_based_clumping.md index f33057c71..468ff3ca1 100644 --- a/docs/python_api/steps/window_based_clumping.md +++ b/docs/python_api/steps/window_based_clumping.md @@ -1,5 +1,5 @@ --- -title: window_based_clumping +title: Window based clumping --- ::: gentropy.window_based_clumping.WindowBasedClumpingStep diff --git a/mkdocs.yml b/mkdocs.yml index 851f6ef8f..8a1e1b653 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -14,7 +14,7 @@ plugins: handlers: python: options: - filters: ["!^_", "!__new__", "__init__"] + filters: ["!^_", "!__new__", "!__init__"] show_signature_annotations: true show_root_heading: true heading_level: 3 diff --git a/pyproject.toml b/pyproject.toml index afd8ce757..cd50651c3 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -16,7 +16,7 @@ dependencies = [ "numpy>=2.3.0", "omegaconf (>=2.3.0, <2.4.0)", "scikit-learn (>=1.6.1, <1.8.0)", - "pandas[gcp,parquet] (>=2.2.3, <2.4.0)", + "pandas[gcp,parquet] (>=2.2.3, <3.1.0)", "skops (>=0.13.0, <0.14.0)", "shap>=0.50.0", "matplotlib (>=3.10.0, <3.11.0)", @@ -27,6 +27,7 @@ dependencies = [ "xgboost>=3.0.4 ; platform_machine == 'x86_64' and sys_platform == 'darwin'", "huggingface-hub>=0.27.1", "wandb (>=0.19.4, <0.26.0)", + "pydantic>=2.12.4", ] classifiers = [ "Programming Language :: Python :: 3.11", diff --git a/src/gentropy/assets/data/gwas_population_2_LD_panel_map.json b/src/gentropy/assets/data/gwas_population_2_LD_panel_map.json index 683e06885..66c80ae1d 100644 --- a/src/gentropy/assets/data/gwas_population_2_LD_panel_map.json +++ b/src/gentropy/assets/data/gwas_population_2_LD_panel_map.json @@ -18,5 +18,6 @@ "NR": "nfe", "Finnish": "fin", "African": "afr", - "Admixed American": "amr" + "Admixed American": "amr", + "Icelandic": "nfe" } diff --git a/src/gentropy/assets/schemas/molecular_complex.json b/src/gentropy/assets/schemas/molecular_complex.json new file mode 100644 index 000000000..4a7730e7c --- /dev/null +++ b/src/gentropy/assets/schemas/molecular_complex.json @@ -0,0 +1,104 @@ +{ + "fields": [ + { "metadata": {}, "name": "id", "nullable": true, "type": "string" }, + { + "metadata": {}, + "name": "description", + "nullable": true, + "type": "string" + }, + { + "metadata": {}, + "name": "properties", + "nullable": true, + "type": "string" + }, + { "metadata": {}, "name": "assembly", "nullable": true, "type": "string" }, + { + "metadata": {}, + "name": "components", + "nullable": true, + "type": { + "containsNull": false, + "elementType": { + "fields": [ + { + "metadata": {}, + "name": "id", + "nullable": false, + "type": "string" + }, + { + "metadata": {}, + "name": "stoichiometry", + "nullable": false, + "type": "string" + }, + { + "metadata": {}, + "name": "source", + "nullable": false, + "type": "string" + } + ], + "type": "struct" + }, + "type": "array" + } + }, + { + "metadata": {}, + "name": "evidenceCodes", + "nullable": true, + "type": { + "containsNull": false, + "elementType": "string", + "type": "array" + } + }, + { + "metadata": {}, + "name": "crossReferences", + "nullable": true, + "type": { + "containsNull": false, + "elementType": { + "fields": [ + { + "metadata": {}, + "name": "source", + "nullable": false, + "type": "string" + }, + { + "metadata": {}, + "name": "id", + "nullable": false, + "type": "string" + } + ], + "type": "struct" + }, + "type": "array" + } + }, + { + "metadata": {}, + "name": "source", + "nullable": false, + "type": { + "fields": [ + { "metadata": {}, "name": "id", "nullable": true, "type": "string" }, + { + "metadata": {}, + "name": "source", + "nullable": true, + "type": "string" + } + ], + "type": "struct" + } + } + ], + "type": "struct" +} diff --git a/src/gentropy/assets/schemas/variant_direction.json b/src/gentropy/assets/schemas/variant_direction.json index 85e4b957d..dafd23a26 100644 --- a/src/gentropy/assets/schemas/variant_direction.json +++ b/src/gentropy/assets/schemas/variant_direction.json @@ -3,24 +3,45 @@ { "metadata": {}, "name": "chromosome", - "nullable": true, + "nullable": false, "type": "string" }, + { + "metadata": {}, + "name": "rangeId", + "nullable": false, + "type": "integer" + }, { "metadata": {}, "name": "originalVariantId", "nullable": false, "type": "string" }, - { "metadata": {}, "name": "type", "nullable": false, "type": "byte" }, + { + "metadata": {}, + "name": "type", + "nullable": false, + "type": "byte" + }, { "metadata": {}, "name": "variantId", "nullable": false, "type": "string" }, - { "metadata": {}, "name": "direction", "nullable": false, "type": "byte" }, - { "metadata": {}, "name": "strand", "nullable": false, "type": "byte" }, + { + "metadata": {}, + "name": "direction", + "nullable": false, + "type": "byte" + }, + { + "metadata": {}, + "name": "strand", + "nullable": false, + "type": "byte" + }, { "metadata": {}, "name": "isStrandAmbiguous", diff --git a/src/gentropy/common/processing.py b/src/gentropy/common/processing.py index f77d2820b..e82f3cd1c 100644 --- a/src/gentropy/common/processing.py +++ b/src/gentropy/common/processing.py @@ -226,6 +226,17 @@ def mac(maf: Column, n: Column) -> Column: |v4 |0.3 |NULL| +---------+----+----+ + + >>> df.withColumn("mac", mac(f.col("maf"), f.col("n"))).show(truncate=False) + +---------+----+----+----+ + |variantId|maf |n |mac | + +---------+----+----+----+ + |v1 |0.1 |100 |20 | + |v2 |0.2 |200 |80 | + |v3 |NULL|150 |NULL| + |v4 |0.3 |NULL|NULL| + +---------+----+----+----+ + """ return ( f.when(maf.isNotNull() & n.isNotNull(), (maf * n * 2).cast(t.IntegerType())) diff --git a/src/gentropy/common/spark.py b/src/gentropy/common/spark.py index 1f005b9ed..426d482fa 100644 --- a/src/gentropy/common/spark.py +++ b/src/gentropy/common/spark.py @@ -946,3 +946,33 @@ def filter_array_struct( .getField(value_column) .alias(value_column) ) + + +def safe_split(c: Column, char: str) -> Column: + """Safe split string and trim white characters. + + Args: + c (Column): Column to split. + char (str): character to use for splitting. + + Returns: + Column: Column after splitting. + + Examples: + >>> data = [("a,a",), ("a, a",), ("a ,a",)] + >>> df = spark.createDataFrame(data, ["A"]) + >>> df.withColumn("S", safe_split(f.col("A"), ",")).show() + +----+------+ + | A| S| + +----+------+ + | a,a|[a, a]| + |a, a|[a, a]| + |a ,a|[a, a]| + +----+------+ + + """ + if not isinstance(char, str): + raise TypeError("`char` must be a string.") + char = re.escape(char) + pat = rf"{char}?\s+{char}?" + return f.split(f.regexp_replace(f.trim(c), pat, char), char) diff --git a/src/gentropy/config.py b/src/gentropy/config.py index 1533ae7ce..e45eb9b58 100644 --- a/src/gentropy/config.py +++ b/src/gentropy/config.py @@ -49,6 +49,48 @@ class ColocalisationConfig(StepConfig): _target_: str = "gentropy.colocalisation.ColocalisationStep" +@dataclass +class deCODEManifestGenerationConfig(StepConfig): + """deCODE data ingestion step configuration.""" + + bucket_listing_path: str = MISSING + output_path: str = MISSING + s3_config_path: str | None = None + _target_: str = "gentropy.decode_ingestion.deCODEManifestGenerationStep" + + +@dataclass +class deCODESummaryStatisticsIngestionConfig(StepConfig): + """deCODE summary statistics ingestion step configuration.""" + + decode_manifest_path: str = MISSING + raw_summary_statistics_path: str = MISSING + _target_: str = "gentropy.decode_ingestion.deCODESummaryStatisticsIngestionStep" + + +@dataclass +class deCODESummaryStatisticsHarmonisationConfig(StepConfig): + """deCODE summary statistics harmonisation step configuration.""" + + raw_summary_statistics_path: str = MISSING + manifest_path: str = MISSING + aptamer_metadata_path: str = MISSING + variant_direction_path: str = MISSING + molecular_complex_path: str = MISSING + # outputs + harmonised_summary_statistics_path: str = MISSING + protein_qtl_study_index_path: str = MISSING + qc_summary_statistics_path: str = MISSING + # config + min_mac_threshold: int = 50 + min_sample_size_threshold: int = 30_000 + flipping_window_size: int = ( + 10_000_000 # must match variant_direction.DEFAULT_WINDOW_SIZE + ) + pval_threshold: float = 5e-8 + _target_: str = "gentropy.decode_ingestion.deCODESummaryStatisticsHarmonisationStep" + + @dataclass class BiosampleIndexConfig(StepConfig): """Biosample index step configuration.""" @@ -705,6 +747,27 @@ class StudyLocusValidationStepConfig(StepConfig): _target_: str = "gentropy.study_locus_validation.StudyLocusValidationStep" +@dataclass +class pQTLStudyIndexTransformationConfig(StepConfig): + """pQTL study index transformation step configuration.""" + + protein_study_index_path: str = MISSING + study_index_path: str = MISSING + target_index_path: str = MISSING + _target_: str = "gentropy.pqtl_study.pQTLStudyIndexTransformationStep" + + +@dataclass +class MolecularComplexIngestionConfig(StepConfig): + """Molecular complex ingestion step configuration.""" + + predicted_complex_tab_path: str = MISSING + experimental_complex_tab_path: str = MISSING + output_path: str = MISSING + + _target_: str = "gentropy.molecular_complex.MolecularComplexIngestionStep" + + @dataclass class Config: """Application configuration.""" @@ -803,3 +866,28 @@ def register_config() -> None: cs.store(group="step", name="credible_set_qc", node=CredibleSetQCStepConfig) cs.store(group="step", name="foldx_integration", node=FoldXVariantAnnotationConfig) cs.store(group="step", name="interval_e2g", node=IntervalE2GStepConfig) + cs.store( + group="step", + name="pQTL_study_index_transformation", + node=pQTLStudyIndexTransformationConfig, + ) + cs.store( + group="step", + name="molecular_complex_ingestion", + node=MolecularComplexIngestionConfig, + ) + cs.store( + group="step", + name="decode_manifest_generation", + node=deCODEManifestGenerationConfig, + ) + cs.store( + group="step", + name="decode_summary_statistics_ingestion", + node=deCODESummaryStatisticsIngestionConfig, + ) + cs.store( + group="step", + name="decode_summary_statistics_harmonisation", + node=deCODESummaryStatisticsHarmonisationConfig, + ) diff --git a/src/gentropy/dataset/molecular_complex.py b/src/gentropy/dataset/molecular_complex.py new file mode 100644 index 000000000..e6b3a689b --- /dev/null +++ b/src/gentropy/dataset/molecular_complex.py @@ -0,0 +1,58 @@ +"""Molecular complex dataset. + +This module defines the `MolecularComplex` dataset, which stores curated and +predicted macromolecular (protein) complexes ingested from the +[Complex Portal](https://www.ebi.ac.uk/complexportal/) via the ComplexTAB flat-file +format. + +The dataset is used in the deCODE proteomics pipeline to annotate multi-protein +SomaScan aptamers with a ``molecularComplexId`` when the set of UniProt IDs measured +by an aptamer matches a known complex. +""" + +from __future__ import annotations + +from dataclasses import dataclass +from typing import TYPE_CHECKING + +from gentropy.common.schemas import parse_spark_schema +from gentropy.dataset.dataset import Dataset + +if TYPE_CHECKING: + from pyspark.sql import types as t + + +@dataclass +class MolecularComplex(Dataset): + """Curated and predicted macromolecular complex annotations. + + Each row represents one complex entry sourced from the Complex Portal and + contains the following information: + + - **id** (`str`) – Complex Portal accession (e.g. ``CPX-1``) + - **description** (`str`) – Free-text description of the complex. + - **properties** (`str`) – Additional complex property annotations. + - **assembly** (`str`) – Known or predicted assembly state. + - **components** (`array>`) – List of + component UniProt protein IDs with stoichiometry and source database. + - **evidenceCodes** (`array`) – ECO evidence codes supporting the + complex annotation. + - **crossReferences** (`array>`) – External database + cross-references (e.g. PDB, GO). + - **source** (`struct`) – PSI-MI ontology term describing the + data source. + + The schema is defined in ``assets/schemas/molecular_complex.json``. + """ + + @classmethod + def get_schema(cls: type[MolecularComplex]) -> t.StructType: + """Return the enforced Spark schema for `MolecularComplex`. + + The schema is loaded from the bundled JSON schema file + ``assets/schemas/molecular_complex.json``. + + Returns: + t.StructType: Schema for the `MolecularComplex` dataset. + """ + return parse_spark_schema("molecular_complex.json") diff --git a/src/gentropy/dataset/pairwise_ld.py b/src/gentropy/dataset/pairwise_ld.py index 6db570ba9..4fe0d60ce 100644 --- a/src/gentropy/dataset/pairwise_ld.py +++ b/src/gentropy/dataset/pairwise_ld.py @@ -36,19 +36,19 @@ def __post_init__(self: PairwiseLD) -> None: """ row_count = self.df.count() - assert ( - int(sqrt(row_count)) == sqrt(row_count) - ), f"The number of rows in a pairwise LD table has to be square. Got: {row_count}" + assert int(sqrt(row_count)) == sqrt(row_count), ( + f"The number of rows in a pairwise LD table has to be square. Got: {row_count}" + ) self.dimension = (int(sqrt(row_count)), int(sqrt(row_count))) super().__post_init__() @classmethod def get_schema(cls: type[PairwiseLD]) -> StructType: - """Provide the schema for the StudyIndex dataset. + """Provide the schema for the dataset. Returns: - StructType: The schema of the StudyIndex dataset. + StructType: The schema of the dataset. """ return parse_spark_schema("pairwise_ld.json") diff --git a/src/gentropy/dataset/study_index.py b/src/gentropy/dataset/study_index.py index 3b3e8ea6e..c96d3da81 100644 --- a/src/gentropy/dataset/study_index.py +++ b/src/gentropy/dataset/study_index.py @@ -11,7 +11,7 @@ from typing import TYPE_CHECKING, cast from pyspark.sql import functions as f -from pyspark.sql.types import ArrayType, StringType, StructType +from pyspark.sql import types as t from pyspark.sql.window import Window from gentropy.assets import data @@ -652,9 +652,9 @@ def annotate_sumstats_qc( ) # Annotate study index with QC information: - return StudyIndex( + return self.__class__( _df=df, - _schema=StudyIndex.get_schema(), + _schema=self.__class__.get_schema(), ) @qc_test @@ -708,7 +708,7 @@ def deconvolute_studies(self: StudyIndex) -> StudyIndex: "qualityControls", f.when( f.col("qualityControls").isNull(), - f.array().cast(ArrayType(StringType())), + f.array().cast(t.ArrayType(t.StringType())), ).otherwise(f.col("qualityControls")), ) # Keeping top hit studies unless the same study is available from a summmary statistics source: @@ -820,7 +820,7 @@ def deconvolute_studies(self: StudyIndex) -> StudyIndex: "traitFromSource", f.last(f.col("traitFromSource"), True).over(full_study_id_window), ) - # Distinct study types are joined together into a string. So, if there's ambiguite, the study will be flagged when the study type is validated: + # Distinct study types are joined together into a string. So, if there's ambiguity, the study will be flagged when the study type is validated: .withColumn( "studyType", f.concat_ws( @@ -848,3 +848,89 @@ def get_summary_statistics_paths(self: StudyIndex) -> list[str]: ) paths = [row["summarystatsLocation"] for row in paths_df.collect()] return paths + + +class ProteinQuantitativeTraitLocusStudyIndex(StudyIndex): + """Protein quantitative trait locus (pQTL) study index dataset. + + A pQTL study index dataset captures all the metadata for pQTL studies. + """ + + @classmethod + def get_schema(cls: type[ProteinQuantitativeTraitLocusStudyIndex]) -> StructType: + """Provide the schema for the ProteinQuantitativeTraitLocusStudyIndex dataset. + + Returns: + StructType: The schema of the ProteinQuantitativeTraitLocusStudyIndex dataset. + """ + study_schema = parse_spark_schema("study_index.json") + return study_schema.add( + t.StructField( + "targetsFromSource", + t.ArrayType( + t.StructType( + [ + t.StructField("proteinId", t.StringType(), nullable=True), + t.StructField("proteinName", t.StringType(), nullable=True), + t.StructField("geneId", t.StringType(), nullable=True), + t.StructField("geneSymbol", t.StringType(), nullable=True), + ] + ), + containsNull=True, + ), + nullable=True, + ), + ).add(t.StructField("molecularComplexId", t.StringType(), nullable=True)) + + def to_study( + self: ProteinQuantitativeTraitLocusStudyIndex, target: TargetIndex + ) -> StudyIndex: + """Convert ProteinQuantitativeTraitLocusStudyIndex to StudyIndex. + + This method maps the pQTL-specific fields to the corresponding fields in the StudyIndex dataset and returns a StudyIndex instance. + Map proteinIds to geneIds and coalesce geneIds and then explode the list of targets to have one row per target. + + Args: + target (TargetIndex): Target index containing the reference gene identifiers (Ensembl gene identifiers) + + Returns: + StudyIndex: A StudyIndex instance with mapped fields from ProteinQuantitativeTraitLocusStudyIndex. + """ + symbol_id_lut = target.symbols_lut().persist() + + _symbol_annot_si = ( + self.df.withColumn("targetFromSource", f.explode("targetsFromSource")) + .select( + *StudyIndex.get_schema().fieldNames(), + f.col("targetFromSource.geneId").alias("geneIdFromSource"), + f.col("targetFromSource.geneSymbol").alias("geneSymbol"), + f.col("targetFromSource.proteinId").alias("proteinId"), + ) + .join(symbol_id_lut, on="geneSymbol", how="left") + .withColumn("geneId", f.coalesce("geneIdFromSource", "geneId")) + .withColumn( + "ambiguousGeneIdMapping", + f.size(f.collect_set("geneId").over(Window.partitionBy("geneSymbol"))) + > 1, + ) + .drop("geneIdFromSource", "geneSymbol") + .persist() + ) + symbol_id_lut.unpersist() + protein_id_lut = target.protein_id_lut().persist() + non_ambiguous_df = ( + _symbol_annot_si.filter(~f.col("ambiguousGeneIdMapping")) + .drop("ambiguousGeneIdMapping") + .select(StudyIndex.get_schema().fieldNames()) + ) + ambiguous_df = ( + _symbol_annot_si.filter(f.col("ambiguousGeneIdMapping")) + .drop("ambiguousGeneIdMapping", "geneId") + .join(protein_id_lut, on="proteinId", how="left") + .select(StudyIndex.get_schema().fieldNames()) + ) + + return StudyIndex( + _df=non_ambiguous_df.unionByName(ambiguous_df), + _schema=StudyIndex.get_schema(), + ) diff --git a/src/gentropy/dataset/target_index.py b/src/gentropy/dataset/target_index.py index 517ff7f1d..5f1863622 100644 --- a/src/gentropy/dataset/target_index.py +++ b/src/gentropy/dataset/target_index.py @@ -6,6 +6,7 @@ from typing import TYPE_CHECKING import pyspark.sql.functions as f +from pyspark.sql import Window from pyspark.sql import types as t from gentropy.common.schemas import parse_spark_schema @@ -77,6 +78,60 @@ def symbols_lut(self: TargetIndex) -> DataFrame: "tss", ) + def protein_id_lut( + self: TargetIndex, + include_par_chr: str = "X", + ) -> DataFrame: + """Mapping between gene id and protein id. + + Args: + include_par_chr (str): Chromosome to include PAR (pseudo-autosomal region) + genes from. Must be ``"X"`` or ``"Y"``. Defaults to ``"X"``. + + Returns: + DataFrame: Gene LUT for UniProt mapping containing `geneId`, `proteinId` columns. + + Raises: + ValueError: If ``include_par_chr`` is not ``"X"`` or ``"Y"``. + + !!! note "PAR gene mapping" + For the PAR (pseudo autosomal region) genes we want to keep only one mapping by default for chromosome X + to avoid the confusion of having the same geneSymbol mapped to two ensembl ids. + + """ + if include_par_chr not in ("X", "Y"): + raise ValueError("include_par_chr must be either 'X' or 'Y'") + + # Condition checks if there are multiple chromosomes for the same proteinId, example: ASMTL gene + # [ENSG00000169093, ENSG00000292339] mapped to X and Y due to PAR region. + is_par = f.concat_ws( + ",", + f.sort_array( + f.collect_set("chromosome").over(Window.partitionBy("proteinId")) + ), + ) == f.lit("X,Y") + + _df = ( + self.df.select( + f.col("id").alias("geneId"), + f.inline("proteinIds"), + f.col("canonicalTranscript.chromosome").alias("chromosome"), + ) + .withColumnRenamed("id", "proteinId") + .select( + f.col("geneId"), + f.col("proteinId"), + is_par.alias("isPAR"), + f.col("chromosome"), + ) + ) + if include_par_chr: + _df = _df.filter( + ~((f.col("isPAR")) & (~f.col("chromosome").isin([include_par_chr]))) + ).drop("isPAR", "chromosome") + + return _df + def tss_lut(self: TargetIndex) -> DataFrame: """Gene TSS lookup table. diff --git a/src/gentropy/dataset/variant_direction.py b/src/gentropy/dataset/variant_direction.py index 31006087d..b2e9fbf10 100644 --- a/src/gentropy/dataset/variant_direction.py +++ b/src/gentropy/dataset/variant_direction.py @@ -13,6 +13,11 @@ from gentropy.common.schemas import parse_spark_schema from gentropy.dataset.dataset import Dataset +#: Default genomic window size (bp) used to partition the VariantDirection dataset. +#: This constant must be used consistently when creating the VariantDirection +#: (via ``from_variant_index``) and when joining against it during harmonisation. +DEFAULT_WINDOW_SIZE: int = 10_000_000 + class Direction(int, Enum): """Allele direction. @@ -93,16 +98,16 @@ class VariantDirection(Dataset): >>> variant_index = VariantIndex(_df=df) >>> variant_direction = VariantDirection.from_variant_index(variant_index) >>> variant_direction.df.show(truncate=False) - +----------+-----------------+----+---------+---------+------+-----------------+--------------------------------+ - |chromosome|originalVariantId|type|variantId|direction|strand|isStrandAmbiguous|originalAlleleFrequencies | - +----------+-----------------+----+---------+---------+------+-----------------+--------------------------------+ - |1 |1_100_A_G |1 |1_100_A_G|1 |1 |false |[{nfe_adj, 0.1}, {fin_adj, 0.2}]| - |1 |1_100_A_G |1 |1_100_G_A|-1 |1 |false |[{nfe_adj, 0.1}, {fin_adj, 0.2}]| - |1 |1_100_A_G |1 |1_100_T_C|1 |-1 |false |[{nfe_adj, 0.1}, {fin_adj, 0.2}]| - |1 |1_100_A_G |1 |1_100_C_T|-1 |-1 |false |[{nfe_adj, 0.1}, {fin_adj, 0.2}]| - |1 |1_100_T_A |1 |1_100_T_A|1 |1 |true |[{nfe_adj, 0.1}, {fin_adj, 0.2}]| - |1 |1_100_T_A |1 |1_100_A_T|-1 |1 |true |[{nfe_adj, 0.1}, {fin_adj, 0.2}]| - +----------+-----------------+----+---------+---------+------+-----------------+--------------------------------+ + +----------+-------+-----------------+----+---------+---------+------+-----------------+--------------------------------+ + |chromosome|rangeId|originalVariantId|type|variantId|direction|strand|isStrandAmbiguous|originalAlleleFrequencies | + +----------+-------+-----------------+----+---------+---------+------+-----------------+--------------------------------+ + |1 |0 |1_100_A_G |1 |1_100_A_G|1 |1 |false |[{nfe_adj, 0.1}, {fin_adj, 0.2}]| + |1 |0 |1_100_A_G |1 |1_100_G_A|-1 |1 |false |[{nfe_adj, 0.1}, {fin_adj, 0.2}]| + |1 |0 |1_100_A_G |1 |1_100_T_C|1 |-1 |false |[{nfe_adj, 0.1}, {fin_adj, 0.2}]| + |1 |0 |1_100_A_G |1 |1_100_C_T|-1 |-1 |false |[{nfe_adj, 0.1}, {fin_adj, 0.2}]| + |1 |0 |1_100_T_A |1 |1_100_T_A|1 |1 |true |[{nfe_adj, 0.1}, {fin_adj, 0.2}]| + |1 |0 |1_100_T_A |1 |1_100_A_T|-1 |1 |true |[{nfe_adj, 0.1}, {fin_adj, 0.2}]| + +----------+-------+-----------------+----+---------+---------+------+-----------------+--------------------------------+ """ @@ -382,17 +387,23 @@ def variant_id(cls, chrom: Column, pos: Column, ref: Column, alt: Column) -> Col return f.concat_ws("_", chrom, pos, ref, alt) @classmethod - def from_variant_index(cls, variant_index: VariantIndex) -> VariantDirection: + def from_variant_index( + cls, variant_index: VariantIndex, window_size: int = DEFAULT_WINDOW_SIZE + ) -> VariantDirection: """Prepare the variant direction DataFrame with DIRECT and FLIPPED entries. Args: variant_index (VariantIndex): Variant index dataset. + window_size (int): Window size for partitioning. Defaults to 10_000,000. Returns: VariantDirection: Variant direction dataset. """ lut = variant_index.df.select( f.col("chromosome"), + f.floor(f.col("position") / window_size) + .cast(t.IntegerType()) + .alias("rangeId"), f.col("variantId").alias("originalVariantId"), cls.variant_type(f.col("referenceAllele"), f.col("alternateAllele")).alias( "type" @@ -408,6 +419,7 @@ def from_variant_index(cls, variant_index: VariantIndex) -> VariantDirection: ).alias("allele"), ).select( f.col("chromosome"), + f.col("rangeId"), f.col("originalVariantId"), f.col("type"), f.col("allele.variantId").alias("variantId"), diff --git a/src/gentropy/datasource/complex_portal/__init__.py b/src/gentropy/datasource/complex_portal/__init__.py new file mode 100644 index 000000000..ace34086a --- /dev/null +++ b/src/gentropy/datasource/complex_portal/__init__.py @@ -0,0 +1,217 @@ +"""Complex Portal protein-complex datasource. + +This module ingests macromolecular complex data from the +[Complex Portal](https://www.ebi.ac.uk/complexportal/) in the **ComplexTAB** +flat-file format and converts it into the `MolecularComplex` dataset. + +Two complementary files are expected: + +- **Experimental** – complexes with direct experimental evidence. +- **Predicted** – computationally predicted complexes. + +Both files are parsed with the same schema, unioned, and filtered to human +complexes only (NCBI taxonomy ID 9606). + +The resulting `MolecularComplex` dataset is used downstream in the deCODE +proteomics pipeline to annotate multi-protein SomaScan aptamers with a +``molecularComplexId``. +""" + +from __future__ import annotations + +from pyspark.sql import Column +from pyspark.sql import functions as f +from pyspark.sql import types as t + +from gentropy import Session +from gentropy.dataset.dataset import Dataset +from gentropy.dataset.molecular_complex import MolecularComplex + + +class ComplexTab(Dataset): + """Parser for the Complex Portal ComplexTAB flat-file format. + + This class reads the ComplexTAB TSV files distributed by the + [Complex Portal](https://www.ebi.ac.uk/complexportal/) and transforms them + into the `MolecularComplex` dataset. It is not instantiated directly; + use `from_complex_tab` to produce a `MolecularComplex` object. + + Class attributes: + HUMAN_TAXONOMY_ID (int): NCBI taxonomy ID for *Homo sapiens* (9606). + Rows with a different taxonomy are discarded during ingestion. + """ + + HUMAN_TAXONOMY_ID = 9606 + + @classmethod + def get_schema(cls) -> t.StructType: + """Return the raw Spark schema matching the ComplexTAB TSV column layout. + + The schema covers all columns present in the ComplexTAB export, including + complex accession, taxonomy, participant list, evidence codes, cross + references, and descriptive fields. + + Returns: + t.StructType: Raw ComplexTAB schema with original column names. + """ + return t.StructType( + [ + t.StructField("#Complex ac", t.StringType(), True), + t.StructField("Recommended name", t.StringType(), True), + t.StructField("Aliases for complex", t.StringType(), True), + t.StructField("Taxonomy identifier", t.IntegerType(), True), + t.StructField( + "Identifiers (and stoichiometry) of molecules in complex", + t.StringType(), + True, + ), + t.StructField("Evidence Code", t.StringType(), True), + t.StructField("Experimental evidence", t.StringType(), True), + t.StructField("Go Annotations", t.StringType(), True), + t.StructField("Cross references", t.StringType(), True), + t.StructField("Description", t.StringType(), True), + t.StructField("Complex properties", t.StringType(), True), + t.StructField("Complex assembly", t.StringType(), True), + t.StructField("Ligand", t.StringType(), True), + t.StructField("Disease", t.StringType(), True), + t.StructField("Agonist", t.StringType(), True), + t.StructField("Antagonist", t.StringType(), True), + t.StructField("Comment", t.StringType(), True), + t.StructField("Source", t.StringType(), True), + t.StructField("Expanded participant list", t.StringType(), True), + ] + ) + + @classmethod + def from_complex_tab( + cls, session: Session, experimental: str, predicted: str + ) -> MolecularComplex: + """Parse experimental and predicted ComplexTAB files into a `MolecularComplex` dataset. + + Both input files are read with the ComplexTAB schema, unioned, and filtered + to human complexes (taxonomy ID 9606). The following fields are extracted + and renamed to match the `MolecularComplex` schema: + + - ``#Complex ac`` → ``id`` + - ``Description`` → ``description`` + - ``Complex properties`` → ``properties`` + - ``Complex assembly`` → ``assembly`` + - ``Expanded participant list`` → ``components`` (parsed by `_parse_components`) + - ``Evidence Code`` → ``evidenceCodes`` (parsed by `_parse_evidence_code`) + - ``Cross references`` → ``crossReferences`` (parsed by `_parse_cross_references`) + - ``Source`` → ``source`` (parsed by `_parse_source`) + + Args: + session (Session): Active Gentropy Spark session. + experimental (str): Path to the experimental ComplexTAB TSV file. + predicted (str): Path to the predicted ComplexTAB TSV file. + + Returns: + MolecularComplex: Parsed and filtered molecular complex dataset. + """ + e = session.load_data( + experimental, fmt="tsv", schema=cls.get_schema(), nullValue="-" + ) + pr = session.load_data( + predicted, fmt="tsv", schema=cls.get_schema(), nullValue="-" + ) + return MolecularComplex( + _df=e.unionByName(pr) + .filter(f.col("Taxonomy identifier") == cls.HUMAN_TAXONOMY_ID) + .select( + f.col("#Complex ac").alias("id"), + f.col("Description").alias("description"), + f.col("Complex properties").alias("properties"), + f.col("Complex assembly").alias("assembly"), + cls._parse_components(f.col("Expanded participant list")).alias( + "components" + ), + cls._parse_evidence_code(f.col("Evidence Code")).alias("evidenceCodes"), + cls._parse_cross_references(f.col("Cross references")).alias( + "crossReferences" + ), + cls._parse_source(f.col("Source")).alias("source"), + ) + ) + + @staticmethod + def _parse_source(c: Column) -> Column: + """Parse the PSI-MI source field into a structured ``{id, source}`` record. + + The field has the format ``psi-mi:"MI:XXXX"(source name)``. + + Args: + c (Column): Raw ``Source`` column. + + Returns: + Column: Struct column with fields ``id`` (PSI-MI accession) and + ``source`` (human-readable source name). + """ + return f.struct( + f.regexp_extract(c, r"psi-mi:\"(.*)\"\((.*)\)", 1).alias("id"), + f.regexp_extract(c, r"psi-mi:\"(.*)\"\((.*)\)", 2).alias("source"), + ) + + @staticmethod + def _parse_evidence_code(c: Column) -> Column: + """Parse the pipe-delimited evidence code field into an array of ECO accessions. + + Each element of the pipe-separated list is expected to contain an ECO + term in the form ``ECO:XXXXXXX``. + + Args: + c (Column): Raw ``Evidence Code`` column. + + Returns: + Column: Array of ECO accession strings (e.g. ``["ECO:0000353"]``). + """ + return f.transform( + f.split(c, r"\|"), lambda x: f.regexp_extract(x, r"(ECO:\d+)", 1) + ) + + @staticmethod + def _parse_cross_references(c: Column) -> Column: + """Parse the pipe-delimited cross-references field into an array of ``{source, id}`` records. + + Each element of the pipe-separated list is expected to have the format + ``source:id(description)``. + + Args: + c (Column): Raw ``Cross references`` column. + + Returns: + Column: Array of structs with fields ``source`` (database name) and + ``id`` (accession within that database). + """ + return f.transform( + f.split(c, r"\|"), + lambda x: f.struct( + f.regexp_extract(x, r"^(.*)\:(.*)\(.*\)$", 1).alias("source"), + f.regexp_extract(x, r"^(.*)\:(.*)\(.*\)$", 2).alias("id"), + ), + ) + + @staticmethod + def _parse_components(c: Column) -> Column: + """Parse the pipe-delimited expanded participant list into an array of component records. + + Each element of the pipe-separated list is expected to have the format + ``UniProtID(stoichiometry)``, for example ``P04637(2)``. + The ``source`` field is always set to ``"uniprot"``. + + Args: + c (Column): Raw ``Expanded participant list`` column. + + Returns: + Column: Array of structs with fields ``id`` (UniProt accession), + ``stoichiometry`` (copy number as a string), and ``source`` + (always ``"uniprot"``). + """ + return f.transform( + f.split(c, r"\|"), + lambda x: f.struct( + f.regexp_extract(x, r"([\w-]+)\((\d+)\)", 1).alias("id"), + f.regexp_extract(x, r"([\w-]+)\((\d+)\)", 2).alias("stoichiometry"), + f.lit("uniprot").alias("source"), + ), + ) diff --git a/src/gentropy/datasource/decode/__init__.py b/src/gentropy/datasource/decode/__init__.py new file mode 100644 index 000000000..b7adea6f7 --- /dev/null +++ b/src/gentropy/datasource/decode/__init__.py @@ -0,0 +1,66 @@ +"""deCODE proteomics datasource module. + +This module provides shared constants and metadata for the deCODE proteomics data source. +It defines the project identifiers used across the ingestion pipeline and the bibliographic +metadata for the underlying publication. + +The deCODE proteomics dataset originates from the study: + Eldjarn GH, Ferkingstad E et al. + "Large-scale plasma proteomics comparisons through genetics and disease associations." + Nature, 2024. PubMed: 37794188 + +Two sub-datasets are supported: + +- **RAW** (`deCODE-proteomics-raw`): Non-normalised SomaScan measurements from ~36,136 Icelandic + individuals. +- **SMP** (`deCODE-proteomics-smp`): SMP-normalised SomaScan measurements from ~35,892 Icelandic + individuals. +""" + +from __future__ import annotations + +from enum import Enum + +from pydantic import BaseModel + + +class deCODEDataSource(str, Enum): + """Enumeration of deCODE proteomics data source identifiers. + + These project IDs are embedded in study IDs and used throughout the pipeline + to distinguish the two SomaScan assay normalisations. + """ + + DECODE_PROTEOMICS_RAW = "deCODE-proteomics-raw" + """Non-normalised SomaScan measurements.""" + DECODE_PROTEOMICS_SMP = "deCODE-proteomics-smp" + """SMP-normalised SomaScan measurements.""" + + +class deCODEPublicationMetadata(BaseModel): + """Bibliographic and cohort metadata for the deCODE proteomics publication. + + All fields carry defaults matching the published study and are used to populate + the study index with consistent provenance information. + """ + + PUBMED_ID: str = "37794188" + """PubMed ID for the deCODE proteomics study.""" + PUB_TITLE: str = "Large-scale plasma proteomics comparisons through genetics and disease associations" + """Title of the deCODE proteomics publication.""" + PUB_FIRST_AUTHOR: str = "Eldjarn GH, Ferkingstad E" + """First author(s) of the deCODE proteomics publication.""" + PUB_DATE: str = "2023" + """Publication date of the deCODE proteomics study.""" + PUB_JOURNAL: str = "Nature" + """Journal where the deCODE proteomics study was published.""" + SMP_SAMPLE_SIZE: int = 35_892 + """Sample size for SMP-normalized proteomics data.""" + SAMPLE_SIZE: int = 36_136 + """Sample size for non-normalized proteomics data.""" + ANCESTRY: str = "Icelandic" + """Ancestry of the study population.""" + COHORTS: str = "deCODE" + """Cohorts involved in the deCODE proteomics study.""" + BIOSAMPLE_ID: str = "UBERON_0001969" + """Biosample ID for deCODE proteomics study - blood plasma.""" diff --git a/src/gentropy/datasource/decode/aptamer_metadata.py b/src/gentropy/datasource/decode/aptamer_metadata.py new file mode 100644 index 000000000..20a7d7689 --- /dev/null +++ b/src/gentropy/datasource/decode/aptamer_metadata.py @@ -0,0 +1,127 @@ +"""deCODE aptamer metadata module. + +This module provides the `AptamerMetadata` dataset that maps each SomaScan +aptamer identifier to one or more human protein targets. The mapping table is derived +from the SomaScan study tables distributed by deCODE and is used during study-index +creation to annotate each assay with curated gene symbols and UniProt protein IDs. +""" + +from __future__ import annotations + +from pyspark.sql import DataFrame +from pyspark.sql import functions as f +from pyspark.sql import types as t + +from gentropy import Session +from gentropy.common.spark import safe_split +from gentropy.dataset.dataset import Dataset + + +class AptamerMetadata(Dataset): + """Mapping from SomaScan aptamer identifiers to protein target metadata. + + Each row describes a single SomaScan aptamer and its one or more protein targets. + Multi-target aptamers (i.e. those measuring a protein complex) are flagged with + ``isProteinComplex = True`` and their ``targetMetadata`` array will contain more + than one element. + + The dataset is created from the aptamer study table supplied by deCODE and is used + in `deCODEStudyIndex.from_manifest` + to join aptamer-level annotations onto the per-study manifest. + """ + + @classmethod + def get_schema(cls) -> t.StructType: + """Return the enforced Spark schema for `AptamerMetadata`. + + Returns: + t.StructType: Expected schema containing ``aptamerId``, ``targetName``, + ``targetFullName``, ``isProteinComplex``, and ``targetMetadata``. + """ + return t.StructType( + [ + t.StructField("aptamerId", t.StringType(), nullable=False), + t.StructField("targetName", t.StringType(), nullable=False), + t.StructField("targetFullName", t.StringType(), nullable=True), + t.StructField("isProteinComplex", t.BooleanType(), nullable=False), + t.StructField( + "targetMetadata", + t.ArrayType( + t.StructType( + [ + t.StructField( + "geneSymbol", t.StringType(), nullable=True + ), + t.StructField( + "proteinId", t.StringType(), nullable=True + ), + ] + ) + ), + ), + ] + ) + + @classmethod + def from_source(cls, session: Session, path: str) -> AptamerMetadata: + """Load and parse the deCODE aptamer metadata file. + + The file at ``path`` is expected to be a TSV with the SomaScan study table + layout (columns: ``seqid``, ``target_name``, ``target_full_name``, ``gene_name``, + ``uniprot``). Each ``seqid`` value is normalised by stripping the ``SeqId.`` prefix + and converting the underscore-separated aptamer identifier to a hyphen-separated one. + + Args: + session (Session): Gentropy session object used to load the source data. + path (str): Path (local or remote) to the aptamer metadata TSV file. + + Returns: + AptamerMetadata: Validated `AptamerMetadata` dataset. + """ + data = session.load_data(path, fmt="tsv") + return cls._transform_source(data) + + @classmethod + def _transform_source(cls, df: DataFrame) -> AptamerMetadata: + """Transform a raw aptamer study table into a validated `AptamerMetadata` dataset. + + The input DataFrame is expected to contain at minimum the columns + ``seqid``, ``target_name``, ``target_full_name``, ``gene_name``, and ``uniprot``. + Multi-valued ``gene_name`` and ``uniprot`` fields (comma-separated) are split + into arrays and zipped to form the ``targetMetadata`` struct array. + + Args: + df (DataFrame): Raw study table as loaded from the aptamer metadata file. + + Returns: + AptamerMetadata: Validated deCODE aptamer metadata dataset. + """ + return cls( + _df=df.select( + "seqid", + "target_name", + "target_full_name", + "gene_name", + "uniprot", + ) + .select( + f.regexp_replace(f.trim("seqid"), "SeqId.", "").alias("aptamerId"), + f.trim("target_name").alias("targetName"), + f.trim("target_full_name").alias("targetFullName"), + safe_split(f.trim("gene_name"), ",").alias("geneSymbol"), + safe_split(f.trim("uniprot"), ",").alias("proteinId"), + ) + .withColumn( + "targetMetadata", + f.arrays_zip("geneSymbol", "proteinId").alias("targetMetadata"), + ) + .withColumn("isProteinComplex", f.size(f.col("targetMetadata")) > 1) + .select( + "aptamerId", + "targetName", + "targetFullName", + "isProteinComplex", + "targetMetadata", + ) + .distinct() + ) diff --git a/src/gentropy/datasource/decode/manifest.py b/src/gentropy/datasource/decode/manifest.py new file mode 100644 index 000000000..d921ef3ad --- /dev/null +++ b/src/gentropy/datasource/decode/manifest.py @@ -0,0 +1,170 @@ +"""deCODE ingestion manifest. + +The `deCODEManifest` dataset catalogues every summary-statistics file available +in the deCODE S3 bucket. It is generated once from an ``aws s3 ls`` bucket listing and +subsequently consumed by downstream ingestion steps to locate per-study TSV gzip files +and to associate each assay with a project identifier. +""" + +from __future__ import annotations + +from pyspark.sql import functions as f +from pyspark.sql import types as t + +from gentropy import Session +from gentropy.dataset.dataset import Dataset +from gentropy.datasource.decode import deCODEDataSource +from gentropy.external.s3 import S3Config + + +class deCODEManifest(Dataset): + """Catalogue of deCODE summary-statistics files derived from an S3 bucket listing. + + Each row corresponds to one SomaScan assay and records the S3 path of its + gzipped TSV summary-statistics file together with provenance metadata such as + file size and accession timestamp. The `studyId` follows the convention + ``{projectId}_{Proteomics_*}`` as embedded in the file path. + + The manifest is produced by `from_bucket_listing` and later consumed by + `deCODEStudyIndex` and `deCODESummaryStatistics`. + """ + + bucket_listing_schema = t.StructType( + [ + t.StructField("date", t.DateType()), + t.StructField("time", t.StringType()), + t.StructField("empty", t.StringType()), # empty field in aws s3 ls output + t.StructField("size", t.StringType()), + t.StructField("unit", t.StringType()), + t.StructField("relativePath", t.StringType()), + ] + ) + + @classmethod + def get_schema(cls) -> t.StructType: + """Return the enforced Spark schema for `deCODEManifest`. + + Returns: + t.StructType: Schema with fields ``projectId``, ``studyId``, + ``hasSumstats``, ``summarystatsLocation``, ``size``, and + ``accessionTimestamp``. + """ + return t.StructType( + [ + t.StructField("projectId", t.StringType()), + t.StructField("studyId", t.StringType()), + t.StructField("hasSumstats", t.BooleanType()), + t.StructField("summarystatsLocation", t.StringType()), + t.StructField("size", t.StringType()), + t.StructField("accessionTimestamp", t.TimestampType()), + ] + ) + + def get_summary_statistics_paths(self) -> list[str]: + """Get summary statistics paths from manifest. + + Returns: + list[str]: List of summary statistics paths. + + Examples: + >>> data = [("path1",), ("path2",)] + >>> schema = "summarystatsLocation STRING" + >>> df = spark.createDataFrame(data, schema) + >>> manifest = deCODEManifest(df) + >>> manifest.get_summary_statistics_paths() + ['path1', 'path2'] + """ + return [ + row.summarystatsLocation + for row in self.df.select("summarystatsLocation").collect() + ] + + @classmethod + def from_bucket_listing( + cls, + session: Session, + path: str, + s3_config_path: str | None = None, + ) -> deCODEManifest: + r"""Create a `deCODEManifest` from an ``aws s3 ls`` bucket listing file. + + The listing file must be produced with the following command (bottom summary + lines should be removed before ingestion): + + ```bash + aws s3 ls \\ + --recursive \\ + --human-readable \\ + --summarize \\ + --profile $1 \\ + $2 \\ + --endpoint-url https://${S3_HOST_URL}:${S3_HOST_PORT} | grep "Proteomics" > manifest.txt + ``` + + The ``s3_config_path`` JSON/YAML file must contain the S3 bucket name so that + fully-qualified ``s3a://`` paths can be constructed for each file. + + Args: + session (Session): Active Gentropy Spark session. + path (str): Path to the ``aws s3 ls`` output text file. + s3_config_path (str | None): Path to the S3 configuration file (used to resolve + the bucket name for constructing absolute ``s3a://`` URIs). + + Returns: + deCODEManifest: Populated manifest dataset. + """ + config = S3Config.read(s3_config_path) + project_id = f.when( + f.col("relativePath").contains("Proteomics_SMP_"), + f.lit(deCODEDataSource.DECODE_PROTEOMICS_SMP.value), + ).otherwise(deCODEDataSource.DECODE_PROTEOMICS_RAW.value) + + manifest_df = ( + session.spark.read.csv( + path, + sep=" ", + header=False, + schema=cls.bucket_listing_schema, + ) + .drop("empty") + .withColumn("projectId", project_id) + .withColumn( + "studyId", + f.concat_ws( + "_", + f.col("projectId"), + f.regexp_extract( + "relativePath", + r"^.*/(Proteomics_.*)\.txt.gz$", + 1, + ), + ), + ) + .withColumn("hasSumstats", f.lit(True)) + .withColumn( + "summarystatsLocation", + f.concat( + f.lit("s3a://"), + f.lit(config.bucket_name), + f.lit("/"), + f.col("relativePath"), + ), + ) + .withColumn("size", f.concat_ws(" ", f.col("size"), f.col("unit"))) + .withColumn( + "accessionTimestamp", + f.to_timestamp( + f.concat_ws(" ", f.col("date"), f.col("time")), + "yyyy-MM-dd HH:mm:ss", + ), + ) + .select( + "projectId", + "studyId", + "hasSumstats", + "summarystatsLocation", + "size", + "accessionTimestamp", + ) + ) + return cls(_df=manifest_df) diff --git a/src/gentropy/datasource/decode/study_index.py b/src/gentropy/datasource/decode/study_index.py new file mode 100644 index 000000000..c4c92e6a7 --- /dev/null +++ b/src/gentropy/datasource/decode/study_index.py @@ -0,0 +1,463 @@ +"""deCODE pQTL study index module. + +This module provides two main classes: + +- **`deCODEStudyIdParts`** – a `NamedTuple` of Spark `Column` objects that represent + the structured components of a deCODE study ID (project, assay type, aptamer, + gene symbol, protein name). + +- **`deCODEStudyIndex`** – static factory helpers that build a + `ProteinQuantitativeTraitLocusStudyIndex` + from the deCODE manifest, aptamer metadata, and molecular-complex datasets. + +The study ID format used throughout the pipeline is:: + + {projectId}_{datasourceType}_{aptamerId}_{geneSymbol}_{proteinName}_{sequenceNumber} + +For example:: + + deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001 +""" + +from __future__ import annotations + +from functools import partial +from typing import NamedTuple + +from pyspark.sql import functions as f +from pyspark.sql import types as t +from pyspark.sql.column import Column + +from gentropy import StudyIndex +from gentropy.dataset.molecular_complex import MolecularComplex +from gentropy.dataset.study_index import ProteinQuantitativeTraitLocusStudyIndex +from gentropy.datasource.decode import deCODEDataSource, deCODEPublicationMetadata +from gentropy.datasource.decode.aptamer_metadata import AptamerMetadata +from gentropy.datasource.decode.manifest import deCODEManifest + + +class deCODEStudyIdParts(NamedTuple): + """deCODE study ID parts. + + Examples: + >>> data = [("deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001",),] + >>> schema = "studyId STRING" + >>> df = spark.createDataFrame(data, schema) + >>> id_parts = deCODEStudyIdParts.extract_study_id_parts(f.col("studyId")) + >>> df.select(*id_parts).show(truncate=False) + +---------------------+------------------+---------+---------------------+----------------------+ + |projectId |datasourceType |aptamerId|geneSymbolFromStudyId|proteinNameFromStudyId| + +---------------------+------------------+---------+---------------------+----------------------+ + |deCODE-proteomics-smp|Proteomics_SMP_PC0|10000-2 |GENE1 |PROTEIN1 | + +---------------------+------------------+---------+---------------------+----------------------+ + + + >>> df.select(id_parts.trait).show(truncate=False) + +-----------------------------------------+ + |traitFromSource | + +-----------------------------------------+ + |Proteomics_SMP_PC0_10000-2_GENE1_PROTEIN1| + +-----------------------------------------+ + + + """ + + project_id: Column + """Project ID extracted from the study ID.""" + datasource_type: Column + """Data source type - SMP or Raw.""" + aptamer_id: Column + """Aptamer identifier extracted from the study ID.""" + gene_symbol: Column + """Gene Symbol derived from the study ID.""" + protein_name: Column + """Protein name derived from the study ID.""" + + @property + def trait(self) -> Column: + """Trait derived from the study ID.""" + return f.concat_ws( + "_", + self.datasource_type, + self.aptamer_id, + self.gene_symbol, + self.protein_name, + ).alias("traitFromSource") + + @staticmethod + def get_pattern() -> str: + """Regex pattern to extract deCODE study ID parts. + + Returns: + str: Regex pattern. + + The pattern captures the following groups: + (1) project ID + (2) study type + (3) inner part (PC0 or SMP_PC0) + (4) aptamer identifier + (5) gene symbol + (6) protein name + (2-6) trait + """ + return r"^([\w-_]+?)_(Proteomics_(SMP_PC0|PC0))_(\d+_\d+)_([A-Za-z0-9]+)_(\w+)_\d+$" + + @classmethod + def extract_study_id_parts(cls, study_id: Column) -> deCODEStudyIdParts: + """Extract gene symbol from study ID. + + Args: + study_id (Column): Study ID column. + + Returns: + deCODEStudyIdParts: Extracted parts of the study ID. + """ + p = partial(f.regexp_extract, study_id, cls.get_pattern()) + return cls( + project_id=p(1).alias("projectId"), + datasource_type=p(2).alias("datasourceType"), + aptamer_id=f.regexp_replace(p(4), "_", "-").alias("aptamerId"), + gene_symbol=cls._mark_missing_gene_id(p(5)).alias("geneSymbolFromStudyId"), + protein_name=cls._mark_missing_protein(p(6)).alias( + "proteinNameFromStudyId" + ), + ) + + @staticmethod + def _mark_missing_gene_id(gene_id: Column) -> Column: + """Mark the geneId as null if `NA` is in geneId. + + Args: + gene_id (Column): Gene ID column extracted from the study ID. + + Returns: + Column: Gene ID column with ``NA`` values replaced by ``null``. + """ + return f.when( + gene_id == f.lit("NA"), + f.lit(None).cast(t.StringType()), + ).otherwise(gene_id) + + @staticmethod + def _mark_missing_protein(protein_name: Column) -> Column: + """Mark the protein name as null if it is a placeholder value. + + Args: + protein_name (Column): Protein name column extracted from the study ID. + + Returns: + Column: Protein name column with ``Deprecated`` and ``No_Protein`` + values replaced by ``null``. + """ + return f.when( + ( + (protein_name == f.lit("Deprecated")) + | (protein_name == f.lit("No_Protein")) + ), + f.lit(None).cast(t.StringType()), + ).otherwise(protein_name) + + +class deCODEStudyIndex: + """Factory helpers for constructing the deCODE pQTL study index. + + This class is not instantiated directly. Its class methods transform the + `deCODEManifest`, + `AptamerMetadata`, and + `MolecularComplex` datasets into a + `ProteinQuantitativeTraitLocusStudyIndex`. + + Sample-size and ancestry metadata are populated from + `deCODEPublicationMetadata`, and the + study ID is optionally updated after harmonisation to incorporate curated + gene symbols and protein names sourced from the aptamer mapping table. + """ + + @classmethod + def get_initial_sample( + cls, project_id: Column, metadata: deCODEPublicationMetadata + ) -> Column: + """Get initial sample size based on projectId. + + Args: + project_id (Column): Project ID column. + metadata (deCODEPublicationMetadata): Metadata for the deCODE publication. + + Returns: + Column: Initial sample size column. + """ + return ( + f.when( + project_id == f.lit(deCODEDataSource.DECODE_PROTEOMICS_RAW.value), + f.lit(f"{metadata.SAMPLE_SIZE:,} Icelandic individuals"), + ) + .when( + project_id == f.lit(deCODEDataSource.DECODE_PROTEOMICS_SMP.value), + f.lit(f"{metadata.SMP_SAMPLE_SIZE:,} Icelandic individuals"), + ) + .otherwise(f.lit(None)) + .alias("initialSampleSize") + ) + + @classmethod + def get_n_samples( + cls, project_id: Column, metadata: deCODEPublicationMetadata + ) -> Column: + """Get number of samples based on projectId. + + Args: + project_id (Column): Project ID column. + metadata (deCODEPublicationMetadata): Metadata for the deCODE publication. + + Returns: + Column: Number of samples column. + """ + return ( + f.when( + project_id == f.lit(deCODEDataSource.DECODE_PROTEOMICS_RAW.value), + f.lit(metadata.SAMPLE_SIZE), + ) + .when( + project_id == f.lit(deCODEDataSource.DECODE_PROTEOMICS_SMP.value), + f.lit(metadata.SMP_SAMPLE_SIZE), + ) + .otherwise(f.lit(None)) + .alias("nSamples") + ) + + @classmethod + def get_discovery_samples( + cls, project_id: Column, metadata: deCODEPublicationMetadata + ) -> Column: + """Get discoverySamples based on projectId. + + Args: + project_id (Column): Project ID column. + metadata (deCODEPublicationMetadata): Metadata for the deCODE publication. + + Returns: + Column: Number of discovery samples column. + """ + return ( + f.when( + project_id == f.lit(deCODEDataSource.DECODE_PROTEOMICS_RAW.value), + f.array( + f.struct( + f.lit(metadata.SAMPLE_SIZE).alias("sampleSize"), + f.lit(metadata.ANCESTRY).alias("ancestry"), + ) + ), + ) + .when( + project_id == f.lit(deCODEDataSource.DECODE_PROTEOMICS_SMP.value), + f.array( + f.struct( + f.lit(metadata.SMP_SAMPLE_SIZE).alias("sampleSize"), + f.lit(metadata.ANCESTRY).alias("ancestry"), + ) + ), + ) + .otherwise(f.lit(None)) + .alias("nDiscoverySamples") + ) + + @classmethod + def from_manifest( + cls, + manifest: deCODEManifest, + aptamer_metadata: AptamerMetadata, + molecular_complex: MolecularComplex, + ) -> ProteinQuantitativeTraitLocusStudyIndex: + """Build a pQTL study index by joining the manifest, aptamer table, and protein complexes. + + Processing steps: + + 1. Parse the structured study-ID components (project, assay type, aptamer ID, + gene symbol, protein name) from every row in the manifest. + 2. Filter out rows where the gene symbol or protein name encoded in the study ID + is missing (``NA`` / ``No_Protein`` / ``Deprecated``). + 3. Inner-join the aptamer mapping table on ``aptamerId`` to obtain curated target + metadata; this restricts the study index to aptamers present in the SomaScan + study table (a subset of the full manifest). + 4. Left-join the protein-complex table on the sorted, comma-joined UniProt protein + ID string to annotate multi-target aptamers with a ``molecularComplexId``. + 5. Populate bibliographic and cohort metadata from + `deCODEPublicationMetadata`, including + sample sizes, biosample ID, ancestry, and LD population structure. + + Args: + manifest (deCODEManifest): Manifest dataset cataloguing all available assays. + aptamer_metadata (AptamerMetadata): Curated aptamer-to-protein mapping table. + molecular_complex (MolecularComplex): Protein complex annotations from + `ComplexTab`. + + Returns: + ProteinQuantitativeTraitLocusStudyIndex: Study index ready for harmonisation. + """ + id_split = deCODEStudyIdParts.extract_study_id_parts(f.col("studyId")) + _manifest = ( + manifest.df.select( + f.col("projectId"), + f.col("studyId"), + f.col("hasSumstats"), + f.col("summarystatsLocation"), + id_split.trait.alias("traitFromSource"), + id_split.aptamer_id.alias("aptamerId"), + id_split.datasource_type.alias("datasourceType"), + id_split.gene_symbol.alias("geneSymbolFromStudyId"), + id_split.gene_symbol.alias("geneFromSourceSymbol"), + id_split.protein_name.alias("proteinNameFromSource"), + ) + # Drop when the gene symbol or protein name are missing + .filter(f.col("geneFromSourceSymbol").isNotNull()) + .filter(f.col("proteinNameFromSource").isNotNull()) + .drop("geneFromSourceSymbol", "proteinNameFromSource") + .alias("_manifest") + ) + + _aptamers = aptamer_metadata.df.select( + f.col("aptamerId").alias("aptamerId"), + f.col("targetMetadata").alias("targetMetadata"), + ).alias("_aptamers") + + # StudyId from manifest contains the molecular trait information, + # but the mapping is inaccurate, so we decide to limit the number of assays + # to trait metadata from the aptamer mapping table which is a subset of the manifest. + _manifest_aptamer_annotated = ( + _manifest.join(_aptamers, on="aptamerId", how="inner") + .withColumn( + "proteinIds", + f.concat_ws( + ",", + f.array_sort( + f.array_distinct( + f.transform( + "targetMetadata", lambda x: x.getField("proteinId") + ) + ) + ), + ), + ) + .alias("_manifest_aptamer_annotated") + ) + + _protein_complex = molecular_complex.df.select( + f.col("id").alias("molecularComplexId"), + f.concat_ws( + ",", + f.array_sort( + f.array_distinct( + f.transform(f.col("components"), lambda x: x.getField("id")) + ) + ), + ).alias("proteinIds"), + ).alias("_protein_complex") + + _manifest_complex_annotated = ( + _manifest_aptamer_annotated.join( + _protein_complex, on="proteinIds", how="left" + ) + .drop("proteinIds") + .withColumn("geneId", f.lit(None).cast(t.StringType())) + .withColumn( + "targetsFromSource", + f.transform( + "targetMetadata", + lambda x: x.withField( + "geneId", f.lit(None).cast(t.StringType()) + ).withField("proteinName", f.lit(None).cast(t.StringType())), + ), + ) + ) + + # Preserve all rows from the manifest + pub = deCODEPublicationMetadata() + return ProteinQuantitativeTraitLocusStudyIndex( + _df=_manifest_complex_annotated.withColumn("studyType", f.lit("pqtl")) + .withColumn("biosampleFromSourceId", f.lit(pub.BIOSAMPLE_ID)) + .withColumn("pubmedId", f.lit(pub.PUBMED_ID)) + .withColumn("publicationFirstAuthor", f.lit(pub.PUB_FIRST_AUTHOR)) + .withColumn("publicationDate", f.lit(pub.PUB_DATE)) + .withColumn("publicationJournal", f.lit(pub.PUB_JOURNAL)) + .withColumn("publicationTitle", f.lit(pub.PUB_TITLE)) + .withColumn( + "initialSampleSize", cls.get_initial_sample(f.col("projectId"), pub) + ) + .withColumn("nSamples", cls.get_n_samples(f.col("projectId"), pub)) + .withColumn( + "discoverySamples", cls.get_discovery_samples(f.col("projectId"), pub) + ) + .withColumn( + "ldPopulationStructure", + StudyIndex.aggregate_and_map_ancestries(f.col("discoverySamples")), + ) + .withColumn("cohorts", f.array(f.lit(pub.COHORTS))) + .select( + "studyId", + "geneId", + "projectId", + "studyType", + "traitFromSource", + # f.lit(None).cast("array").alias("traitFromSourceMappedIds"), + "biosampleFromSourceId", + "pubmedId", + "publicationTitle", + "publicationFirstAuthor", + "publicationDate", + "publicationJournal", + # f.lit(None) + # .cast("array") + # .alias("backgroundTraitsFromSourceMappedIds"), + "initialSampleSize", + # f.lit(None).cast(t.IntegerType()).alias("nCases"), + # f.lit(None).cast(t.IntegerType()).alias("nControls"), + "nSamples", + "cohorts", + "ldPopulationStructure", + "discoverySamples", + # f.lit(None) + # .cast("array>") + # .alias("replicationSamples"), + f.lit(None).cast("array").alias("qualityControls"), + # f.lit(None).cast("array").alias("aalysisFlags"), + "summarystatsLocation", + "hasSumstats", + # f.lit(None).cast("string").alias("conditions"), + # f.array() + # .cast("array>") + # .alias("sumstatQCValues"), + # f.lit(None).cast("array").alias("diseaseIds"), + # f.lit(None).cast("array").alias("backgroundDiseaseIds"), + "targetsFromSource", + "molecularComplexId", + ) + ) + + @staticmethod + def update_study_id(study_id: Column, targets: Column) -> Column: + """Update study ID to include gene symbol and protein name from target metadata. + + Args: + study_id (Column): Original study ID column. + targets (Column): Target metadata column containing gene symbol and protein name. + + Returns: + Column: Updated study ID column with gene symbol and protein name. + + The updated study ID will have the format: + {projectId}_{datasourceType}_{aptamerId}_{geneSymbols}_{proteinNames} + + Where geneSymbols and proteinNames are comma-joined values from the targets array. + + In case the geneSymbol or proteinName are missing, we use the placeholder value "_NA" + to maintain the structure of the study ID. + """ + study_id_parts = deCODEStudyIdParts.extract_study_id_parts(study_id) + return f.concat_ws( + "_", + study_id_parts.project_id, + study_id_parts.datasource_type, + study_id_parts.aptamer_id, + f.concat_ws(",", f.transform(targets, lambda x: f.coalesce(x.getField("geneSymbol"), f.lit("_NA")))), + f.concat_ws(",", f.transform(targets, lambda x: f.coalesce(x.getField("proteinId"), f.lit("_NA")))), + ).alias("updatedStudyId") diff --git a/src/gentropy/datasource/decode/summary_statistics.py b/src/gentropy/datasource/decode/summary_statistics.py new file mode 100644 index 000000000..67932beea --- /dev/null +++ b/src/gentropy/datasource/decode/summary_statistics.py @@ -0,0 +1,415 @@ +"""deCODE summary statistics module. + +This module provides: + +- **`deCODEHarmonisationConfig`** – a Pydantic model that holds the quality-control + and harmonisation parameters (MAC threshold, sample-size threshold, flipping window). + +- **`deCODESummaryStatistics`** – a utility class with two main pipelines: + + 1. `txtgz_to_parquet` – parallel ingestion of raw gzipped TSV files from the + deCODE S3 bucket into partitioned Parquet. + 2. `from_source` – harmonisation (schema alignment, MAC/sample-size filtering, + allele flipping against gnomAD EUR AF, EAF inference, sanity filtering, and + study-ID update). +""" + +from __future__ import annotations + +from concurrent.futures import ThreadPoolExecutor + +from pydantic import BaseModel +from pyspark.sql import Column, DataFrame +from pyspark.sql import functions as f +from pyspark.sql import types as t + +from gentropy import Session, SummaryStatistics +from gentropy.common.processing import mac, normalize_chromosome +from gentropy.common.stats import pvalue_from_neglogpval +from gentropy.dataset.study_index import ProteinQuantitativeTraitLocusStudyIndex +from gentropy.dataset.variant_direction import DEFAULT_WINDOW_SIZE, VariantDirection +from gentropy.datasource.decode import deCODEDataSource +from gentropy.datasource.decode.study_index import deCODEStudyIndex + + +class deCODEHarmonisationConfig(BaseModel): + """Configuration for deCODE harmonisation step. + + !!! note "Variant flipping logic" + The flipping window size has to be the same as the one used for + creating the variant direction dataset, otherwise the join will produce incorrect results. + The default value is sourced from `gentropy.dataset.variant_direction.DEFAULT_WINDOW_SIZE` + to keep both sides in sync. + """ + + min_mac: int + """Minimal value of Minor Allelic Count to include in harmonisation.""" + min_sample_size: int + """Minimal value of Sample Size to include in harmonisation.""" + flipping_window_size: int = DEFAULT_WINDOW_SIZE + """Window size (bp) used to partition the VariantDirection dataset (exact match only!). + + Defaults to `DEFAULT_WINDOW_SIZE` from `gentropy.dataset.variant_direction`. + """ + + +class deCODESummaryStatistics: + """Utility class for ingesting and harmonising deCODE proteomics summary statistics. + + This class is never instantiated directly. It exposes two class-method pipelines: + + * `txtgz_to_parquet` – reads one or more gzipped TSV files from the deCODE + S3 bucket in parallel (using a `ThreadPoolExecutor`) + and writes them as Parquet files partitioned by ``studyId``. + + * `from_source` – takes the raw Parquet output together with the + `VariantDirection` gnomAD reference + and the `ProteinQuantitativeTraitLocusStudyIndex` + and produces fully harmonised `SummaryStatistics` and an updated + study index with curated study IDs. + + Class attributes: + N_THREAD_OPTIMAL (int): Recommended number of ingestion threads (10). + N_THREAD_MAX (int): Hard upper limit on ingestion threads (500). + raw_schema (StructType): Spark schema of the raw deCODE TSV files. + """ + + N_THREAD_OPTIMAL = 10 + N_THREAD_MAX = 500 + + raw_schema = t.StructType( + [ + t.StructField("Chrom", t.StringType()), + t.StructField("Pos", t.LongType()), + t.StructField("Name", t.StringType()), + t.StructField("rsids", t.StringType()), + t.StructField("effectAllele", t.StringType()), + t.StructField("otherAllele", t.StringType()), + t.StructField("Beta", t.DoubleType()), + t.StructField("Pval", t.DoubleType()), + t.StructField("minus_log10_pval", t.DoubleType()), + t.StructField("SE", t.DoubleType()), + t.StructField("N", t.LongType()), + t.StructField("impMAF", t.DoubleType()), + ] + ) + + @classmethod + def txtgz_to_parquet( + cls, + session: Session, + summary_statistics_list: list[str], + raw_summary_statistics_output_path: str, + n_threads: int = N_THREAD_OPTIMAL, + ) -> None: + """Convert txt.gz (tsv) summary statistics to Parquet format. + + This method reads multiple gzipped TSV summary statistics files, + processes them in parallel using the specified number of threads, + and writes the combined output in Parquet format, partitioned by studyId. + + Args: + session (Session): Gentropy session. + summary_statistics_list (list[str]): List of summary statistics paths. + raw_summary_statistics_output_path (str): Output path for raw summary statistics in Parquet format. + n_threads (int): Number of threads to use. + + """ + if len(summary_statistics_list) == 0: + session.logger.warning("No summary statistics paths found to process.") + return + + if not isinstance(n_threads, int) or n_threads < 1: + session.logger.warning( + f"Invalid n_threads value: {n_threads}. Falling back to 10 threads." + ) + n_threads = cls.N_THREAD_OPTIMAL + if n_threads < cls.N_THREAD_OPTIMAL: + session.logger.warning( + f"Using low n_threads value: {n_threads}. This may lead to sub-optimal performance." + ) + if n_threads > cls.N_THREAD_MAX: + session.logger.warning( + f"Using high n_threads value: {n_threads}, this may lead to overloading spark driver." + ) + n_threads = cls.N_THREAD_MAX + + def process_one(input_path: str, output_path: str) -> None: + session.logger.info( + f"Converting gzipped summary statistics to Parquet from {input_path} to {output_path}." + ) + project_id = f.when( + f.input_file_name().contains("Proteomics_SMP"), + f.lit(deCODEDataSource.DECODE_PROTEOMICS_SMP.value), + ).otherwise(deCODEDataSource.DECODE_PROTEOMICS_RAW.value) + ( + session.spark.read.csv( + input_path, + sep="\t", + header=True, + schema=cls.raw_schema, + ) + .withColumn( + "studyId", + f.concat_ws( + "_", + project_id, + f.regexp_extract( + f.input_file_name(), r"^.*/(Proteomics_.*)\.txt.gz$", 1 + ), + ), + ) + # Ensure that the size of each partition is ~100Mb + .repartitionByRange(15, "Chrom", "Pos") + .write.mode("append") + .partitionBy("studyId") + .parquet(output_path) + ) + + with ThreadPoolExecutor(max_workers=n_threads) as pool: + pool.map( + lambda path: process_one(path, raw_summary_statistics_output_path), + summary_statistics_list, + ) + + @classmethod + def _infer_allele_frequency(cls, imp_maf: Column, eur_af: Column) -> Column: + """Infer allele frequency from imputed MAF and European AF. + + Args: + imp_maf (Column): Imputed minor allele frequency from source. + eur_af (Column): European allele frequency from gnomAD. + + Returns: + Column: Inferred allele frequency. + + !!! note "Inference logic" + The effect allele frequency (EAF) is inferred by comparing the imputed minor allele frequency (impMAF) + from deCODE with the European allele frequency (EUR_AF) from gnomAD. + + * If `EUR_AF` is null, the effect allele frequency cannot be inferred. In this case, the imputed + minor allele frequency (`impMAF`) is used as the EAF. This typically occurs for variants that are + unique to deCODE and absent from the gnomAD European population. + + * If `EUR_AF` is closer to `impMAF` than to `1 − impMAF`, the effect allele is assumed to be the + minor allele in the Icelandic population, and `impMAF` is used as the EAF. + + * If `EUR_AF` is closer to `1 − impMAF` than to `impMAF`, the effect allele is assumed to be the + major allele in the Icelandic population, and `1 − impMAF` is used as the EAF. + + Examples: + >>> data = [(0.01, 0.02), (0.01, 0.6), (0.01, None)] + >>> df = spark.createDataFrame(data, ["impMAF", "EUR_AF"]) + >>> df.withColumn("EAF", deCODESummaryStatistics._infer_allele_frequency(f.col("impMAF"), f.col("EUR_AF"))).show() + +------+------+----+ + |impMAF|EUR_AF| EAF| + +------+------+----+ + | 0.01| 0.02|0.01| + | 0.01| 0.6|0.99| + | 0.01| NULL|0.01| + +------+------+----+ + + """ + d1 = f.abs(eur_af - imp_maf) + d2 = f.abs(eur_af - (1 - imp_maf)) + + return ( + f.when(eur_af.isNull(), imp_maf) + .when(d1 <= d2, imp_maf) + .otherwise(1 - imp_maf) + .alias("effectAlleleFrequencyFromSource") + ) + + @classmethod + def from_source( + cls, + raw_summary_statistics: DataFrame, + variant_direction: VariantDirection, + decode_study_index: ProteinQuantitativeTraitLocusStudyIndex, + config: deCODEHarmonisationConfig, + ) -> tuple[SummaryStatistics, ProteinQuantitativeTraitLocusStudyIndex]: + """Harmonise raw deCODE summary statistics and produce an updated study index. + + The harmonisation pipeline performs the following steps in order: + + 1. **Schema alignment** – renames deCODE-specific column names to the + gentropy standard (e.g. ``Chrom`` → ``chromosome``, ``Beta`` → ``beta``). + 2. **MAC / sample-size filtering** – discards variants below + ``config.min_mac`` or ``config.min_sample_size`` to remove underpowered + associations and reduce output volume (~33 M → ~25 M rows). + 3. **Allele-flipping** – left-joins against the gnomAD `VariantDirection` dataset + (positive strand only) using ``(chromosome, rangeId, variantId)``. + Variants found in gnomAD are flipped to the gnomAD reference orientation; + unmatched variants are kept as-is. + 4. **EAF inference** – `_infer_allele_frequency` maps the deCODE + ``impMAF`` to an effect-allele frequency using the gnomAD EUR AF. + 5. **Sanity filter** – applies the standard `SummaryStatistics.sanity_filter`. + 6. **Study-ID update** – replaces the raw study IDs derived from file paths + with IDs that embed curated gene symbols and protein names from the + aptamer mapping table. + + !!! note "Variant flipping window" + ``config.flipping_window_size`` **must** match the window used when + building the `VariantDirection` dataset. A mismatch will silently produce + incorrect join keys. + + Args: + raw_summary_statistics (DataFrame): Raw summary-statistics Parquet DataFrame + as produced by `txtgz_to_parquet`. + variant_direction (VariantDirection): gnomAD variant-direction reference + used for allele flipping and EAF inference. + decode_study_index (ProteinQuantitativeTraitLocusStudyIndex): pQTL study + index produced by `deCODEStudyIndex.from_manifest`. + config (deCODEHarmonisationConfig): Configuration used during the harmonisation step. + + Returns: + tuple[SummaryStatistics, ProteinQuantitativeTraitLocusStudyIndex]: + A 2-tuple of the harmonised summary statistics and the study index + with updated, curated study IDs. + """ + # Get the estimated number of distinct studies to set the number of partitions for the final join + n_sumstats = decode_study_index.df.count() + pval = pvalue_from_neglogpval(f.col("neglogPval")) + _sumstats = ( + raw_summary_statistics.select( + normalize_chromosome(f.col("Chrom")).alias("chromosome"), + f.col("Pos").cast(t.IntegerType()).alias("position"), + f.col("effectAllele").alias("alt"), + f.col("otherAllele").alias("ref"), + f.col("Beta").cast(t.DoubleType()).alias("beta"), + f.col("minus_log10_pval").alias("neglogPval"), + f.col("SE").cast(t.DoubleType()).alias("standardError"), + f.col("N").cast(t.IntegerType()).alias("sampleSize"), + f.col("impMAF").cast(t.FloatType()).alias("impMAF"), + f.col("studyId"), + ) + .select( + f.col("studyId"), + f.concat_ws( + "_", + f.col("chromosome"), + f.col("position"), + f.col("alt"), + f.col("ref"), + ).alias("variantId"), + f.col("chromosome"), + f.col("position"), + f.col("beta"), + f.col("sampleSize"), + pval.mantissa.alias("pValueMantissa"), + pval.exponent.alias("pValueExponent"), + f.col("impMAF"), + f.col("standardError"), + f.floor(f.col("position") / config.flipping_window_size) + .cast(t.IntegerType()) + .alias("rangeId"), + ) + # Apply filtering on MAC and sample size + # This should reduce the number of variants from ~33mln to ~25mln + .filter(f.col("sampleSize") >= config.min_sample_size) + .filter(mac(f.col("impMAF"), f.col("sampleSize")) >= config.min_mac) + .repartitionByRange( + n_sumstats * 300 * 22, "studyId", "chromosome", "rangeId" + ) + .persist() + .alias("sumstats") + ) + + _vd = ( + # Need only positive strand variants + variant_direction.df.filter(f.col("strand") == 1) + .select( + f.col("chromosome"), + f.col("rangeId"), + f.col("originalVariantId"), + f.col("variantId"), + f.col("direction"), + f.filter( + f.col("originalAlleleFrequencies"), + lambda x: x.getField("populationName") == "nfe_adj", + ) + .getItem(0) + .getField("alleleFrequency") + .cast(t.FloatType()) + .alias("eur_af"), + ) + # NOTE: repartition("chromosome") produces very uneven partitions, + # Spark attempts then to fall back to `dynamic partitioning` algorithm + # which fails after N failures. + .repartitionByRange(n_sumstats * 300 * 22, "chromosome", "rangeId") + .persist() + .alias("vd") + ) + + _flipped = ( + _sumstats.join(_vd, on=["chromosome", "rangeId", "variantId"], how="left") + .select( + f.col("sumstats.studyId").alias("studyId"), + f.coalesce( + f.col("vd.originalVariantId"), f.col("sumstats.variantId") + ).alias("variantId"), + f.col("sumstats.chromosome").alias("chromosome"), + f.col("sumstats.position").alias("position"), + (f.col("sumstats.beta") * f.coalesce(f.col("vd.direction"), f.lit(1))) + .cast("double") + .alias("beta"), + f.col("sumstats.sampleSize").alias("sampleSize"), + f.col("sumstats.pValueMantissa").alias("pValueMantissa"), + f.col("sumstats.pValueExponent").alias("pValueExponent"), + cls._infer_allele_frequency( + f.col("sumstats.impMAF"), f.col("vd.eur_af") + ).alias("effectAlleleFrequencyFromSource"), + f.col("sumstats.standardError").alias("standardError"), + ) + .select( + f.col("studyId"), + f.col("variantId"), + f.col("chromosome"), + f.col("position"), + f.col("beta"), + f.col("sampleSize"), + f.col("pValueMantissa"), + f.col("pValueExponent"), + f.col("effectAlleleFrequencyFromSource"), + f.col("standardError"), + ) + .sort("studyId", "chromosome", "position") + # Approximate number of partitions = 15 * number of studies + .repartitionByRange(n_sumstats * 10, "studyId", "chromosome", "position") + ) + + si = decode_study_index.df.withColumn( + "updatedStudyId", + deCODEStudyIndex.update_study_id( + f.col("studyId"), f.col("targetsFromSource") + ), + ) + _vd.unpersist() + _sumstats.unpersist() + + _harmonised = SummaryStatistics( + _df=SummaryStatistics(_flipped) + .sanity_filter() + .df.join( + si.select(f.col("updatedStudyId"), f.col("studyId")), + on="studyId", + how="left", + ) + # In case the sumstat was not found in studyIndex, resolve with original studyId + # To avoid losing summary statistics data. + .withColumn( + "studyId", f.coalesce(f.col("updatedStudyId"), f.col("studyId")) + ) + .drop("updatedStudyId") + .persist() + ) + + _pqtl_si = ProteinQuantitativeTraitLocusStudyIndex( + _df=si.drop("studyId") + .withColumnRenamed("updatedStudyId", "studyId") + .persist() + ) + + return (_harmonised, _pqtl_si) + + return (_harmonised, _pqtl_si) diff --git a/src/gentropy/decode_ingestion.py b/src/gentropy/decode_ingestion.py new file mode 100644 index 000000000..b38e16863 --- /dev/null +++ b/src/gentropy/decode_ingestion.py @@ -0,0 +1,345 @@ +r"""deCODE ingestion step. + +## Process overview + +The ingestion pipeline for the deCODE dataset consists of the following steps, which +must be executed in order: + +1. **Obtain an S3 bucket listing** from the deCODE S3 bucket: + + ```bash + aws s3 ls \ + --recursive \ + --human-readable \ + --summarize \ + --profile $1 \ + $2 \ + --endpoint-url https://${S3_HOST_URL}:${S3_HOST_PORT} \ + | grep "Proteomics" > manifest.txt + ``` + +2. **Generate the manifest** from the bucket listing using `deCODEManifestGenerationStep`. +3. **Ingest protein-complex data** from predicted and experimental files using `MolecularComplexIngestionStep`. +4. **Ingest raw summary statistics** from the `txt.gz` files to Parquet using `deCODESummaryStatisticsIngestionStep`. +5. **Harmonise summary statistics** (including study-index creation and QC) using `deCODESummaryStatisticsHarmonisationStep`. +6. **Transform the pQTL study index** into a standard study index using `pQTLStudyIndexTransformationStep`. + +!!! note "Filtering variants" + During the harmonisation step, variants with minor allele count (MAC) < 50 and sample size < 30,000 + are discarded to ensure sufficient statistical power and to reduce false positives. + +!!! note "Allele flipping" + The harmonisation step includes allele flipping based on the gnomAD EUR allele frequency: + + - If the allele exists in gnomAD, it is harmonised to the gnomAD allele order. + - If the allele does not exist in gnomAD, it is kept as-is (no flip). + - If the allele is strand-ambiguous it is kept as in gnomAD, or retained as-is if not in gnomAD. + + +!!! note "Effect Allele frequency" + Because deCODE summary statistics report only the minor allele frequency _m_, the + effect allele frequency is **inferred using gnomAD EUR allele frequency** _e_: + + ```math + \begin{aligned} + d_1 &:= |e - m|, \\ + d_2 &:= |(1 - e) - m|, \\ + \text{effectAlleleFrequencyFromSource} &= + \begin{cases} + m, & \text{if } e \text{ is null},\\[4pt] + m, & \text{if } d_1 \le d_2,\\[4pt] + 1 - m, & \text{otherwise}. + \end{cases} + \end{aligned} + ``` + +## Data flow + +```mermaid +flowchart TD + subgraph INPUTS + A1["S3 bucket listing (aws s3 ls)"] + A2["S3 config (s3_config_path)"] + A3[AptamerMetadata] + A4[gnomAD VariantDirection] + A5[predicted_complex_tab] + A6[experimental_complex_tab] + A7[TargetIndex] + end + + subgraph OUTPUTS + O1[harmonised_summary_statistics] + O2[protein_qtl_study_index] + O3[qc_summary_statistics] + O4[study_index] + end + + A1 --> MGEN[deCODEManifestGenerationStep] + A2 --> MGEN + MGEN --> P1[manifest] + + A5 --> MCGEN[MolecularComplexIngestionStep] + A6 --> MCGEN + MCGEN --> P2[molecular_complex] + + P1 --> INGEST[deCODESummaryStatisticsIngestionStep] + INGEST --> P3[raw_summary_statistics] + + P3 --> HARM[deCODESummaryStatisticsHarmonisationStep] + P1 --> HARM + A3 --> HARM + A4 --> HARM + P2 --> HARM + + HARM --> O1 + HARM --> O2 + HARM --> O3 + + O2 --> TRANS[pQTLStudyIndexTransformationStep] + A7 --> TRANS + TRANS --> O4 + + classDef parquet fill:#bd757c,stroke:#73343A,color:#333 + class A1,A2,A3,A4,A5,A6,A7,P1,P2,P3,O1,O2,O3,O4 parquet +``` + +??? tip "Inputs" + - [x] **S3 bucket listing** — text file produced by `aws s3 ls`, required by `deCODEManifestGenerationStep`. + - [x] **S3 config** — JSON/YAML file with the bucket name used to construct `s3a://` paths. + - [x] **AptamerMetadata** — SomaScan study table mapping aptamer IDs to gene symbols and UniProt IDs. + - [x] **gnomAD VariantDirection** — used for allele flipping and EAF inference during harmonisation. + - [x] **Protein-complex tables** — predicted and experimental files for `MolecularComplexIngestionStep`. + - [x] **TargetIndex** — Ensembl gene annotations used by `pQTLStudyIndexTransformationStep`. + +??? tip "Outputs" + This pipeline produces 4 artefacts: + + - [x] **harmonised_summary_statistics** — harmonised summary statistics in Parquet format. + - [x] **protein_qtl_study_index** — pQTL study index annotated with QC values. + - [x] **qc_summary_statistics** — per-study summary-statistics QC metrics in Parquet format. + - [x] **study_index** — standard study index with resolved Ensembl gene IDs. + +""" + +from __future__ import annotations + +from gentropy import ( + Session, + SummaryStatisticsQC, +) +from gentropy.dataset.molecular_complex import MolecularComplex +from gentropy.dataset.variant_direction import VariantDirection +from gentropy.datasource.decode.aptamer_metadata import AptamerMetadata +from gentropy.datasource.decode.manifest import deCODEManifest +from gentropy.datasource.decode.study_index import deCODEStudyIndex +from gentropy.datasource.decode.summary_statistics import ( + deCODEHarmonisationConfig, + deCODESummaryStatistics, +) + + +class deCODEManifestGenerationStep: + """Build the deCODE manifest Parquet dataset from an ``aws s3 ls`` bucket listing. + + This step should be run **once** after obtaining a fresh listing of the deCODE S3 + bucket. The resulting manifest is consumed by all downstream ingestion steps. + + See `deCODEManifest.from_bucket_listing` for details on the expected input file format. + """ + + def __init__( + self, + session: Session, + bucket_listing_path: str, + output_path: str, + s3_config_path: str | None = None, + ) -> None: + """Initialise and execute the deCODE manifest generation step. + + Args: + session (Session): Active Gentropy Spark session. + bucket_listing_path (str): Path to the text file produced by + ``aws s3 ls --recursive --human-readable --summarize``. + output_path (str): Destination path for the manifest Parquet dataset. + s3_config_path (str | None): Optional path to the S3 configuration file containing + the bucket name used to construct fully-qualified ``s3a://`` paths. If not provided, + the method will attempt to load from environment variables. + """ + manifest = deCODEManifest.from_bucket_listing( + session=session, + s3_config_path=s3_config_path, + path=bucket_listing_path, + ) + manifest.df.repartition(1).write.mode(session.write_mode).parquet(output_path) + + +class deCODESummaryStatisticsIngestionStep: + """Ingest deCODE summary statistics from gzipped TSV files into Parquet format. + + Reads all summary-statistics paths recorded in the manifest and converts them + in parallel (up to `deCODESummaryStatistics.N_THREAD_MAX` + concurrent threads) from the deCODE S3 bucket into a single partitioned Parquet dataset. + + The step expects the Spark session to be configured with the Hadoop AWS connector + so that ``s3a://`` paths are accessible. A representative configuration is shown + in the example below. + + Examples: + >>> session = Session( + ... spark_uri="yarn", + ... extended_spark_conf={ + ... # Executor + ... "spark.executor.memory": "32g", + ... "spark.executor.cores": "8", + ... "spark.excutor.memoryOverhead": "4g", + ... "spark.dynamicAllocation.enabled": "true", + ... "spark.sql.files.maxPartitionBytes": "512m", + ... # Driver + ... "spark.driver.memory": "25g", + ... "spark.executor.extraJavaOptions": "-XX:+UseG1GC -XX:MaxGCPauseMillis=200 -XX:+ParallelRefProcEnabled -XX:+AlwaysPreTouch", + ... "spark.jars.packages": "org.apache.hadoop:hadoop-aws:3.3.6,com.amazonaws:aws-java-sdk-bundle:1.12.367", + ... "spark.hadoop.fs.s3a.impl": "org.apache.hadoop.fs.s3a.S3AFileSystem", + ... "spark.hadoop.fs.s3a.endpoint": f"https://{credentials.s3_host_url}:{credentials.s3_host_port}", + ... "spark.hadoop.fs.s3a.path.style.access": "true", + ... "spark.hadoop.fs.s3a.connection.ssl.enabled": "true", + ... "spark.hadoop.fs.s3a.access.key": f"{credentials.access_key_id}", + ... "spark.hadoop.fs.s3a.secret.key": f"{credentials.secret_access_key}", + ... # Throughput tuning + ... "spark.hadoop.fs.s3a.connection.maximum": "1000", + ... "spark.hadoop.fs.s3a.threads.max": "1024", + ... "spark.hadoop.fs.s3a.attempts.maximum": "20", + ... "spark.hadoop.fs.s3a.connection.timeout": "600000", # 10min + ... }, + ... ) # doctest: +SKIP + """ + + def __init__( + self, + session: Session, + decode_manifest_path: str, + raw_summary_statistics_path: str, + ) -> None: + """Initialise and execute the deCODE summary-statistics ingestion step. + + Args: + session (Session): Active Gentropy Spark session with S3 connectivity + configured via the Hadoop AWS connector (see class docstring). + decode_manifest_path (str): Path to the manifest Parquet dataset produced + by `deCODEManifestGenerationStep`. + raw_summary_statistics_path (str): Destination path for the raw summary + statistics Parquet dataset, partitioned by ``studyId``. + """ + manifest = deCODEManifest.from_parquet(session, decode_manifest_path) + summary_statistics_paths = manifest.get_summary_statistics_paths() + deCODESummaryStatistics.txtgz_to_parquet( + session=session, + summary_statistics_list=summary_statistics_paths, + raw_summary_statistics_output_path=raw_summary_statistics_path, + n_threads=deCODESummaryStatistics.N_THREAD_MAX, + ) + + +class deCODESummaryStatisticsHarmonisationStep: + """Harmonise ingested deCODE summary statistics and generate pQTL study-index and QC outputs. + + The step performs the following operations in sequence: + + 1. Builds the `ProteinQuantitativeTraitLocusStudyIndex` + from the manifest, aptamer metadata, and molecular-complex datasets. + 2. Runs the harmonisation pipeline (`deCODESummaryStatistics.from_source`) + which includes schema alignment, MAC/sample-size filtering, allele flipping + against gnomAD EUR AF, EAF inference, sanity filtering, and study-ID update. + 3. Executes `SummaryStatisticsQC` and writes per-study QC metrics to Parquet. + 4. Annotates the pQTL study index with QC results and writes it to Parquet. + """ + + def __init__( + self, + session: Session, + # inputs + raw_summary_statistics_path: str, + manifest_path: str, + aptamer_metadata_path: str, + variant_direction_path: str, + molecular_complex_path: str, + # outputs + harmonised_summary_statistics_path: str, + protein_qtl_study_index_path: str, + qc_summary_statistics_path: str, + # config + min_mac_threshold: int = 50, + min_sample_size_threshold: int = 30_000, + flipping_window_size: int = 10_000_000, + pval_threshold: float = 5e-8, + ) -> None: + """Initialise and execute the deCODE summary-statistics harmonisation step. + + Args: + session (Session): Active Gentropy Spark session. + raw_summary_statistics_path (str): Path to the raw summary-statistics Parquet + dataset produced by `deCODESummaryStatisticsIngestionStep`. + manifest_path (str): Path to the manifest Parquet dataset produced by + `deCODEManifestGenerationStep`. + aptamer_metadata_path (str): Path to the aptamer metadata TSV file. + variant_direction_path (str): Path to the gnomAD + `VariantDirection` Parquet dataset + used for allele flipping and EAF inference. + molecular_complex_path (str): Path to the molecular-complex Parquet dataset + produced by `MolecularComplexIngestionStep`. + harmonised_summary_statistics_path (str): Destination path for the harmonised + summary-statistics Parquet dataset, partitioned by ``studyId``. + protein_qtl_study_index_path (str): Destination path for the pQTL study index + Parquet dataset annotated with QC results. + qc_summary_statistics_path (str): Destination path for the per-study QC metrics + Parquet dataset. + min_mac_threshold (int): Minimum minor allele count (MAC) required to retain a + variant. Defaults to 50. + min_sample_size_threshold (int): Minimum sample size required to retain a variant. + Defaults to 30,000. + flipping_window_size (int): Genomic window size (bp) used to partition the + VariantDirection dataset for the allele-flipping join. Must match the value + used when building the VariantDirection dataset. Defaults to 10,000,000. + pval_threshold (float): P-value threshold used by `SummaryStatisticsQC`. + Defaults to 1e-6. + """ + config = deCODEHarmonisationConfig( + min_mac=min_mac_threshold, + min_sample_size=min_sample_size_threshold, + flipping_window_size=flipping_window_size, + ) + + # 1. Produce the PQTLStudyIndex + m = deCODEManifest.from_parquet(session, manifest_path).persist() + mc = MolecularComplex.from_parquet(session, molecular_complex_path).persist() + am = AptamerMetadata.from_source(session, aptamer_metadata_path).persist() + _pqtl_si = deCODEStudyIndex.from_manifest(m, am, mc).persist() + m.unpersist() + am.unpersist() + mc.unpersist() + + # 2. Produce harmonised summary statistics + gvd = VariantDirection.from_parquet(session, variant_direction_path) + rss = session.spark.read.parquet(raw_summary_statistics_path) + hss, pqtl_si = deCODESummaryStatistics.from_source(rss, gvd, _pqtl_si, config) + + hss.persist() + pqtl_si.persist() + + hss.df.write.mode(session.write_mode).partitionBy("studyId").option( + "maxRecordsPerFile", 50_000_000 + ).parquet(harmonised_summary_statistics_path) + + # 3. Run QualityControl + hss_qc = SummaryStatisticsQC.from_summary_statistics( + hss, pval_threshold + ).persist() + hss.unpersist() + hss_qc.df.coalesce(1).write.mode(session.write_mode).parquet( + qc_summary_statistics_path + ) + ( + pqtl_si.annotate_sumstats_qc(hss_qc) + .df.coalesce(1) + .write.mode(session.write_mode) + .parquet(protein_qtl_study_index_path) + ) diff --git a/src/gentropy/external/s3.py b/src/gentropy/external/s3.py new file mode 100644 index 000000000..721a207e6 --- /dev/null +++ b/src/gentropy/external/s3.py @@ -0,0 +1,169 @@ +"""Module for S3 configuration.""" + +from __future__ import annotations + +import json +import logging +import os + +from pydantic import BaseModel + + +class S3Config(BaseModel): + """Model for S3 configuration. + + Note: + This configuration is used to connect to S3 compatible storage. + Ensure that the access key and secret key have the necessary permissions + to access the specified bucket. This configuration can be loaded from a JSON file + using the `from_file` class method. + + Examples: + --- + >>> config = S3Config( + ... bucket_name="my-bucket", + ... s3_host_port=9000, + ... s3_host_url="s3.my-domain.com", + ... access_key_id="my-access-key-id", + ... secret_access_key="my-secret-access-key", + ... ) + >>> print(config.bucket_name) + my-bucket + >>> print(config.s3_host_port) + 9000 + >>> print(config.s3_host_url) + s3.my-domain.com + >>> print(config.access_key_id) + my-access-key-id + >>> print(config.secret_access_key) + my-secret-access-key + """ + + bucket_name: str + """Name of the bucket, without s3:// or s3a:// prefix.""" + s3_host_port: int + """Port number of the S3 host.""" + s3_host_url: str + """URL of the S3 host.""" + access_key_id: str + """Access key ID for S3 authentication.""" + secret_access_key: str + """Secret access key for S3 authentication.""" + + @classmethod + def from_file(cls, path: str) -> S3Config: + """Load S3 configuration from a file. + + Args: + path (str): Path to the configuration file. + + Returns: + S3Config: S3 configuration instance. + + Examples: + --- + >>> import tempfile + >>> import os + >>> config_data = { + ... "bucket_name": "my-bucket", + ... "s3_host_port": 9000, + ... "s3_host_url": "s3.my-domain.com", + ... "access_key_id": "my-access-key-id", + ... "secret_access_key": "my-secret-access-key", + ... } + >>> with tempfile.NamedTemporaryFile(mode='w', delete=False) as tmpfile: + ... json.dump(config_data, tmpfile) + ... tmpfile_path = tmpfile.name + >>> config = S3Config.from_file(tmpfile_path) + >>> config.bucket_name + 'my-bucket' + >>> os.remove(tmpfile_path) + + """ + with open(path, encoding="utf-8") as f: + config_data = json.load(f) + return cls(**config_data) + + @classmethod + def from_env(cls) -> S3Config: + """Load S3 configuration from environment variables. + + Returns: + S3Config: S3 configuration instance. + + !!! note: + The following environment variables must be set: + - `AWS_S3_BUCKET_NAME`: Name of the S3 bucket. + - `AWS_ENDPOINT_URL`: Endpoint URL of the S3 service in the format 'host:port'. + - `AWS_ACCESS_KEY_ID`: Access key ID for S3 authentication. + - `AWS_SECRET_ACCESS_KEY`: Secret access key for S3 authentication. + + Examples: + --- + >>> import os + >>> os.environ["AWS_S3_BUCKET_NAME"] = "my-bucket" + >>> os.environ["AWS_ENDPOINT_URL"] = "s3.my-domain.com:9000" + >>> os.environ["AWS_ACCESS_KEY_ID"] = "my-access-key-id" + >>> os.environ["AWS_SECRET_ACCESS_KEY"] = "my-secret-access-key" + >>> config = S3Config.from_env() + >>> config.bucket_name + 'my-bucket' + """ + bucket = os.getenv("AWS_S3_BUCKET_NAME") + if bucket is None: + raise ValueError("AWS_S3_BUCKET_NAME environment variable is not set.") + + endpoint_url = os.getenv("AWS_ENDPOINT_URL", "s3.amazonaws.com") + if not endpoint_url: + raise ValueError("AWS_ENDPOINT_URL environment variable is not set.") + + _split = endpoint_url.split(":") + if not len(_split) == 2: + raise ValueError( + "AWS_ENDPOINT_URL environment variable must be in the format 'host:port'." + ) + s3_host_url = _split[0] + s3_host_port_str = _split[1] + if not s3_host_port_str.isdigit(): + raise ValueError( + "Port number in AWS_ENDPOINT_URL environment variable must be an integer." + ) + + access_key_id = os.getenv("AWS_ACCESS_KEY_ID") + if access_key_id is None: + raise ValueError("AWS_ACCESS_KEY_ID environment variable is not set.") + + secret_access_key = os.getenv("AWS_SECRET_ACCESS_KEY") + if secret_access_key is None: + raise ValueError("AWS_SECRET_ACCESS_KEY environment variable is not set.") + + return cls( + bucket_name=bucket, + s3_host_port=int(s3_host_port_str), + s3_host_url=s3_host_url, + access_key_id=access_key_id, + secret_access_key=secret_access_key, + ) + + @classmethod + def read(cls, path: str | None = None) -> S3Config: + """Read from file or environment variables. + + Args: + path (str | None): Optional path to the configuration file. If not provided, + the method will attempt to load from environment variables. + + Returns: + S3Config: S3 configuration instance. + """ + if path is None: + logging.info( + "No S3 configuration file path provided. Attempting to load from environment variables." + ) + return cls.from_env() + try: + return cls.from_file(path) + except Exception as e: + logging.warning(f"Failed to load S3 configuration from file: {e}") + logging.info("Falling back to environment variables for S3 configuration.") + return cls.from_env() diff --git a/src/gentropy/molecular_complex.py b/src/gentropy/molecular_complex.py new file mode 100644 index 000000000..385ddd030 --- /dev/null +++ b/src/gentropy/molecular_complex.py @@ -0,0 +1,39 @@ +"""Steps to ingest molecular complex data into a `MolecularComplex` Parquet dataset.""" + +from __future__ import annotations + +from gentropy import Session +from gentropy.datasource.complex_portal import ComplexTab + + +class MolecularComplexIngestionStep: + """Ingest predicted and experimental protein-complex data into a `MolecularComplex` Parquet dataset. + + The molecular complex dataset is derived from ComplexTAB files from the Complex Portal. + """ + + def __init__( + self, + session: Session, + predicted_complex_tab_path: str, + experimental_complex_tab_path: str, + output_path: str, + ) -> None: + """Initialise and execute the molecular complex ingestion step. + + Args: + session (Session): Active Gentropy Spark session. + predicted_complex_tab_path (str): Path to the predicted protein-complex + tab-separated file. + experimental_complex_tab_path (str): Path to the experimental protein-complex + tab-separated file. + output_path (str): Destination path for the merged + `MolecularComplex` Parquet dataset. + """ + ComplexTab.from_complex_tab( + session=session, + experimental=experimental_complex_tab_path, + predicted=predicted_complex_tab_path, + ).coalesce(session.output_partitions).df.write.mode("overwrite").parquet( + output_path + ) diff --git a/src/gentropy/pqtl_study.py b/src/gentropy/pqtl_study.py new file mode 100644 index 000000000..0eb971dde --- /dev/null +++ b/src/gentropy/pqtl_study.py @@ -0,0 +1,42 @@ +"""Methods for transforming a `ProteinQuantitativeTraitLocusStudyIndex` into a standard `StudyIndex`.""" + +from __future__ import annotations + +from gentropy import Session, TargetIndex +from gentropy.dataset.study_index import ProteinQuantitativeTraitLocusStudyIndex + + +class pQTLStudyIndexTransformationStep: + """Transform a `ProteinQuantitativeTraitLocusStudyIndex` into a standard `StudyIndex`. + + This step resolves gene-level and protein-level annotations from the + `TargetIndex` (e.g. Ensembl gene IDs) and + writes a study index compatible with the downstream Open Targets genetics pipeline. + """ + + def __init__( + self, + session: Session, + protein_study_index_path: str, + study_index_path: str, + target_index_path: str, + ) -> None: + """Initialise and execute the pQTL study-index transformation step. + + Args: + session (Session): Active Gentropy Spark session. + protein_study_index_path (str): Path to the + `ProteinQuantitativeTraitLocusStudyIndex`. + study_index_path (str): Destination path for the resolved + `StudyIndex` Parquet dataset. + target_index_path (str): Path to the + `TargetIndex` Parquet dataset used + to map gene symbols to Ensembl gene IDs. + """ + pqtl = ProteinQuantitativeTraitLocusStudyIndex.from_parquet( + session, protein_study_index_path + ) + ti = TargetIndex.from_parquet(session, target_index_path) + + s = pqtl.to_study(ti) + s.df.coalesce(1).write.mode(session.write_mode).parquet(study_index_path) diff --git a/tests/gentropy/data_samples/aws_bucket_listing.txt b/tests/gentropy/data_samples/aws_bucket_listing.txt new file mode 100644 index 000000000..26e8d7192 --- /dev/null +++ b/tests/gentropy/data_samples/aws_bucket_listing.txt @@ -0,0 +1,2 @@ +2022-05-29 09:27:28 927.2 MiB some_folder/Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001.txt.gz +2022-05-29 09:27:35 926.0 MiB some_folder/Proteomics_PC0_10001_1_GENE2__SOME_PROTEIN_2_00000001.txt.gz diff --git a/tests/gentropy/data_samples/complex_tab/9606.tsv b/tests/gentropy/data_samples/complex_tab/9606.tsv new file mode 100644 index 000000000..055010aca --- /dev/null +++ b/tests/gentropy/data_samples/complex_tab/9606.tsv @@ -0,0 +1,9 @@ +#Complex ac Recommended name Aliases for complex Taxonomy identifier Identifiers (and stoichiometry) of molecules in complex Evidence Code Experimental evidence Go Annotations Cross references Description Complex properties Complex assembly Ligand Disease Agonist Antagonist Comment Source Expanded participant list +CPX-1 SMAD2-SMAD3-SMAD4 complex SMAD2/SMAD3/SMAD4 transcription factor complex 9606 P84022(1)|Q13485(1)|Q15796(1) ECO:0005547(biological system reconstruction evidence based on inference from background scientific knowledge used in manual assertion) - GO:0071144(heteromeric SMAD protein complex)|GO:0003690(double-stranded DNA binding)|GO:0003700(DNA-binding transcription factor activity)|GO:0006355(regulation of DNA-templated transcription)|GO:0032924(activin receptor signaling pathway)|GO:0007179(transforming growth factor beta receptor signaling pathway) reactome:R-HSA-9736938(identity)|reactome:R-HSA-9736929(identity)|pubmed:35359452(see-also)|qsproteome:QS143229(identity)|pubmed:16322555(see-also)|complex portal:CPX-1(complex-primary)|wwpdb:1U7V(subset) A transcription factor complex which binds to the promoters of target genes and recruits co-activators and histone acetyltransferases, such as p300, CBP and P300/CBP-associated factor, facilitating transcription. In response to TGF-beta/activin-family protein binding, TGF-beta type II receptors phosphorylate TGF-beta type I receptors (ALK4, 5 and 7) which in turn phosphorylates SMAD2 on two Ser-465 and Ser-467, and SMAD3 on Ser-423 and Ser-425. This enables binding to SMAD4 to form heteromeric SMAD complexes that enter the nucleus to initiate gene transcription. Because of their relatively low DNA-binding affinity, SMAD complexes interact with a wide variety of DNA-binding proteins. Crosstalk with other signalling pathways and interaction with other DNA-binding cofactors define the specific binding patterns of SMADs; in addition, interaction with coactivators/corepressors modulates their transcriptional activity. Preferential formation of the regulatory R-Smad/SMAD4 heterotrimer over the R-Smad homotrimer is largely enthalpy driven, contributed by the unique presence of strong electrostatic interactions within the heterotrimeric interfaces. These electrostatic interactions exist only in the heterotrimer due to specific charged residues in the SMAD4 subunit, Asp-493 and Arg-378, mediating complementary electrostatic interactions with the neighbouring R-Smad subunits. Heterotrimer - - - - - psi-mi:"MI:0469"(IntAct) P84022(1)|Q13485(1)|Q15796(1) +CPX-8 bZIP transcription factor complex, ATF4-CREB1 - 9606 P16220(1)|P18848(1) ECO:0005544(biological system reconstruction evidence based on orthology evidence used in manual assertion) - GO:0000977(RNA polymerase II transcription regulatory region sequence-specific DNA binding)|GO:0000981(DNA-binding transcription factor activity, RNA polymerase II-specific)|GO:0005634(nucleus)|GO:0006357(regulation of transcription by RNA polymerase II)|GO:0090575(RNA polymerase II transcription regulator complex) qsproteome:QS184715(identity)|complex portal:CPX-8(complex-primary)|complex portal:CPX-6(inferred-from)|pubmed:23661758(see-also)|pubmed:28186491(see-also)|pubmed:12871976(see-also) Transcription factor complex that binds the cAMP response element (CRE) (consensus: 5'-GTGACGT[AC][AG]-3') of the GRP78 (HSPA5) promoter. Involved in the ER stress response pathway. - Heterodimer - - - - - psi-mi:"MI:0469"(IntAct) P16220(1)|P18848(1) +CPX-9 bZIP transcription factor complex, ATF1-ATF4 ATF4-ATF1 transcription factor complex 9606 P18846(1)|P18848(1) ECO:0005544(biological system reconstruction evidence based on orthology evidence used in manual assertion) - GO:0005634(nucleus)|GO:0000977(RNA polymerase II transcription regulatory region sequence-specific DNA binding)|GO:0000981(DNA-binding transcription factor activity, RNA polymerase II-specific)|GO:0045944(positive regulation of transcription by RNA polymerase II)|GO:0090575(RNA polymerase II transcription regulator complex) qsproteome:QS220074(identity)|pubmed:23661758(see-also)|pubmed:28186491(see-also)|complex portal:CPX-9(complex-primary)|complex portal:CPX-7(inferred-from)|pubmed:12871976(see-also) Transcription factor complex which binds to a specific DNA consensus sequence to regulate transcription. The DNA recognition sequence depends on the composition of the bZIP dimer with the complex either binding to the preferred region of one of the partners or to a novel bZIP cognate site. Dimerization is mediated by the basic leucine-zipper (bZIP) 60-80 amino acid domain, consisting of a highly conserved DNA binding basic region and a more diversified leucine zipper dimerization region. The latter domain adopts an alpha helical structure where leucine, or leucine-like, side chains line up on the same side of the helix and interact with the alpha helix of the leucine zipper of the other family member to enable dimer formation. DNA binding specificity appears to be linked to low-affinity binding sites which guide transcription factors to their cognate target sites. Heterodimer - - - - - psi-mi:"MI:0469"(IntAct) P18846(1)|P18848(1) +CPX-11 SMAD2 homotrimer - 9606 Q15796(3) ECO:0000353(physical interaction evidence used in manual assertion) intact:EBI-25772101 GO:0071142(homomeric SMAD protein complex) qsproteome:QS155995(identity)|pubmed:16322555(see-also)|wwpdb:1khx(identity)|complex portal:CPX-11(complex-primary)|pubmed:11779503(see-also) In the absence of Smad4, R-Smad phosphorylation results in homotrimerization, however, this complex does not appear to import into the nucleus and is assumed to be transcriptionally inactive. The R-Smad homotrimer is stabilized by the interaction between phosphoserine residues of the C-terminal tail and positively charged residues in an adjacent subunit, as well as through extensive hydrogen bonds and van der Waals contacts at the conserved trimer interface. Homotrimer - - - - - psi-mi:"MI:0469"(IntAct) Q15796(3) +CPX-12 SMAD3 homotrimer - 9606 P84022(3) ECO:0005546(physical interaction evidence used in manual assertion) - GO:0071142(homomeric SMAD protein complex) qsproteome:QS134252(identity)|pubmed:16322555(see-also)|complex portal:CPX-12(complex-primary)|pubmed:29234012(see-also)|wwpdb:5OD6(identity)|pubmed:22045334(see-also) In the absence of Smad4, R-Smad phosphorylation results in homotrimerization, however, this complex does not appear to import into the nucleus and is assumed to be transcriptionally inactive. The R-Smad homotrimer is stabilized by the interaction between phosphoserine residues of the C-terminal tail and positively charged residues in an adjacent subunit, as well as through extensive hydrogen bonds and van der Waals contacts at the conserved trimer interface. Homotrimer - - - - - psi-mi:"MI:0469"(IntAct) P84022(3) +CPX-17 Telomerase catalytic core complex - 9606 O14746(2)|URS00004A7003_9606(2) ECO:0000353(physical interaction evidence used in manual assertion) intact:EBI-8789396 GO:0000722(telomere maintenance via recombination)|GO:0007004(telomere maintenance via telomerase)|GO:0000333(telomerase catalytic core complex)|GO:0003720(telomerase activity) qsproteome:QS241426(identity)|efo:MONDO:0004992(see-also)|efo:MONDO:0019499(see-also)|efo:EFO:0000768(see-also)|efo:MONDO:0015780(see-also)|pubmed:22057212(see-also)|intenz:2.7.7.49(identity)|pubmed:11432839(see-also)|complex portal:CPX-17(complex-primary) A ribonucleoprotein complex essential for the replication of chromosome termini in most eukaryotes. Catalytic component of the telomerase holoenzyme complex whose main activity is the elongation of telomeres. Acts as a reverse transcriptase that adds simple sequence repeats to chromosome ends by copying a template sequence within the RNA component of the enzyme. Catalyzes the RNA-dependent extension of 3'-chromosomal termini with the 6-nucleotide telomeric repeat unit, 5'-TTAGGG-3'. The catalytic cycle involves primer binding, primer extension and release of product once the template boundary has been reached or nascent product translocation followed by further extension. Overexpressed telomerase results in telomere lengthening which may lead to cell immortalization and cancer cell pathogenesis. - Homodimer - Causes a range of cancers when overexpressed.|Aplastic anemia (AA) [MIM:609135]: A form of anemia in which the bone marrow fails to produce adequate numbers of peripheral blood elements. It is characterized by peripheral pancytopenia and marrow hypoplasia.|Idiopathic pulmonary fibrosis [MIM:178500]: A lung disease characterized by shortness of breath, radiographically evident diffuse pulmonary infiltrates, and varying degrees of inflammation and fibrosis on biopsy. In some cases, the disorder can be rapidly progressive and characterized by sequential acute lung injury with subsequent scarring and end-stage lung disease.|Dyskeratosis congenita: A group of rare multisystem disorders caused by defective telomere maintenance. Clinical features are highly variable and include bone marrow failure, predisposition to malignancy, and pulmonary and hepatic fibrosis. The classic clinical triad of abnormal skin pigmentation, leukoplakia, and nail dystrophy is not always observed. Other features include premature graying of the hair, aplastic anemia, low platelets, osteoporosis, epiphora, dental abnormalities and testicular atrophy, among others. Early mortality is often associated with bone marrow failure, infections, fatal pulmonary complications, or malignancy. - - - psi-mi:"MI:0469"(IntAct) O14746(2) +CPX-20 TERT-RMRP complex - 9606 O14746(0)|URS000075C8FA_9606(0) ECO:0000353(physical interaction evidence used in manual assertion) intact:EBI-9875772 GO:1990572(TERT-RMRP complex)|GO:0003968(RNA-directed 5'-3' RNA polymerase activity)|GO:0030422(production of siRNA involved in RNA interference) qsproteome:QS179647(identity)|efo:MONDO:0009595(see-also)|intenz:2.7.7.49(identity)|complex portal:CPX-20(complex-primary)|pubmed:19701182(see-also)|rhea:RHEA:22508(identity) A ribonucleoprotein complex that has RNA-directed RNA polymerase (RdRP) activity and produces double-stranded RNAs that can be processed into small interfering RNA in a DICER (Q9UPY3)-dependent manner. Composed of telomerase reverse transcriptase (TERT) and the non-coding RNA component of mitochondrial RNA processing endoribonuclease (RMRP). - - Cartilage-hair hypoplasia [MONDO:0009595]: A form of short-limbed dwarfism due to skeletal dysplasia. - - - psi-mi:"MI:0469"(IntAct) O14746(0) +CPX-35 ANPR-A receptor complex NPR1 receptor complex 9606 P16066(2) ECO:0005544(biological system reconstruction evidence based on orthology evidence used in manual assertion) - GO:0004383(guanylate cyclase activity)|GO:0007168(receptor guanylyl cyclase signaling pathway)|GO:0008217(regulation of blood pressure)|GO:0016941(natriuretic peptide receptor activity)|GO:0042277(peptide binding)|GO:1990620(ANPR-A receptor complex) qsproteome:QS164165(identity)|pubmed:14600147(see-also)|pubmed:15117952(see-also)|pubmed:10894551(see-also)|intenz:4.6.1.2(identity)|reactome:R-HSA-6784600(identity)|complex portal:CPX-35(complex-primary)|complex portal:CPX-33(inferred-from)|rhea:RHEA:13665(identity) Dimeric receptor complex expressed in the atrium. Binding of the ligand AMP in response to atrial distension (high blood volume) plays a major role in the regulation of blood pressure and salt-fluid volume homeostasis. Binding of atrial natriuretic peptide ANP to ANPR-A dimer activates the receptor and stimulates its guanylate cyclase activity, thereby elevating intracellular cGMP levels. cGMP, in return mediates the hormonal actions through cGMP-regulated ion channels, protein kinases and phosphodiesterases. The end result is a reduction in blood volume and, therefore, a reduction in cardiac output and systemic blood pressure. The ANPR-A dimer complex is composed of two ANPR-A molecules. The ANPR-A monomer has a membrane-distal and a membrane-proximal domain, each consisting of a central beta-sheet surrounded by alpha helices. The ANPR-A monomers form a head-to-head dimer through their membrane distal domains. The membrane-distal domains also bind chloride ions, necessary for ANP binding. ANP binding induces structural changes to the ANPR-A dimer. These involve a shift of the relative positions of the two ANPR-A monomers. This brings two active sites of the GCase domains to optimal proximity and orientation, thereby giving rise to the GCase catalytic activity. Homodimer Chloride ion (CHEBI:15422)|ATP (CHEBI:15422)|ANP (P01160-PRO_0000001494) - - - - psi-mi:"MI:0469"(IntAct) P16066(2) diff --git a/tests/gentropy/data_samples/complex_tab/9606_predicted.tsv b/tests/gentropy/data_samples/complex_tab/9606_predicted.tsv new file mode 100644 index 000000000..0afe70ceb --- /dev/null +++ b/tests/gentropy/data_samples/complex_tab/9606_predicted.tsv @@ -0,0 +1,10 @@ +#Complex ac Recommended name Aliases for complex Taxonomy identifier Identifiers (and stoichiometry) of molecules in complex Evidence Code Experimental evidence Go Annotations Cross references Description Complex properties Complex assembly Ligand Disease Agonist Antagonist Comment Source Expanded participant list +CPX-10565 - - 9606 O95274(0)|Q7Z404(0)|Q8N4W6(0)|Q96S52(0)|Q9BZM5(0)|Q9H330(0)|Q9H490(0) ECO:0008004(machine learning method evidence used in automatic assertion) - - qsproteome:QS199499(identity)|complex portal:CPX-10565(complex-primary)|humap:huMAP3_06250.1(identity) - - - - - - - - psi-mi:"MI:2424"(HuMap) O95274(0)|Q7Z404(0)|Q8N4W6(0)|Q96S52(0)|Q9BZM5(0)|Q9H330(0)|Q9H490(0) +CPX-10560 - - 9606 Q13349(0)|Q9BW72(0) ECO:0008004(machine learning method evidence used in automatic assertion) - - qsproteome:QS201849(identity)|complex portal:CPX-10560(complex-primary)|humap:huMAP3_05475.1(identity) - - - - - - - - psi-mi:"MI:2424"(HuMap) Q13349(0)|Q9BW72(0) +CPX-10574 - - 9606 Q86U28(0)|Q96AX2(0) ECO:0008004(machine learning method evidence used in automatic assertion) - - qsproteome:QS205663(identity)|complex portal:CPX-10574(complex-primary)|humap:huMAP3_03526.1(identity) - - - - - - - - psi-mi:"MI:2424"(HuMap) Q86U28(0)|Q96AX2(0) +CPX-10584 - - 9606 O43824(0)|Q16698(0)|Q7L0Y3(0)|Q99714(0)|Q9BQ52(0)|Q9H1N7(0) ECO:0008004(machine learning method evidence used in automatic assertion) - - qsproteome:QS182825(identity)|complex portal:CPX-10584(complex-primary)|humap:huMAP3_00934.1(identity) - - - - - - - - psi-mi:"MI:2424"(HuMap) O43824(0)|Q16698(0)|Q7L0Y3(0)|Q99714(0)|Q9BQ52(0)|Q9H1N7(0) +CPX-10577 - - 9606 Q8NB25(0)|Q9NZQ0(0) ECO:0008004(machine learning method evidence used in automatic assertion) - - qsproteome:QS140637(identity)|complex portal:CPX-10577(complex-primary)|humap:huMAP3_04245.1(identity) - - - - - - - - psi-mi:"MI:2424"(HuMap) Q8NB25(0)|Q9NZQ0(0) +CPX-10549 - - 9606 Q7L4S7(0)|Q99836(0) ECO:0008004(machine learning method evidence used in automatic assertion) - - qsproteome:QS138973(identity)|complex portal:CPX-10549(complex-primary)|humap:huMAP3_01261.1(identity) - - - - - - - - psi-mi:"MI:2424"(HuMap) Q7L4S7(0)|Q99836(0) +CPX-10595 - - 9606 Q86XR5(0)|Q92623(0) ECO:0008004(machine learning method evidence used in automatic assertion) - - qsproteome:QS207849(identity)|complex portal:CPX-10595(complex-primary)|humap:huMAP3_13714.1(identity) - - - - - - - - psi-mi:"MI:2424"(HuMap) Q86XR5(0)|Q92623(0) +CPX-10562 - - 9606 O60888(0)|P22681(0)|Q15464(0)|Q155Q3(0)|Q8TDY4(0)|Q8WUP2(0) ECO:0008004(machine learning method evidence used in automatic assertion) - - qsproteome:QS210004(identity)|complex portal:CPX-10562(complex-primary)|humap:huMAP3_12360.1(identity) - - - - - - - - psi-mi:"MI:2424"(HuMap) O60888(0)|P22681(0)|Q15464(0)|Q155Q3(0)|Q8TDY4(0)|Q8WUP2(0) +CPX-10570 - - 9606 O95389(0)|P09544(0)|P22692(0)|P46531(0)|Q04721(0)|Q06330(0)|Q6ZMS7(0)|Q92585(0)|Q96RG2(0)|Q9GZT5(0)|Q9UM47(0) ECO:0008004(machine learning method evidence used in automatic assertion) - - complex portal:CPX-10570(complex-primary)|humap:huMAP3_14676.1(identity) - - - - - - - - psi-mi:"MI:2424"(HuMap) O95389(0)|P09544(0)|P22692(0)|P46531(0)|Q04721(0)|Q06330(0)|Q6ZMS7(0)|Q92585(0)|Q96RG2(0)|Q9GZT5(0)|Q9UM47(0) diff --git a/tests/gentropy/data_samples/decode/decode_2023_aptamer_mapping.tsv b/tests/gentropy/data_samples/decode/decode_2023_aptamer_mapping.tsv new file mode 100644 index 000000000..00ac18eec --- /dev/null +++ b/tests/gentropy/data_samples/decode/decode_2023_aptamer_mapping.tsv @@ -0,0 +1,5030 @@ +seqid uniprot target_name target_full_name gene_name +SeqId.16561-9 P04217 Alpha-1B-glycoprotein Alpha-1B-glycoprotein A1BG +SeqId.12423-38 Q9NQ94 A1CF APOBEC1 complementation factor A1CF +SeqId.3708-62 P01023 a2-Macroglobulin Alpha-2-macroglobulin A2M +SeqId.15482-12 A8K2U0 A2ML1 Alpha-2-macroglobulin-like protein 1 A2ML1 +SeqId.8759-29 Q9NPC4 "a1,4-Galactosyltransferase" Lactosylceramide 4-alpha-galactosyltransferase A4GALT +SeqId.10835-25 Q9UNA3 A4GCT "Alpha-1,4-N-acetylglucosaminyltransferase" A4GNT +SeqId.11926-23 Q6PD74 P34 Alpha- and gamma-adaptin-binding protein p34 AAGAB +SeqId.12340-17 P49588 SYAC "Alanine--tRNA ligase, cytoplasmic" AARS +SeqId.17320-19 Q9NRN7 ADPPT L-aminoadipate-semialdehyde dehydrogenase-phosphopantetheinyl transferase AASDHPPT +SeqId.8935-22 O95255 MRP6 Multidrug resistance-associated protein 6 ABCC6 +SeqId.17370-186 Q9NUJ1 ABHDA "Mycophenolic acid acyl-glucuronide esterase, mitochondrial" ABHD10 +SeqId.7825-7 Q8N2K0 ABD12 Monoacylglycerol lipase ABHD12 ABHD12 +SeqId.5715-4 Q9BUJ0 ABHEA Protein ABHD14A ABHD14A +SeqId.19325-21 Q96IU4 ABHEB Protein ABHD14B ABHD14B +SeqId.3341-33 P00519 ABL1 Tyrosine-protein kinase ABL1 ABL1 +SeqId.3342-76 P42684 ABL2 Abelson tyrosine-protein kinase 2 ABL2 +SeqId.5261-13 P42684 ABL2 Abelson tyrosine-protein kinase 2 ABL2 +SeqId.13578-98 O94929 ABLM3 Actin-binding LIM protein 3 ABLIM3 +SeqId.9253-52 P16442 BGAT Histo-blood group ABO system transferase ABO +SeqId.17782-23 P09110 THIK "3-ketoacyl-CoA thiolase, peroxisomal" ACAA1 +SeqId.11406-82 Q9UKU7 ACAD8 "Isobutyryl-CoA dehydrogenase, mitochondrial" ACAD8 +SeqId.17857-6 P28330 ACADL "Long-chain specific acyl-CoA dehydrogenase, mitochondrial" ACADL +SeqId.17333-20 P11310 ACADM "Medium-chain specific acyl-CoA dehydrogenase, mitochondrial" ACADM +SeqId.17393-13 P16219 SCAD "Short-chain specific acyl-CoA dehydrogenase, mitochondrial" ACADS +SeqId.17403-14 P45954 acyl-Coenzyme A dehydrogenase "Short/branched chain specific acyl-CoA dehydrogenase, mitochondrial" ACADSB +SeqId.19262-219 P49748 ACADV "Very long-chain specific acyl-CoA dehydrogenase, mitochondrial" ACADVL +SeqId.3280-49 P16112 Aggrecan Aggrecan core protein ACAN +SeqId.12343-14 Q15057 CENB2 "Arf-GAP with coiled-coil, ANK repeat and PH domain-containing protein 2" ACAP2 +SeqId.19197-95 P24752 THIL "Acetyl-CoA acetyltransferase, mitochondrial" ACAT1 +SeqId.17341-89 Q9BWD1 THIC "Acetyl-CoA acetyltransferase, cytosolic" ACAT2 +SeqId.10075-75 Q9BR61 ACBD6 Acyl-CoA-binding domain-containing protein 6 ACBD6 +SeqId.19341-36 Q9BR61 ACBD6 Acyl-CoA-binding domain-containing protein 6 ACBD6 +SeqId.13563-259 Q8N6N7 ACBD7 Acyl-CoA-binding domain-containing protein 7 ACBD7 +SeqId.10714-7 P12821 ACE Angiotensin-converting enzyme ACE +SeqId.2805-6 Q9BYF1 ACE2 Angiotensin-converting enzyme 2 ACE2 +SeqId.15553-22 P22303 ACES Acetylcholinesterase ACHE +SeqId.12700-9 P53396 ACLY ATP-citrate synthase ACLY +SeqId.17675-17 Q9NPJ3 ACO13 Acyl-coenzyme A thioesterase 13 ACOT13 +SeqId.17400-71 O14734 ACOT8 Acyl-coenzyme A thioesterase 8 ACOT8 +SeqId.3858-5 P24666 PPAC Low molecular weight phosphotyrosine protein phosphatase ACP1 +SeqId.9237-54 P11117 Lysosomal acid phosphatase Lysosomal acid phosphatase ACP2 +SeqId.3232-28 P13686 TrATPase Tartrate-resistant acid phosphatase type 5 ACP5 +SeqId.5742-14 Q9NPH0 PPA6 Lysophosphatidic acid phosphatase type 6 ACP6 +SeqId.6079-59 Q8TE99 ACPL2 2-phosphoxylose phosphatase 1 ACPL2 +SeqId.19317-114 P15309 Prostatic acid phosphatase Prostatic acid phosphatase ACPP +SeqId.10507-166 P26436 sperm protein 10 Acrosomal protein SP-10 ACRV1 +SeqId.15301-24 P26436 sperm protein 10 Acrosomal protein SP-10 ACRV1 +SeqId.17466-72 Q96CM8 ACSF2 "Acyl-CoA synthetase family member 2, mitochondrial" ACSF2 +SeqId.9843-5 P12814 ACTN1 Alpha-actinin-1 ACTN1 +SeqId.9844-138 P35609 ACTN2 Alpha-actinin-2 ACTN2 +SeqId.2806-49 P36896 Activin RIB Activin receptor type-1B ACVR1B +SeqId.19208-8 P27037 Activin RIIA Activin receptor type-2A ACVR2A +SeqId.9412-52 Q13705 Activin RIIB Activin receptor type-2B ACVR2B +SeqId.16318-12 P37023 ALK-1 Serine/threonine-protein kinase receptor R3 ACVRL1 +SeqId.3343-1 Q03154 Aminoacylase-1 Aminoacylase-1 ACY1 +SeqId.12812-25 P14621 ACYP2 Acylphosphatase-2 ACYP2 +SeqId.8405-108 O14672 ADAM 10 Disintegrin and metalloproteinase domain-containing protein 10 ADAM10 +SeqId.8654-13 O14672 ADAM 10 Disintegrin and metalloproteinase domain-containing protein 10 ADAM10 +SeqId.6586-19 O75078 ADA11 Disintegrin and metalloproteinase domain-containing protein 11 ADAM11 +SeqId.4420-7 O43184 ADAM12 Disintegrin and metalloproteinase domain-containing protein 12 ADAM12 +SeqId.15455-40 Q13444 ADA15 Disintegrin and metalloproteinase domain-containing protein 15 ADAM15 +SeqId.9956-7 Q13444 ADA15 Disintegrin and metalloproteinase domain-containing protein 15 ADAM15 +SeqId.8882-1 P78536 ADAM 17 Disintegrin and metalloproteinase domain-containing protein 17 ADAM17 +SeqId.8959-61 P78536 ADAM 17 Disintegrin and metalloproteinase domain-containing protein 17 ADAM17 +SeqId.8948-13 Q9H013 ADA19 Disintegrin and metalloproteinase domain-containing protein 19 ADAM19 +SeqId.7933-75 Q9P0K1 ADA22 Disintegrin and metalloproteinase domain-containing protein 22 ADAM22 +SeqId.7049-2 O75077 ADAM 23 Disintegrin and metalloproteinase domain-containing protein 23 ADAM23 +SeqId.13549-15 Q9UKF5 ADA29 Disintegrin and metalloproteinase domain-containing protein 29 ADAM29 +SeqId.8520-8 Q9UKF2 ADA30 Disintegrin and metalloproteinase domain-containing protein 30 ADAM30 +SeqId.7827-20 Q8TC27 ADA32 Disintegrin and metalloproteinase domain-containing protein 32 ADAM32 +SeqId.10753-31 Q9H2U9 ADAM7 Disintegrin and metalloproteinase domain-containing protein 7 ADAM7 +SeqId.3795-6 Q13443 ADAM 9 Disintegrin and metalloproteinase domain-containing protein 9 ADAM9 +SeqId.9115-78 O15204 ADEC1 ADAM DEC1 ADAMDEC1 +SeqId.3174-2 Q9UHI8 ATS1 A disintegrin and metalloproteinase with thrombospondin motifs 1 ADAMTS1 +SeqId.3175-51 Q76LX8 ATS13 A disintegrin and metalloproteinase with thrombospondin motifs 13 ADAMTS13 +SeqId.4533-76 Q8TE58 ATS15 A disintegrin and metalloproteinase with thrombospondin motifs 15 ADAMTS15 +SeqId.8845-2 O15072 ATS3 A disintegrin and metalloproteinase with thrombospondin motifs 3 ADAMTS3 +SeqId.2809-25 O75173 ADAMTS-4 A disintegrin and metalloproteinase with thrombospondin motifs 4 ADAMTS4 +SeqId.3168-8 Q9UNA0 ADAMTS-5 A disintegrin and metalloproteinase with thrombospondin motifs 5 ADAMTS5 +SeqId.6441-62 Q9UKP5 ATS6 A disintegrin and metalloproteinase with thrombospondin motifs 6 ADAMTS6 +SeqId.16890-37 Q8N6G6 ATL1 ADAMTS-like protein 1 ADAMTSL1 +SeqId.6379-62 Q86TH1 ATL2 ADAMTS-like protein 2 ADAMTSL2 +SeqId.9794-17 Q96D53 ADCK4 AarF domain-containing protein kinase 4 ADCK4 +SeqId.8446-4 P18509 PACAP-27 Pituitary adenylate cyclase-activating polypeptide 27 ADCYAP1 +SeqId.8285-64 P18509 PACA Pituitary adenylate cyclase-activating polypeptide ADCYAP1 +SeqId.8450-36 P18509 PACAP-38 Pituitary adenylate cyclase-activating polypeptide 38 ADCYAP1 +SeqId.4546-27 Q9UHX3 EMR2 Adhesion G protein-coupled receptor E2 ADGRE2 +SeqId.11243-90 Q5T601 GPR110 Adhesion G-protein coupled receptor F1 ADGRF1 +SeqId.6409-57 Q8IZF2 GP116 Adhesion G protein-coupled receptor F5 ADGRF5 +SeqId.4551-72 Q8IZF4 GP114 Adhesion G-protein coupled receptor G5 ADGRG5 +SeqId.17396-23 P07327 ADH1A Alcohol dehydrogenase 1A ADH1A +SeqId.9834-62 P00325 ADH1B Alcohol dehydrogenase 1B ADH1B +SeqId.15525-294 P00326 ADH1G Alcohol dehydrogenase 1C ADH1C +SeqId.8325-37 P08319 ADH4 Alcohol dehydrogenase 4 ADH4 +SeqId.11369-23 P11766 ADHX Alcohol dehydrogenase class-3 ADH5 +SeqId.18206-18 P28332 ADH6 Alcohol dehydrogenase 6 ADH6 +SeqId.11377-19 P40394 ADH7 Alcohol dehydrogenase class 4 mu/sigma chain ADH7 +SeqId.12457-10 Q9BV57 MTND "1,2-dihydroxy-3-keto-5-methylthiopentene dioxygenase" ADI1 +SeqId.3554-24 Q15848 Adiponectin Adiponectin ADIPOQ +SeqId.19207-119 P55263 ADK Adenosine kinase ADK +SeqId.7922-5 P35318 Adrenomedullin Adrenomedullin ADM +SeqId.14115-34 P35318 Adrenomedullin Adrenomedullin ADM +SeqId.8100-15 Q7Z4H4 ADM2 ADM2 ADM2 +SeqId.6221-1 Q9BRR6 ADPGK ADP-dependent glucokinase ADPGK +SeqId.18395-5 P54922 ADPRH [Protein ADP-ribosylarginine] hydrolase ADPRH +SeqId.17332-3 Q9NX46 ARHL2 Poly(ADP-ribose) glycohydrolase ARH3 ADPRHL2 +SeqId.3347-9 P25098 BARK1 beta-adrenergic receptor kinase 1 ADRBK1 +SeqId.9057-19 Q16186 ADRM1 Proteasomal ubiquitin receptor ADRM1 ADRM1 +SeqId.5023-23 P30566 PUR8 Adenylosuccinate lyase ADSL +SeqId.12644-63 P30520 PURA2 Adenylosuccinate synthetase isozyme 2 ADSS +SeqId.13998-26 Q8N142 PURA1 Adenylosuccinate synthetase isozyme 1 ADSSL1 +SeqId.18396-10 Q08117 AES Amino-terminal enhancer of split AES +SeqId.9889-42 Q8TED9 AF1L1 Actin filament-associated protein 1-like 1 AFAP1L1 +SeqId.4763-31 P43652 Afamin Afamin AFM +SeqId.5792-8 P02771 AFP alpha-Fetoprotein AFP +SeqId.10435-2 P20933 ASPG N(4)-(beta-N-acetylglucosaminyl)-L-asparaginase AGA +SeqId.14291-53 Q99490 AGAP2 "Arf-GAP with GTPase, ANK repeat and PH domain-containing protein 2" AGAP2 +SeqId.13960-15 Q96P47 AGAP3 "Arf-GAP with GTPase, ANK repeat and PH domain-containing protein 3" AGAP3 +SeqId.4125-52 Q15109 sRAGE "Advanced glycosylation end product-specific receptor, soluble" AGER +SeqId.11681-8 P52594 NUPL Arf-GAP domain and FG repeat-containing protein 1 AGFG1 +SeqId.8051-10 Q8N302 AGGF1 Angiogenic factor with G patch and FHA domains 1 AGGF1 +SeqId.15312-14 Q9UL18 AGO1 Protein argonaute-1 AGO1 +SeqId.15323-112 Q9H9G7 AGO3 Protein argonaute-3 AGO3 +SeqId.4959-2 O95994 AGR2 Anterior gradient protein 2 homolog AGR2 +SeqId.17342-13 Q8TD06 AGR3 Anterior gradient protein 3 AGR3 +SeqId.15483-377 O00468 Agrin Agrin AGRN +SeqId.2813-11 O00253 ART Agouti-related protein AGRP +SeqId.3484-60 P01019 Angiotensinogen Angiotensinogen AGT +SeqId.12652-37 O43865 SAHH2 Adenosylhomocysteinase 2 AHCYL1 +SeqId.11633-89 O95433 AHSA1 Activator of 90 kDa heat shock protein ATPase homolog 1 AHSA1 +SeqId.3581-53 P02765 a2-HS-Glycoprotein Alpha-2-HS-glycoprotein AHSG +SeqId.9025-5 Q9NZD4 AHSP Alpha-hemoglobin-stabilizing protein AHSP +SeqId.17347-80 Q96BJ3 CA080 "Axin interactor, dorsalization-associated protein" AIDA +SeqId.2849-49 P55008 AIF1 Allograft inflammatory factor 1 AIF1 +SeqId.18871-24 Q9BQI0 AIF1L Allograft inflammatory factor 1-like AIF1L +SeqId.9522-3 O95831 AIF "Apoptosis-inducing factor 1, mitochondrial" AIFM1 +SeqId.2714-78 Q12904 EMAP-2 Endothelial monocyte-activating polypeptide 2 AIMP1 +SeqId.3839-60 O00170 AIP AH receptor-interacting protein AIP +SeqId.5012-67 P00568 "Myokinase, human" Adenylate kinase isoenzyme 1 AK1 +SeqId.11368-32 P54819 KAD2 "Adenylate kinase 2, mitochondrial" AK2 +SeqId.17432-25 P27144 KAD4 "Adenylate kinase 4, mitochondrial" AK4 +SeqId.13613-23 Q9Y6K8 Adenylate kinase isoenzyme 5 Adenylate kinase isoenzyme 5 AK5 +SeqId.18399-1 O43687 AKA7A A-kinase anchor protein 7 isoforms alpha and beta AKAP7 +SeqId.4192-10 P14550 AK1A1 Alcohol dehydrogenase [NADP(+)] AKR1A1 +SeqId.16606-85 P15121 Aldose reductase Aldose reductase AKR1B1 +SeqId.16081-38 O60218 Aldose reductase-like Aldo-keto reductase family 1 member B10 AKR1B10 +SeqId.12618-50 Q04828 Aldo-keto reductase 1C1 Aldo-keto reductase family 1 member C1 AKR1C1 +SeqId.17377-1 P42330 Aldose reductase-like C3 Aldo-keto reductase family 1 member C3 AKR1C3 +SeqId.18397-5 P17516 AK1C4 Aldo-keto reductase family 1 member C4 AKR1C4 +SeqId.18398-1 P51857 AK1D1 3-oxo-5-beta-steroid 4-dehydrogenase AKR1D1 +SeqId.4188-1 O43488 Aflatoxin B1 aldehyde reductase Aflatoxin B1 aldehyde reductase member 2 AKR7A2 +SeqId.18173-11 O95154 ARK73 Aflatoxin B1 aldehyde reductase member 3 AKR7A3 +SeqId.15627-83 P31749 PKB RAC-alpha serine/threonine-protein kinase AKT1 +SeqId.14685-17 P31751 PKB beta RAC-beta serine/threonine-protein kinase AKT2 +SeqId.5360-9 P31751 PKB beta RAC-beta serine/threonine-protein kinase AKT2 +SeqId.3392-68 Q9Y243 PKB gamma Protein kinase B gamma AKT3 +SeqId.3392-68 Q9Y243 PKB gamma Protein kinase B gamma AKT3 +SeqId.3392-68 Q9Y243 PKB gamma Protein kinase B gamma AKT3 +SeqId.15523-9 P13716 HEM2 Delta-aminolevulinic acid dehydratase ALAD +SeqId.18380-78 P02768 Albumin Serum albumin ALB +SeqId.5451-1 Q13740 ALCAM CD166 antigen ALCAM +SeqId.11265-8 P00352 Retinal dehydrogenase 1 Retinal dehydrogenase 1 ALDH1A1 +SeqId.9835-16 P47895 AL1A3 Aldehyde dehydrogenase family 1 member A3 ALDH1A3 +SeqId.18381-16 P05091 ALDH-E2 "Aldehyde dehydrogenase, mitochondrial" ALDH2 +SeqId.11480-1 P30838 "Aldehyde dehydrogenase, class 3" "Aldehyde dehydrogenase, dimeric NADP-preferring" ALDH3A1 +SeqId.12940-35 P43353 AL3B1 Aldehyde dehydrogenase family 3 member B1 ALDH3B1 +SeqId.17792-158 P51649 SSDH "Succinate-semialdehyde dehydrogenase, mitochondrial" ALDH5A1 +SeqId.19136-22 Q02252 MMSA "Methylmalonate-semialdehyde dehydrogenase [acylating], mitochondrial" ALDH6A1 +SeqId.5864-10 P04075 aldolase A Fructose-bisphosphate aldolase A ALDOA +SeqId.18185-118 P05062 ALDOB Fructose-bisphosphate aldolase B ALDOB +SeqId.9876-20 P09972 aldolase C Fructose-bisphosphate aldolase C ALDOC +SeqId.8249-124 Q9UM73 ALK ALK tyrosine kinase receptor ALK +SeqId.18400-52 Q6NS38 ALKB2 DNA oxidative demethylase ALKBH2 ALKBH2 +SeqId.18401-18 Q96Q83 ALKB3 Alpha-ketoglutarate-dependent dioxygenase alkB homolog 3 ALKBH3 +SeqId.12422-143 O15296 LX15B Arachidonate 15-lipoxygenase B ALOX15B +SeqId.17441-4 P09923 "Alkaline phosphatase, intestine" Intestinal-type alkaline phosphatase ALPI +SeqId.16926-44 P05186 "Alkaline phosphatase, liver" "Alkaline phosphatase, tissue-nonspecific isozyme" ALPL +SeqId.7813-6 P05187 "Alkaline phosphatase, placental" "Alkaline phosphatase, placental type" ALPP +SeqId.6706-18 P10696 PPBN "Alkaline phosphatase, placental-like" ALPPL2 +SeqId.6715-63 P10696 PPBN "Alkaline phosphatase, placental-like" ALPPL2 +SeqId.15453-3 P02760 a1-Microglobulin Alpha-1-microglobulin AMBP +SeqId.4923-79 P03971 MIS Muellerian-inhibiting factor AMH +SeqId.5094-62 Q86YT9 JAML1 Junctional adhesion molecule-like AMICA1 +SeqId.9979-13 Q86WK6 AMGO1 Amphoterin-induced protein 1 AMIGO1 +SeqId.14134-49 Q86SJ2 AMGO2 Amphoterin-induced protein 2 AMIGO2 +SeqId.18402-1 Q6DCA0 AMERL AMMECR1-like protein AMMECR1L +SeqId.4322-28 Q9BXJ7 AMNLS Protein amnionless AMN +SeqId.18403-25 Q01433 AMPD2 AMP deaminase 2 AMPD2 +SeqId.7918-114 P04745 "Amylase, alpha 1A" Alpha-amylase 1 AMY1A +SeqId.18917-53 P04746 Pancreatic alpha-amylase Pancreatic alpha-amylase AMY2A +SeqId.15556-49 P19961 Alpha-amylase 2B Alpha-amylase 2B AMY2B +SeqId.12345-4 Q9UM13 APC10 Anaphase-promoting complex subunit 10 ANAPC10 +SeqId.11690-47 Q9UJX3 APC7 Anaphase-promoting complex subunit 7 ANAPC7 +SeqId.4874-3 P03950 Angiogenin Angiogenin ANG +SeqId.2811-27 Q15389 Angiopoietin-1 Angiopoietin-1 ANGPT1 +SeqId.2602-2 O15123 Angiopoietin-2 Angiopoietin-2 ANGPT2 +SeqId.2500-2 Q9Y264 Angiopoietin-4 Angiopoietin-4 ANGPT4 +SeqId.11142-11 O95841 ANGL1 Angiopoietin-related protein 1 ANGPTL1 +SeqId.9092-33 O95841 ANGL1 Angiopoietin-related protein 1 ANGPTL1 +SeqId.10391-1 Q9Y5C1 ANGL3 Angiopoietin-related protein 3 ANGPTL3 +SeqId.3796-79 Q9BY76 ANGL4 Angiopoietin-related protein 4 ANGPTL4 +SeqId.6371-50 O43827 ANGL7 Angiopoietin-related protein 7 ANGPTL7 +SeqId.7624-19 Q01484 ANK2 Ankyrin-2 ANK2 +SeqId.15361-37 Q15327 ANKR1 Ankyrin repeat domain-containing protein 1 ANKRD1 +SeqId.12445-50 Q96NW4 ANR27 Ankyrin repeat domain-containing protein 27 ANKRD27 +SeqId.7851-30 Q86W74 ANR46 Ankyrin repeat domain-containing protein 46 ANKRD46 +SeqId.18404-22 Q6NXT1 ANR54 Ankyrin repeat domain-containing protein 54 ANKRD54 +SeqId.13073-14 P39687 AN32A Acidic leucine-rich nuclear phosphoprotein 32 family member A ANP32A +SeqId.4194-26 Q92688 AN32B Acidic leucine-rich nuclear phosphoprotein 32 family member B ANP32B +SeqId.15457-14 P15144 Aminopeptidase N Aminopeptidase N ANPEP +SeqId.10464-6 Q9H6X2 ANTR1 Anthrax toxin receptor 1 ANTXR1 +SeqId.15559-5 P58335 ANTR2 Anthrax toxin receptor 2 ANTXR2 +SeqId.4960-72 P04083 annexin I Annexin A1 ANXA1 +SeqId.13605-16 Q9UJ72 ANX10 Annexin A10 ANXA10 +SeqId.17513-11 P50995 ANX11 Annexin A11 ANXA11 +SeqId.17835-28 P27216 ANX13 Annexin A13 ANXA13 +SeqId.13700-10 P07355 annexin II Annexin A2 ANXA2 +SeqId.4961-17 P07355 annexin II Annexin A2 ANXA2 +SeqId.17163-117 P12429 Annexin III Annexin A3 ANXA3 +SeqId.17164-15 P09525 annexin IV Annexin A4 ANXA4 +SeqId.14158-17 P08758 Annexin V Annexin A5 ANXA5 +SeqId.5335-73 P08133 annexin VI Annexin A6 ANXA6 +SeqId.14203-3 P20073 ANXA7 Annexin A7 ANXA7 +SeqId.18244-1 P20073 ANXA7 Annexin A7 ANXA7 +SeqId.18290-6 P13928 Annexin A8 Annexin A8 ANXA8 +SeqId.13588-11 O76027 ANXA9 Annexin A9 ANXA9 +SeqId.15486-126 P19801 ABP1 Amiloride-sensitive amine oxidase [copper-containing] AOC1 +SeqId.6434-18 O75106 Amine oxidase Retina-specific copper amine oxidase AOC2 +SeqId.12714-38 O75843 AP1G2 AP-1 complex subunit gamma-like 2 AP1G2 +SeqId.18405-117 P56377 AP1S2 AP-1 complex subunit sigma-2 AP1S2 +SeqId.13621-31 O94973 AP2A2 AP-2 complex subunit alpha-2 AP2A2 +SeqId.10076-1 O00189 AP4M1 AP-4 complex subunit mu-1 AP4M1 +SeqId.13583-19 O14727 Apaf-1 Apoptotic protease-activating factor 1 APAF1 +SeqId.12822-34 O00213 APBB1 Amyloid beta A4 precursor protein-binding family B member 1 APBB1 +SeqId.14206-28 O00213 APBB1 Amyloid beta A4 precursor protein-binding family B member 1 APBB1 +SeqId.12753-6 Q92870 APBB2 Amyloid beta A4 precursor protein-binding family B member 2 APBB2 +SeqId.12761-12 Q92870 APBB2 Amyloid beta A4 precursor protein-binding family B member 2 APBB2 +SeqId.12784-10 O95704 APBB3 Amyloid beta A4 precursor protein-binding family B member 3 APBB3 +SeqId.13589-10 O95704 APBB3 Amyloid beta A4 precursor protein-binding family B member 3 APBB3 +SeqId.6599-5 Q8J025 APCD1 Protein APCDD1 APCDD1 +SeqId.2474-54 P02743 SAP Serum amyloid P-component APCS +SeqId.9849-13 P27695 APEX1 DNA-(apurinic or apyrimidinic site) lyase APEX1 +SeqId.6622-90 Q9ULZ1 APEL Apelin APLN +SeqId.7210-25 P51693 Amyloid-like protein 1 Amyloid-like protein 1 APLP1 +SeqId.10627-87 Q06481 APLP2 Amyloid-like protein 2 APLP2 +SeqId.10605-22 Q9HDC9 APMAP Adipocyte plasma membrane-associated protein APMAP +SeqId.2750-3 P02647 Apo A-I Apolipoprotein A-I APOA1 +SeqId.16621-77 Q8NCW5 AIBP NAD(P)H-hydrate epimerase APOA1BP +SeqId.7127-3 P02652 Apo A-II Apolipoprotein A-II APOA2 +SeqId.17685-9 P06727 Apo A-IV Apolipoprotein A-IV APOA4 +SeqId.15363-32 Q6Q788 Apo A-V Apolipoprotein A-V APOA5 +SeqId.2797-56 P04114 Apo B Apolipoprotein B APOB +SeqId.13930-3 Q9HC16 ABC3G DNA dC->dU-editing enzyme APOBEC-3G APOBEC3G +SeqId.15364-101 P02654 Apo C-I Apolipoprotein C-I APOC1 +SeqId.6350-43 P02655 Apo C-II Apolipoprotein C-II APOC2 +SeqId.6461-54 P02656 Apo C-III Apolipoprotein C-III APOC3 +SeqId.4712-28 P05090 Apo D Apolipoprotein D APOD +SeqId.2418-55 P02649 Apo E Apolipoprotein E APOE +SeqId.12370-30 Q13790 Apo F Apolipoprotein F APOF +SeqId.8288-27 P02749 b2-Glycoprotein I Beta-2-glycoprotein 1 APOH +SeqId.11510-31 O14791 Apo L1 Apolipoprotein L1 APOL1 +SeqId.9506-10 O14791 Apo L1 Apolipoprotein L1 APOL1 +SeqId.16823-75 O95236 APOL3 Apolipoprotein L3 APOL3 +SeqId.10445-20 O95445 ApoM Apolipoprotein M APOM +SeqId.3171-57 P05067 amyloid precursor protein Amyloid beta A4 protein APP +SeqId.12825-18 Q9UKG1 DP13A DCC-interacting protein 13-alpha APPL1 +SeqId.10088-37 P07741 APT Adenine phosphoribosyltransferase APRT +SeqId.17736-105 Q7Z2E3 APTX Aprataxin APTX +SeqId.11363-58 P55087 AQP4 Aquaporin-4 AQP4 +SeqId.12583-77 P10398 ARAF Serine/threonine-protein kinase A-Raf ARAF +SeqId.2970-60 P15514 AREG Amphiregulin AREG +SeqId.19239-5 P84077 ARF1 ADP-ribosylation factor 1 ARF1 +SeqId.12578-13 P61204 ARF3 ADP-ribosylation factor 3 ARF3 +SeqId.18408-26 P18085 ARF4 ADP-ribosylation factor 4 ARF4 +SeqId.18409-61 P84085 ARF5 ADP-ribosylation factor 5 ARF5 +SeqId.12425-104 P62330 ARF6 ADP-ribosylation factor 6 ARF6 +SeqId.11556-19 Q8N6T3 ARFG1 ADP-ribosylation factor GTPase-activating protein 1 ARFGAP1 +SeqId.11664-32 Q8N6H7 ARFG2 ADP-ribosylation factor GTPase-activating protein 2 ARFGAP2 +SeqId.13488-3 P53367 ARFP1 Arfaptin-1 ARFIP1 +SeqId.12630-8 P53365 ARFP2 Arfaptin-2 ARFIP2 +SeqId.5867-60 P05089 ARGI1 Arginase-1 ARG1 +SeqId.17752-24 P78540 Arginase "Arginase-2, mitochondrial" ARG2 +SeqId.11955-1 Q07960 RHG01 Rho GTPase-activating protein 1 ARHGAP1 +SeqId.9815-5 Q07960 RHG01 Rho GTPase-activating protein 1 ARHGAP1 +SeqId.11333-82 P42331 RHG25 Rho GTPase-activating protein 25 ARHGAP25 +SeqId.12807-89 Q7Z6I6 RHG30 Rho GTPase-activating protein 30 ARHGAP30 +SeqId.6289-78 Q6ZRI8 RHG36 Rho GTPase-activating protein 36 ARHGAP36 +SeqId.14748-31 Q13017 RHG05 Rho GTPase-activating protein 5 ARHGAP5 +SeqId.6454-38 P52565 Rho-GDIa Rho GDP-dissociation inhibitor 1 ARHGDIA +SeqId.9846-32 P52566 Rho-GDI beta Rho GDP-dissociation inhibitor 2 ARHGDIB +SeqId.13976-9 Q92888 ARHG1 Rho guanine nucleotide exchange factor 1 ARHGEF1 +SeqId.9061-3 O15013 ARHGA Rho guanine nucleotide exchange factor 10 ARHGEF10 +SeqId.12848-9 Q92974 ARHG2 Rho guanine nucleotide exchange factor 2 ARHGEF2 +SeqId.13519-112 Q86VW2 ARHGP Rho guanine nucleotide exchange factor 25 ARHGEF25 +SeqId.13932-45 Q14155 COOL-1 Rho guanine nucleotide exchange factor 7 ARHGEF7 +SeqId.9898-161 O14497 ARI1A AT-rich interactive domain-containing protein 1A ARID1A +SeqId.3875-62 Q99856 ARI3A AT-rich interactive domain-containing protein 3A ARID3A +SeqId.12392-30 P40616 ARL1 ADP-ribosylation factor-like protein 1 ARL1 +SeqId.12433-8 Q969Q4 ARL11 ADP-ribosylation factor-like protein 11 ARL11 +SeqId.18410-26 Q8N4G2 ARL14 ADP-ribosylation factor-like protein 14 ARL14 +SeqId.18411-83 Q9NXU5 ARL15 ADP-ribosylation factor-like protein 15 ARL15 +SeqId.12587-65 P36404 ARL2 ADP-ribosylation factor-like protein 2 ARL2 +SeqId.18407-36 Q9Y2Y0 AR2BP ADP-ribosylation factor-like protein 2-binding protein ARL2BP +SeqId.12571-14 P36405 ARL3 ADP-ribosylation factor-like protein 3 ARL3 +SeqId.18413-24 P49703 ARL4D ADP-ribosylation factor-like protein 4D ARL4D +SeqId.18414-26 Q9Y689 ARL5A ADP-ribosylation factor-like protein 5A ARL5A +SeqId.17404-5 Q96KC2 ARL5B ADP-ribosylation factor-like protein 5B ARL5B +SeqId.18415-16 Q9H0F7 ARL6 ADP-ribosylation factor-like protein 6 ARL6 +SeqId.13503-19 O75915 PRAF3 PRA1 family protein 3 ARL6IP5 +SeqId.8569-147 Q9NVJ2 ARL8B ADP-ribosylation factor-like protein 8B ARL8B +SeqId.18416-3 Q6T311 ARL9 ADP-ribosylation factor-like protein 9 ARL9 +SeqId.9107-59 Q8N2F6 ARM10 Armadillo repeat-containing protein 10 ARMC10 +SeqId.8785-1 Q96C12 ARMC5 Armadillo repeat-containing protein 5 ARMC5 +SeqId.12689-56 O15143 ARC1B Actin-related protein 2/3 complex subunit 1B ARPC1B +SeqId.13573-5 O15145 p21-ARC Actin-related protein 2/3 complex subunit 3 ARPC3 +SeqId.18419-20 O15511 p16-ARC Actin-related protein 2/3 complex subunit 5 ARPC5 +SeqId.4963-19 P56211 ARP19 cAMP-regulated phosphoprotein 19 ARPP19 +SeqId.12860-7 Q9UBL0 cAMP-regulated phosphoprotein 21 cAMP-regulated phosphoprotein 21 ARPP21 +SeqId.12643-4 P49407 ARRB1 Beta-arrestin-1 ARRB1 +SeqId.12352-70 Q96B67 ARRD3 Arrestin domain-containing protein 3 ARRDC3 +SeqId.3583-54 P15289 Arylsulfatase A Arylsulfatase A ARSA +SeqId.3172-28 P15848 ARSB Arylsulfatase B ARSB +SeqId.8269-327 Q6UWY0 ARSK Arylsulfatase K ARSK +SeqId.7970-315 Q13508 NAR3 Ecto-ADP-ribosyltransferase 3 ART3 +SeqId.6576-1 Q93070 ART4 Ecto-ADP-ribosyltransferase 4 ART4 +SeqId.2939-10 Q5T4W7 Artemin Artemin ARTN +SeqId.18417-3 Q9HBK9 AS3MT Arsenite methyltransferase AS3MT +SeqId.5748-20 Q13510 Acid ceramidase Acid ceramidase ASAH1 +SeqId.3212-30 Q9NR71 ASAH2 Neutral ceramidase ASAH2 +SeqId.13518-5 O43150 ASAP2 "Arf-GAP with SH3 domain, ANK repeat and PH domain-containing protein 2" ASAP2 +SeqId.19601-15 Q96DX5 ASB9 Ankyrin repeat and SOCS box protein 9 ASB9 +SeqId.10647-18 Q8N9N2 ASCC1 Activating signal cointegrator 1 complex subunit 1 ASCC1 +SeqId.18172-71 Q9Y294 ASF1A Histone chaperone ASF1A ASF1A +SeqId.5452-71 P07306 ASGR1 Asialoglycoprotein receptor 1 ASGR1 +SeqId.9474-22 P07307 ASGR2 Asialoglycoprotein receptor 2 ASGR2 +SeqId.12622-96 Q9NR48 ASH1L Histone-lysine N-methyltransferase ASH1L ASH1L +SeqId.12832-10 Q9UBL3 ASH2L Set1/Ash2 histone methyltransferase complex subunit ASH2 ASH2L +SeqId.6951-26 Q96FT7 ASIC4 Acid-sensing ion channel 4 ASIC4 +SeqId.5676-54 P42127 ASIP Agouti-signaling protein ASIP +SeqId.11241-8 P04424 ARLY Argininosuccinate lyase ASL +SeqId.10089-7 O95671 ASML N-acetylserotonin O-methyltransferase-like protein ASMTL +SeqId.13620-10 O43681 ASNA ATPase ASNA1 ASNA1 +SeqId.18187-16 P45381 ACY2 Aspartoacylase ASPA +SeqId.6998-106 Q12797 HAAH Aspartyl/asparaginyl beta-hydroxylase ASPH +SeqId.6451-64 Q9BXN1 ASPN Asporin ASPN +SeqId.10902-53 Q53RT3 APRV1 Retroviral-like aspartic protease 1 ASPRV1 +SeqId.18313-4 Q7L266 Asparaginase-like protein 1 Isoaspartyl peptidase/L-asparaginase ASRGL1 +SeqId.7993-23 Q6HA08 ASTL Astacin-like metalloendopeptidase ASTL +SeqId.6625-31 Q8NBU5 ATAD1 ATPase family AAA domain-containing protein 1 ATAD1 +SeqId.13043-157 Q6PL18 ATAD2 ATPase family AAA domain-containing protein 2 ATAD2 +SeqId.11277-23 P18850 ATF6A Cyclic AMP-dependent transcription factor ATF-6 alpha ATF6 +SeqId.11387-3 Q99941 ATF6B Cyclic AMP-dependent transcription factor ATF-6 beta ATF6B +SeqId.18156-7 Q9NT62 ATG3 Ubiquitin-like-conjugating enzyme ATG3 ATG3 +SeqId.13629-25 Q9Y4P1 ATG4B Cysteine protease ATG4B ATG4B +SeqId.12597-68 Q9H1Y0 Autophagy protein 5 Autophagy protein 5 ATG5 +SeqId.12627-97 O95352 ATG7 Ubiquitin-like modifier-activating enzyme ATG7 ATG7 +SeqId.19233-75 O00244 ATOX1 Copper transport protein ATOX1 ATOX1 +SeqId.13659-36 Q9HD20 AT131 Manganese-transporting ATPase 13A1 ATP13A1 +SeqId.13392-13 P05026 AT1B1 Sodium/potassium-transporting ATPase subunit beta-1 ATP1B1 +SeqId.7218-87 P14415 AT1B2 Sodium/potassium-transporting ATPase subunit beta-2 ATP1B2 +SeqId.8990-42 P54709 AT1B3 Sodium/potassium-transporting ATPase subunit beta-3 ATP1B3 +SeqId.9933-49 Q9UN42 AT1B4 Protein ATP1B4 ATP1B4 +SeqId.13510-7 Q93084 AT2A3 Sarcoplasmic/endoplasmic reticulum calcium ATPase 3 ATP2A3 +SeqId.9994-217 P51164 ATP4B Potassium-transporting ATPase subunit beta ATP4B +SeqId.4965-27 P06576 ATP synthase beta chain "ATP synthase subunit beta, mitochondrial" ATP5B +SeqId.7788-1 P18859 CF6 "ATP synthase-coupling factor 6, mitochondrial" ATP5J +SeqId.11539-4 P56134 ATPK "ATP synthase subunit f, mitochondrial" ATP5J2 +SeqId.9202-309 P48047 ATPO "ATP synthase subunit O, mitochondrial" ATP5O +SeqId.15499-11 O75882 Attractin Attractin ATRN +SeqId.16825-20 P54252 ATX3 Ataxin-3 ATXN3 +SeqId.3091-70 O14965 Aurora kinase A Aurora kinase A AURKA +SeqId.3346-72 Q96GD4 AURKB Aurora kinase B AURKB +SeqId.12925-105 Q9Y2T1 AXIN2 Axin-2 AXIN2 +SeqId.8429-16 Q9Y2T1 AXIN2 Axin-2 AXIN2 +SeqId.9312-8 P25311 AZGP1 Zinc-alpha-2-glycoprotein AZGP1 +SeqId.14713-46 P20160 Azurocidin Azurocidin AZU1 +SeqId.3485-28 P61769 b2-Microglobulin Beta-2-microglobulin B2M +SeqId.10574-10 P61769 b2-Microglobulin Beta-2-microglobulin B2M +SeqId.9541-15 Q9Y5Z6 B3GT1 "Beta-1,3-galactosyltransferase 1" B3GALT1 +SeqId.11638-42 O43825 B3GT2 "Beta-1,3-galactosyltransferase 2" B3GALT2 +SeqId.7981-230 Q96L58 B3GT6 "Beta-1,3-galactosyltransferase 6" B3GALT6 +SeqId.5727-35 Q6Y288 B3GLT "Beta-1,3-glucosyltransferase" B3GALTL +SeqId.6897-38 O94766 B3GA3 Galactosylgalactosylxylosylprotein 3-beta-glucuronosyltransferase 3 B3GAT3 +SeqId.7980-72 Q9NY97 B3GN2 "N-acetyllactosaminide beta-1,3-N-acetylglucosaminyltransferase 2" B3GNT2 +SeqId.16585-16 Q9C0J1 B3GN4 "N-acetyllactosaminide beta-1,3-N-acetylglucosaminyltransferase 4" B3GNT4 +SeqId.7082-2 Q6ZMB0 B3GN6 "UDP-GlcNAc:betaGal beta-1,3-N-acetylglucosaminyltransferase 6" B3GNT6 +SeqId.9297-12 Q7Z7M8 B3GN8 "UDP-GlcNAc:betaGal beta-1,3-N-acetylglucosaminyltransferase 8" B3GNT8 +SeqId.8976-13 Q00973 B4GN1 "Beta-1,4 N-acetylgalactosaminyltransferase 1" B4GALNT1 +SeqId.13381-49 P15291 B4GT1 "Beta-1,4-galactosyltransferase 1" B4GALT1 +SeqId.9595-11 O60909 B4GT2 "Beta-1,4-galactosyltransferase 2" B4GALT2 +SeqId.6921-24 O60512 B4GT3 "Beta-1,4-galactosyltransferase 3" B4GALT3 +SeqId.10425-3 O43286 B4GT5 "Beta-1,4-galactosyltransferase 5" B4GALT5 +SeqId.10832-24 Q9UBX8 B4GT6 "Beta-1,4-galactosyltransferase 6" B4GALT6 +SeqId.7806-33 Q9UBV7 B4GT7 "Beta-1,4-galactosyltransferase 7" B4GALT7 +SeqId.12451-62 O14867 BACH1 Transcription regulator protein BACH1 BACH1 +SeqId.12756-3 Q9BYV9 BACH2 Transcription regulator protein BACH2 BACH2 +SeqId.5870-23 Q92934 BAD Bcl2-associated agonist of cell death BAD +SeqId.17195-43 Q99933 BAG-1 BAG family molecular chaperone regulator 1 BAG1 +SeqId.19228-11 O95816 BAG-2 BAG family molecular chaperone regulator 2 BAG2 +SeqId.10078-5 O95817 BAG3 BAG family molecular chaperone regulator 3 BAG3 +SeqId.12844-10 O95429 BAG4 BAG family molecular chaperone regulator 4 BAG4 +SeqId.12743-18 Q9UL15 BAG5 BAG family molecular chaperone regulator 5 BAG5 +SeqId.6294-11 Q86Y30 BAGE2 B melanoma antigen 2 BAGE2 +SeqId.15365-41 O60242 BAI3 Adhesion G protein-coupled receptor B3 BAI3 +SeqId.19331-18 Q9UQB8 BAIP2 Brain-specific angiogenesis inhibitor 1-associated protein 2 BAIAP2 +SeqId.8811-24 Q13145 BAMBI BMP and activin membrane-bound inhibitor homolog BAMBI +SeqId.13977-28 Q99728 BARD1 BRCA1-associated RING domain protein 1 BARD1 +SeqId.19227-18 Q16520 BATF Basic leucine zipper transcriptional factor ATF-like BATF +SeqId.8858-21 Q9NR55 BATF3 Basic leucine zipper transcriptional factor ATF-like 3 BATF3 +SeqId.2816-50 P50895 BCAM Basal Cell Adhesion Molecule BCAM +SeqId.3461-58 Q96GW7 PGCB Brevican core protein BCAN +SeqId.11570-94 Q9UHQ4 BAP29 B-cell receptor-associated protein 29 BCAP29 +SeqId.12634-79 O75815 BCAR3 Breast cancer anti-estrogen resistance protein 3 BCAR3 +SeqId.5262-57 O75815 BCAR3 Breast cancer anti-estrogen resistance protein 3 BCAR3 +SeqId.19365-11 O15382 BCAT2 "Branched-chain-amino-acid aminotransferase, mitochondrial" BCAT2 +SeqId.18304-19 Q9P287 BCCIP BRCA2 and CDKN1A-interacting protein BCCIP +SeqId.15514-26 P06276 Pseudocholinesterase Cholinesterase BCHE +SeqId.8768-4 O95999 Bcl-10 B-cell lymphoma/leukemia 10 BCL10 +SeqId.3412-7 P10415 Bcl-2 Apoptosis regulator Bcl-2 BCL2 +SeqId.3413-50 Q16548 BFL1 Bcl-2-related protein A1 BCL2A1 +SeqId.4423-77 Q07817 BCL2-like 1 protein Bcl-2-like protein 1 BCL2L1 +SeqId.7249-307 Q9HD36 B2L10 Bcl-2-like protein 10 BCL2L10 +SeqId.17451-13 O43521 BIM Bcl-2-like protein 11 BCL2L11 +SeqId.13097-11 Q92843 Apoptosis regulator Bcl-W Bcl-2-like protein 2 BCL2L2 +SeqId.13111-79 P41182 BCL6 B-cell lymphoma 6 protein BCL6 +SeqId.17329-2 Q9BUT1 BDH2 3-hydroxybutyrate dehydrogenase type 2 BDH2 +SeqId.14047-78 P23560 BDNF Brain-derived neurotrophic factor BDNF +SeqId.2421-7 P23560 BDNF Brain-derived neurotrophic factor BDNF +SeqId.8929-7 A6H8Y1 BDP1 Transcription factor TFIIIB component B'' homolog BDP1 +SeqId.13032-1 Q14457 BECN1 Beclin-1 BECN1 +SeqId.10959-125 Q9NYM9 BET1L BET1-like protein BET1L +SeqId.11067-13 P02818 Osteocalcin Osteocalcin BGLAP +SeqId.3284-75 P21810 BGN Biglycan BGN +SeqId.14226-120 Q9H2M3 BHMT2 S-methylmethionine--homocysteine S-methyltransferase BHMT2 BHMT2 +SeqId.5798-3 P55957 BID BH3-interacting domain death agonist BID +SeqId.9574-11 O00499 BIN1 Myc box-dependent-interacting protein 1 BIN1 +SeqId.10046-55 Q13490 cIAP-1 Baculoviral IAP repeat-containing protein 2 BIRC2 +SeqId.4973-18 Q13489 cIAP-2 Baculoviral IAP repeat-containing protein 3 BIRC3 +SeqId.3472-40 O15392 Survivin Baculoviral IAP repeat-containing protein 5 BIRC5 +SeqId.15412-40 Q96CA5 KIAP Baculoviral IAP repeat-containing protein 7 BIRC7 +SeqId.15504-39 Q96CA5 Livin B Baculoviral IAP repeat-containing protein 7 Isoform beta BIRC7 +SeqId.11338-49 P51451 BLK Tyrosine-protein kinase BLK BLK +SeqId.14250-115 Q13867 BLMH Bleomycin hydrolase BLMH +SeqId.19225-11 Q8WV28 BLNK B-cell linker protein BLNK +SeqId.11382-5 P53004 BIEA Biliverdin reductase A BLVRA +SeqId.17148-7 P30043 BLVRB Flavin reductase (NADPH) BLVRB +SeqId.3348-49 P13497 BMP-1 Bone morphogenetic protein 1 BMP1 +SeqId.3587-53 O95393 BMP10 Bone morphogenetic protein 10 BMP10 +SeqId.11129-66 O95972 BMP15 Bone morphogenetic protein 15 BMP15 +SeqId.15666-21 P12643 BMP-2 Bone morphogenetic protein 2 BMP2 +SeqId.16748-1 P12645 BMP-3 Bone morphogenetic protein 3 BMP3 +SeqId.15667-39 P12644 BMP-4 Bone morphogenetic protein 4 BMP4 +SeqId.6326-20 P12644 BMP-4 Bone morphogenetic protein 4 BMP4 +SeqId.8459-10 P22004 BMP-6 Bone morphogenetic protein 6 BMP6 +SeqId.2972-57 P18075 BMP-7 Bone morphogenetic protein 7 BMP7 +SeqId.15668-19 P34820 BMP-8 Bone morphogenetic protein 8B BMP8B +SeqId.15368-3 Q8N8U9 BMPER BMP-binding endothelial regulator protein BMPER +SeqId.10550-37 O00238 BMP RIB Bone morphogenetic protein receptor type-1B BMPR1B +SeqId.4862-63 Q13873 BMP RII Bone morphogenetic protein receptor type-2 BMPR2 +SeqId.3414-40 P51813 BMX Cytoplasmic tyrosine-protein kinase BMX BMX +SeqId.7045-4 Q12983 BNIP3 BCL2/adenovirus E1B 19 kDa protein-interacting protein 3 BNIP3 +SeqId.7835-2 O60238 BNI3L BCL2/adenovirus E1B 19 kDa protein-interacting protein 3-like BNIP3L +SeqId.4328-2 Q9BWV1 BOC Brother of CDO BOC +SeqId.15370-5 Q9Y3E2 BOLA1 BolA-like protein 1 BOLA1 +SeqId.8404-102 Q9H3K6 BolA-like protein 2 BolA-like protein 2 BOLA2 +SeqId.5980-55 Q53S33 BOLA3 BolA-like protein 3 BOLA3 +SeqId.12020-39 P07738 PMGE Bisphosphoglycerate mutase BPGM +SeqId.17813-21 Q86WA6 BPHL Valacyclovir hydrolase BPHL +SeqId.4126-22 P17213 BPI Bactericidal permeability-increasing protein BPI +SeqId.6473-55 Q9NP55 PLUNC BPI fold-containing family A member 1 BPIFA1 +SeqId.16302-11 Q96DR5 SPLC2 BPI fold-containing family A member 2 BPIFA2 +SeqId.15367-38 Q8TDL5 LPLC1 BPI fold-containing family B member 1 BPIFB1 +SeqId.17814-8 O95861 BPNT1 "3'(2'),5'-bisphosphate nucleotidase 1" BPNT1 +SeqId.12482-5 Q12830 BPTF Nucleosome-remodeling factor subunit BPTF BPTF +SeqId.15669-7 P15056 BRAF1 Serine/threonine-protein kinase B-raf BRAF +SeqId.10876-300 Q6PJG6 BRAT1 BRCA1-associated ATM activator 1 BRAT1 +SeqId.11607-15 O95696 BRD1 Bromodomain-containing protein 1 BRD1 +SeqId.10074-128 P25440 BRD2 Bromodomain-containing protein 2 BRD2 +SeqId.15372-43 P25440 BRD2 Bromodomain-containing protein 2 BRD2 +SeqId.10043-31 O60885 BRD4 Bromodomain-containing protein 4 BRD4 +SeqId.12748-6 Q58F21 BRDT Bromodomain testis-specific protein BRDT +SeqId.19596-18 Q92994 BRF-1 Transcription factor IIIB 90 kDa subunit BRF1 +SeqId.6612-90 Q6PL45 CP079 BRICHOS domain-containing protein 5 BRICD5 +SeqId.11671-19 P55201 BRPF1 Peregrin BRPF1 +SeqId.9790-28 Q8IWQ3 BR serine/threonine kinase 2 Serine/threonine-protein kinase BRSK2 BRSK2 +SeqId.3585-54 P35613 BASI Basigin BSG +SeqId.4535-50 Q10588 BST1 ADP-ribosyl cyclase/cyclic ADP-ribose hydrolase 2 BST1 +SeqId.8832-55 Q10589 BST-2 Bone marrow stromal antigen 2 BST2 +SeqId.13088-397 P35070 BTC Betacellulin BTC +SeqId.15644-1 P43251 Biotinidase Biotinidase BTD +SeqId.11325-8 P78543 BTG2 Protein BTG2 BTG2 +SeqId.19202-10 Q06187 BTK Tyrosine-protein kinase BTK BTK +SeqId.16308-14 Q7Z6A9 BTLA B- and T-lymphocyte attenuator BTLA +SeqId.8869-5 Q7KYR7 BT2A1 Butyrophilin subfamily 2 member A1 BTN2A1 +SeqId.7081-2 O00481 BT3A1 Butyrophilin subfamily 3 member A1 BTN3A1 +SeqId.17692-2 O00478 BT3A3 Butyrophilin subfamily 3 member A3 BTN3A3 +SeqId.10848-137 Q6UXE8 BTNL3 Butyrophilin-like protein 3 BTNL3 +SeqId.9026-40 Q6UX41 BTNL8 Butyrophilin-like protein 8 BTNL8 +SeqId.7950-142 Q6UXG8 BTNL9 Butyrophilin-like protein 9 BTNL9 +SeqId.12033-3 O43683 BUB1 Mitotic checkpoint serine/threonine-protein kinase BUB1 BUB1 +SeqId.11220-53 Q8TEF2 CJ105 Uncharacterized protein C10orf105 C10orf105 +SeqId.8220-15 Q96D05 CJ035 Uncharacterized protein C10orf35 C10orf35 +SeqId.11531-24 Q9H7M9 GI24 V-type immunoglobulin domain-containing suppressor of T-cell activation C10orf54 +SeqId.14123-34 Q9H7M9 GI24 V-type immunoglobulin domain-containing suppressor of T-cell activation C10orf54 +SeqId.8307-47 Q9H3H3 CK068 UPF0696 protein C11orf68 C11orf68 +SeqId.8686-342 Q53FT3 HIKES Protein Hikeshi C11orf73 +SeqId.11116-16 Q6NUJ2 CK087 Uncharacterized protein C11orf87 C11orf87 +SeqId.8383-20 C9JXX5 CK094 Uncharacterized protein C11orf94 C11orf94 +SeqId.8303-102 Q9HB07 MYG1 "UPF0160 protein MYG1, mitochondrial" C12orf10 +SeqId.6439-59 Q9H972 CN093 Uncharacterized protein C14orf93 C14orf93 +SeqId.12394-53 Q6UWD8 CP054 Transmembrane protein C16orf54 C16orf54 +SeqId.9070-1 Q0P5P2 CQ067 Uncharacterized protein C17orf67 C17orf67 +SeqId.6571-75 Q8N4C9 CQ078 Uncharacterized protein C17orf78 C17orf78 +SeqId.9030-56 A1L188 CQ089 Uncharacterized protein C17orf89 C17orf89 +SeqId.8236-8 Q8TCD1 CR032 UPF0729 protein C18orf32 C18orf32 +SeqId.9445-44 Q8NEA5 CS018 Uncharacterized protein C19orf18 C19orf18 +SeqId.7183-102 Q6UXH0 TD26 Angiopoietin-like protein 8 C19orf80 +SeqId.7821-6 Q13901 C1D Nuclear nucleic acid-binding protein C1D C1D +SeqId.5735-54 Q96EU7 C1GLC C1GALT1-specific chaperone 1 C1GALT1C1 +SeqId.8366-19 Q9H7X2 CA115 Uncharacterized protein C1orf115 C1orf115 +SeqId.6896-3 Q8NEQ5 CA162 Transmembrane protein C1orf162 C1orf162 +SeqId.10667-78 Q5T7R7 CA185 Uncharacterized protein C1orf185 C1orf185 +SeqId.8102-239 Q6ZWK4 CA186 Uncharacterized protein C1orf186 C1orf186 +SeqId.8035-6 Q9H425 CA198 Uncharacterized protein C1orf198 C1orf198 +SeqId.8088-56 Q8IVY1 CA210 Type III endosome membrane protein TEMP C1orf210 +SeqId.7989-5 A1L170 CA226 Uncharacterized protein C1orf226 C1orf226 +SeqId.6937-251 Q9BWL3 CA043 Uncharacterized protein C1orf43 C1orf43 +SeqId.2753-2 P02745 P02746 P02747 C1q Complement C1q subcomponent C1QA C1QB C1QC +SeqId.2753-2 P02745 P02746 P02747 C1q Complement C1q subcomponent C1QA C1QB C1QC +SeqId.2753-2 P02745 P02746 P02747 C1q Complement C1q subcomponent C1QA C1QB C1QC +SeqId.4967-1 Q07021 C1QBP "Complement component 1 Q subcomponent-binding protein, mitochondrial" C1QBP +SeqId.14100-63 P02747 C1QC Complement C1q subcomponent subunit C C1QC +SeqId.6404-20 O75973 C1QRF C1q-related factor C1QL1 +SeqId.15670-15 Q7Z5L3 C1QL2 Complement C1q-like protein 2 C1QL2 +SeqId.7132-55 Q86Z23 C1QL4 Complement C1q-like protein 4 C1QL4 +SeqId.6304-8 Q9BXJ1 C1QT1 Complement C1q tumor necrosis factor-related protein 1 C1QTNF1 +SeqId.7251-64 Q9BXJ4 C1QT3 Complement C1q tumor necrosis factor-related protein 3 C1QTNF3 +SeqId.7810-20 Q9BXJ0 C1QTNF5 Complement C1q tumor necrosis factor-related protein 5 C1QTNF5 +SeqId.16605-2 P0C862 C1T9A Complement C1q and tumor necrosis factor-related protein 9A C1QTNF9 +SeqId.3285-23 P00736 C1r Complement C1r subcomponent C1R +SeqId.9348-1 Q9NZP8 C1RL1 Complement C1r subcomponent-like protein C1RL +SeqId.8840-61 P09871 C1s Complement C1s subcomponent C1S +SeqId.3186-2 P06681 C2 Complement C2 C2 +SeqId.7046-6 Q96LM9 CT173 Uncharacterized protein C20orf173 C20orf173 +SeqId.5981-6 P30042 ES1 "ES1 protein homolog, mitochondrial" C21orf33 +SeqId.7073-69 Q8WYQ4 CV015 Uncharacterized protein C22orf15 C22orf15 +SeqId.6362-6 Q9H1Z8 AUGN Augurin C2orf40 +SeqId.5677-15 Q6UXQ4 CB066 Uncharacterized protein C2orf66 C2orf66 +SeqId.4900-8 P01024 C3a C3a anaphylatoxin C3 +SeqId.2754-50 P01024 C3 Complement C3 C3 +SeqId.2683-1 P01024 iC3b "Complement C3b, inactivated" C3 +SeqId.4480-59 P01024 C3b Complement C3b C3 +SeqId.5803-24 P01024 C3d Complement C3d fragment C3 +SeqId.6994-19 Q9UK00 CC018 Uncharacterized protein C3orf18 C3orf18 +SeqId.2182-54 P0C0L4 P0C0L5 C4b Complement C4b C4A C4B +SeqId.2182-54 P0C0L4 P0C0L5 C4b Complement C4b C4A C4B +SeqId.18821-9 P0C0L4 P0C0L5 C4a C4a anaphylatoxin C4A C4B +SeqId.18821-9 P0C0L4 P0C0L5 C4a C4a anaphylatoxin C4A C4B +SeqId.4481-34 "P0C0L4, P0C0L5" C4 Complement C4 C4A C4B +SeqId.4481-34 "P0C0L4, P0C0L5" C4 Complement C4 C4A C4B +SeqId.9449-150 P04003 C4b-binding protein alpha chain C4b-binding protein alpha chain C4BPA +SeqId.7155-46 P20851 C4b-binding protein beta chain C4b-binding protein beta chain C4BPB +SeqId.9490-3 Q8N8J7 CD032 Uncharacterized protein C4orf32 C4orf32 +SeqId.2851-63 P01031 C5a C5a anaphylatoxin C5 +SeqId.2381-52 P01031 C5 Complement C5 C5 +SeqId.4482-66 "P01031,P13671" "C5b, 6 Complex" Complement C5b-C6 complex C5 C6 +SeqId.4482-66 "P01031,P13671" "C5b, 6 Complex" Complement C5b-C6 complex C5 C6 +SeqId.6378-2 Q86SI9 CEI Protein CEI C5orf38 +SeqId.9100-32 Q6UWT4 CE046 Uncharacterized protein C5orf46 C5orf46 +SeqId.13378-80 A6NC05 YD286 Glutaredoxin-like protein C5orf63 C5orf63 +SeqId.4127-75 P13671 C6 Complement component C6 C6 +SeqId.10885-36 Q6UWU4 CF089 Bombesin receptor-activated protein C6orf89 C6orf89 +SeqId.2888-49 P10643 C7 Complement component C7 C7 +SeqId.9544-24 Q9H7B7 CG069 Uncharacterized protein C7orf69 C7orf69 +SeqId.8927-6 E0CX11 CG073 Uncharacterized protein C7orf73 C7orf73 +SeqId.2429-27 "P07357,P07358,P07360" C8 Complement component C8 C8A C8B C8G +SeqId.2429-27 "P07357,P07358,P07360" C8 Complement component C8 C8A C8B C8G +SeqId.2429-27 "P07357,P07358,P07360" C8 Complement component C8 C8A C8B C8G +SeqId.14708-59 P07360 CO8G Complement component C8 gamma chain C8G +SeqId.3060-43 P02748 C9 Complement component C9 C9 +SeqId.7778-104 Q96LW7 BINCA Caspase recruitment domain-containing protein 19 C9orf89 +SeqId.4969-2 P00915 Carbonic anhydrase I Carbonic anhydrase 1 CA1 +SeqId.13666-222 Q9NS85 Carbonic Anhydrase X Carbonic anhydrase-related protein 10 CA10 +SeqId.8859-51 O75493 CAH11 Carbonic anhydrase-related protein 11 CA11 +SeqId.19347-37 O43570 Carbonic Anhydrase XII Carbonic anhydrase 12 CA12 +SeqId.3420-21 Q8N1Q1 Carbonic anhydrase XIII Carbonic anhydrase 13 CA13 +SeqId.4970-55 P00918 carbonic anhydrase II Carbonic anhydrase 2 CA2 +SeqId.3799-11 P07451 Carbonic anhydrase III Carbonic anhydrase 3 CA3 +SeqId.14069-61 P22748 Carbonic Anhydrase IV Carbonic anhydrase 4 CA4 +SeqId.8791-151 P35218 Carbonic Anhydrase VA "Carbonic anhydrase 5A, mitochondrial" CA5A +SeqId.17673-34 Q9Y2D0 Carbonic Anhydrase VB "Carbonic anhydrase 5B, mitochondrial" CA5B +SeqId.3352-80 P23280 Carbonic anhydrase 6 Carbonic anhydrase 6 CA6 +SeqId.3356-50 P43166 Carbonic anhydrase VII Carbonic anhydrase 7 CA7 +SeqId.11390-24 P35219 Carbonic Anhydrase VIII Carbonic anhydrase-related protein CA8 +SeqId.3798-71 Q16790 Carbonic anhydrase 9 Carbonic anhydrase 9 CA9 +SeqId.17757-86 Q9Y376 CAB39 Calcium-binding protein 39 CAB39 +SeqId.7105-7 Q9BTV7 CABL2 CDK5 and ABL1 enzyme substrate 2 CABLES2 +SeqId.7104-71 Q86V35 CABP7 Calcium-binding protein 7 CABP7 +SeqId.8885-6 Q8IZS8 CA2D3 Voltage-dependent calcium channel subunit alpha-2/delta-3 CACNA2D3 +SeqId.11130-158 O00305 CACB4 Voltage-dependent L-type calcium channel subunit beta-4 CACNB4 +SeqId.12432-23 Q9HB71 CYBP Calcyclin-binding protein CACYBP +SeqId.3326-58 Q9BY67 Nectin-like protein 2 Cell adhesion molecule 1 CADM1 +SeqId.16907-3 Q8N3J6 Nectin-like protein 3 Cell adhesion molecule 2 CADM2 +SeqId.3630-27 Q8N126 Nectin-like protein 1 Cell adhesion molecule 3 CADM3 +SeqId.9918-23 P05937 Calbindin D28 Calbindin CALB1 +SeqId.16803-4 P22676 CALB2 Calretinin CALB2 +SeqId.17170-15 P10092 CALCB Calcitonin gene-related peptide 2 CALCB +SeqId.12534-10 Q13137 CACO2 Calcium-binding and coiled-coil domain-containing protein 2 CALCOCO2 +SeqId.10933-107 Q9BXU9 CABP8 Calcium-binding protein 8 CALN1 +SeqId.5264-65 P27797 calreticulin Calreticulin CALR +SeqId.8924-55 Q9NYX4 CALY Neuron-specific vesicular protein calcyon CALY +SeqId.3592-4 Q14012 CAMK1 Calcium/calmodulin-dependent protein kinase type 1 CAMK1 +SeqId.3418-12 Q8IU85 CAMK1D Calcium/calmodulin-dependent protein kinase type 1D CAMK1D +SeqId.3350-53 Q9UQM7 CAMK2A Calcium/calmodulin-dependent protein kinase type II subunit alpha CAMK2A +SeqId.3351-1 Q13554 CAMK2B Calcium/calmodulin-dependent protein kinase type II subunit beta CAMK2B +SeqId.3419-49 Q13557 CAMK2D Calcium/calmodulin-dependent protein kinase type II subunit delta CAMK2D +SeqId.18904-23 Q16566 KCC4 Calcium/calmodulin-dependent protein kinase type IV CAMK4 +SeqId.18860-2 Q8N5S9 CaMKK alpha Calcium/calmodulin-dependent protein kinase kinase 1 CAMKK1 +SeqId.15481-45 P49913 LL-37 Antibacterial protein LL-37 CAMP +SeqId.9384-17 P49913 Cathelicidin peptide Cathelicidin antimicrobial peptide CAMP +SeqId.13937-75 Q86VP6 CAND1 Cullin-associated NEDD8-dissociated protein 1 CAND1 +SeqId.6480-1 Q8WVQ1 CANT1 Soluble calcium-activated nucleotidase 1 CANT1 +SeqId.8834-58 P27824 Calnexin Calnexin CANX +SeqId.12034-28 Q01518 CAP 1 Adenylyl cyclase-associated protein 1 CAP1 +SeqId.4968-50 P40121 CAPG Macrophage-capping protein CAPG +SeqId.2668-70 P07384 P04632 Calpain I Calpain I CAPN1 CAPNS1 +SeqId.2668-70 P07384 P04632 Calpain I Calpain I CAPN1 CAPNS1 +SeqId.14684-17 P17655 CAN2 Calpain-2 catalytic subunit CAPN2 +SeqId.12385-4 P20807 CAN3 Calpain-3 CAPN3 +SeqId.18299-13 P04632 CPNS1 Calpain small subunit 1 CAPNS1 +SeqId.13688-2 Q8WWF8 CAPSL Calcyphosin-like protein CAPSL +SeqId.11449-22 P52907 CAZA1 F-actin-capping protein subunit alpha-1 CAPZA1 +SeqId.18267-74 Q5XLA6 CAR17 Caspase recruitment domain-containing protein 17 CARD17 +SeqId.18190-15 P57730 ICBR Caspase recruitment domain-containing protein 18 CARD18 +SeqId.11405-150 Q9H257 CARD9 Caspase recruitment domain-containing protein 9 CARD9 +SeqId.12808-103 Q9Y2V2 CHSP1 Calcium-regulated heat-stable protein 1 CARHSP1 +SeqId.14098-28 P49589 SYCC "Cysteine--tRNA ligase, cytoplasmic" CARS +SeqId.5743-82 Q16568 CART Cocaine- and amphetamine-regulated transcript protein CARTPT +SeqId.10613-33 Q6P4E1 CASC4 Protein CASC4 CASC4 +SeqId.8838-10 Q6P4E1 CASC4 Protein CASC4 CASC4 +SeqId.16754-40 O14936 CSKP Peripheral plasma membrane protein CASK CASK +SeqId.5340-24 Q92851 Caspase-10 Caspase-10 CASP10 +SeqId.16617-14 P31944 Caspase-14 Caspase-14 CASP14 +SeqId.4904-7 P42575 Caspase-2 Caspase-2 CASP2 +SeqId.3593-72 P42574 Caspase-3 Caspase-3 CASP3 +SeqId.18158-45 Q14790 Caspase-8 Caspase-8 CASP8 +SeqId.11263-57 P31415 CASQ1 Calsequestrin-1 CASQ1 +SeqId.19291-2 O14958 CASQ2 Calsequestrin-2 CASQ2 +SeqId.12855-16 Q9NQ75 CT032 Cas scaffolding protein family member 4 CASS4 +SeqId.3026-5 P20810 Calpastatin Calpastatin CAST +SeqId.3488-64 P04040 Catalase Catalase CAT +SeqId.9457-3 P51636 CAV2 Caveolin-2 CAV2 +SeqId.8690-25 P56539 CAV3 Caveolin-3 CAV3 +SeqId.10048-7 Q13951 PEBB Core-binding factor subunit beta CBFB +SeqId.12016-60 P22681 CBL E3 ubiquitin-protein ligase CBL CBL +SeqId.9313-27 P23435 CBLN1 Cerebellin-1 CBLN1 +SeqId.5688-65 Q9NTU7 CBLN4 Cerebellin-4 CBLN4 +SeqId.12381-26 P16152 CBR1 Carbonyl reductase [NADPH] 1 CBR1 +SeqId.14091-42 O75828 Carbonyl reductase 3 Carbonyl reductase [NADPH] 3 CBR3 +SeqId.10086-39 P35520 CBS Cystathionine beta-synthase CBS +SeqId.18817-50 P83916 CBX1 Chromobox protein homolog 1 CBX1 +SeqId.18868-7 Q13185 CBX3 Chromobox protein homolog 3 CBX3 +SeqId.4540-11 P45973 CBX5 Chromobox protein homolog 5 CBX5 +SeqId.13027-20 O95931 CBX7 Chromobox protein homolog 7 CBX7 +SeqId.17365-7 Q16773 KAT1 Kynurenine--oxoglutarate transaminase 1 CCBL1 +SeqId.12682-5 Q6YP21 KAT3 Kynurenine--oxoglutarate transaminase 3 CCBL2 +SeqId.12788-6 Q96ES7 SGF29 SAGA-associated factor 29 homolog CCDC101 +SeqId.6388-21 Q96EE4 CC126 Coiled-coil domain-containing protein 126 CCDC126 +SeqId.15300-66 Q9H6E4 CC134 Coiled-coil domain-containing protein 134 CCDC134 +SeqId.7797-11 Q9P0B6 CC167 Coiled-coil domain-containing protein 167 CCDC167 +SeqId.18264-12 Q86WR0 CCD25 Coiled-coil domain-containing protein 25 CCDC25 +SeqId.12399-194 Q8IVM0 CCD50 Coiled-coil domain-containing protein 50 CCDC50 +SeqId.12790-10 Q96ER9 CCD51 Coiled-coil domain-containing protein 51 CCDC51 +SeqId.11158-40 Q6ZP65 BICR1 Bicaudal D-related protein 1 CCDC64 +SeqId.3234-23 Q76M96 URB Coiled-coil domain-containing protein 80 CCDC80 +SeqId.7792-58 Q9GZT6 CC90B "Coiled-coil domain-containing protein 90B, mitochondrial" CCDC90B +SeqId.6918-183 P06307 CCKN Cholecystokinin CCK +SeqId.2770-51 P22362 I-309 C-C motif chemokine 1 CCL1 +SeqId.5301-7 P51671 Eotaxin Eotaxin CCL11 +SeqId.4144-13 Q99616 MCP-4 C-C motif chemokine 13 CCL13 +SeqId.2900-53 Q16627 HCC-1 C-C motif chemokine 14 CCL14 +SeqId.18289-16 Q16663 MIP-5 C-C motif chemokine 15 CCL15 +SeqId.4913-78 O15467 HCC-4 C-C motif chemokine 16 CCL16 +SeqId.3519-3 Q92583 TARC C-C motif chemokine 17 CCL17 +SeqId.3044-3 P55774 PARC C-C motif chemokine 18 CCL18 +SeqId.4922-13 Q99731 MIP-3b C-C motif chemokine 19 CCL19 +SeqId.2578-67 P13500 MCP-1 C-C motif chemokine 2 CCL2 +SeqId.2468-62 P78556 MIP-3a C-C motif chemokine 20 CCL20 +SeqId.2516-57 O00585 6Ckine C-C motif chemokine 21 CCL21 +SeqId.3508-78 O00626 MDC C-C motif chemokine 22 CCL22 +SeqId.2913-1 P55773 MPIF-1 C-C motif chemokine 23 CCL23 +SeqId.3028-36 P55773 Ck-b-8-1 Ck-beta-8-1 CCL23 +SeqId.4128-27 O00175 Eotaxin-2 C-C motif chemokine 24 CCL24 +SeqId.2705-5 O15444 TECK C-C motif chemokine 25 CCL25 +SeqId.9168-31 Q9Y258 Eotaxin-3 C-C motif chemokine 26 CCL26 +SeqId.2192-63 Q9Y4X3 CTACK C-C motif chemokine 27 CCL27 +SeqId.2890-59 Q9NRJ3 CCL28 C-C motif chemokine 28 CCL28 +SeqId.3040-59 P10147 MIP-1a C-C motif chemokine 3 CCL3 +SeqId.2783-18 P16619 LD78-beta C-C motif chemokine 3-like 1 CCL3L1 +SeqId.2781-63 Q8NHW4 LAG-1 C-C motif chemokine 4-like CCL4L1 +SeqId.5480-49 P13501 RANTES C-C motif chemokine 5 CCL5 +SeqId.4886-3 P80098 MCP-3 C-C motif chemokine 7 CCL7 +SeqId.13748-4 P80075 MCP-2 C-C motif chemokine 8 CCL8 +SeqId.12347-29 Q9BSQ5 CCM2 Cerebral cavernous malformations 2 protein CCM2 +SeqId.15319-226 P78396 CCNA1 Cyclin-A1 CCNA1 +SeqId.15574-37 P20248 Cyclin A Cyclin-A2 CCNA2 +SeqId.5347-59 P14635 Cyclin B1 G2/mitotic-specific cyclin-B1 CCNB1 +SeqId.9728-4 Q9NPC3 CIP1 E3 ubiquitin-protein ligase CCNB1IP1 CCNB1IP1 +SeqId.18208-3 O95067 CCNB2 G2/mitotic-specific cyclin-B2 CCNB2 +SeqId.18913-3 P51946 Cyclin H Cyclin-H CCNH +SeqId.9848-22 P51946 Cyclin H Cyclin-H CCNH +SeqId.8889-5 Q9ULG6 CCPG1 Cell cycle progression protein 1 CCPG1 +SeqId.13068-139 O14618 CCS Copper chaperone for superoxide dismutase CCS +SeqId.12569-25 P48643 TCP-1-epsilon T-complex protein 1 subunit epsilon CCT5 +SeqId.13673-21 Q99832 TCPH T-complex protein 1 subunit eta CCT7 +SeqId.12699-28 P50990 TCP-1-theta T-complex protein 1 subunit theta CCT8 +SeqId.3290-50 Q6YHK3 CD109 CD109 antigen CD109 +SeqId.16914-104 P08571 sCD14 "Monocyte differentiation antigen CD14, soluble" CD14 +SeqId.8969-49 P08571 CD14 Monocyte differentiation antigen CD14 CD14 +SeqId.17677-47 O95971 BY55 CD160 antigen CD160 +SeqId.5028-59 Q86VB7 sCD163 Scavenger receptor cysteine-rich type 1 protein M130 CD163 +SeqId.6915-2 Q6UWJ8 C16L2 CD164 sialomucin-like 2 protein CD164L2 +SeqId.13116-25 Q8N6Q3 CD177 CD177 antigen CD177 +SeqId.10814-7 P06126 CD1A T-cell surface glycoprotein CD1a CD1A +SeqId.8749-194 P15813 CD1D Antigen-presenting glycoprotein CD1d CD1D +SeqId.7100-31 P06729 CD2 T-cell surface antigen CD2 CD2 +SeqId.5112-73 P41217 OX2G OX-2 membrane glycoprotein CD200 +SeqId.5103-30 Q8TD46 MO2R1 Cell surface glycoprotein CD200 receptor 1 CD200R1 +SeqId.8980-19 Q6Q8B3 MO2R2 Cell surface glycoprotein CD200 receptor 2 CD200R1L +SeqId.3361-26 Q9UJ71 CLC4K C-type lectin domain family 4 member K CD207 +SeqId.3029-52 Q9NNX6 DC-SIGN CD209 antigen CD209 +SeqId.5062-60 Q15762 CD226 CD226 antigen CD226 +SeqId.5063-12 Q9BZW8 CD244 Natural killer cell receptor 2B4 CD244 +SeqId.15567-2 P20963 CD3-zeta T-cell surface glycoprotein CD3 zeta chain CD247 +SeqId.15491-20 Q9HCU0 CD248 Endosialin CD248 +SeqId.5412-53 P26842 CD27 CD27 antigen CD27 +SeqId.5060-62 Q9NZQ7 B7-H1 Programmed cell death 1 ligand 1 CD274 +SeqId.5630-48 Q9UGN4 CM35H CMRF35-like molecule 8 CD300A +SeqId.5066-134 Q08708 CLM6 CMRF35-like molecule 6 CD300C +SeqId.10798-4 Q496F6 CLM2 CMRF35-like molecule 2 CD300E +SeqId.10713-151 A8K4G0 CLM7 CMRF35-like molecule 7 CD300LB +SeqId.5623-11 Q8TDQ1 CLM1 CMRF35-like molecule 1 CD300LF +SeqId.16320-139 Q9NPF0 CD320 CD320 antigen CD320 +SeqId.3166-92 P20138 Siglec-3 Myeloid cell surface antigen CD33 CD33 +SeqId.2973-15 P16671 CD36 ANTIGEN Platelet glycoprotein 4 CD36 +SeqId.18202-22 P11049 CD37 Leukocyte antigen CD37 CD37 +SeqId.11513-92 P28907 CD38 ADP-ribosyl cyclase/cyclic ADP-ribose hydrolase 1 CD38 +SeqId.18870-1 P07766 CD3E T-cell surface glycoprotein CD3 epsilon chain CD3E +SeqId.8069-85 P07766 CD3E T-cell surface glycoprotein CD3 epsilon chain CD3E +SeqId.7924-7 P09693 CD3G T-cell surface glycoprotein CD3 gamma chain CD3G +SeqId.3143-3 P01730 sCD4 T-cell surface glycoprotein CD4 CD4 +SeqId.3534-14 P29965 "CD40 ligand, soluble" CD40 ligand CD40LG +SeqId.9283-8 P16070 CD44 CD44 antigen CD44 +SeqId.17682-1 P15529 CD46 Membrane cofactor protein CD46 +SeqId.6653-58 Q08722 CD47 Leukocyte surface antigen CD47 CD47 +SeqId.3292-75 P09326 CD48 CD48 antigen CD48 +SeqId.14065-11 P06127 CD5 T-cell surface glycoprotein CD5 CD5 +SeqId.5596-75 P06127 CD5 T-cell surface glycoprotein CD5 CD5 +SeqId.5069-9 P08174 DAF Complement decay-accelerating factor CD55 +SeqId.10938-13 P19256 sLFA-3 Lymphocyte function-associated antigen 3 CD58 +SeqId.11514-196 P13987 CD59 CD59 glycoprotein CD59 +SeqId.3293-2 O43866 CD5L CD5 antigen-like CD5L +SeqId.9190-7 P08962 CD63 CD63 antigen CD63 +SeqId.18922-27 P34810 CD68 Macrosialin CD68 +SeqId.16618-7 Q07108 CD69 Early activation antigen CD69 CD69 +SeqId.12008-3 P09564 CD7 T-cell antigen CD7 CD7 +SeqId.5807-77 P32970 CD70 CD70 antigen CD70 +SeqId.7009-8 P21854 CD72 B-cell differentiation antigen CD72 CD72 +SeqId.6974-6 P04233 HG2A HLA class II histocompatibility antigen gamma chain CD74 +SeqId.8748-45 P04233 HG2A HLA class II histocompatibility antigen gamma chain CD74 +SeqId.15674-3 P11912 CD79A B-cell antigen receptor complex-associated protein alpha chain CD79A +SeqId.7796-10 P11912 CD79A B-cell antigen receptor complex-associated protein alpha chain CD79A +SeqId.6351-55 P40259 CD79B B-cell antigen receptor complex-associated protein beta chain CD79B +SeqId.13726-4 P33681 B7 T-lymphocyte activation antigen CD80 CD80 +SeqId.19612-3 P60033 CD81 CD81 antigen CD81 +SeqId.5065-8 Q01151 CD83 CD83 antigen CD83 +SeqId.5337-64 P42081 B7-2 T-lymphocyte activation antigen CD86 CD86 +SeqId.15462-28 P01732 CD8A T-cell surface glycoprotein CD8 alpha chain CD8A +SeqId.9310-2 P10966 CD8B T-cell surface glycoprotein CD8 beta chain CD8B +SeqId.17449-23 P21926 CD9 CD9 antigen CD9 +SeqId.14136-234 Q9NPY3 C1QR1 Complement component C1q receptor CD93 +SeqId.9735-44 P40200 TACT T-cell surface protein tactile CD96 +SeqId.18881-7 P48960 CD97 CD97 antigen CD97 +SeqId.10539-30 Q8TCZ2 C99L2 CD99 antigen-like protein 2 CD99L2 +SeqId.3422-4 P06493 P14635 CDK1/cyclin B Cyclin-dependent kinase 1:G2/mitotic-specific cyclin-B1 complex CDC2 CCNB1 +SeqId.3422-4 P06493 P14635 CDK1/cyclin B Cyclin-dependent kinase 1:G2/mitotic-specific cyclin-B1 complex CDC2 CCNB1 +SeqId.11548-84 P30304 MPIP1 M-phase inducer phosphatase 1 CDC25A +SeqId.12427-8 P30305 MPIP2 M-phase inducer phosphatase 2 CDC25B +SeqId.12532-28 P49427 UB2R1 Ubiquitin-conjugating enzyme E2 R1 CDC34 +SeqId.3879-50 Q16543 CDC37 Hsp90 co-chaperone Cdc37 CDC37 +SeqId.9840-2 P60953 Cdc42Hs Cell division control protein 42 homolog CDC42 +SeqId.12706-2 Q5VT25 MRCKA Serine/threonine-protein kinase MRCK alpha CDC42BPA +SeqId.3629-60 Q9Y5S2 MRCKB Serine/threonine-protein kinase MRCK beta CDC42BPB +SeqId.16818-200 Q9H5V8 CDCP1 CUB domain-containing protein 1 CDCP1 +SeqId.8589-13 Q9H5V8 CDCP1 CUB domain-containing protein 1 CDCP1 +SeqId.18429-10 P12830 Cadherin E Cadherin-1 CDH1 +SeqId.16305-10 P55287 Cadherin-11 Cadherin-11 CDH11 +SeqId.7763-25 P55287 Cadherin-11 Cadherin-11 CDH11 +SeqId.19388-2 P55289 Cadherin-12 Cadherin-12 CDH12 +SeqId.11215-6 P55291 CAD15 Cadherin-15 CDH15 +SeqId.5410-53 P55291 CAD15 Cadherin-15 CDH15 +SeqId.16613-3 Q12864 CAD17 Cadherin-17 CDH17 +SeqId.3797-1 P19022 Cadherin-2 Cadherin-2 CDH2 +SeqId.2643-57 P22223 P-Cadherin Cadherin-3 CDH3 +SeqId.2819-23 P33151 Cadherin-5 Cadherin-5 CDH5 +SeqId.16312-45 P55285 Cadherin-6 Cadherin-6 CDH6 +SeqId.7959-34 Q9ULB5 CADH7 Cadherin-7 CDH7 +SeqId.16021-30 P55286 Cadherin-8 Cadherin-8 CDH8 +SeqId.8372-29 Q96JP9 CDHR1 Cadherin-related family member 1 CDHR1 +SeqId.8222-49 Q6ZTQ4 CDHR3 Cadherin-related family member 3 CDHR3 +SeqId.9962-1 Q9HBB8 MUCDL Cadherin-related family member 5 CDHR5 +SeqId.3357-67 P24941 P20248 CDK2/cyclin A Cyclin-dependent kinase 2:Cyclin-A2 complex CDK2 CCNA2 +SeqId.3357-67 P24941 P20248 CDK2/cyclin A Cyclin-dependent kinase 2:Cyclin-A2 complex CDK2 CCNA2 +SeqId.9450-18 O14519 CDKA1 Cyclin-dependent kinase 2-associated protein 1 CDK2AP1 +SeqId.18227-3 O75956 CDKA2 Cyclin-dependent kinase 2-associated protein 2 CDK2AP2 +SeqId.3358-51 Q00535 Q15078 CDK5/p35 Cyclin-dependent kinase 5:Cyclin-dependent kinase 5 activator 1 complex CDK5 CDK5R1 +SeqId.3358-51 Q00535 Q15078 CDK5/p35 Cyclin-dependent kinase 5:Cyclin-dependent kinase 5 activator 1 complex CDK5 CDK5R1 +SeqId.3359-11 P49336 P24863 CDK8/cyclin C Cyclin-dependent kinase 8:Cyclin-C complex CDK8 CCNC +SeqId.3359-11 P49336 P24863 CDK8/cyclin C Cyclin-dependent kinase 8:Cyclin-C complex CDK8 CCNC +SeqId.18291-8 P38936 p21 Cyclin-dependent kinase inhibitor 1 CDKN1A +SeqId.3719-2 P46527 p27Kip1 Cyclin-dependent kinase inhibitor 1B CDKN1B +SeqId.9874-28 P42772 p15-INK4b Cyclin-dependent kinase 4 inhibitor B CDKN2B +SeqId.12521-3 P42773 CDN2C Cyclin-dependent kinase 4 inhibitor C CDKN2C +SeqId.12376-85 P55273 p19-INK4d Cyclin-dependent kinase 4 inhibitor D CDKN2D +SeqId.14178-18 Q16667 CDKN3 Cyclin-dependent kinase inhibitor 3 CDKN3 +SeqId.4962-52 Q49AH0 ARMEL Cerebral dopamine neurotrophic factor CDNF +SeqId.4541-49 Q4KMG0 CDON Cell adhesion molecule-related/down-regulated by oncogenes CDON +SeqId.7085-81 Q15517 CDSN Corneodesmosin CDSN +SeqId.7097-8 Q9Y6F8 CDY1 Testis-specific chromodomain protein Y 1 CDY1 +SeqId.10752-8 Q8N8U2 CDYL2 Chromodomain Y-like protein 2 CDYL2 +SeqId.7048-4 Q7Z692 CEA19 Carcinoembryonic antigen-related cell adhesion molecule 19 CEACAM19 +SeqId.10453-7 Q6UY09 CEA20 Carcinoembryonic antigen-related cell adhesion molecule 20 CEACAM20 +SeqId.7204-1 Q3KPI0 CEA21 Carcinoembryonic antigen-related cell adhesion molecule 21 CEACAM21 +SeqId.8999-19 P40198 CEAM3 Carcinoembryonic antigen-related cell adhesion molecule 3 CEACAM3 +SeqId.10910-6 O75871 CEAM4 Carcinoembryonic antigen-related cell adhesion molecule 4 CEACAM4 +SeqId.7184-13 Q14002 CEAM7 Carcinoembryonic antigen-related cell adhesion molecule 7 CEACAM7 +SeqId.18873-8 P31997 CEAM8 Carcinoembryonic antigen-related cell adhesion molecule 8 CEACAM8 +SeqId.18874-66 P49715 CEBPA CCAAT/enhancer-binding protein alpha CEBPA +SeqId.15675-3 P17676 CEBPB CCAAT/enhancer-binding protein beta CEBPB +SeqId.19572-10 P53567 CEBPG CCAAT/enhancer-binding protein gamma CEBPG +SeqId.6077-63 Q9NZK5 CECR1 Adenosine deaminase CECR1 CECR1 +SeqId.9796-4 P19835 CEL Bile salt-activated lipase CEL +SeqId.6107-3 Q9UNI1 ELA1 Chymotrypsin-like elastase family member 1 CELA1 +SeqId.7140-1 P08217 ELA2A Chymotrypsin-like elastase family member 2A CELA2A +SeqId.6357-83 P08861 ELA3B Chymotrypsin-like elastase family member 3B CELA3B +SeqId.7245-2 O95319 CELF2 CUGBP Elav-like family member 2 CELF2 +SeqId.8817-29 Q7Z7K6 CENPV Centromere protein V CENPV +SeqId.8864-59 Q5EE01 CENPW Centromere protein W CENPW +SeqId.6230-56 O95813 CER1 Cerberus CER1 +SeqId.13494-6 Q8N5B7 CERS5 Ceramide synthase 5 CERS5 +SeqId.15487-164 P23141 "carboxylesterase, liver" Liver carboxylesterase 1 CES1 +SeqId.13078-3 P41208 CETN2 Centrin-2 CETN2 +SeqId.17410-5 O15182 CETN3 Centrin-3 CETN3 +SeqId.6553-68 Q9UL16 CCD19 Cilia- and flagella-associated protein 45 CFAP45 +SeqId.4129-72 P00751 Factor B Complement factor B CFB +SeqId.3294-55 P0CG37 CFC1 Cryptic protein CFC1 +SeqId.2946-52 P00746 Factor D Complement factor D CFD +SeqId.4159-130 P08603 Factor H Complement factor H CFH +SeqId.15468-14 Q03591 FHR1 Complement factor H-related protein 1 CFHR1 +SeqId.15584-9 P36980 FHR2 Complement factor H-related protein 2 CFHR2 +SeqId.16836-1 Q02985 FHR3 Complement factor H-related protein 3 CFHR3 +SeqId.6471-53 Q92496 FHR4 Complement factor H-related protein 4 CFHR4 +SeqId.16055-3 Q9BXR6 complement factor H-related 5 Complement factor H-related protein 5 CFHR5 +SeqId.2567-5 P05156 Factor I Complement factor I CFI +SeqId.4203-50 P23528 Cofilin-1 Cofilin-1 CFL1 +SeqId.15339-32 Q9Y281 COF2 Cofilin-2 CFL2 +SeqId.16837-20 O15519 FLIP CASP8 and FADD-like apoptosis regulator CFLAR +SeqId.2960-66 P27918 Properdin Properdin CFP +SeqId.7717-95 P13569 CFTR Cystic fibrosis transmembrane conductance regulator CFTR +SeqId.14056-4 P01215 Glycoprotein hormones a-chain Glycoprotein hormones alpha chain CGA +SeqId.4914-10 "P01215,P01233" HCG Human Chorionic Gonadotropin CGA CGB +SeqId.3032-11 "P01215, P01225" FSH Follicle stimulating hormone CGA FSHB +SeqId.3032-11 "P01215, P01225" FSH Follicle stimulating hormone CGA FSHB +SeqId.2953-31 "P01215, P01229" Luteinizing hormone Luteinizing hormone CGA LHB +SeqId.2953-31 "P01215, P01229" Luteinizing hormone Luteinizing hormone CGA LHB +SeqId.3521-16 P01215 P01222 TSH Thyroid Stimulating Hormone CGA TSHB +SeqId.3521-16 P01215 P01222 TSH Thyroid Stimulating Hormone CGA TSHB +SeqId.6213-10 Q6NT52 CGB2 Choriogonadotropin subunit beta variant 2 CGB2 +SeqId.6257-56 Q99674 CGRE1 Cell growth regulator with EF hand domain protein 1 CGREF1 +SeqId.13460-4 O15335 CHAD Chondroadherin CHAD +SeqId.11270-17 Q8WYQ3 CHC10 "Coiled-coil-helix-coiled-coil-helix domain-containing protein 10, mitochondrial" CHCHD10 +SeqId.14005-2 Q9P2D1 CHD7 Chromodomain-helicase-DNA-binding protein 7 CHD7 +SeqId.2853-68 O14757 CHK1 Serine/threonine-protein kinase Chk1 CHEK1 +SeqId.19328-51 O96017 Chk2 Serine/threonine-protein kinase Chk2 CHEK2 +SeqId.11320-29 Q96EP1 CHFR E3 ubiquitin-protein ligase CHFR CHFR +SeqId.8476-11 P10645 CgA Chromogranin-A CHGA +SeqId.8235-48 P05060 SCG1 Secretogranin-1 CHGB +SeqId.11104-13 P36222 YKL-40 Chitinase-3-like protein 1 CHI3L1 +SeqId.9383-24 Q15782 CH3L2 Chitinase-3-like protein 2 CHI3L2 +SeqId.16591-71 Q9BZP6 CHIA Acidic mammalian chitinase CHIA +SeqId.3600-2 Q13231 Chitotriosidase-1 Chitotriosidase-1 CHIT1 +SeqId.7761-125 Q9Y259 CHKB Choline/ethanolamine kinase CHKB +SeqId.8958-51 O00533 CHL1 Neural cell adhesion molecule L1-like protein CHL1 +SeqId.17728-61 O43633 CHM2A Charged multivesicular body protein 2a CHMP2A +SeqId.17350-13 Q9UQN3 CHM2B Charged multivesicular body protein 2b CHMP2B +SeqId.12458-79 Q99653 CHP1 Calcineurin B homologous protein 1 CHP1 +SeqId.13438-115 Q9H2X0 CHRD Chordin CHRD +SeqId.3362-61 Q9BU40 CRDL1 Chordin-like protein 1 CHRDL1 +SeqId.6086-15 Q6WN34 CRDL2 Chordin-like protein 2 CHRDL2 +SeqId.7803-4 O43916 CHST1 Carbohydrate sulfotransferase 1 CHST1 +SeqId.7779-86 Q9NPF2 CHSTB Carbohydrate sulfotransferase 11 CHST11 +SeqId.6626-81 Q9NRB3 CHSTC Carbohydrate sulfotransferase 12 CHST12 +SeqId.7262-191 Q8NCH0 CHSTE Carbohydrate sulfotransferase 14 CHST14 +SeqId.4469-78 Q7LFX5 ST4S6 Carbohydrate sulfotransferase 15 CHST15 +SeqId.18863-176 Q9Y4C5 CHST2 Carbohydrate sulfotransferase 2 CHST2 +SeqId.7189-55 Q7LGC8 CHST3 Carbohydrate sulfotransferase 3 CHST3 +SeqId.18876-77 Q8NCG5 CHST4 Carbohydrate sulfotransferase 4 CHST4 +SeqId.7020-13 Q9GZS9 CHST5 Carbohydrate sulfotransferase 5 CHST5 +SeqId.4429-51 Q9GZX3 CHST6 Carbohydrate sulfotransferase 6 CHST6 +SeqId.11646-4 Q7L1S5 Carbohydrate sulfotransferase 9 Carbohydrate sulfotransferase 9 CHST9 +SeqId.5717-2 O75339 CILP Cartilage intermediate layer protein 1 CILP +SeqId.8841-65 Q8IUL8 CILP2 Cartilage intermediate layer protein 2 CILP2 +SeqId.19383-131 Q9BW66 CINP Cyclin-dependent kinase 2-interacting protein CINP +SeqId.12724-81 Q14011 CIRBP Cold-inducible RNA-binding protein CIRBP +SeqId.7745-3 Q9NZ45 ZCD1 CDGSH iron-sulfur domain-containing protein 1 CISD1 +SeqId.8094-20 Q8N5K1 CISD2 CDGSH iron-sulfur domain-containing protein 2 CISD2 +SeqId.5345-51 Q8WWK9 CKAP2 Cytoskeleton-associated protein 2 CKAP2 +SeqId.7221-56 Q07065 CKAP4 Cytoskeleton-associated protein 4 CKAP4 +SeqId.3800-71 P12277 CK-BB Creatine kinase B-type CKB +SeqId.3714-49 P12277 P06732 CK-MB Creatine kinase M-type:Creatine kinase B-type heterodimer CKB CKM +SeqId.3714-49 P12277 P06732 CK-MB Creatine kinase M-type:Creatine kinase B-type heterodimer CKB CKM +SeqId.15542-19 P12532 KCRU "Creatine kinase U-type, mitochondrial" CKMT1A +SeqId.18197-97 P17540 KCRS "Creatine kinase S-type, mitochondrial" CKMT2 +SeqId.12530-14 P61024 CKS-1 Cyclin-dependent kinases regulatory subunit 1 CKS1B +SeqId.11094-104 Q05315 LPPL Galectin-10 CLC +SeqId.10496-11 A8K7I4 CaCC Calcium-activated chloride channel regulator 1 CLCA1 +SeqId.8950-4 Q9UQC9 CLCA2 Calcium-activated chloride channel regulator 2 CLCA2 +SeqId.13683-18 P51801 CLCKB Chloride channel protein ClC-Kb CLCNKB +SeqId.10955-4 Q8IUN9 CLC10 C-type lectin domain family 10 member A CLEC10A +SeqId.2966-65 Q9Y240 SCGF-beta Stem cell growth factor-beta CLEC11A +SeqId.4500-50 Q9Y240 SCGF-alpha Stem cell growth factor-alpha CLEC11A +SeqId.11187-11 Q5QGZ9 CL12A C-type lectin domain family 12 member A CLEC12A +SeqId.4332-6 Q9P126 CLC1B C-type lectin domain family 1 member B CLEC1B +SeqId.10953-14 Q6UVW9 CLC2A C-type lectin domain family 2 member A CLEC2A +SeqId.7786-83 Q92478 CLC2B C-type lectin domain family 2 member B CLEC2B +SeqId.7054-87 Q9UHP7 CLC2D C-type lectin domain family 2 member D CLEC2D +SeqId.8242-9 P0C7M8 CLC2L C-type lectin domain family 2 member L CLEC2L +SeqId.5701-81 P05452 Tetranectin Tetranectin CLEC3B +SeqId.8853-2 Q9UMR7 CLC4A C-type lectin domain family 4 member A CLEC4A +SeqId.9094-5 Q8WTT0 CLC4C C-type lectin domain family 4 member C CLEC4C +SeqId.7752-31 Q8WXI8 CLC4D C-type lectin domain family 4 member D CLEC4D +SeqId.10781-19 Q6UXB4 CLC4G C-type lectin domain family 4 member G CLEC4G +SeqId.3030-3 Q9H2X3 DC-SIGNR C-type lectin domain family 4 member M CLEC4M +SeqId.6911-103 Q6EIG7 CLC6A C-type lectin domain family 6 member A CLEC6A +SeqId.3603-60 Q9BXN2 CLC7A C-type lectin domain family 7 member A CLEC7A +SeqId.10600-24 O14967 CLGN Calmegin CLGN +SeqId.5013-2 O00299 NCC27 Chloride intracellular channel protein 1 CLIC1 +SeqId.17837-5 O15247 CLIC2 Chloride intracellular channel protein 2 CLIC2 +SeqId.15314-49 Q9Y696 CLIC4 Chloride intracellular channel protein 4 CLIC4 +SeqId.12475-48 Q9NZA1 CLIC5 Chloride intracellular channel protein 5 CLIC5 +SeqId.11659-31 Q14677 EPN4 Clathrin interactor 1 CLINT1 +SeqId.11327-56 P49760 CLK2 Dual specificity protein kinase CLK2 CLK2 +SeqId.10440-26 Q9H6B4 ACAM CXADR-like membrane protein CLMP +SeqId.9585-80 Q9H6B4 ACAM CXADR-like membrane protein CLMP +SeqId.8874-53 O75503 CLN5 Ceroid-lipofuscinosis neuronal protein 5 CLN5 +SeqId.17196-5 Q16740 ClpP endopeptidase "ATP-dependent Clp protease proteolytic subunit, mitochondrial" CLPP +SeqId.5749-53 P04118 COL Colipase CLPS +SeqId.9526-3 A2RUU4 COLL1 Colipase-like protein 1 CLPSL1 +SeqId.7767-1 Q6UWE3 CF126 Colipase-like protein 2 CLPSL2 +SeqId.15521-4 O94985 Alcadein alpha-1 Calsyntenin-1 CLSTN1 +SeqId.18882-7 Q9H4D0 CSTN2 Calsyntenin-2 CLSTN2 +SeqId.6291-55 Q9BQT9 Alcadein-beta Calsyntenin-3 CLSTN3 +SeqId.19257-11 P09496 CLCA Clathrin light chain A CLTA +SeqId.13711-10 Q00610 CLH1 Clathrin heavy chain 1 CLTC +SeqId.4542-24 P10909 Clusterin Clusterin CLU +SeqId.3423-59 P23946 Chymase Chymase CMA1 +SeqId.19115-13 Q96DG6 CMBL Carboxymethylenebutenolidase homolog CMBL +SeqId.18243-9 P30085 Cytidylate kinase UMP-CMP kinase CMPK1 +SeqId.5456-59 Q96KN2 CNDP1 Beta-Ala-His dipeptidase CNDP1 +SeqId.3192-3 Q96KP4 Glutamate carboxypeptidase Cytosolic non-specific dipeptidase CNDP2 +SeqId.13532-25 Q8N9A8 NEPR1 Nuclear envelope phosphatase-regulatory subunit 1 CNEP1R1 +SeqId.12872-35 Q16280 CNGA2 Cyclic nucleotide-gated olfactory channel CNGA2 +SeqId.15566-10 P51911 Calponin-1 Calponin-1 CNN1 +SeqId.18877-15 Q99439 CNN2 Calponin-2 CNN2 +SeqId.13482-14 A5YKK6 CNOT1 CCR4-NOT transcription complex subunit 1 CNOT1 +SeqId.6609-22 P09543 CN37 "2',3'-cyclic-nucleotide 3'-phosphodiesterase" CNP +SeqId.17327-3 Q9BT09 CNPY3 Protein canopy homolog 3 CNPY3 +SeqId.15465-79 Q8N129 CNPY4 Protein canopy homolog 4 CNPY4 +SeqId.18218-48 Q96F85 CB032 CB1 cannabinoid receptor-interacting protein 1 CNRIP1 +SeqId.3489-9 P26441 CNTF Ciliary neurotrophic factor CNTF +SeqId.14101-2 P26992 CNTFR alpha Ciliary neurotrophic factor receptor subunit alpha CNTFR +SeqId.2974-61 Q12860 contactin-1 Contactin-1 CNTN1 +SeqId.3296-92 Q02246 CNTN2 Contactin-2 CNTN2 +SeqId.3298-52 Q8IWV2 Contactin-4 Contactin-4 CNTN4 +SeqId.3299-29 O94779 Contactin-5 Contactin-5 CNTN5 +SeqId.6965-19 Q9UHC6 CNTP2 Contactin-associated protein-like 2 CNTNAP2 +SeqId.9044-1 Q8WYK1 CNTP5 Contactin-associated protein-like 5 CNTNAP5 +SeqId.7888-58 Q9Y2R0 CCD56 "Cytochrome c oxidase assembly factor 3 homolog, mitochondrial" COA3 +SeqId.7227-75 O43405 COCH Cochlin COCH +SeqId.9543-131 Q96MW5 COG8 Conserved oligomeric Golgi complex subunit 8 COG8 +SeqId.15653-9 Q03692 COAA1 Collagen alpha-1(X) chain COL10A1 +SeqId.11278-4 P13942 COL11A2 Collagen alpha-2(XI) chain COL11A2 +SeqId.6570-1 Q5TAT6 CODA1 Collagen alpha-1(XIII) chain COL13A1 +SeqId.8974-172 P39059 COFA1 Collagen alpha-1(XV) chain COL15A1 +SeqId.2201-17 P39060 Endostatin Endostatin COL18A1 +SeqId.11140-56 P02452 CO1A1 Collagen alpha-1(I) chain COL1A1 +SeqId.13484-69 P02452 CO1A1 Collagen alpha-1(I) chain COL1A1 +SeqId.8804-39 Q9P218 COKA1 Collagen alpha-1(XX) chain COL20A1 +SeqId.4543-65 Q86Y22 CONA1 Collagen alpha-1(XXIII) chain COL23A1 +SeqId.7006-4 Q9BXS0 COPA1 Collagen alpha-1(XXV) chain COL25A1 +SeqId.10702-1 Q2UY09 COSA1 Collagen alpha-1(XXVIII) chain COL28A1 +SeqId.15569-15 P02458 Collagen II Collagen Type II COL2A1 +SeqId.18875-125 P02458 Chondrocalcin Chondrocalcin COL2A1 +SeqId.18880-81 P02461 Collagen Type III Collagen Type III COL3A1 +SeqId.13535-2 Q9Y5P4 C43BP Collagen type IV alpha-3-binding protein COL4A3BP +SeqId.13950-9 Q9Y5P4 C43BP Collagen type IV alpha-3-binding protein COL4A3BP +SeqId.16828-8 P12109 Collagen a1(VI) Collagen alpha-1(VI) chain COL6A1 +SeqId.16753-46 P12110 CO6A2 Collagen alpha-2(VI) chain COL6A2 +SeqId.10511-10 P12111 Collagen alpha-3(VI) Collagen alpha-3(VI) chain COL6A3 +SeqId.11196-31 P12111 Collagen alpha-3(VI) Collagen alpha-3(VI) chain COL6A3 +SeqId.11155-16 A8TX70 CO6A5 Collagen alpha-5(VI) chain COL6A5 +SeqId.4807-13 P27658 CO8A1 Collagen alpha-1(VIII) chain COL8A1 +SeqId.15466-30 P20849 CO9A1 Collagen alpha-1(IX) chain COL9A1 +SeqId.6631-17 P20849 CO9A1 Collagen alpha-1(IX) chain COL9A1 +SeqId.6558-5 Q9Y6Z7 COL10 Collectin-10 COLEC10 +SeqId.4430-44 Q9BWP8 Collectin Kidney 1 Collectin-11 COLEC11 +SeqId.5457-5 Q5KU26 COLEC12 Collectin-12 COLEC12 +SeqId.5638-23 Q8NBJ5 GT251 Procollagen galactosyltransferase 1 COLGALT1 +SeqId.7234-12 Q8IYK4 GT252 Procollagen galactosyltransferase 2 COLGALT2 +SeqId.12509-115 Q8N668 COMD1 COMM domain-containing protein 1 COMMD1 +SeqId.2823-7 Q86VX2 COMMD7 COMM domain-containing protein 7 COMMD7 +SeqId.17683-2 Q9P000 COMD9 COMM domain-containing protein 9 COMMD9 +SeqId.8043-153 P49747 COMP Cartilage oligomeric matrix protein COMP +SeqId.18382-109 P21964 Catechol O-methyltransferase Catechol O-methyltransferase COMT +SeqId.19310-81 O14579 COPE Coatomer subunit epsilon COPE +SeqId.14029-42 P61201 CSN2 COP9 signalosome complex subunit 2 COPS2 +SeqId.12384-92 Q9H9Q2 CSN7B COP9 signalosome complex subunit 7b COPS7B +SeqId.4905-63 Q14019 Coactosin-like protein Coactosin-like protein COTL1 +SeqId.7850-1 Q96KJ9 COX42 "Cytochrome c oxidase subunit 4 isoform 2, mitochondrial" COX4I2 +SeqId.18226-148 P20674 COX5A "Cytochrome c oxidase subunit 5A, mitochondrial" COX5A +SeqId.7887-57 P10606 COX5B "Cytochrome c oxidase subunit 5B, mitochondrial" COX5B +SeqId.10535-25 Q02221 CX6A2 "Cytochrome c oxidase subunit 6A2, mitochondrial" COX6A2 +SeqId.8903-1 P09669 COX6C Cytochrome c oxidase subunit 6C COX6C +SeqId.8390-25 P24310 CX7A1 "Cytochrome c oxidase subunit 7A1, mitochondrial" COX7A1 +SeqId.9590-10 O14548 COX7R "Cytochrome c oxidase subunit 7A-related protein, mitochondrial" COX7A2L +SeqId.17453-34 P00450 Ceruloplasmin Ceruloplasmin CP +SeqId.9276-7 P48052 CBPA2 Carboxypeptidase A2 CPA2 +SeqId.9267-2 Q9UI42 CBPA4 Carboxypeptidase A4 CPA4 +SeqId.15375-49 P15086 Carboxypeptidase B1 Carboxypeptidase B CPB1 +SeqId.3518-54 Q96IY4 TAFI Carboxypeptidase B2 CPB2 +SeqId.7917-17 O75976 CBPD Carboxypeptidase D CPD +SeqId.5343-74 P16870 CBPE Carboxypeptidase E CPE +SeqId.18332-17 O14810 CPLX1 Complexin-1 CPLX1 +SeqId.15321-8 Q6PUV4 CPLX2 Complexin-2 CPLX2 +SeqId.9416-77 P14384 CBPM Carboxypeptidase M CPM +SeqId.7142-5 P15169 CBPN Carboxypeptidase N catalytic chain CPN1 +SeqId.6415-90 P22792 CPN2 Carboxypeptidase N subunit 2 CPN2 +SeqId.5346-24 Q99829 CPNE1 Copine-1 CPNE1 +SeqId.18241-18 P36551 HEM6 "Oxygen-dependent coproporphyrinogen-III oxidase, mitochondrial" CPOX +SeqId.9394-19 Q9Y646 Aminopeptidase Carboxypeptidase Q CPQ +SeqId.11709-29 Q92523 CPT1B "Carnitine O-palmitoyltransferase 1, muscle isoform" CPT1B +SeqId.8891-7 Q9H3G5 CPVL Probable serine carboxypeptidase CPVL CPVL +SeqId.6255-74 Q96SM3 CPXM1 Probable carboxypeptidase X1 CPXM1 +SeqId.6493-9 Q66K79 CBPZ Carboxypeptidase Z CPZ +SeqId.19556-12 P17927 Complement receptor type 1 Complement receptor type 1 CR1 +SeqId.15570-99 P20023 Complement receptor type 2 Complement receptor type 2 CR2 +SeqId.11967-23 P29762 RABP1 Cellular retinoic acid-binding protein 1 CRABP1 +SeqId.11696-7 P29373 RABP2 Cellular retinoic acid-binding protein 2 CRABP2 +SeqId.15322-35 P78560 CRADD Death domain-containing protein CRADD CRADD +SeqId.12637-7 P43155 CACP Carnitine O-acetyltransferase CRAT +SeqId.17771-35 O75575 RPC9 DNA-directed RNA polymerase III subunit RPC9 CRCP +SeqId.11198-37 Q96BA8 CR3L1 Cyclic AMP-responsive element-binding protein 3-like protein 1 CREB3L1 +SeqId.17336-54 Q70SY1 CR3L2 Cyclic AMP-responsive element-binding protein 3-like protein 2 CREB3L2 +SeqId.11308-8 Q8TEY5 CR3L4 Cyclic AMP-responsive element-binding protein 3-like protein 4 CREB3L4 +SeqId.13614-6 Q92793 CREB-binding protein CREB-binding protein CREBBP +SeqId.9357-4 O75629 CREG1 Protein CREG1 CREG1 +SeqId.7628-40 Q96HD1 CREL1 Cysteine-rich with EGF-like domain protein 1 CRELD1 +SeqId.19637-9 P06850 CRH Corticoliberin CRH +SeqId.5614-44 P06850 CRH Corticoliberin CRH +SeqId.6039-24 P24387 CRHBP Corticotropin-releasing factor-binding protein CRHBP +SeqId.15492-1 Q9NZV1 CRIM1 Cysteine-rich motor neuron 1 protein CRIM1 +SeqId.8699-43 Q9NZV1 CRIM1 Cysteine-rich motor neuron 1 protein CRIM1 +SeqId.18275-5 P50238 CRIP1 Cysteine-rich protein 1 CRIP1 +SeqId.9053-16 P52943 CRIP2 Cysteine-rich protein 2 CRIP2 +SeqId.19294-26 Q9P021 CRIPT Cysteine-rich PDZ-binding protein CRIPT +SeqId.9282-12 P16562 CRIS2 Cysteine-rich secretory protein 2 CRISP2 +SeqId.3187-52 P54108 CRIS3 Cysteine-rich secretory protein 3 CRISP3 +SeqId.5691-2 Q9H0B8 CRLD2 Cysteine-rich secretory protein LCCL domain-containing 2 CRISPLD2 +SeqId.4976-57 P46108 CRK Adapter molecule crk CRK +SeqId.9877-28 P46109 CRKL Crk-like protein CRKL +SeqId.14747-9 O75462 CRLF1 Cytokine receptor-like factor 1 CRLF1 +SeqId.2607-54 O75462 Q9UBD9 CLF-1/CLC Complex Cytokine receptor-like factor 1:Cardiotrophin-like cytokine factor 1 Complex CRLF1 CLCF1 +SeqId.2607-54 O75462 Q9UBD9 CLF-1/CLC Complex Cytokine receptor-like factor 1:Cardiotrophin-like cytokine factor 1 Complex CRLF1 CLCF1 +SeqId.13694-24 Q9HC73 TSLP R Cytokine receptor-like factor 2 CRLF2 +SeqId.18323-39 Q14194 DRP-1 Dihydropyrimidinase-related protein 1 CRMP1 +SeqId.17738-7 Q9UBG3 CRNN Cornulin CRNN +SeqId.13929-27 Q9UKG9 OCTC Peroxisomal carnitine O-octanoyltransferase CROT +SeqId.4337-49 P02741 CRP C-reactive protein CRP +SeqId.5632-6 Q9NQ79 CRAC1 Cartilage acidic protein 1 CRTAC1 +SeqId.7968-15 O95727 CRTAM Cytotoxic and regulatory T-cell molecule CRTAM +SeqId.10087-10 P02489 Alpha crystallin A chain Alpha-crystallin A chain CRYAA +SeqId.17751-68 P53674 CRBB1 Beta-crystallin B1 CRYBB1 +SeqId.10000-28 P43320 CRBB2 Beta-crystallin B2 CRYBB2 +SeqId.12366-16 P07320 CRGD Gamma-crystallin D CRYGD +SeqId.19311-15 P22914 CRBS Beta-crystallin S CRYGS +SeqId.13983-27 Q08257 QOR Quinone oxidoreductase CRYZ +SeqId.9207-60 O95825 QORL1 Quinone oxidoreductase-like protein 1 CRYZL1 +SeqId.18309-18 O75390 CISY "Citrate synthase, mitochondrial" CS +SeqId.5716-49 Q6PB30 CSAG1 Putative chondrosarcoma-associated gene 1 protein CSAG1 +SeqId.12754-14 Q9Y534 CSDC2 Cold shock domain-containing protein C2 CSDC2 +SeqId.12735-39 O75534 CSDE1 Cold shock domain-containing protein E1 CSDE1 +SeqId.3738-54 P09603 CSF-1 Macrophage colony-stimulating factor 1 CSF1 +SeqId.13682-47 P07333 M-CSF R Macrophage colony-stimulating factor 1 receptor CSF1R +SeqId.4697-59 P04141 GM-CSF Granulocyte-macrophage colony-stimulating factor CSF2 +SeqId.10438-19 P15509 CSF2R Granulocyte-macrophage colony-stimulating factor receptor subunit alpha CSF2RA +SeqId.10512-13 P32927 IL3RB Cytokine receptor common subunit beta CSF2RB +SeqId.11137-43 P32927 IL3RB Cytokine receptor common subunit beta CSF2RB +SeqId.4840-73 P09919 G-CSF Granulocyte colony-stimulating factor CSF3 +SeqId.2719-3 Q99062 G-CSF-R Granulocyte colony-stimulating factor receptor CSF3R +SeqId.10772-21 Q8N6G5 CGAT2 Chondroitin sulfate N-acetylgalactosaminyltransferase 2 CSGALNACT2 +SeqId.13103-125 P0DML2 P0DML3 CSH Chorionic somatomammotropin hormone CSH1 CSH2 +SeqId.13103-125 P0DML2 P0DML3 CSH Chorionic somatomammotropin hormone CSH1 CSH2 +SeqId.3363-31 P41240 CSK Tyrosine-protein kinase CSK CSK +SeqId.9598-23 Q96PZ7 CSMD1 CUB and sushi domain-containing protein 1 CSMD1 +SeqId.9971-5 Q7Z408 CSMD2 CUB and sushi domain-containing protein 2 CSMD2 +SeqId.16587-1 P05814 Beta-casein Beta-casein CSN2 +SeqId.11289-31 P48730 KC1D Casein kinase I isoform delta CSNK1D +SeqId.12653-13 P78368 CSNK1G2 Casein kinase I isoform gamma-2 CSNK1G2 +SeqId.17436-193 P78368 CSNK1G2 Casein kinase I isoform gamma-2 CSNK1G2 +SeqId.5224-20 P68400 CSK21 Casein kinase II subunit alpha CSNK2A1 +SeqId.3427-63 P68400 CSK21 Casein kinase II subunit alpha CSNK2A1 +SeqId.5225-50 P68400 P67870 CK2-A1:B Casein kinase II 2-alpha:2-beta heterotetramer CSNK2A1 CSNK2B +SeqId.5225-50 P68400 P67870 CK2-A1:B Casein kinase II 2-alpha:2-beta heterotetramer CSNK2A1 CSNK2B +SeqId.13681-173 P19784 CSK22 Casein kinase II subunit alpha' CSNK2A2 +SeqId.5226-36 P19784 P67870 CK2-A2:B Casein kinase II 2-alpha':2-beta heterotetramer CSNK2A2 CSNK2B +SeqId.5226-36 P19784 P67870 CK2-A2:B Casein kinase II 2-alpha':2-beta heterotetramer CSNK2A2 CSNK2B +SeqId.11330-15 P67870 CSK2B Casein kinase II subunit beta CSNK2B +SeqId.8951-162 Q6UVK1 CSPG4 Chondroitin sulfate proteoglycan 4 CSPG4 +SeqId.15529-33 P21291 Cysteine-rich protein 1 Cysteine and glycine-rich protein 1 CSRP1 +SeqId.12968-2 Q16527 CSRP2 Cysteine and glycine-rich protein 2 CSRP2 +SeqId.9171-11 P50461 CSRP3 Cysteine and glycine-rich protein 3 CSRP3 +SeqId.5459-33 P01037 CYTN Cystatin-SN CST1 +SeqId.4324-33 P09228 CYTT Cystatin-SA CST2 +SeqId.2609-59 P01034 Cystatin C Cystatin-C CST3 +SeqId.14076-74 P01036 Cystatin-S Cystatin-S CST4 +SeqId.3803-10 P28325 CYTD Cystatin-D CST5 +SeqId.14711-27 Q15828 Cystatin M Cystatin-M CST6 +SeqId.3302-58 O76096 CYTF Cystatin-F CST7 +SeqId.10572-65 O60676 CST8 Cystatin-8 CST8 +SeqId.6368-9 Q9H114 CST1L Cystatin-like 1 CSTL1 +SeqId.9363-11 Q8WUE5 CX048 Cancer/testis antigen 55 CT55 +SeqId.11217-16 Q13363 CTBP1 C-terminal-binding protein 1 CTBP1 +SeqId.14624-51 P49711 CTCF Transcriptional repressor CTCF CTCF +SeqId.2889-37 Q16619 Cardiotrophin-1 Cardiotrophin-1 CTF1 +SeqId.2975-19 P29279 CTGF Connective tissue growth factor CTGF +SeqId.15467-10 Q96CG8 CTHR1 Collagen triple helix repeat-containing protein 1 CTHRC1 +SeqId.3022-4 P16410 CTLA-4 Cytotoxic T-lymphocyte protein 4 CTLA4 +SeqId.9872-23 P26232 CTNA2 Catenin alpha-2 CTNNA2 +SeqId.8424-269 P35222 b-Catenin Catenin beta-1 CTNNB1 +SeqId.9842-2 P35222 b-Catenin Catenin beta-1 CTNNB1 +SeqId.5671-1 P17538 Chymotrypsin Chymotrypsinogen B CTRB1 +SeqId.5648-28 Q6GPI1 CTRB2 Chymotrypsinogen B2 CTRB2 +SeqId.5626-20 Q99895 CTRC Chymotrypsin-C CTRC +SeqId.9229-9 P40313 CTRL Chymotrypsin-like protease CTRL-1 CTRL +SeqId.3179-51 P10619 Cathepsin A Lysosomal protective protein CTSA +SeqId.8007-19 P07858 Cathepsin B Cathepsin B CTSB +SeqId.3178-5 P53634 CATC Dipeptidyl peptidase 1 CTSC +SeqId.5508-62 P07339 Cathepsin D Cathepsin D CTSD +SeqId.15376-134 P14091 CATE Cathepsin E CTSE +SeqId.9212-22 Q9UBX1 CATF Cathepsin F CTSF +SeqId.2431-17 P08311 Cathepsin G Cathepsin G CTSG +SeqId.8465-52 P09668 Cathepsin H Cathepsin H CTSH +SeqId.9443-137 P43235 cathepsin K Cathepsin K CTSK +SeqId.9264-11 P43234 CATO Cathepsin O CTSO +SeqId.3181-50 P25774 Cathepsin S Cathepsin S CTSS +SeqId.3364-76 O60911 Cathepsin V Cathepsin L2 CTSV +SeqId.4971-1 Q9UBR2 CATZ Cathepsin Z CTSZ +SeqId.12904-180 O60494 cubilin cubilin CUBN +SeqId.17797-1 Q13616 CUL1 Cullin-1 CUL1 +SeqId.10045-47 Q13618 CUL3 Cullin-3 CUL3 +SeqId.13743-56 Q13620 CUL4B Cullin-4B CUL4B +SeqId.12991-49 Q8IWT3 CUL9 Cullin-9 CUL9 +SeqId.15315-64 Q9NTM9 CUTC Copper homeostasis protein cutC homolog CUTC +SeqId.7943-16 Q86UP6 CUZD1 CUB and zona pellucida-like domain-containing protein 1 CUZD1 +SeqId.2827-23 P78423 Fractalkine/CX3CL-1 Fractalkine CX3CL1 +SeqId.11204-80 P78310 CXAR Coxsackievirus and adenovirus receptor CXADR +SeqId.2985-35 P09341 Gro-a Growth-regulated alpha protein CXCL1 +SeqId.4141-79 P02778 IP-10 C-X-C motif chemokine 10 CXCL10 +SeqId.3038-9 O14625 I-TAC C-X-C motif chemokine 11 CXCL11 +SeqId.3516-60 P48061 SDF-1 Stromal cell-derived factor 1 CXCL12 +SeqId.9278-9 P48061 SDF-1 Stromal cell-derived factor 1 CXCL12 +SeqId.3487-32 O43927 BLC C-X-C motif chemokine 13 CXCL13 +SeqId.5730-60 O95715 BRAK C-X-C motif chemokine 14 CXCL14 +SeqId.2436-49 Q9H2A7 "CXCL16, soluble" C-X-C motif chemokine 16 CXCL16 +SeqId.9495-10 Q6UXB2 VCC1 C-X-C motif chemokine 17 CXCL17 +SeqId.3148-49 P19875 Gro-b Gro-beta CXCL2 +SeqId.3148-49 P19875 Gro-b Gro-beta CXCL2 +SeqId.2979-8 P42830 ENA-78 C-X-C motif chemokine 5 CXCL5 +SeqId.3495-15 P80162 GCP-2 C-X-C motif chemokine 6 CXCL6 +SeqId.3447-64 P10145 IL-8 Interleukin-8 CXCL8 +SeqId.11593-21 Q07325 MIG C-X-C motif chemokine 9 CXCL9 +SeqId.9188-119 Q07325 MIG C-X-C motif chemokine 9 CXCL9 +SeqId.13377-3 Q8N8Q1 C56D1 Cytochrome b561 domain-containing protein 1 CYB561D1 +SeqId.11287-14 P00167 Cytochrome b5 Cytochrome b5 CYB5A +SeqId.10924-258 Q8WUJ1 NEUFC Neuferricin CYB5D2 +SeqId.18255-6 Q9UHQ9 NB5R1 NADH-cytochrome b5 reductase 1 CYB5R1 +SeqId.19143-38 Q6BCY4 NB5R2 NADH-cytochrome b5 reductase 2 CYB5R2 +SeqId.7215-18 P00387 NADH-cytochrome b5 reductase NADH-cytochrome b5 reductase 3 CYB5R3 +SeqId.2942-50 P99999 Cytochrome c Cytochrome c CYCS +SeqId.11546-7 Q8WWM9 CYGB Cytoglobin CYGB +SeqId.2943-5 P08684 Cytochrome P450 3A4 Cytochrome P450 3A4 CYP3A4 +SeqId.7879-12 P08684 Cytochrome P450 3A4 Cytochrome P450 3A4 CYP3A4 +SeqId.6264-9 O00622 CYR61 Protein CYR61 CYR61 +SeqId.12533-135 Q99418 CYH2 Cytohesin-2 CYTH2 +SeqId.12746-4 Q9UIA0 CYH4 Cytohesin-4 CYTH4 +SeqId.13612-7 O60759 CYTIP Cytohesin-interacting protein CYTIP +SeqId.8402-22 Q9NRR1 CYTL1 Cytokine-like protein 1 CYTL1 +SeqId.8369-102 Q14118 DAG1 Dystroglycan DAG1 +SeqId.19120-33 P14920 OXDA D-amino-acid oxidase DAO +SeqId.19141-22 P51397 DAP1 Death-associated protein 1 DAP +SeqId.13955-33 P53355 DAPK1 Death-associated protein kinase 1 DAPK1 +SeqId.4355-13 Q9UIK4 DAPK2 Death-associated protein kinase 2 DAPK2 +SeqId.11615-16 Q9UN19 DAPP1 Dual adapter for phosphotyrosine and 3-phosphotyrosine and 3-phosphoinositide DAPP1 +SeqId.12675-14 P14868 SYDC "Aspartate--tRNA ligase, cytoplasmic" DARS +SeqId.12395-86 Q6PI48 SYDM "Aspartate--tRNA ligase, mitochondrial" DARS2 +SeqId.16919-1 P07108 ACBP Acyl-CoA-binding protein DBI +SeqId.4978-54 Q9UJU6 DBNL Drebrin-like protein DBNL +SeqId.11283-13 Q96JK2 DCAF5 DDB1- and CUL4-associated factor 5 DCAF5 +SeqId.9402-18 Q8N8Z6 DCBD1 "Discoidin, CUB and LCCL domain-containing protein 1" DCBLD1 +SeqId.19367-34 P42126 D3D2 "Enoyl-CoA delta isomerase 1, mitochondrial" DCI +SeqId.9836-20 P27707 DCK Deoxycytidine kinase DCK +SeqId.17156-72 O15075 DCAK1 Serine/threonine-protein kinase DCLK1 DCLK1 +SeqId.7826-1 Q9C098 DCLK3 Serine/threonine-protein kinase DCLK3 DCLK3 +SeqId.2666-53 P07585 Bone proteoglycan II Decorin DCN +SeqId.14008-22 Q9NPI6 DCP1A mRNA-decapping enzyme 1A DCP1A +SeqId.12715-30 Q8IZD4 DCP1B mRNA-decapping enzyme 1B DCP1B +SeqId.17756-69 P32321 DCTD Deoxycytidylate deaminase DCTD +SeqId.5879-51 Q13561 Dynactin subunit 2 Dynactin subunit 2 DCTN2 +SeqId.18311-44 O00399 DCTN6 Dynactin subunit 6 DCTN6 +SeqId.4314-12 Q9H773 XTP3A dCTP pyrophosphatase 1 DCTPP1 +SeqId.17366-6 Q96GG9 DCNL1 DCN1-like protein 1 DCUN1D1 +SeqId.19511-8 Q6PH85 DCNL2 DCN1-like protein 2 DCUN1D2 +SeqId.13553-4 Q8IWE4 DCNL3 DCN1-like protein 3 DCUN1D3 +SeqId.8760-10 Q9BTE7 DCNL5 DCN1-like protein 5 DCUN1D5 +SeqId.17758-79 Q7Z4W1 DCXR L-xylulose reductase DCXR +SeqId.19392-6 O94760 DDAH1 "N(G),N(G)-dimethylarginine dimethylaminohydrolase 1" DDAH1 +SeqId.3538-26 P20711 dopa decarboxylase Aromatic-L-amino-acid decarboxylase DDC +SeqId.19119-10 P35638 DDIT3 DNA damage-inducible transcript 3 protein DDIT3 +SeqId.17817-22 Q9NX09 DDIT4 DNA damage-inducible transcript 4 protein DDIT4 +SeqId.17161-1 P39656 OST48 Dolichyl-diphosphooligosaccharide--protein glycosyltransferase 48 kDa subunit DDOST +SeqId.4122-12 Q08345 discoidin domain receptor 1 Epithelial discoidin domain-containing receptor 1 DDR1 +SeqId.15381-45 Q16832 Discoidin domain receptor 2 Discoidin domain-containing receptor 2 DDR2 +SeqId.19237-17 P30046 D-dopachrome decarboxylase D-dopachrome decarboxylase DDT +SeqId.18813-15 Q9NUU7 DD19A ATP-dependent RNA helicase DDX19A DDX19A +SeqId.5460-60 Q9UMR2 DEAD-box protein 19B ATP-dependent RNA helicase DDX19B DDX19B +SeqId.13946-8 Q9BUQ8 DDX23 Probable ATP-dependent RNA helicase DDX23 DDX23 +SeqId.13984-23 Q9UHL0 DDX25 ATP-dependent RNA helicase DDX25 DDX25 +SeqId.9742-59 Q13838 BAT1 Spliceosome RNA helicase DDX39B DDX39B +SeqId.14216-35 Q7L014 DDX46 Probable ATP-dependent RNA helicase DDX46 DDX46 +SeqId.12382-2 O95786 DDX58 Probable ATP-dependent RNA helicase DDX58 DDX58 +SeqId.12869-68 P26196 DDX6 Probable ATP-dependent RNA helicase DDX6 DDX6 +SeqId.6369-82 O75398 DEAF1 Deformed epidermal autoregulatory factor 1 homolog DEAF1 +SeqId.12687-2 Q16698 DECR "2,4-dienoyl-CoA reductase, mitochondrial" DECR1 +SeqId.18343-10 Q9NUI1 DECR2 "Peroxisomal 2,4-dienoyl-CoA reductase" DECR2 +SeqId.14090-23 Q9H4E7 DEFI6 Differentially expressed in FDCP 6 homolog DEF6 +SeqId.19579-5 P59665 HNP-1 Neutrophil defensin 1 DEFA1 +SeqId.16785-45 Q01523 HD-5 Defensin-5 DEFA5 +SeqId.6629-3 P60022 HBD-1 Beta-defensin 1 DEFB1 +SeqId.5679-16 P81534 HBD-3 Beta-defensin 103 DEFB103A +SeqId.5763-67 Q8WTQ1 HBD-4 Beta-defensin 104 DEFB104A +SeqId.5664-57 Q8N104 D106A Beta-defensin 106 DEFB106A +SeqId.6399-52 Q8IZN7 D107A Beta-defensin 107 DEFB107A +SeqId.5611-56 Q8NET1 D108B Beta-defensin 108B DEFB108B +SeqId.8340-9 Q30KQ9 DB110 Beta-defensin 110 DEFB110 +SeqId.5689-1 Q30KQ8 DB112 Beta-defensin 112 DEFB112 +SeqId.13374-4 Q30KQ7 DB113 Beta-defensin 113 DEFB113 +SeqId.8391-12 Q30KQ5 DB115 Beta-defensin 115 DEFB115 +SeqId.11144-10 Q30KQ4 DB116 Beta-defensin 116 DEFB116 +SeqId.9306-7 Q96PH6 DB118 Beta-defensin 118 DEFB118 +SeqId.8315-5 Q8N690 DB119 Beta-defensin 119 DEFB119 +SeqId.5765-53 Q5J5C9 DB121 Beta-defensin 121 DEFB121 +SeqId.9486-13 Q8N687 DB125 Beta-defensin 125 DEFB125 +SeqId.6360-7 Q7Z7B8 DB128 Beta-defensin 128 DEFB128 +SeqId.8347-222 Q9H1M3 DB129 Beta-defensin 129 DEFB129 +SeqId.9022-49 Q7Z7B7 DB132 Beta-defensin 132 DEFB132 +SeqId.6411-58 Q30KP9 DB135 Beta-defensin 135 DEFB135 +SeqId.9332-6 Q30KP8 DB136 Beta-defensin 136 DEFB136 +SeqId.13397-88 O15263 HBD-2 Beta-defensin 4A DEFB4A +SeqId.19287-59 O43583 DENR Density-regulated protein DENR +SeqId.7178-59 Q9NTK1 DEPP Protein DEPP DEPP +SeqId.13393-46 Q9BUN8 DERL1 Derlin-1 DERL1 +SeqId.12030-82 P17661 Desmin Desmin DES +SeqId.11356-19 Q96DF8 DGC14 Protein DGCR14 DGCR14 +SeqId.8055-33 P98153 IDD Integral membrane protein DGCR2/IDD DGCR2 +SeqId.9444-70 Q14129 DGCR6 Protein DGCR6 DGCR6 +SeqId.12895-28 Q9Y6T7 DGKB Diacylglycerol kinase beta DGKB +SeqId.9823-2 P00374 DYR Dihydrofolate reductase DHFR +SeqId.4389-2 O43323 DHH Desert hedgehog protein N-product DHH +SeqId.9856-22 P49366 DHYS Deoxyhypusine synthase DHPS +SeqId.17467-1 Q9BPW9 DHRS9 Dehydrogenase/reductase SDR family member 9 DHRS9 +SeqId.13645-14 Q92620 PRP16 Pre-mRNA-splicing factor ATP-dependent RNA helicase PRP16 DHX38 +SeqId.14012-17 Q96C10 LGP2 Probable ATP-dependent RNA helicase DHX58 DHX58 +SeqId.11601-26 Q14562 DHX8 ATP-dependent RNA helicase DHX8 DHX8 +SeqId.10527-22 Q08211 DHX9 ATP-dependent RNA helicase A DHX9 +SeqId.3122-6 Q9NR28 SMAC "Diablo homolog, mitochondrial" DIABLO +SeqId.14329-4 Q9BTC0 DIDO1 Death-inducer obliterator 1 DIDO1 +SeqId.12694-28 Q9UNQ2 DIM1 Probable dimethyladenosine transferase DIMT1 +SeqId.17793-4 O95057 DIRA1 GTP-binding protein Di-Ras1 DIRAS1 +SeqId.12406-119 O95661 ARHI GTP-binding protein Di-Ras3 DIRAS3 +SeqId.13441-30 Q155Q3 DIXC1 Dixin DIXDC1 +SeqId.3535-84 O94907 DKK1 Dickkopf-related protein 1 DKK1 +SeqId.15678-71 Q9UBU2 DKK2 Dickkopf-related protein 2 DKK2 +SeqId.3607-71 Q9UBP4 DKK3 Dickkopf-related protein 3 DKK3 +SeqId.3365-7 Q9UBT3 Dkk-4 Dickkopf-related protein 4 DKK4 +SeqId.16309-30 Q9UK85 Soggy-1 Dickkopf-like protein 1 DKKL1 +SeqId.15527-90 P09622 DLDH "Dihydrolipoyl dehydrogenase, mitochondrial" DLD +SeqId.19620-16 Q15700 DLG2 Disks large homolog 2 DLG2 +SeqId.7897-75 Q92796 DLG3 Disks large homolog 3 DLG3 +SeqId.8070-88 P78352 DLG4 Disks large homolog 4 DLG4 +SeqId.6496-60 P80370 DLK1 Protein delta homolog 1 DLK1 +SeqId.8380-244 P80370 DLK1 Protein delta homolog 1 DLK1 +SeqId.6373-54 P80370 DLK1 Protein delta homolog 1 DLK1 +SeqId.9359-9 Q6UY11 EGFL9 Protein delta homolog 2 DLK2 +SeqId.5349-69 O00548 DLL1 Delta-like protein 1 DLL1 +SeqId.9974-8 Q9NYJ7 DLL3 Delta-like protein 3 DLL3 +SeqId.3305-6 Q9NR61 DLL4 Delta-like protein 4 DLL4 +SeqId.11422-2 O60479 DLX3 Homeobox protein DLX-3 DLX3 +SeqId.11910-27 Q92988 DLX4 Homeobox protein DLX-4 DLX4 +SeqId.19212-4 Q9UGM3 DMBT1 Deleted in malignant brain tumors 1 protein DMBT1 +SeqId.5963-9 Q6E0U4 Dermokine Dermokine DMKN +SeqId.8535-102 Q6E0U4 Dermokine Dermokine DMKN +SeqId.11396-39 Q9UI46 DNAI1 "Dynein intermediate chain 1, axonemal" DNAI1 +SeqId.11582-63 O60884 DNJA2 DnaJ homolog subfamily A member 2 DNAJA2 +SeqId.9744-139 Q8WW22 DNJA4 DnaJ homolog subfamily A member 4 DNAJA4 +SeqId.3852-19 P25685 HSP 40 DnaJ homolog subfamily B member 1 DNAJB1 +SeqId.7110-2 Q9UBS4 DJB11 DnaJ homolog subfamily B member 11 DNAJB11 +SeqId.8006-12 Q9NXW2 DJB12 DnaJ homolog subfamily B member 12 DNAJB12 +SeqId.8053-16 Q8TBM8 DJB14 DnaJ homolog subfamily B member 14 DNAJB14 +SeqId.11438-6 P25686 DNJB2 DnaJ homolog subfamily B member 2 DNAJB2 +SeqId.18884-22 Q9UDY4 DNJB4 DnaJ homolog subfamily B member 4 DNAJB4 +SeqId.11606-22 O75190 DNJB6 DnaJ homolog subfamily B member 6 DNAJB6 +SeqId.11214-40 Q9UBS3 DNJB9 DnaJ homolog subfamily B member 9 DNAJB9 +SeqId.8297-8 Q8IXB1 DJC10 DnaJ homolog subfamily C member 10 DNAJC10 +SeqId.9783-75 Q9NVH1 DJC11 DnaJ homolog subfamily C member 11 DNAJC11 +SeqId.7197-2 Q9Y5T4 DJC15 DnaJ homolog subfamily C member 15 DNAJC15 +SeqId.10454-99 Q9Y2G8 DJC16 DnaJ homolog subfamily C member 16 DNAJC16 +SeqId.14655-1 Q9NVM6 DJC17 DnaJ homolog subfamily C member 17 DNAJC17 +SeqId.8033-1 Q9H819 DJC18 DnaJ homolog subfamily C member 18 DNAJC18 +SeqId.4545-53 Q96DA6 DnaJ homolog Mitochondrial import inner membrane translocase subunit TIM14 DNAJC19 +SeqId.12799-65 Q9NZQ0 DJC27 DnaJ homolog subfamily C member 27 DNAJC27 +SeqId.7866-11 Q96LL9 DJC30 DnaJ homolog subfamily C member 30 DNAJC30 +SeqId.8016-19 Q9NNZ3 DNJC4 DnaJ homolog subfamily C member 4 DNAJC4 +SeqId.8653-132 Q9NNZ3 DNJC4 DnaJ homolog subfamily C member 4 DNAJC4 +SeqId.6324-11 Q92874 DNSL2 Deoxyribonuclease-1-like 2 DNASE1L2 +SeqId.6533-20 Q8WZ79 DNS2B Deoxyribonuclease-2-beta DNASE2B +SeqId.11442-1 Q8NFT8 DNER Delta and Notch-like epidermal growth factor-related receptor DNER +SeqId.9769-48 Q8NFT8 DNER Delta and Notch-like epidermal growth factor-related receptor DNER +SeqId.11572-4 P50570 DYN2 Dynamin-2 DNM2 +SeqId.19142-39 Q9UJW3 DNM3L DNA (cytosine-5)-methyltransferase 3-like DNMT3L +SeqId.7997-118 Q14184 DOC2B Double C2-like domain-containing protein beta DOC2B +SeqId.14002-18 Q9BZ29 DOCK9 Dedicator of cytokinesis protein 9 DOCK9 +SeqId.16831-7 Q99704 DOK1 Docking protein 1 DOK1 +SeqId.14246-50 O60496 DOK2 Docking protein 2 DOK2 +SeqId.19578-19 O60496 DOK2 Docking protein 2 DOK2 +SeqId.9123-18 Q8N350 DOS Protein Dos DOS +SeqId.12692-56 Q8TEK3 DOT1L "Histone-lysine N-methyltransferase, H3 lysine-79 specific" DOT1L +SeqId.8794-13 P16444 DPEP1 Dipeptidase 1 DPEP1 +SeqId.8327-26 Q9H4A9 DPEP2 Dipeptidase 2 DPEP2 +SeqId.7890-68 Q8N608 DPP10 Inactive dipeptidyl peptidase 10 DPP10 +SeqId.15460-9 P27487 CD26 Dipeptidyl peptidase 4 DPP4 +SeqId.8346-9 Q9UHL4 DPP2 Dipeptidyl peptidase 2 DPP7 +SeqId.4979-34 Q07507 DERM Dermatopontin DPT +SeqId.13943-38 Q9C005 DPY30 Protein dpy-30 homolog DPY30 +SeqId.13567-1 Q16555 DPYL2 Dihydropyrimidinase-related protein 2 DPYSL2 +SeqId.12707-26 Q14195 DPYL3 Dihydropyrimidinase-related protein 3 DPYSL3 +SeqId.12683-156 Q9BPU6 DPYL5 Dihydropyrimidinase-related protein 5 DPYSL5 +SeqId.7084-1 Q8NBI3 DRAXI Draxin DRAXIN +SeqId.17849-6 Q9Y295 DRG1 Developmentally-regulated GTP-binding protein 1 DRG1 +SeqId.8034-6 A6NNA5 DRGX Dorsal root ganglia homeobox protein DRGX +SeqId.10882-12 Q08554 Desmocollin-1 Desmocollin-1 DSC1 +SeqId.13126-52 Q02487 DSC2 Desmocollin-2 DSC2 +SeqId.4981-6 Q14574 DSC3 Desmocollin-3 DSC3 +SeqId.9175-48 O60469 DSCAM Down syndrome cell adhesion molecule DSCAM +SeqId.18886-28 Q8TD84 DSCL1 Down syndrome cell adhesion molecule-like protein 1 DSCAML1 +SeqId.2976-58 Q02413 Desmoglein-1 Desmoglein-1 DSG1 +SeqId.9484-75 Q14126 Desmoglein-2 Desmoglein-2 DSG2 +SeqId.16317-20 P32926 Desmoglein-3 Desmoglein-3 DSG3 +SeqId.18883-4 P60981 DEST Destrin DSTN +SeqId.19194-9 Q8TEA8 Histidyl-tRNA synthetase-related D-tyrosyl-tRNA(Tyr) deacylase 1 DTD1 +SeqId.18280-29 Q96FN9 DTD2 Putative D-tyrosyl-tRNA(Tyr) deacylase 2 DTD2 +SeqId.11430-49 Q86Y01 DTX1 E3 ubiquitin-protein ligase DTX1 DTX1 +SeqId.11643-73 Q8TDB6 DTX3L E3 ubiquitin-protein ligase DTX3L DTX3L +SeqId.19504-22 P23919 KTHY Thymidylate kinase DTYMK +SeqId.13506-10 Q9NX74 DUS2L tRNA-dihydrouridine(20) synthase [NAD(P)+]-like DUS2 +SeqId.6525-17 Q6B8I1 DUSP13 Dual specificity protein phosphatase 13 isoform A DUSP13 +SeqId.12838-28 Q9H1R2 DUS15 Dual specificity protein phosphatase 15 DUSP15 +SeqId.14631-22 Q9BY84 DUS16 Dual specificity protein phosphatase 16 DUSP16 +SeqId.17326-44 Q9BVJ7 DUS23 Dual specificity protein phosphatase 23 DUSP23 +SeqId.8967-6 Q9BV47 DUS26 Dual specificity protein phosphatase 26 DUSP26 +SeqId.9940-35 Q4G0W2 DUS28 Dual specificity phosphatase 28 DUSP28 +SeqId.3480-7 P51452 DUS3 Dual specificity protein phosphatase 3 DUSP3 +SeqId.10035-6 Q13115 DUS4 Dual specificity protein phosphatase 4 DUSP4 +SeqId.12341-8 Q16828 DUS6 Dual specificity protein phosphatase 6 DUSP6 +SeqId.9995-6 P33316 DUT "Deoxyuridine 5'-triphosphate nucleotidohydrolase, mitochondrial" DUT +SeqId.13575-40 O14641 DVL2 Segment polarity protein dishevelled homolog DVL-2 DVL2 +SeqId.3881-49 P63167 DLC8 "Dynein light chain 1, cytoplasmic" DYNLL1 +SeqId.11493-169 Q96FJ2 DYL2 "Dynein light chain 2, cytoplasmic" DYNLL2 +SeqId.3845-51 Q9NP97 DLRB1 Dynein light chain roadblock-type 1 DYNLRB1 +SeqId.17827-53 Q8TF09 DLRB2 Dynein light chain roadblock-type 2 DYNLRB2 +SeqId.14331-262 P63172 DYLT1 Dynein light chain Tctex-type 1 DYNLT1 +SeqId.12867-40 P51808 DYLT3 Dynein light chain Tctex-type 3 DYNLT3 +SeqId.4359-87 O43781 DYRK3 Dual specificity tyrosine-phosphorylation-regulated kinase 3 DYRK3 +SeqId.19323-1 O00559 RCAS1 Receptor-binding cancer antigen expressed on SiSo cells EBAG9 +SeqId.10851-77 Q14213 IL27B Interleukin-27 subunit beta EBI3 +SeqId.8767-44 P42892 Endothelin-converting enzyme 1 Endothelin-converting enzyme 1 ECE1 +SeqId.7076-17 O95672 ECEL1 Endothelin-converting enzyme-like 1 ECEL1 +SeqId.12662-82 Q13011 ECH1 "Delta(3,5)-Delta(2,4)-dienoyl-CoA isomerase, mitochondrial" ECH1 +SeqId.17787-1 P30084 Enoyl-CoA hydratase "Enoyl-CoA hydratase, mitochondrial" ECHS1 +SeqId.12859-33 O75521 PECI "Enoyl-CoA delta isomerase 2, mitochondrial" ECI2 +SeqId.3366-51 Q16610 ECM1 Extracellular matrix protein 1 ECM1 +SeqId.14024-196 Q92838 EDA "Ectodysplasin-A, secreted form" EDA +SeqId.2826-53 Q92838 EDA "Ectodysplasin-A, secreted form" EDA +SeqId.3083-71 Q9HAV5 XEDAR Tumor necrosis factor receptor superfamily member 27 EDA2R +SeqId.2977-7 Q9UNE0 EDAR Tumor necrosis factor receptor superfamily member EDAR EDAR +SeqId.13066-42 Q6P2E9 EDC4 Enhancer of mRNA-decapping protein 4 EDC4 +SeqId.9536-16 Q14507 EP3A Epididymal secretory protein E3-alpha EDDM3A +SeqId.7782-34 P56851 EP3B Epididymal secretory protein E3-beta EDDM3B +SeqId.12415-122 O60869 EDF1 Endothelial differentiation-related factor 1 EDF1 +SeqId.9360-33 O43854 EDIL3 EGF-like repeat and discoidin I-like domain-containing protein 3 EDIL3 +SeqId.6495-14 P05305 Endothelin 1 Endothelin-1 EDN1 +SeqId.12574-36 P20800 Endothelin 2 Endothelin-2 EDN2 +SeqId.15383-200 P14138 Endothelin 3 Endothelin-3 EDN3 +SeqId.14043-12 Q15075 EEA1 Early endosome antigen 1 EEA1 +SeqId.5882-34 P24534 EF-1-beta Elongation factor 1-beta EEF1B2 +SeqId.17826-341 P29692 EF1D Elongation factor 1-delta EEF1D +SeqId.12332-7 O00418 EF2K Eukaryotic elongation factor 2 kinase EEF2K +SeqId.10830-5 O75071 K0494 EF-hand calcium-binding domain-containing protein 14 EFCAB14 +SeqId.8480-29 Q12805 FBLN3 EGF-containing fibulin-like extracellular matrix protein 1 EFEMP1 +SeqId.6226-69 Q8IYU8 EFHA1 "Calcium uptake protein 2, mitochondrial" EFHA1 +SeqId.6912-6 Q86XE3 EFHA2 "Calcium uptake protein 3, mitochondrial" EFHA2 +SeqId.19616-100 Q9BUP0 EFHD1 EF-hand domain-containing protein D1 EFHD1 +SeqId.14124-6 O43921 Ephrin-A2 Ephrin-A2 EFNA2 +SeqId.14153-8 P52797 Ephrin-A3 Ephrin-A3 EFNA3 +SeqId.2614-28 P52798 Ephrin-A4 Ephrin-A4 EFNA4 +SeqId.2615-60 P52803 Ephrin-A5 Ephrin-A5 EFNA5 +SeqId.13104-32 P98172 EFNB1 Ephrin-B1 EFNB1 +SeqId.14131-37 P52799 EFNB2 Ephrin-B2 EFNB2 +SeqId.8772-5 P52799 EFNB2 Ephrin-B2 EFNB2 +SeqId.2514-65 Q15768 Ephrin-B3 Ephrin-B3 EFNB3 +SeqId.7785-1 Q15768 Ephrin-B3 Ephrin-B3 EFNB3 +SeqId.12572-236 O43281 EFS Embryonal Fyn-associated substrate EFS +SeqId.5509-7 P01133 EGF Epidermal growth factor EGF +SeqId.17454-15 Q8IUX8 EGFL6 Epidermal growth factor-like protein 6 EGFL6 +SeqId.12338-27 Q63HQ2 EGFLA Pikachurin EGFLAM +SeqId.19567-1 P00533 EGFRvIII Epidermal growth factor receptor variant III EGFR +SeqId.2677-1 P00533 ERBB1 Epidermal growth factor receptor EGFR +SeqId.9901-28 Q9GZT9 EGLN1 Egl nine homolog 1 EGLN1 +SeqId.12813-18 Q8NDI1 EHBP1 EH domain-binding protein 1 EHBP1 +SeqId.11421-10 Q9H223 EHD4 EH domain-containing protein 4 EHD4 +SeqId.13387-55 Q9NZC4 EHF ETS homologous factor EHF +SeqId.5843-60 Q96KQ7 NG36 Histone-lysine N-methyltransferase EHMT2 EHMT2 +SeqId.8079-39 Q8N140 EID3 EP300-interacting inhibitor of differentiation 3 EID3 +SeqId.13545-97 Q8N9N8 EIF1A Probable RNA-binding protein EIF1AD EIF1AD +SeqId.9850-38 P47813 IF1AX "Eukaryotic translation initiation factor 1A, X-chromosomal" EIF1AX +SeqId.19224-5 O14602 IF1AY "Eukaryotic translation initiation factor 1A, Y-chromosomal" EIF1AY +SeqId.12701-1 O60739 EIF1B Eukaryotic translation initiation factor 1b EIF1B +SeqId.14284-23 Q9P2K8 E2AK4 eIF-2-alpha kinase GCN2 EIF2AK4 +SeqId.10080-9 Q14232 EI2BA Translation initiation factor eIF-2B subunit alpha EIF2B1 +SeqId.19259-176 P05198 IF2A Eukaryotic translation initiation factor 2 subunit 1 EIF2S1 +SeqId.11454-87 O75821 EIF3G Eukaryotic translation initiation factor 3 subunit G EIF3G +SeqId.13497-34 O75822 EIF3J Eukaryotic translation initiation factor 3 subunit J EIF3J +SeqId.18829-4 P60842 IF4A1 Eukaryotic initiation factor 4A-I EIF4A1 +SeqId.18824-7 Q14240 IF4A2 Eukaryotic initiation factor 4A-II EIF4A2 +SeqId.4997-19 P38919 IF4A3 Eukaryotic initiation factor 4A-III EIF4A3 +SeqId.14675-20 P23588 IF4B Eukaryotic translation initiation factor 4B EIF4B +SeqId.19263-147 P06730 IF4E Eukaryotic translation initiation factor 4E EIF4E +SeqId.9745-20 O60573 IF4E2 Eukaryotic translation initiation factor 4E type 2 EIF4E2 +SeqId.17372-5 Q13541 4EBP1 Eukaryotic translation initiation factor 4E-binding protein 1 EIF4EBP1 +SeqId.4184-43 Q13542 4EBP2 Eukaryotic translation initiation factor 4E-binding protein 2 EIF4EBP2 +SeqId.18859-7 O60516 4EBP3 Eukaryotic translation initiation factor 4E-binding protein 3 EIF4EBP3 +SeqId.4230-1 P78344 IF4G2 Eukaryotic translation initiation factor 4 gamma 2 EIF4G2 +SeqId.13991-47 O43432 IF4G3 Eukaryotic translation initiation factor 4 gamma 3 EIF4G3 +SeqId.5885-55 Q15056 eIF-4H Eukaryotic translation initiation factor 4H EIF4H +SeqId.2612-5 P55010 eIF-5 Eukaryotic translation initiation factor 5 EIF5 +SeqId.5888-29 P63241 eIF-5A-1 Eukaryotic translation initiation factor 5A-1 EIF5A +SeqId.11355-10 Q9GZV4 IF5A2 Eukaryotic translation initiation factor 5A-2 EIF5A2 +SeqId.13671-40 P08246 Elastase Neutrophil elastase ELANE +SeqId.11592-1 Q15717 ELAV1 ELAV-like protein 1 ELAVL1 +SeqId.13457-33 Q9UKW6 ELF5 ETS-related transcription factor Elf-5 ELF5 +SeqId.10006-25 P19419 ELK1 ETS domain-containing protein Elk-1 ELK1 +SeqId.5707-55 P41970 ELK3 ETS domain-containing protein Elk-3 ELK3 +SeqId.11459-81 P55199 ELL RNA polymerase II elongation factor ELL ELL +SeqId.11494-4 O00472 ELL2 RNA polymerase II elongation factor ELL2 ELL2 +SeqId.12764-3 Q92556 ELMO1 Engulfment and cell motility protein 1 ELMO1 +SeqId.11989-35 Q8N766 EMC1 ER membrane protein complex subunit 1 EMC1 +SeqId.13516-46 Q5J8M3 TMM85 ER membrane protein complex subunit 4 EMC4 +SeqId.17770-42 O43402 EMC8 ER membrane protein complex subunit 8 EMC8 +SeqId.9547-29 Q96A84 EMID1 EMI domain-containing protein 1 EMID1 +SeqId.8773-172 Q9NT22 EMIL3 EMILIN-3 EMILIN3 +SeqId.9757-29 Q8N8S7 ENAH Protein enabled homolog ENAH +SeqId.5656-53 P21128 PP11 Poly(U)-specific endoribonuclease ENDOU +SeqId.4908-6 P17813 Endoglin Endoglin ENG +SeqId.16781-2 Q8NFI3 ENASE Cytosolic endo-beta-N-acetylglucosaminidase ENGASE +SeqId.11105-171 P06733 Alpha enolase Alpha-enolase ENO1 +SeqId.10339-48 P09104 NSE Gamma-enolase ENO2 +SeqId.16616-137 P13929 ENOB Beta-enolase ENO3 +SeqId.12933-17 Q8TC92 ENOX1 Ecto-NOX disulfide-thiol exchanger 1 ENOX1 +SeqId.13422-66 Q16206 ENOX2 Ecto-NOX disulfide-thiol exchanger 2 ENOX2 +SeqId.15558-63 Q07075 AMPE Glutamyl aminopeptidase ENPEP +SeqId.16892-23 Q13822 ENPP2 Ectonucleotide pyrophosphatase/phosphodiesterase family member 2 ENPP2 +SeqId.6556-5 Q9UJA9 ENPP5 Ectonucleotide pyrophosphatase/phosphodiesterase family member 5 ENPP5 +SeqId.15579-26 Q6UWR7 ENPP6 Ectonucleotide pyrophosphatase/phosphodiesterase family member 6 ENPP6 +SeqId.4435-66 Q6UWV6 ENPP7 Ectonucleotide pyrophosphatase/phosphodiesterase family member 7 ENPP7 +SeqId.17734-13 O43768 a-endosulfine Alpha-endosulfine ENSA +SeqId.7947-19 Q96N21 AP4AT AP-4 complex accessory subunit tepsin ENTHD2 +SeqId.3182-38 P49961 CD39 Ectonucleoside triphosphate diphosphohydrolase 1 ENTPD1 +SeqId.7999-23 P49961 CD39 Ectonucleoside triphosphate diphosphohydrolase 1 ENTPD1 +SeqId.18887-7 Q9Y5L3 ENTP2 Ectonucleoside triphosphate diphosphohydrolase 2 ENTPD2 +SeqId.4436-1 O75355 ENTP3 Ectonucleoside triphosphate diphosphohydrolase 3 ENTPD3 +SeqId.4437-56 O75356 ENTP5 Ectonucleoside triphosphate diphosphohydrolase 5 ENTPD5 +SeqId.8932-1 O75354 ENTP6 Ectonucleoside triphosphate diphosphohydrolase 6 ENTPD6 +SeqId.4706-17 P11171 41 Protein 4.1 EPB41 +SeqId.13993-20 Q9H4G0 E41L1 Band 4.1-like protein 1 EPB41L1 +SeqId.9040-144 Q9UM22 EPDR1 Mammalian ependymin-related protein 1 EPDR1 +SeqId.3431-54 P21709 EphA1 Ephrin type-A receptor 1 EPHA1 +SeqId.5076-53 Q5JZY3 EPHAA Ephrin type-A receptor 10 EPHA10 +SeqId.4834-61 P29317 Epithelial cell kinase Ephrin type-A receptor 2 EPHA2 +SeqId.3432-21 P29320 EPHA3 Ephrin type-A receptor 3 EPHA3 +SeqId.16288-17 P54764 EPHA4 Ephrin type-A receptor 4 EPHA4 +SeqId.3806-55 P54756 EphA5 Ephrin type-A receptor 5 EPHA5 +SeqId.15580-2 Q15375 EPHA7 Ephrin type-A receptor 7 EPHA7 +SeqId.17680-12 P54762 EPHB1 Ephrin type-B receptor 1 EPHB1 +SeqId.8225-86 P29323 EPHB2 Ephrin type-B receptor 2 EPHB2 +SeqId.9220-7 P54753 EPHB3 Ephrin type-B receptor 3 EPHB3 +SeqId.15530-33 P54760 EphB4 Ephrin type-B receptor 4 EPHB4 +SeqId.5078-82 O15197 EphB6 Ephrin type-B receptor 6 EPHB6 +SeqId.5813-58 P01588 Epo Erythropoietin EPO +SeqId.19575-4 P19235 EPO-R Erythropoietin receptor EPOR +SeqId.4212-5 Q9UBC2 EP15R Epidermal growth factor receptor substrate 15-like 1 EPS15L1 +SeqId.11162-37 Q9NQ60 EQTN Equatorin EQTN +SeqId.4964-67 Q9NZ08 ARTS1 Endoplasmic reticulum aminopeptidase 1 ERAP1 +SeqId.8960-3 Q6P179 LRAP Endoplasmic reticulum aminopeptidase 2 ERAP2 +SeqId.2616-23 P04626 ERBB2 Receptor tyrosine-protein kinase erbB-2 ERBB2 +SeqId.2617-56 P21860 ERBB3 Receptor tyrosine-protein kinase erbB-3 ERBB3 +SeqId.2618-10 Q15303 ERBB4 Receptor tyrosine-protein kinase erbB-4 ERBB4 +SeqId.12585-39 P07992 ERCC1 DNA excision repair protein ERCC-1 ERCC1 +SeqId.9895-77 Q92889 XPF DNA repair endonuclease XPF ERCC4 +SeqId.4956-2 O14944 EPI Epiregulin EREG +SeqId.11614-29 P84090 ERH Enhancer of rudimentary homolog ERH +SeqId.8957-72 Q96DZ1 XTP3B Endoplasmic reticulum lectin 1 ERLEC1 +SeqId.8776-10 O75477 ERLN1 Erlin-1 ERLIN1 +SeqId.8631-13 Q96PL5 ERMAP Erythroid membrane-associated protein ERMAP +SeqId.11229-16 O75460 ERN1 Serine/threonine-protein kinase/endoribonuclease IRE1 ERN1 +SeqId.7060-2 Q96HE7 ERO1A ERO1-like protein alpha ERO1L +SeqId.7994-41 Q86YB8 ERO1B ERO1-like protein beta ERO1LB +SeqId.9333-59 Q96DN0 ERP27 Endoplasmic reticulum resident protein 27 ERP27 +SeqId.13728-19 P30040 ERP29 Endoplasmic reticulum resident protein 29 ERP29 +SeqId.6064-4 Q9BS26 TXNDC4 Endoplasmic reticulum resident protein 44 ERP44 +SeqId.12531-5 B6SEH8 ERVV1 Endogenous retrovirus group V member 1 Env polyprotein ERVV-1 +SeqId.7841-84 Q96AP7 ESAM Endothelial cell-selective adhesion molecule ESAM +SeqId.4984-83 P10768 Esterase D S-formylglutathione hydrolase ESD +SeqId.3805-16 Q9NQ30 Endocan Endothelial cell-specific molecule 1 ESM1 +SeqId.8828-21 Q6NXG1 ESRP1 Epithelial splicing regulatory protein 1 ESRP1 +SeqId.9873-17 P11474 ERRalpha Steroid hormone receptor ERR1 ESRRA +SeqId.17435-43 P13804 ETFA "Electron transfer flavoprotein subunit alpha, mitochondrial" ETFA +SeqId.3847-56 O95571 ETHE1 "Persulfide dioxygenase ETHE1, mitochondrial" ETHE1 +SeqId.8328-9 Q9HBU6 EKI1 Ethanolamine kinase 1 ETNK1 +SeqId.12350-86 P15036 ETS2 Protein C-ets-2 ETS2 +SeqId.13403-5 P41161 ETV5 ETS translocation variant 5 ETV5 +SeqId.8062-15 Q9NVM1 F176B Protein eva-1 homolog B EVA1B +SeqId.8877-22 P58658 F176C Protein eva-1 homolog C EVA1C +SeqId.11656-110 Q9UI08 EVL Ena/VASP-like protein EVL +SeqId.14019-73 Q92817 EVPL Envoplakin EVPL +SeqId.12988-49 Q01844 EWS RNA-binding protein EWS EWSR1 +SeqId.7930-3 Q9Y3B2 EXOS1 Exosome complex component CSL4 EXOSC1 +SeqId.12605-1 Q9NQT5 Exosome component 3 Exosome complex component RRP40 EXOSC3 +SeqId.18909-11 Q96B26 EXOS8 Exosome complex component RRP43 EXOSC8 +SeqId.6528-95 Q9UBQ6 EXTL2 Exostosin-like 2 EXTL2 +SeqId.9365-91 Q5T1H1 EYS Protein eyes shut homolog EYS +SeqId.9753-17 P15311 Ezrin Ezrin EZR +SeqId.3077-66 P00742 Coagulation Factor Xa Coagulation factor Xa F10 +SeqId.4878-3 P00742 Coagulation Factor X Coagulation Factor X F10 +SeqId.2190-55 P03951 Coagulation Factor XI Coagulation Factor XI F11 +SeqId.16927-9 "P00488, P05160" Coagulation factor XIII Coagulation factor XIII F13A1 F13B +SeqId.16927-9 "P00488, P05160" Coagulation factor XIII Coagulation factor XIII F13A1 F13B +SeqId.5658-64 P05160 coagulation factor XIII B Coagulation factor XIII B chain F13B +SeqId.4157-2 P00734 Thrombin Thrombin F2 +SeqId.5316-54 P00734 Prothrombin Prothrombin F2 +SeqId.4931-59 P13726 TF Tissue Factor F3 +SeqId.4906-35 P12259 Coagulation Factor V Coagulation Factor V F5 +SeqId.3184-25 P08709 Coagulation Factor VII Coagulation factor VII F7 +SeqId.13499-30 P00451 Coagulation Factor VIII Coagulation Factor VIII F8 +SeqId.4876-32 P00740 Coagulation Factor IX Coagulation factor IX F9 +SeqId.5307-12 P00740 Coagulation Factor IXab Coagulation factor IXab F9 +SeqId.8396-42 Q6GMR7 FAAH2 Fatty-acid amide hydrolase 2 FAAH2 +SeqId.11516-7 P07148 FABPL "Fatty acid-binding protein, liver" FABP1 +SeqId.18888-37 A6NFH5 FBP12 Fatty acid-binding protein 12 FABP12 +SeqId.15385-116 P12104 FABP2 "Fatty acid-binding protein, intestinal" FABP2 +SeqId.5437-63 P05413 FABP "Fatty acid-binding protein, heart" FABP3 +SeqId.15386-7 P15090 FABPA "Fatty acid-binding protein, adipocyte" FABP4 +SeqId.4985-11 Q01469 FABPE "Fatty acid-binding protein, epidermal" FABP5 +SeqId.6450-8 P51161 FABP6 Gastrotropin FABP6 +SeqId.18194-18 Q0Z7S8 FABP9 Fatty acid-binding protein 9 FABP9 +SeqId.16593-3 Q13158 FADD FAS-associated death domain protein FADD +SeqId.9738-7 Q96CS3 FAF2 FAS-associated factor 2 FAF2 +SeqId.11424-4 P16930 FAAA Fumarylacetoacetase FAH +SeqId.17819-30 Q6P587 FAHD1 "Acylpyruvase FAHD1, mitochondrial" FAHD1 +SeqId.16594-44 Q9NVQ4 FAIM1 Fas apoptotic inhibitory molecule 1 FAIM +SeqId.6574-11 O60667 FAIM3 Fas apoptotic inhibitory molecule 3 FAIM3 +SeqId.2760-2 O95990 DRR1 Protein FAM107A FAM107A +SeqId.8556-5 Q9H6L5 F134B Protein FAM134B FAM134B +SeqId.6284-7 Q6UX46 F150B ALK and LTK ligand 2 FAM150B +SeqId.7856-51 Q8WW52 F151A Protein FAM151A FAM151A +SeqId.13431-74 Q6UWV7 F159A Membrane protein FAM159A FAM159A +SeqId.6531-29 Q96A26 F162A Protein FAM162A FAM162A +SeqId.11163-7 Q5T6X4 F162B Protein FAM162B FAM162B +SeqId.10880-38 P0C2L3 F163B Protein FAM163B FAM163B +SeqId.5610-32 Q5VUB5 CJ038 Protein FAM171A1 FAM171A1 +SeqId.13479-8 A8MVW0 F1712 Protein FAM171A2 FAM171A2 +SeqId.8061-102 Q6P995 F171B Protein FAM171B FAM171B +SeqId.8786-6 Q6P995 F171B Protein FAM171B FAM171B +SeqId.5615-62 Q8WUF8 F172A Protein FAM172A FAM172A +SeqId.7148-42 Q9BQD7 F173A Protein FAM173A FAM173A +SeqId.6597-24 Q8TBP5 TM157 Membrane protein FAM174A FAM174A +SeqId.8784-7 Q6UWZ7 F175A BRCA1-A complex subunit Abraxas FAM175A +SeqId.8945-7 Q15018 F175B BRISC complex subunit Abro1 FAM175B +SeqId.8039-41 Q8N128 F177A Protein FAM177A1 FAM177A1 +SeqId.5719-66 Q15884 CI061 Protein FAM189A2 FAM189A2 +SeqId.5753-21 Q7Z5A9 F19A1 Protein FAM19A1 FAM19A1 +SeqId.6430-36 Q8N3H0 F19A2 Protein FAM19A2 FAM19A2 +SeqId.7839-99 Q7Z5A8 F19A3 Protein FAM19A3 FAM19A3 +SeqId.6511-17 Q96LR4 F19A4 Protein FAM19A4 FAM19A4 +SeqId.5609-92 Q7Z5A7 F19A5 Protein FAM19A5 FAM19A5 +SeqId.7066-199 Q5JX69 F209B Protein FAM209B FAM209B +SeqId.6433-57 Q96MK3 FA20A Pseudokinase FAM20A FAM20A +SeqId.7198-197 O75063 FA20B Glycosaminoglycan xylosylkinase FAM20B +SeqId.14593-152 Q96ND0 F210A Protein FAM210A FAM210A +SeqId.13423-94 Q9BRX8 CJ058 Redox-regulatory protein FAM213A FAM213A +SeqId.8775-61 Q8N5W8 FA24B Protein FAM24B FAM24B +SeqId.5618-50 P58499 FAM3B Protein FAM3B FAM3B +SeqId.9177-6 P58499 FAM3B Protein FAM3B FAM3B +SeqId.13102-1 Q96BQ1 FAM3D Protein FAM3D FAM3D +SeqId.19176-27 Q9NUQ9 FA49B Protein FAM49B FAM49B +SeqId.14341-8 Q0P6D2 FA69C Protein FAM69C FAM69C +SeqId.11336-9 Q9NPI8 FANCF Fanconi anemia group F protein FANCF +SeqId.10063-10 Q9NW38 FANCL E3 ubiquitin-protein ligase FANCL FANCL +SeqId.15581-16 Q8TC84 FANK1 Fibronectin type 3 and ankyrin repeat domains protein 1 FANK1 +SeqId.5029-3 Q12884 SEPR Prolyl endopeptidase FAP FAP +SeqId.13941-82 O95363 SYFM "Phenylalanine--tRNA ligase, mitochondrial" FARS2 +SeqId.5392-73 P25445 "Fas, soluble" Tumor necrosis factor receptor superfamily member 6 FAS +SeqId.9459-7 P25445 "Fas, soluble" Tumor necrosis factor receptor superfamily member 6 FAS +SeqId.3052-8 P48023 "Fas ligand, soluble" "Tumor necrosis factor ligand superfamily member 6, soluble form" FASLG +SeqId.8403-18 P49327 Fatty acid synthase Fatty acid synthase FASN +SeqId.7740-33 Q969F0 FATE1 Fetal and adult testis-expressed transcript protein FATE1 +SeqId.9074-6 Q96IV6 CE004 Fatty acid hydroxylase domain-containing protein 2 FAXDC2 +SeqId.13994-1 P22087 FBRL rRNA 2'-O-methyltransferase fibrillarin FBL +SeqId.6470-19 P23142 fibulin 1 Fibulin-1 FBLN1 +SeqId.15585-304 Q9UBX5 fibulin 5 Fibulin-5 FBLN5 +SeqId.7206-20 P09467 F16P1 "Fructose-1,6-bisphosphatase 1" FBP1 +SeqId.9867-23 O00757 F16P2 "Fructose-1,6-bisphosphatase isozyme 2" FBP2 +SeqId.11416-23 Q9UKA2 FBXL4 F-box/LRR-repeat protein 4 FBXL4 +SeqId.9951-36 Q9UKA2 FBXL4 F-box/LRR-repeat protein 4 FBXL4 +SeqId.12846-3 Q9UKA1 FBXL5 F-box/LRR-repeat protein 5 FBXL5 +SeqId.14628-72 Q9UK99 FBX3 F-box only protein 3 FBXO3 +SeqId.9568-289 Q8WWV6 FCAMR High affinity immunoglobulin alpha and immunoglobulin mu Fc receptor FCAMR +SeqId.4987-17 P24071 FCAR Immunoglobulin alpha Fc receptor FCAR +SeqId.9254-18 P12319 FCERA High affinity immunoglobulin epsilon receptor subunit alpha FCER1A +SeqId.3291-30 P06734 CD23 Low affinity immunoglobulin epsilon Fc receptor FCER2 +SeqId.3312-64 P12314 FCGR1 High affinity immunoglobulin gamma Fc receptor I FCGR1A +SeqId.3309-2 P12318 FCG2A Low affinity immunoglobulin gamma Fc region receptor II-a FCGR2A +SeqId.3310-62 P31994 FCG2B Low affinity immunoglobulin gamma Fc region receptor II-b FCGR2B +SeqId.15388-24 P08637 FcRIIIa Low affinity immunoglobulin gamma Fc region receptor III-A FCGR3A +SeqId.3311-27 O75015 FCG3B Low affinity immunoglobulin gamma Fc region receptor III-B FCGR3B +SeqId.15582-25 O00602 FCN1 Ficolin-1 FCN1 +SeqId.13717-15 Q15485 FCN2 Ficolin-2 FCN2 +SeqId.3313-21 Q15485 FCN2 Ficolin-2 FCN2 +SeqId.5462-62 O75636 Ficolin-3 Ficolin-3 FCN3 +SeqId.5728-60 Q96LA6 FCRL1 Fc receptor-like protein 1 FCRL1 +SeqId.4440-15 Q96P31 FCRL3 Fc receptor-like protein 3 FCRL3 +SeqId.8973-23 Q96PJ5 FCRL4 Fc receptor-like protein 4 FCRL4 +SeqId.8991-115 Q96PJ5 FCRL4 Fc receptor-like protein 4 FCRL4 +SeqId.6103-70 Q96RD9 FCRL5 Fc receptor-like protein 5 FCRL5 +SeqId.6617-12 Q6DN72 FCRL6 Fc receptor-like protein 6 FCRL6 +SeqId.15583-18 Q6BAA4 FCRLB Fc receptor-like B FCRLB +SeqId.17346-61 Q8NFU4 FDSCP Follicular dendritic cell secreted peptide FDCSP +SeqId.11231-12 Q6P4F2 ADXL "Adrenodoxin-like protein, mitochondrial" FDX1L +SeqId.12577-100 P39748 FLAP endonuclease-1 Flap endonuclease 1 FEN1 +SeqId.4220-39 P16591 FER Tyrosine-protein kinase Fer FER +SeqId.12599-10 Q86UX7 URP2 Fermitin family homolog 3 FERMT3 +SeqId.3367-8 Q9UGM5 FETUB Fetuin-B FETUB +SeqId.12740-55 Q99581 FEV Protein FEV FEV +SeqId.2796-62 P02671 P02675 P02679 Fibrinogen Fibrinogen FGA FGB FGG +SeqId.2796-62 P02671 P02675 P02679 Fibrinogen Fibrinogen FGA FGB FGG +SeqId.2796-62 P02671 P02675 P02679 Fibrinogen Fibrinogen FGA FGB FGG +SeqId.4907-56 P02671 P02675 P02679 D-dimer D-dimer FGA FGB FGG +SeqId.4907-56 P02671 P02675 P02679 D-dimer D-dimer FGA FGB FGG +SeqId.4907-56 P02671 P02675 P02679 D-dimer D-dimer FGA FGB FGG +SeqId.18890-227 P02675 Fibrinogen B Fibrinogen beta chain FGB +SeqId.3486-58 P05230 b-ECGF Fibroblast growth factor 1 FGF1 +SeqId.2441-2 O15520 FGF-10 Fibroblast growth factor 10 FGF10 +SeqId.4392-54 P61328 FGF-12 Fibroblast growth factor 12 FGF12 +SeqId.4393-3 O43320 FGF-16 Fibroblast growth factor 16 FGF16 +SeqId.3494-71 O60258 FGF-17 Fibroblast growth factor 17 FGF17 +SeqId.2761-49 O76093 FGF-18 Fibroblast growth factor 18 FGF18 +SeqId.13724-27 O95750 FGF-19 Fibroblast growth factor 19 FGF19 +SeqId.3025-50 P09038 bFGF Fibroblast growth factor 2 FGF2 +SeqId.2763-66 Q9NP95 FGF-20 Fibroblast growth factor 20 FGF20 +SeqId.9513-9 Q9HCT0 FGF22 Fibroblast growth factor 22 FGF22 +SeqId.3807-1 Q9GZV9 FGF23 Fibroblast growth factor 23 FGF23 +SeqId.7894-155 P11487 FGF-3 Fibroblast growth factor 3 FGF3 +SeqId.4123-60 P08620 FGF-4 Fibroblast growth factor 4 FGF4 +SeqId.3065-65 P12034 FGF-5 Fibroblast growth factor 5 FGF5 +SeqId.4130-71 P10767 FGF-6 Fibroblast growth factor 6 FGF6 +SeqId.4487-1 P21781 FGF7 Fibroblast growth factor 7 FGF7 +SeqId.2443-10 P55075 FGF-8B Fibroblast growth factor 8 isoform B FGF8 +SeqId.17166-4 P55075 FGF-8F Fibroblast growth factor 8 isoform F FGF8 +SeqId.19570-12 P55075 FGF-8 Fibroblast growth factor 8 FGF8 +SeqId.4394-71 P55075 FGF-8A Fibroblast growth factor 8 isoform A FGF8 +SeqId.19584-33 P31371 FGF9 Fibroblast growth factor 9 FGF9 +SeqId.15494-11 Q14512 FGFP1 Fibroblast growth factor-binding protein 1 FGFBP1 +SeqId.11219-95 Q8TAT2 FGFP3 Fibroblast growth factor-binding protein 3 FGFBP3 +SeqId.5532-53 P11362 bFGF-R Fibroblast growth factor receptor 1 FGFR1 +SeqId.3808-76 P21802 FGFR-2 Fibroblast growth factor receptor 2 FGFR2 +SeqId.13669-6 P22607 FGFR-3 Fibroblast growth factor receptor 3 FGFR3 +SeqId.3809-1 P22607 FGFR-3 Fibroblast growth factor receptor 3 FGFR3 +SeqId.4988-49 P22455 FGFR4 Fibroblast growth factor receptor 4 FGFR4 +SeqId.6237-11 Q8N441 FGRL1 Fibroblast growth factor receptor-like 1 FGFRL1 +SeqId.4989-7 P02679 Fibrinogen g-chain dimer Fibrinogen gamma chain FGG +SeqId.5581-28 Q08830 FGL1 Fibrinogen-like protein 1 FGL1 +SeqId.19635-69 Q14314 FGL2 Fibroleukin FGL2 +SeqId.3810-50 P09769 FGR Tyrosine-protein kinase Fgr FGR +SeqId.13384-110 P07954 FUMH "Fumarate hydratase, mitochondrial" FH +SeqId.9826-135 P49789 Fragile histidine triad protein Bis(5'-adenosyl)-triphosphatase FHIT +SeqId.16814-13 Q13642 SLIM 1 Four and a half LIM domains protein 1 FHL1 +SeqId.9378-6 Q8N539 FBCD1 Fibrinogen C domain-containing protein 1 FIBCD1 +SeqId.19169-88 O43427 FIBP Acidic fibroblast growth factor intracellular-binding protein FIBP +SeqId.6948-82 Q92562 FIG4 Polyphosphoinositide phosphatase FIG4 +SeqId.13098-93 O43915 VEGF-D Vascular endothelial growth factor D FIGF +SeqId.14705-1 O43915 VEGF-D Vascular endothelial growth factor D FIGF +SeqId.17746-77 Q9Y3D6 FIS1 Mitochondrial fission 1 protein FIS1 +SeqId.7921-65 Q86VR8 FJX1 Four-jointed box protein 1 FJX1 +SeqId.9340-17 Q9NWM8 FKB14 Peptidyl-prolyl cis-trans isomerase FKBP14 FKBP14 +SeqId.11568-2 P68106 FKB1B Peptidyl-prolyl cis-trans isomerase FKBP1B FKBP1B +SeqId.9339-204 P26885 FKBP2 Peptidyl-prolyl cis-trans isomerase FKBP2 FKBP2 +SeqId.18383-9 Q00688 FKBP3 Peptidyl-prolyl cis-trans isomerase FKBP3 FKBP3 +SeqId.17722-5 Q02790 FKBP52 protein Peptidyl-prolyl cis-trans isomerase FKBP4 FKBP4 +SeqId.12529-32 O75344 FKBP6 Inactive peptidyl-prolyl cis-trans isomerase FKBP6 FKBP6 +SeqId.9288-7 Q9Y680 FKBP7 Peptidyl-prolyl cis-trans isomerase FKBP7 FKBP7 +SeqId.12677-164 Q13045 FLII Protein flightless-1 homolog FLII +SeqId.11171-25 P21333 filamin A Filamin-A FLNA +SeqId.4547-59 Q9NZU1 FLRT1 Leucine-rich repeat transmembrane protein FLRT1 FLRT1 +SeqId.13122-19 O43155 FLRT2 Leucine-rich repeat transmembrane protein FLRT2 FLRT2 +SeqId.13123-3 Q9NZU0 FLRT3 Leucine-rich repeat transmembrane protein FLRT3 FLRT3 +SeqId.9128-34 Q9NZU0 FLRT3 Leucine-rich repeat transmembrane protein FLRT3 FLRT3 +SeqId.16315-105 P17948 VEGF sR1 Vascular endothelial growth factor receptor 1 FLT1 +SeqId.8231-122 P17948 VEGF sR1 Vascular endothelial growth factor receptor 1 FLT1 +SeqId.3437-80 P36888 Flt-3 Receptor-type tyrosine-protein kinase FLT3 FLT3 +SeqId.14093-10 P49771 Flt3 ligand Fms-related tyrosine kinase 3 ligand FLT3LG +SeqId.16035-8 P35916 VEGF sR3 Vascular endothelial growth factor receptor 3 FLT4 +SeqId.6367-66 Q06828 fibromodulin fibromodulin FMOD +SeqId.7713-102 Q06787 FMR1 Fragile X mental retardation protein 1 FMR1 +SeqId.3435-53 P02751 FN1.4 Fibronectin Fragment 4 FN1 +SeqId.3434-34 P02751 FN1.3 Fibronectin Fragment 3 FN1 +SeqId.4131-72 P02751 Fibronectin Fibronectin FN1 +SeqId.13451-2 Q9H6D8 FNDC4 Fibronectin type III domain-containing protein 4 FNDC4 +SeqId.5478-50 Q04609 PSMA Glutamate carboxypeptidase 2 FOLH1 +SeqId.17455-42 P15328 FOLR1 Folate receptor alpha FOLR1 +SeqId.15587-20 P14207 FOLR2 Folate receptor beta FOLR2 +SeqId.15495-9 P41439 FOLR3 Folate receptor gamma FOLR3 +SeqId.14051-54 Q99958 FOXC2 Forkhead box protein C2 FOXC2 +SeqId.9896-21 P55316 FOXGB Forkhead box protein G1 FOXG1 +SeqId.14204-55 Q9P0K8 FOXJ2 Forkhead box protein J2 FOXJ2 +SeqId.11375-49 P58012 FOXL2 Forkhead box protein L2 FOXL2 +SeqId.10056-5 Q08050 FOXM1 Forkhead box protein M1 FOXM1 +SeqId.11540-37 O43524 FOXO3A Forkhead box protein O3 FOXO3 +SeqId.8017-23 Q96CU9 FXRD1 FAD-dependent oxidoreductase domain-containing protein 1 FOXRED1 +SeqId.7246-4 Q5SZK8 FREM2 FRAS1-related extracellular matrix protein 2 FREM2 +SeqId.7976-19 Q9P0K9 FRS1L DOMON domain-containing protein FRRS1L FRRS1L +SeqId.13025-4 Q8WU20 FRS2 Fibroblast growth factor receptor substrate 2 FRS2 +SeqId.13740-51 Q92765 sFRP-3 Secreted frizzled-related protein 3 FRZB +SeqId.8036-75 P01225 FSHB Follitropin subunit beta FSHB +SeqId.4132-27 P19883 FST Follistatin FST +SeqId.13112-179 Q12841 FSTL1 Follistatin-related protein 1 FSTL1 +SeqId.3438-10 O95633 FSTL3 Follistatin-related protein 3 FSTL3 +SeqId.9350-3 Q6MZW2 FSTL4 Follistatin-related protein 4 FSTL4 +SeqId.7099-33 Q8N475 FSTL5 Follistatin-related protein 5 FSTL5 +SeqId.9213-24 O95954 FTCD Formimidoyltransferase-cyclodeaminase FTCD +SeqId.5934-1 P02794 P02792 Ferritin Ferritin FTH1 FTL +SeqId.5934-1 P02794 P02792 Ferritin Ferritin FTH1 FTL +SeqId.15324-58 P02792 Ferritin light chain Ferritin light chain FTL +SeqId.8048-9 Q8N4E7 FTMT "Ferritin, mitochondrial" FTMT +SeqId.6276-16 P09958 Furin Furin FURIN +SeqId.7156-2 Q6P4F1 FUT10 "Alpha-(1,3)-fucosyltransferase 10" FUT10 +SeqId.9121-28 Q10981 FUT2 Galactoside 2-alpha-L-fucosyltransferase 2 FUT2 +SeqId.4548-4 P21217 Fucosyltransferase 3 Galactoside 3(4)-L-fucosyltransferase FUT3 +SeqId.4549-78 Q11128 FUT5 "Alpha-(1,3)-fucosyltransferase 5" FUT5 +SeqId.8244-16 Q9BYC5 FUT8 "Alpha-(1,6)-fucosyltransferase" FUT8 +SeqId.6991-24 Q9Y231 FUT9 "Alpha-(1,3)-fucosyltransferase 9" FUT9 +SeqId.15389-1 Q16595 FRDA "Frataxin, mitochondrial" FXN +SeqId.13076-4 P51114 FXR1 Fragile X mental retardation syndrome-related protein 1 FXR1 +SeqId.3813-3 P06241 FYN Tyrosine-protein kinase Fyn FYN +SeqId.11647-6 Q9ULW2 Frizzled-10 Frizzled-10 FZD10 +SeqId.8931-124 P27469 G0S2 G0/G1 switch protein 2 G0S2 +SeqId.19266-35 Q13283 G3BP1 Ras GTPase-activating protein-binding protein 1 G3BP1 +SeqId.9831-12 Q9UN86 G3BP2 Ras GTPase-activating protein-binding protein 2 G3BP2 +SeqId.7065-1 O95866 G6B Protein G6b G6B +SeqId.8659-68 O95866 G6B Protein G6b G6B +SeqId.19297-4 P11413 G6PD Glucose-6-phosphate 1-dehydrogenase G6PD +SeqId.9385-4 P10253 GAA Lysosomal alpha-glucosidase GAA +SeqId.17735-130 O95166 GBRAP Gamma-aminobutyric acid receptor-associated protein GABARAP +SeqId.12661-44 Q9H0R8 GBRL1 Gamma-aminobutyric acid receptor-associated protein-like 1 GABARAPL1 +SeqId.12494-99 P60520 GBRL2 Gamma-aminobutyric acid receptor-associated protein-like 2 GABARAPL2 +SeqId.11279-42 Q9UBS5 GABR1 Gamma-aminobutyric acid type B receptor subunit 1 GABBR1 +SeqId.13948-50 O75899 GABR2 Gamma-aminobutyric acid type B receptor subunit 2 GABBR2 +SeqId.9930-48 O75899 GABR2 Gamma-aminobutyric acid type B receptor subunit 2 GABBR2 +SeqId.11280-6 Q99259 DCE1 Glutamate decarboxylase 1 GAD1 +SeqId.9302-90 Q8TAE8 G45IP Growth arrest and DNA damage-inducible proteins-interacting protein 1 GADD45GIP1 +SeqId.18268-5 Q6NT46 GAG2A G antigen 2A GAGE2A +SeqId.15390-3 P22466 Galanin Galanin GAL +SeqId.8696-15 Q99999 G3ST1 Galactosylceramide sulfotransferase GAL3ST1 +SeqId.10734-339 Q9H3Q3 G3ST2 Galactose-3-O-sulfotransferase 2 GAL3ST2 +SeqId.11457-53 Q14376 GALE UDP-glucose 4-epimerase GALE +SeqId.11448-34 P51570 GALK1 Galactokinase GALK1 +SeqId.7090-17 Q10472 GALT1 Polypeptide N-acetylgalactosaminyltransferase 1 GALNT1 +SeqId.7003-4 Q86SR1 GLT10 Polypeptide N-acetylgalactosaminyltransferase 10 GALNT10 +SeqId.8700-325 Q8NCW6 GLT11 Polypeptide N-acetylgalactosaminyltransferase 11 GALNT11 +SeqId.10908-2 Q8IUC8 GLT13 Polypeptide N-acetylgalactosaminyltransferase 13 GALNT13 +SeqId.8923-94 Q8N428 GLTL1 Polypeptide N-acetylgalactosaminyltransferase 16 GALNT16 +SeqId.5764-4 Q10471 GALT2 Polypeptide N-acetylgalactosaminyltransferase 2 GALNT2 +SeqId.6593-5 Q14435 GALT3 Polypeptide N-acetylgalactosaminyltransferase 3 GALNT3 +SeqId.9398-30 Q9UBC7 GALP Galanin-like peptide GALP +SeqId.10054-3 Q9H2C0 GAN Gigaxonin GAN +SeqId.15325-14 P17677 NEUM Neuromodulin GAP43 +SeqId.3848-14 P04406 "GAPDH, liver" Glyceraldehyde-3-phosphate dehydrogenase GAPDH +SeqId.8004-15 O14556 G3PT "Glyceraldehyde-3-phosphate dehydrogenase, testis-specific" GAPDHS +SeqId.5463-22 P54826 GAS1 Growth arrest-specific protein 1 GAS1 +SeqId.15391-114 Q14393 GAS-6 Growth arrest-specific protein 6 GAS6 +SeqId.17721-82 O60861 GAS7 Growth arrest-specific protein 7 GAS7 +SeqId.18188-12 P50440 GATM "Glycine amidinotransferase, mitochondrial" GATM +SeqId.15326-64 P32455 GBP1 Guanylate-binding protein 1 GBP1 +SeqId.18891-98 P32456 GBP2 Guanylate-binding protein 2 GBP2 +SeqId.7818-101 Q6ZN66 GBP6 Guanylate-binding protein 6 GBP6 +SeqId.15589-1 P02774 "Gc-Globulin, Mixed Type" Vitamin D-binding protein GC +SeqId.12594-5 P28676 GRAN Grancalcin GCA +SeqId.19258-24 Q92947 GCDH "Glutaryl-CoA dehydrogenase, mitochondrial" GCDH +SeqId.4891-50 P01275 Glucagon Glucagon GCG +SeqId.11185-145 P30793 GCH1 GTP cyclohydrolase 1 GCH1 +SeqId.12960-9 P35557 HXK4 Glucokinase GCK +SeqId.5223-59 Q14397 GCKR Glucokinase regulatory protein GCKR +SeqId.18214-2 P48507 GSH0 Glutamate--cysteine ligase regulatory subunit GCLM +SeqId.7016-12 Q02742 GCNT1 "Beta-1,3-galactosyl-O-glycosyl-glycoprotein beta-1,6-N-acetylglucosaminyltransferase" GCNT1 +SeqId.7143-9 Q8NFS9 GNT2C "N-acetyllactosaminide beta-1,6-N-acetylglucosaminyl-transferase, isoform C" GCNT2 +SeqId.10842-7 Q9P109 GCNT4 "Beta-1,3-galactosyl-O-glycosyl-glycoprotein beta-1,6-N-acetylglucosaminyltransferase 4" GCNT4 +SeqId.10956-82 P23434 GCSH "Glycine cleavage system H protein, mitochondrial" GCSH +SeqId.12667-2 Q9Y2T3 GUAD Guanine deaminase GDA +SeqId.16749-79 P55107 BMP-3b Growth/differentiation factor 10 GDF10 +SeqId.6517-14 P55107 BMP-3b Growth/differentiation factor 10 GDF10 +SeqId.14587-16 O95390 GDF-11 Growth/differentiation factor 11 GDF11 +SeqId.2765-4 O95390 O14793 GDF-11/8 Growth/differentiation factor 11/8 GDF11 MSTN +SeqId.2765-4 O95390 O14793 GDF-11/8 Growth/differentiation factor 11/8 GDF11 MSTN +SeqId.4374-45 Q99988 MIC-1 Growth/differentiation factor 15 GDF15 +SeqId.4880-21 Q9UK05 GDF2 Growth/differentiation factor 2 GDF2 +SeqId.16755-195 Q9NR23 GDF-3 Growth/differentiation factor 3 GDF3 +SeqId.2752-62 P43026 BMP-14 Growth/differentiation factor 5 GDF5 +SeqId.16756-30 Q7Z4P5 GDF7 Growth/differentiation factor 7 GDF7 +SeqId.3067-67 O60383 GDF-9 Growth/differentiation factor 9 GDF9 +SeqId.16810-3 P31150 RhoGDI Rab GDP dissociation inhibitor alpha GDI1 +SeqId.2647-66 P50395 Rab GDP dissociation inhibitor beta Rab GDP dissociation inhibitor beta GDI2 +SeqId.5822-22 P39905 GDNF Glial cell line-derived neurotrophic factor GDNF +SeqId.12817-1 P55040 GEM GTP-binding protein GEM GEM +SeqId.3034-1 P14136 GFAP Glial fibrillary acidic protein GFAP +SeqId.15398-2 P55789 HERV1 FAD-linked sulfhydryl oxidase ALR GFER +SeqId.3314-74 P56159 GFRa-1 GDNF family receptor alpha-1 GFRA1 +SeqId.2515-14 O00451 GFRa-2 GDNF family receptor alpha-2 GFRA2 +SeqId.2505-49 O60609 GFRa-3 GDNF family receptor alpha-3 GFRA3 +SeqId.6920-1 Q6UXV0 GFRAL GDNF family receptor alpha-like GFRAL +SeqId.13594-158 Q9UJY5 GGA1 ADP-ribosylation factor-binding protein GGA1 GGA1 +SeqId.11683-19 Q9NZ52 GGA3 ADP-ribosylation factor-binding protein GGA3 GGA3 +SeqId.9370-69 Q92820 GGH Gamma-glutamyl hydrolase GGH +SeqId.17786-5 O95749 GGPPS Geranylgeranyl pyrophosphate synthase GGPS1 +SeqId.6334-9 P36268 GGT2 Inactive gamma-glutamyltranspeptidase 2 GGT2 +SeqId.8462-18 P01241 HGH Somatotropin GH1 +SeqId.10978-39 P01242 SOM2 Growth hormone variant GH2 +SeqId.9730-22 Q8N2G8 GHDC GH3 domain-containing protein GHDC +SeqId.2948-58 P10912 Growth hormone receptor Growth hormone receptor GHR +SeqId.16293-1 P01286 Growth hormone-releasing factor Somatoliberin GHRH +SeqId.9487-60 P01286 Growth hormone-releasing factor Somatoliberin GHRH +SeqId.6518-85 Q9UBU3 ghrelin Appetite-regulating hormone GHRL +SeqId.8447-11 Q9UBU3 ghrelin Appetite-regulating hormone GHRL +SeqId.17672-184 P27352 Gastric intrinsic factor Gastric intrinsic factor GIF +SeqId.19302-7 Q6P9H5 GIMA6 GTPase IMAP family member 6 GIMAP6 +SeqId.16292-288 P09681 GIP Gastric inhibitory polypeptide GIP +SeqId.5755-29 P09681 GIP Gastric inhibitory polypeptide GIP +SeqId.19260-4 O14908 GIPC1 PDZ domain-containing protein GIPC1 GIPC1 +SeqId.9937-7 P17302 CXA1 Gap junction alpha-1 protein GJA1 +SeqId.12711-19 P48165 CXA8 Gap junction alpha-8 protein GJA8 +SeqId.11678-105 Q9UKL4 CXD2 Gap junction delta-2 protein GJD2 +SeqId.15374-15 Q9NS71 CA11 protein Gastrokine-1 GKN1 +SeqId.6416-8 Q86XP6 GKN2 Gastrokine-2 GKN2 +SeqId.15588-17 P06280 "galactosidase, alpha" Alpha-galactosidase A GLA +SeqId.10554-23 P16278 BGAL Beta-galactosidase GLB1 +SeqId.7808-5 O94923 GLCE D-glucuronyl C5-epimerase GLCE +SeqId.9265-10 P48060 GLIP1 Glioma pathogenesis-related protein 1 GLIPR1 +SeqId.15522-2 Q9H4G4 GAPR1 Golgi-associated plant pathogenesis-related protein 1 GLIPR2 +SeqId.9883-29 Q04760 Glyoxalase I Lactoylglutathione lyase GLO1 +SeqId.13085-18 P43220 GLP1R Glucagon-like peptide 1 receptor GLP1R +SeqId.18386-36 P35754 GLRX1 Glutaredoxin-1 GLRX +SeqId.12486-8 Q9NS18 GLRX2 "Glutaredoxin-2, mitochondrial" GLRX2 +SeqId.16596-25 O76003 GLRX3 Glutaredoxin-3 GLRX3 +SeqId.16597-11 Q86SX6 GLRX5 "Glutaredoxin-related protein 5, mitochondrial" GLRX5 +SeqId.8955-60 Q68CQ7 GL8D1 Glycosyltransferase 8 domain-containing protein 1 GLT8D1 +SeqId.12513-8 Q9NZD2 GLTP Glycolipid transfer protein GLTP +SeqId.7948-129 A6NH11 GLTD2 Glycolipid transfer protein domain-containing protein 2 GLTPD2 +SeqId.19238-12 P15104 GLNA Glutamine synthetase GLUL +SeqId.19506-6 Q6IB77 GLYAT Glycine N-acyltransferase GLYAT +SeqId.15441-6 P17900 SAP3 Ganglioside GM2 activator GM2A +SeqId.18337-4 O60547 GMDS "GDP-mannose 4,6 dehydratase" GMDS +SeqId.12804-5 Q9UKD1 GMEB2 Glucocorticoid modulatory element-binding protein 2 GMEB2 +SeqId.17784-23 P60983 GMFB Glia maturation factor beta GMFB +SeqId.13062-4 O60234 GMFG Glia maturation factor gamma GMFG +SeqId.17703-40 O75496 GEMI Geminin GMNN +SeqId.19254-125 P36959 GMPR1 GMP reductase 1 GMPR +SeqId.19446-1 Q9P2T1 GMPR2 GMP reductase 2 GMPR2 +SeqId.18184-28 P49915 GUAA GMP synthase [glutamine-hydrolyzing] GMPS +SeqId.19271-64 P63096 GNAI1 Guanine nucleotide-binding protein G(i) subunit alpha-1 GNAI1 +SeqId.12650-43 P08754 GNAI3 Guanine nucleotide-binding protein G(k) subunit alpha GNAI3 +SeqId.5757-45 O95467 GNAS3 Neuroendocrine secretory protein 55 GNAS +SeqId.18282-1 P61952 GBG11 Guanine nucleotide-binding protein G(I)/G(S)/G(O) subunit gamma-11 GNG11 +SeqId.10917-40 O14610 GBGT2 Guanine nucleotide-binding protein G(I)/G(S)/G(O) subunit gamma-T2 GNGT2 +SeqId.3195-50 P22749 Granulysin Granulysin GNLY +SeqId.14006-36 Q14749 GNMT Glycine N-methyltransferase GNMT +SeqId.8909-77 P46926 GNPI1 Glucosamine-6-phosphate isomerase 1 GNPDA1 +SeqId.13954-9 Q96EK6 GNA1 Glucosamine 6-phosphate N-acetyltransferase GNPNAT1 +SeqId.10666-7 Q9UJJ9 GNPTG N-acetylglucosamine-1-phosphotransferase subunit gamma GNPTG +SeqId.5627-53 P01148 GON1 Progonadoliberin-1 GNRH1 +SeqId.10708-3 O43555 GON2 Progonadoliberin-2 GNRH2 +SeqId.3616-3 P15586 GNS N-acetylglucosamine-6-sulfatase GNS +SeqId.19174-141 Q7Z5G4 GOGA7 Golgin subfamily A member 7 GOLGA7 +SeqId.17456-53 Q8NBJ4 GOLM1 Golgi membrane protein 1 GOLM1 +SeqId.8983-7 Q8NBJ4 GOLM1 Golgi membrane protein 1 GOLM1 +SeqId.7247-1 Q5T7V8 GORAB RAB6-interacting golgin GORAB +SeqId.7805-52 O95249 GOS-28 Golgi SNAP receptor complex member 1 GOSR1 +SeqId.10426-21 O14653 GOSR2 Golgi SNAP receptor complex member 2 GOSR2 +SeqId.4912-17 P17174 GOT1 "Aspartate aminotransferase, cytoplasmic" GOT1 +SeqId.4990-87 P07359 GP1BA Platelet glycoprotein Ib alpha chain GP1BA +SeqId.7185-29 P40197 GPV Platelet glycoprotein V GP5 +SeqId.3194-36 Q9HCN6 GPVI Platelet glycoprotein VI GP6 +SeqId.8697-38 P35052 Glypican 1 Glypican-1 GPC1 +SeqId.3315-15 Q8N158 GPC2 Glypican-2 GPC2 +SeqId.4842-62 P51654 Glypican 3 Glypican-3 GPC3 +SeqId.18892-48 O75487 GPC4 Glypican-4 GPC4 +SeqId.4991-12 P78333 GPC5 Glypican-5 GPC5 +SeqId.5350-14 Q9Y625 GPC6 Glypican-6 GPC6 +SeqId.12786-61 Q9NPB8 GDE5 Glycerophosphocholine phosphodiesterase GPCPD1 GPCPD1 +SeqId.13697-51 P21695 GPDA "Glycerol-3-phosphate dehydrogenase [NAD(+)], cytoplasmic" GPD1 +SeqId.12420-10 Q8N335 GPD1L Glycerol-3-phosphate dehydrogenase 1-like protein GPD1L +SeqId.6395-58 Q96T91 GPHA2 Glycoprotein hormone alpha-2 GPHA2 +SeqId.4272-46 P06744 PHI Glucose-6-phosphate isomerase GPI +SeqId.16599-38 Q9HCN4 GPN1 GPN-loop GTPase 1 GPN1 +SeqId.8289-8 Q14956 GPNMB Transmembrane glycoprotein NMB GPNMB +SeqId.8606-39 Q14956 GPNMB Transmembrane glycoprotein NMB GPNMB +SeqId.11371-1 Q96P66 GP101 Probable G-protein coupled receptor 101 GPR101 +SeqId.12963-1 Q5VW38 GP107 Protein GPR107 GPR107 +SeqId.11465-4 Q8IZ08 GP135 Probable G-protein coupled receptor 135 GPR135 +SeqId.12766-33 Q7Z601 GP142 Probable G-protein coupled receptor 142 GPR142 +SeqId.13540-1 Q8NDV2 GPR26 G-protein coupled receptor 26 GPR26 +SeqId.18893-26 Q9Y653 GPR56 Adhesion G-protein coupled receptor G1 GPR56 +SeqId.10767-52 Q8IZP9 GPR64 G-protein coupled receptor 64 GPR64 +SeqId.12503-5 Q15743 SPR1 Ovarian cancer G-protein coupled receptor 1 GPR68 +SeqId.16015-19 P24298 ALT Alanine aminotransferase 1 GPT +SeqId.15591-28 P07203 Glutathione peroxidase Glutathione peroxidase 1 GPX1 +SeqId.18894-1 P18283 GPX2 Glutathione peroxidase 2 GPX2 +SeqId.9475-22 O75715 GPX5 Epididymal secretory glutathione peroxidase GPX5 +SeqId.8345-27 Q96SL4 GPX7 Glutathione peroxidase 7 GPX7 +SeqId.8336-267 Q8IYS0 GRM1C GRAM domain-containing protein 1C GRAMD1C +SeqId.8842-16 Q8IYS0 GRM1C GRAM domain-containing protein 1C GRAMD1C +SeqId.12820-1 Q13588 GRAP GRB2-related adapter protein GRAP +SeqId.16074-12 O75791 GRB2-related adapter protein 2 GRB2-related adapter protein 2 GRAP2 +SeqId.5265-12 O75791 GRB2-related adapter protein 2 GRB2-related adapter protein 2 GRAP2 +SeqId.11358-15 Q13322 GRB10 Growth factor receptor-bound protein 10 GRB10 +SeqId.13628-58 Q14449 GRB14 Growth factor receptor-bound protein 14 GRB14 +SeqId.5464-52 P62993 GRB2 adapter protein Growth factor receptor-bound protein 2 GRB2 +SeqId.11281-6 Q14451 GRB7 Growth factor receptor-bound protein 7 GRB7 +SeqId.18878-15 O60565 GREM1 Gremlin-1 GREM1 +SeqId.5598-3 Q9H772 GREM2 Gremlin-2 GREM2 +SeqId.18295-102 Q9UBQ7 GRHPR Glyoxylate reductase/hydroxypyruvate reductase GRHPR +SeqId.10760-107 P48058 GRIA4 Glutamate receptor 4 GRIA4 +SeqId.13493-5 Q9ULK0 GRID1 "Glutamate receptor ionotropic, delta-1" GRID1 +SeqId.12758-47 O43424 GRID2 "Glutamate receptor ionotropic, delta-2" GRID2 +SeqId.4992-49 P28799 GRN Granulins GRN +SeqId.5897-58 P07492 Gastrin-releasing peptide Gastrin-releasing peptide GRP +SeqId.8400-74 P07492 Gastrin-releasing peptide Gastrin-releasing peptide GRP +SeqId.7113-1 Q9HAV7 GRPE1 "GrpE protein homolog 1, mitochondrial" GRPEL1 +SeqId.3441-64 P49840 GSK-3 alpha Glycogen synthase kinase-3 alpha GSK3A +SeqId.3441-64 P49840 GSK-3 alpha Glycogen synthase kinase-3 alpha GSK3A +SeqId.12849-25 Q9P0R6 GSKIP GSK3-beta interaction protein GSKIP +SeqId.16607-78 P06396 Gelsolin Gelsolin GSN +SeqId.4775-34 P06396 Gelsolin Gelsolin GSN +SeqId.19273-3 P00390 Glutathione reductase "Glutathione reductase, mitochondrial" GSR +SeqId.15526-33 P48637 GSHB Glutathione synthetase GSS +SeqId.17138-8 P08263 GST A1-1 Glutathione S-transferase A1 GSTA1 +SeqId.4993-16 Q16772 GSTA3 Glutathione S-transferase A3 GSTA3 +SeqId.14645-253 O15217 GSTA4 Glutathione S-transferase A4 GSTA4 +SeqId.13474-40 Q9Y2Q3 GSTK1 Glutathione S-transferase kappa 1 GSTK1 +SeqId.15395-15 P09488 GST M1-1 Glutathione S-transferase Mu 1 GSTM1 +SeqId.9748-31 P21266 GSTM3-3 Glutathione S-transferase Mu 3 GSTM3 +SeqId.18895-54 Q03013 GSTM4 Glutathione S-transferase Mu 4 GSTM4 +SeqId.12436-84 P78417 GST omega-1 Glutathione S-transferase omega-1 GSTO1 +SeqId.4911-49 P09211 Glutathione S-transferase Pi Glutathione S-transferase P GSTP1 +SeqId.19230-12 P30711 GSTT1 Glutathione S-transferase theta-1 GSTT1 +SeqId.11273-176 P0CG30 GSTT2 Glutathione S-transferase theta-2B GSTT2B +SeqId.16872-248 O43708 MAAI Maleylacetoacetate isomerase GSTZ1 +SeqId.13609-11 P78347 GTF2I General transcription factor II-I GTF2I +SeqId.10008-43 P43080 GUC1A Guanylyl cyclase-activating protein 1 GUCA1A +SeqId.6223-5 Q16661 GUC2B Guanylate cyclase activator 2B GUCA2B +SeqId.17325-10 Q16774 KGUA Guanylate kinase GUK1 +SeqId.19180-38 Q9UBP9 GULP1 PTB domain-containing engulfment adapter protein 1 GULP1 +SeqId.15562-24 P08236 BGLR Beta-glucuronidase GUSB +SeqId.8229-1 Q4G148 GXLT1 Glucoside xylosyltransferase 1 GXYLT1 +SeqId.3440-7 P12544 granzyme A Granzyme A GZMA +SeqId.4133-54 P10144 Granzyme B Granzyme B GZMB +SeqId.3373-5 P20718 Granzyme H Granzyme H GZMH +SeqId.9545-156 P49863 Granzyme K Granzyme K GZMK +SeqId.5704-74 P51124 Granzyme M Granzyme M GZMM +SeqId.12709-63 Q92522 H1X Histone H1x H1FX +SeqId.4163-5 P0C0S5 Histone H2A.z Histone H2A.z H2AFZ +SeqId.7161-25 O95479 G6PE GDH/6PGL endoplasmic bifunctional protein H6PD +SeqId.5861-78 P46952 3HAO "3-hydroxyanthranilate 3,4-dioxygenase" HAAO +SeqId.10815-2 Q5JVS0 HABP4 Intracellular hyaluronan-binding protein 4 HABP4 +SeqId.17739-1 Q16836 HCDH "Hydroxyacyl-coenzyme A dehydrogenase, mitochondrial" HADH +SeqId.19267-14 Q16775 GLO2 "Hydroxyacylglutathione hydrolase, mitochondrial" HAGH +SeqId.3504-58 P81172 LEAP-1 Hepcidin HAMP +SeqId.17768-50 Q9UJM8 HAOX1 Hydroxyacid oxidase 1 HAO1 +SeqId.3196-6 P10915 HPLN1 Hyaluronan and proteoglycan link protein 1 HAPLN1 +SeqId.6455-52 Q86UW8 HPLN4 Hyaluronan and proteoglycan link protein 4 HAPLN4 +SeqId.17450-51 P12081 Histidyl-tRNA synthetase "Histidine--tRNA ligase, cytoplasmic" HARS +SeqId.19327-31 O14929 Hat1 Histone acetyltransferase type B catalytic subunit HAT1 +SeqId.9021-1 Q96D42 TIM-1 Hepatitis A virus cellular receptor 1 HAVCR1 +SeqId.11481-25 Q8TDQ0 TIMD3 Hepatitis A virus cellular receptor 2 HAVCR2 +SeqId.5134-52 Q8TDQ0 TIMD3 Hepatitis A virus cellular receptor 2 HAVCR2 +SeqId.4915-64 "P69905, P68871" Hemoglobin Hemoglobin HBA1 HBB +SeqId.4915-64 "P69905, P68871" Hemoglobin Hemoglobin HBA1 HBB +SeqId.17137-160 P68871 Beta-globin Hemoglobin subunit beta HBB +SeqId.6992-67 P02042 HBD Hemoglobin subunit delta HBD +SeqId.14094-29 Q99075 HB-EGF Heparin-binding EGF-like growth factor HBEGF +SeqId.18198-51 P09105 HBAT Hemoglobin subunit theta-1 HBQ1 +SeqId.6919-3 P02008 HBAZ Hemoglobin subunit zeta HBZ +SeqId.13495-48 Q8TDS4 HCAR2 Hydroxycarboxylic acid receptor 2 HCAR2 +SeqId.3374-49 P08631 HCK Tyrosine-protein kinase HCK HCK +SeqId.12774-12 O60741 HCN1 Potassium/sodium hyperpolarization-activated cyclic nucleotide-gated channel 1 HCN1 +SeqId.18897-31 Q92769 HDAC2 Histone deacetylase 2 HDAC2 +SeqId.2859-69 Q9BY41 HDAC8 Histone deacetylase 8 HDAC8 +SeqId.16758-96 P51858 HDGF Hepatoma-derived growth factor HDGF +SeqId.8953-47 P51858 HDGF Hepatoma-derived growth factor HDGF +SeqId.18898-36 Q5TGJ6 HDGL1 Hepatoma-derived growth factor-like protein 1 HDGFL1 +SeqId.4553-65 Q7Z4V5 HDGR2 Hepatoma-derived growth factor-related protein 2 HDGFRP2 +SeqId.18899-82 Q9Y3E1 HDGR3 Hepatoma-derived growth factor-related protein 3 HDGFRP3 +SeqId.13472-35 Q9H0R4 HDHD2 Haloacid dehalogenase-like hydrolase domain-containing protein 2 HDHD2 +SeqId.19482-11 Q9BSH5 HDHD3 Haloacid dehalogenase-like hydrolase domain-containing protein 3 HDHD3 +SeqId.13570-43 Q00341 VIGLN Vigilin HDLBP +SeqId.18225-13 Q9NRV9 HEBP1 Heme-binding protein 1 HEBP1 +SeqId.12669-30 Q76N89 HECW1 E3 ubiquitin-protein ligase HECW1 HECW1 +SeqId.8810-26 Q14CZ8 HEPACAM Hepatocyte cell adhesion molecule HEPACAM +SeqId.9116-28 A8MVW5 HECA2 HEPACAM family member 2 HEPACAM2 +SeqId.6354-13 Q6MZM0 HPHL1 Hephaestin-like protein 1 HEPHL1 +SeqId.12705-9 Q15751 HERC1 Probable E3 ubiquitin-protein ligase HERC1 HERC1 +SeqId.7860-9 Q5GLZ8 HERC4 Probable E3 ubiquitin-protein ligase HERC4 HERC4 +SeqId.12934-1 Q9UII4 HERC5 E3 ISG15--protein ligase HERC5 HERC5 +SeqId.9779-63 Q9BSE4 HERP2 Homocysteine-responsive endoplasmic reticulum-resident ubiquitin-like domain member 2 protein HERPUD2 +SeqId.15470-11 P07686 Hexosaminidase B Beta-hexosaminidase subunit beta HEXB +SeqId.15596-7 O94992 HEXI1 Protein HEXIM1 HEXIM1 +SeqId.14205-6 Q96MH2 HEXI2 Protein HEXIM2 HEXIM2 +SeqId.3332-57 Q6ZVN8 RGM-C Hemojuvelin HFE2 +SeqId.9832-33 Q93099 HGD "Homogentisate 1,2-dioxygenase" HGD +SeqId.2681-23 P14210 HGF Hepatocyte growth factor HGF +SeqId.3617-80 Q04756 HGFA Hepatocyte growth factor activator HGFAC +SeqId.13644-30 O14964 HGS Hepatocyte growth factor-regulated tyrosine kinase substrate HGS +SeqId.10833-64 Q96QV1 HHIP Hedgehog-interacting protein HHIP +SeqId.14132-21 Q9UM44 HHLA2 HERV-H LTR-associating protein 2 HHLA2 +SeqId.4693-72 P31937 3HIDH "3-hydroxyisobutyrate dehydrogenase, mitochondrial" HIBADH +SeqId.12396-19 Q6NVY1 HIBCH "3-hydroxyisobutyryl-CoA hydrolase, mitochondrial" HIBCH +SeqId.13089-6 Q16665 HIF-1a Hypoxia-inducible factor 1-alpha HIF1A +SeqId.17199-43 Q9NWT6 HIF1N Hypoxia-inducible factor 1-alpha inhibitor HIF1AN +SeqId.5900-11 P49773 HINT1 Histidine triad nucleotide-binding protein 1 HINT1 +SeqId.5612-16 Q9BX68 HINT2 "Histidine triad nucleotide-binding protein 2, mitochondrial" HINT2 +SeqId.19329-31 Q9H422 HIPK3 Homeodomain-interacting protein kinase 3 HIPK3 +SeqId.2987-37 P16403 Histone H1.2 Histone H1.2 HIST1H1C +SeqId.14146-92 P68431 H31 Histone H3.1 HIST1H3A +SeqId.14143-8 Q16778 H2B2E Histone H2B type 2-E HIST2H2BE +SeqId.14144-3 Q7L7L0 H2A3 Histone H2A type 3 HIST3H2A +SeqId.18823-52 Q8N257 H2B3B Histone H2B type 3-B HIST3H2BB +SeqId.13131-5 P19367 HXK1 Hexokinase-1 HK1 +SeqId.13130-150 P52789 HXK2 Hexokinase-2 HK2 +SeqId.19518-12 P52790 HXK3 Hexokinase-3 HK3 +SeqId.7757-5 P01906 DQA2 "HLA class II histocompatibility antigen, DQ alpha 2 chain" HLA-DQA2 +SeqId.6962-5 P79483 DRB3 "HLA class II histocompatibility antigen, DR beta 3 chain" HLA-DRB3 +SeqId.19636-23 P17693 HLA-G "HLA class I histocompatibility antigen, alpha chain G" HLA-G +SeqId.11530-37 P08397 HEM3 Porphobilinogen deaminase HMBS +SeqId.12712-9 Q9NP66 HM20A High mobility group protein 20A HMG20A +SeqId.11551-16 Q9P0W2 HM20B SWI/SNF-related matrix-associated actin-dependent regulator of chromatin subfamily E member 1-related HMG20B +SeqId.16536-3 P17096 HMGA1 High mobility group protein HMG-I/HMG-Y HMGA1 +SeqId.19516-10 P52926 HMGA2 High mobility group protein HMGI-C HMGA2 +SeqId.2524-56 P09429 HMG-1 High mobility group protein B1 HMGB1 +SeqId.6913-189 P26583 HMG-2 High mobility group protein B2 HMGB2 +SeqId.12775-6 O15347 HMGB3 High mobility group protein B3 HMGB3 +SeqId.5230-99 P04035 HMGR 3-hydroxy-3-methylglutaryl-coenzyme A reductase HMGCR +SeqId.13496-19 Q01581 HMCS1 "Hydroxymethylglutaryl-CoA synthase, cytoplasmic" HMGCS1 +SeqId.13704-5 P54868 HMCS2 "Hydroxymethylglutaryl-CoA synthase, mitochondrial" HMGCS2 +SeqId.9187-2 P05114 HMGN1 Non-histone chromosomal protein HMG-14 HMGN1 +SeqId.13544-9 Q92619 HMHA1 Rho GTPase-activating protein 45 HMHA1 +SeqId.17398-55 P09601 HO-1 Heme oxygenase 1 HMOX1 +SeqId.2622-18 P30519 HO-2 Heme oxygenase 2 HMOX2 +SeqId.19335-2 Q9UK76 HN1 Hematological and neurological expressed 1 protein HN1 +SeqId.11193-27 P20823 HNF1A Hepatocyte nuclear factor 1-alpha HNF1A +SeqId.10041-3 P41235 HNF4A Hepatocyte nuclear factor 4-alpha HNF4A +SeqId.12466-7 P09651 ROA1 Heterogeneous nuclear ribonucleoprotein A1 HNRNPA1 +SeqId.5351-52 P22626 hnRNP A2/B1 Heterogeneous nuclear ribonucleoproteins A2/B1 HNRNPA2B1 +SeqId.8894-80 Q99729 hnRNP A/B Heterogeneous nuclear ribonucleoprotein A/B HNRNPAB +SeqId.11429-80 P07910 hnRNP C1/C2 Heterogeneous nuclear ribonucleoproteins C1/C2 HNRNPC +SeqId.18348-89 Q14103 HNRPD Heterogeneous nuclear ribonucleoprotein D0 HNRNPD +SeqId.10852-114 O14979 HNRDL Heterogeneous nuclear ribonucleoprotein D-like HNRNPDL +SeqId.9764-79 P52597 HNRPF Heterogeneous nuclear ribonucleoprotein F HNRNPF +SeqId.14309-8 P31943 HNRH1 Heterogeneous nuclear ribonucleoprotein H HNRNPH1 +SeqId.19333-4 P61978 hnRNP K Heterogeneous nuclear ribonucleoprotein K HNRNPK +SeqId.12783-29 P52272 HNRPM Heterogeneous nuclear ribonucleoprotein M HNRNPM +SeqId.13512-28 O43390 HNRPR Heterogeneous nuclear ribonucleoprotein R HNRNPR +SeqId.10024-44 Q86XE5 HOGA1 "4-hydroxy-2-oxoglutarate aldolase, mitochondrial" HOGA1 +SeqId.19229-92 Q86YM7 HOME1 Homer protein homolog 1 HOMER1 +SeqId.12685-57 Q9NSB8 HOME2 Homer protein homolog 2 HOMER2 +SeqId.19196-73 Q9BPY8 HOP Homeodomain-only protein HOPX +SeqId.3054-3 P00738 "Haptoglobin, Mixed Type" Haptoglobin HP +SeqId.7905-30 P00738 HPT Haptoglobin isoform 2 HP +SeqId.17791-25 P37235 HPCL1 Hippocalcin-like protein 1 HPCAL1 +SeqId.17509-6 P32754 HPPD 4-hydroxyphenylpyruvate dioxygenase HPD +SeqId.4995-16 P15428 HPG- 15-hydroxyprostaglandin dehydrogenase [NAD(+)] HPGD +SeqId.12549-33 O60760 PTGD2 Hematopoietic prostaglandin D synthase HPGDS +SeqId.19290-5 P00492 HPRT Hypoxanthine-guanine phosphoribosyltransferase HPRT1 +SeqId.5604-30 Q9Y251 HPSE Heparanase HPSE +SeqId.15347-12 P02790 Hemopexin Hemopexin HPX +SeqId.18900-37 P01112 H-ras (WT) GTPase HRas HRAS +SeqId.7822-11 Q9NWW9 HRSL2 HRAS-like suppressor 2 HRASLS2 +SeqId.6584-1 P23327 SRCH Sarcoplasmic reticulum histidine-rich calcium-binding protein HRC +SeqId.4996-66 P04196 HRG Histidine-rich glycoprotein HRG +SeqId.8008-28 O00198 HRK Activator of apoptosis harakiri HRK +SeqId.14636-25 P52758 Ribonuclease UK114 Ribonuclease UK114 HRSP12 +SeqId.15497-9 O14792 HS3S1 Heparan sulfate glucosamine 3-O-sulfotransferase 1 HS3ST1 +SeqId.8268-98 Q9Y663 HS3SA Heparan sulfate glucosamine 3-O-sulfotransferase 3A1 HS3ST3A1 +SeqId.6986-17 Q9Y662 HS3SB Heparan sulfate glucosamine 3-O-sulfotransferase 3B1 HS3ST3B1 +SeqId.19370-30 Q9Y661 HS3S4 Heparan sulfate glucosamine 3-O-sulfotransferase 4 HS3ST4 +SeqId.8998-15 Q9Y661 HS3S4 Heparan sulfate glucosamine 3-O-sulfotransferase 4 HS3ST4 +SeqId.10731-10 Q8IZT8 HS3S5 Heparan sulfate glucosamine 3-O-sulfotransferase 5 HS3ST5 +SeqId.5465-32 O60243 H6ST1 Heparan-sulfate 6-O-sulfotransferase 1 HS6ST1 +SeqId.13524-25 Q96MM7 H6ST2 Heparan-sulfate 6-O-sulfotransferase 2 HS6ST2 +SeqId.18896-23 Q8IZP7 H6ST3 Heparan-sulfate 6-O-sulfotransferase 3 HS6ST3 +SeqId.19316-2 Q8IWL3 HSC20 "Iron-sulfur cluster co-chaperone protein HscB, mitochondrial" HSCB +SeqId.4708-3 P14061 17-beta-HSD 1 Estradiol 17-beta-dehydrogenase 1 HSD17B1 +SeqId.4217-49 Q99714 ERAB 3-hydroxyacyl-CoA dehydrogenase type-2 HSD17B10 +SeqId.17397-8 Q8NBQ5 DHB11 Estradiol 17-beta-dehydrogenase 11 HSD17B11 +SeqId.13972-4 Q9BPX1 DHB14 17-beta-hydroxysteroid dehydrogenase 14 HSD17B14 +SeqId.8272-22 P56937 DHB7 3-keto-steroid reductase HSD17B7 +SeqId.9929-16 P56937 DHB7 3-keto-steroid reductase HSD17B7 +SeqId.19491-11 Q92506 DHB8 Estradiol 17-beta-dehydrogenase 8 HSD17B8 +SeqId.11616-9 Q00613 HSF1 Heat shock factor protein 1 HSF1 +SeqId.19139-3 O75031 HSF2B Heat shock factor 2-binding protein HSF2BP +SeqId.2625-53 P07900 HSP 90a Hsp90alpha HSP90AA1 +SeqId.2625-53 P07900 HSP 90a Hsp90alpha HSP90AA1 +SeqId.5467-15 P08238 HSP 90b Heat shock protein HSP 90-beta HSP90AB1 +SeqId.6393-63 P14625 Endoplasmin Endoplasmin HSP90B1 +SeqId.17515-6 P48723 STCH Heat shock 70 kDa protein 13 HSPA13 +SeqId.4124-24 P0DMV8 HSP 70 Heat shock 70 kDa protein 1A HSPA1A +SeqId.18901-26 P0DMV9 HS71B Heat shock 70 kDa protein 1B HSPA1B +SeqId.12041-33 P34931 HS71L Heat shock 70 kDa protein 1-like HSPA1L +SeqId.16588-10 P11021 BiP 78 kDa glucose-regulated protein HSPA5 +SeqId.13672-3 P17066 HSP76 Heat shock 70 kDa protein 6 HSPA6 +SeqId.5903-91 P11142 HSP70 protein 8 Heat shock cognate 71 kDa protein HSPA8 +SeqId.13492-44 P38646 HSPA9B "Stress-70 protein, mitochondrial" HSPA9 +SeqId.11103-24 P04792 HSP 27 Heat shock protein beta-1 HSPB1 +SeqId.19127-1 O14558 HSPB6 Heat shock protein beta-6 HSPB6 +SeqId.18236-3 Q3ZCW2 LEGL Galectin-related protein HSPC159 +SeqId.2682-68 P10809 HSP 60 "60 kDa heat shock protein, mitochondrial" HSPD1 +SeqId.17150-8 P61604 HSP 10 "10 kDa heat shock protein, mitochondrial" HSPE1 +SeqId.15626-223 P98160 Perlecan Basement membrane-specific heparan sulfate proteoglycan core protein HSPG2 +SeqId.17704-74 Q92598 HS105 Heat shock protein 105 kDa HSPH1 +SeqId.10630-5 Q9BUP3 HTAI2 Oxidoreductase HTATIP2 HTATIP2 +SeqId.7753-21 Q9BUP3 HTAI2 Oxidoreductase HTATIP2 HTATIP2 +SeqId.10608-9 P15515 HIS1 Histatin-1 HTN1 +SeqId.10603-1 P15516 HIS3 Histatin-3 HTN3 +SeqId.13556-28 P28223 5HT2A 5-hydroxytryptamine receptor 2A HTR2A +SeqId.13561-5 P50406 5HT6R 5-hydroxytryptamine receptor 6 HTR6 +SeqId.13547-5 P34969 5HT7R 5-hydroxytryptamine receptor 7 HTR7 +SeqId.15594-47 Q92743 HTRA1 Serine protease HTRA1 HTRA1 +SeqId.3317-33 O43464 HTRA2 "Serine protease HTRA2, mitochondrial" HTRA2 +SeqId.8309-12 Q12794 HYAL1 Hyaluronidase-1 HYAL1 +SeqId.19639-53 P10997 IAPP Islet amyloid polypeptide IAPP +SeqId.12815-9 P41252 SYIC "Isoleucine--tRNA ligase, cytoplasmic" IARS +SeqId.3415-61 P21815 BSP Bone sialoprotein 2 IBSP +SeqId.4342-10 P05362 sICAM-1 Intercellular adhesion molecule 1 ICAM1 +SeqId.5486-73 P13598 sICAM-2 Intercellular adhesion molecule 2 ICAM2 +SeqId.2649-77 P32942 sICAM-3 Intercellular adhesion molecule 3 ICAM3 +SeqId.6550-4 Q14773 ICAM4 Intercellular adhesion molecule 4 ICAM4 +SeqId.5124-69 Q9UMF0 sICAM-5 Intercellular adhesion molecule 5 ICAM5 +SeqId.8245-27 Q9UMF0 sICAM-5 Intercellular adhesion molecule 5 ICAM5 +SeqId.5061-27 O75144 B7-H2 ICOS ligand ICOSLG +SeqId.6380-23 Q14197 ICT1 "Peptidyl-tRNA hydrolase ICT1, mitochondrial" ICT1 +SeqId.15402-2 P41134 ID-1 DNA-binding protein inhibitor ID-1 ID1 +SeqId.15403-53 Q02363 ID2 DNA-binding protein inhibitor ID-2 ID2 +SeqId.3197-70 P14735 IDE Insulin-degrading enzyme IDE +SeqId.18338-26 O75874 IDH Isocitrate dehydrogenase [NADP] cytoplasmic IDH1 +SeqId.19275-68 P51553 IDH3G "Isocitrate dehydrogenase [NAD] subunit gamma, mitochondrial" IDH3G +SeqId.17712-7 Q13907 IDI1 Isopentenyl-diphosphate Delta-isomerase 1 IDI1 +SeqId.17832-12 Q9BXS1 IDI2 Isopentenyl-diphosphate delta-isomerase 2 IDI2 +SeqId.9759-13 P14902 INDO "Indoleamine 2,3-dioxygenase 1" IDO1 +SeqId.3198-4 P22304 IDS Iduronate 2-sulfatase IDS +SeqId.3169-70 P35475 IDUA Alpha-L-iduronidase IDUA +SeqId.9786-310 P46695 IEX1 Radiation-inducible immediate-early gene IEX-1 IER3 +SeqId.12893-159 Q16666 IP16 Gamma-interferon-inducible protein 16 IFI16 +SeqId.13940-19 Q16666 IP16 Gamma-interferon-inducible protein 16 IFI16 +SeqId.9853-3 P09913 IFIT2 Interferon-induced protein with tetratricopeptide repeats 2 IFIT2 +SeqId.13642-90 O14879 CIG49 Interferon-induced protein with tetratricopeptide repeats 3 IFIT3 +SeqId.18389-11 P01562 IFNA1 Interferon alpha-1/13 IFNA1 +SeqId.14128-121 P01566 IFN10 Interferon alpha-10 IFNA10 +SeqId.7180-114 P01570 IFN14 Interferon alpha-14 IFNA14 +SeqId.6421-52 P05015 IFN16 Interferon alpha-16 IFNA16 +SeqId.3497-13 P01563 IFN-aA Interferon alpha-2 IFNA2 +SeqId.15404-3 P01568 IFN21 Interferon alpha-21 IFNA21 +SeqId.15405-23 P05014 IFNA4 Interferon alpha-4 IFNA4 +SeqId.6210-100 P01569 IFNA5 Interferon alpha-5 IFNA5 +SeqId.5714-88 P05013 IFNA6 Interferon alpha-6 IFNA6 +SeqId.14129-1 P01567 IFNA7 Interferon alpha-7 IFNA7 +SeqId.6214-84 P32881 IFNA8 Interferon alpha-8 IFNA8 +SeqId.9183-7 P17181 IFN-a/b R1 Interferon alpha/beta receptor 1 IFNAR1 +SeqId.14127-240 P01574 IFN-b Interferon beta IFNB1 +SeqId.15346-31 P01579 IFN-g Interferon gamma IFNG +SeqId.5825-49 P15260 IFN-g R1 Interferon gamma receptor 1 IFNGR1 +SeqId.8818-13 P38484 INGR2 Interferon gamma receptor 2 IFNGR2 +SeqId.9180-6 P38484 INGR2 Interferon gamma receptor 2 IFNGR2 +SeqId.4396-54 Q8IU54 IFN-lambda 1 Interferon lambda-1 IFNL1 +SeqId.4397-26 Q8IZJ0 IFN-lambda 2 Interferon lambda-2 IFNL2 +SeqId.5713-9 Q8IZI9 IFN-lambda 3 Interferon lambda-3 IFNL3 +SeqId.7192-37 Q8IU57 CRF2-12 Interferon lambda receptor 1 IFNLR1 +SeqId.7196-21 P05000 IFN-w Interferon omega-1 IFNW1 +SeqId.12358-6 P78318 IGBP1 Immunoglobulin-binding protein 1 IGBP1 +SeqId.11952-1 Q8IVU1 IGDC3 Immunoglobulin superfamily DCC subclass member 3 IGDCC3 +SeqId.7118-24 Q8IVU1 IGDC3 Immunoglobulin superfamily DCC subclass member 3 IGDCC3 +SeqId.9793-145 Q8TDY8 IGDC4 Immunoglobulin superfamily DCC subclass member 4 IGDCC4 +SeqId.2952-75 P05019 IGF-I Insulin-like growth factor I IGF1 +SeqId.8406-17 P05019 IGF-I Insulin-like growth factor I IGF1 +SeqId.4232-19 P08069 IGF-I sR Insulin-like growth factor 1 receptor IGF1R +SeqId.15295-81 P01344 IGF-II Insulin-like growth factor II IGF2 +SeqId.16057-6 P11717 IGF-II receptor Cation-independent mannose-6-phosphate receptor IGF2R +SeqId.6605-17 P35858 IGFALS Insulin-like growth factor-binding protein complex acid labile subunit IGFALS +SeqId.2771-35 P08833 IGFBP-1 Insulin-like growth factor-binding protein 1 IGFBP1 +SeqId.8469-41 P18065 IGFBP-2 Insulin-like growth factor-binding protein 2 IGFBP2 +SeqId.2571-12 P17936 IGFBP-3 Insulin-like growth factor-binding protein 3 IGFBP3 +SeqId.2950-57 P22692 IGFBP-4 Insulin-like growth factor-binding protein 4 IGFBP4 +SeqId.19581-15 P24593 IGFBP-5 Insulin-like growth factor-binding protein 5 IGFBP5 +SeqId.14088-38 P24592 IGFBP-6 Insulin-like growth factor-binding protein 6 IGFBP6 +SeqId.3320-49 Q16270 IGFBP-7 Insulin-like growth factor-binding protein 7 IGFBP7 +SeqId.7815-49 Q8WX77 IBPL1 Insulin-like growth factor-binding protein-like 1 IGFBPL1 +SeqId.6961-14 Q6UXB1 IGFL3 Insulin growth factor-like family member 3 IGFL3 +SeqId.7244-16 Q9H665 TM149 IGF-like family receptor 1 IGFLR1 +SeqId.11089-7 P01876 P01877 IgA Immunoglobulin A IGHA1 IGHA2 +SeqId.11089-7 P01876 P01877 IgA Immunoglobulin A IGHA1 IGHA2 +SeqId.4916-2 P01880 IgD Immunoglobulin D IGHD IGK@ IGL@ +SeqId.4135-84 P01854 IgE Immunoglobulin E IGHE IGK@ IGL@ +SeqId.2744-57 P01857 IgG Immunoglobulin G IGHG1 IGHG2 IGHG3 IGHG4 IGK@ IGL@ +SeqId.13230-174 P01859 "IgG2, Kappa" "Ig gamma-2, Kappa" IGHG2 +SeqId.13231-90 P01861 "IgG4, Kappa" "Ig gamma-4, Kappa" IGHG4 +SeqId.3069-52 P01871 IgM Immunoglobulin M IGHM IGJ IGK@ IGL@ +SeqId.15306-20 P01591 IgJ Immunoglobulin J chain IGJ +SeqId.6485-59 P15814 IGLL1 Immunoglobulin lambda-like polypeptide 1 IGLL1 +SeqId.6478-2 A6NGN9 IGLO5 IgLON family member 5 IGLON5 +SeqId.10700-10 Q5DX21 IGS11 Immunoglobulin superfamily member 11 IGSF11 +SeqId.9715-15 O75054 IGSF3 Immunoglobulin superfamily member 3 IGSF3 +SeqId.6984-6 Q969P0 IGSF8 Immunoglobulin superfamily member 8 IGSF8 +SeqId.9060-27 Q9UPX0 TUTLB Protein turtle homolog B IGSF9B +SeqId.19606-28 Q14623 ihh Indian hedgehog protein IHH +SeqId.7207-4 Q13123 RED Protein Red IK +SeqId.2773-50 P22301 IL-10 Interleukin-10 IL10 +SeqId.10344-334 Q13651 IL-10 Ra Interleukin-10 receptor subunit alpha IL10RA +SeqId.8104-21 Q13651 IL-10 Ra Interleukin-10 receptor subunit alpha IL10RA +SeqId.2631-50 Q08334 IL-10 Rb Interleukin-10 receptor subunit beta IL10RB +SeqId.4493-92 P20809 IL-11 Interleukin-11 IL11 +SeqId.18216-22 Q14626 IL-11 RA Interleukin-11 receptor subunit alpha IL11RA +SeqId.10367-62 "P29459, P29460" IL-12 Interleukin-12 IL12A IL12B +SeqId.10367-62 "P29459, P29460" IL-12 Interleukin-12 IL12A IL12B +SeqId.13733-5 P29460 IL-12 p40 Interleukin-12 subunit beta IL12B +SeqId.10365-132 "P29460, Q9NPF7" IL-23 Interleukin-23 IL12B IL23A +SeqId.10365-132 "P29460, Q9NPF7" IL-23 Interleukin-23 IL12B IL23A +SeqId.2632-5 P42701 IL-12 Rb1 Interleukin-12 receptor subunit beta-1 IL12RB1 +SeqId.3815-14 Q99665 IL-12 RB2 Interleukin-12 receptor subunit beta-2 IL12RB2 +SeqId.3072-4 P35225 IL-13 Interleukin-13 IL13 +SeqId.2633-52 P78552 IL-13 Ra1 Interleukin-13 receptor subunit alpha-1 IL13RA1 +SeqId.19568-17 P40933 IL-15 Interleukin-15 IL15 +SeqId.14054-17 Q13261 IL-15 Ra Interleukin-15 receptor subunit alpha IL15RA +SeqId.3445-53 Q13261 IL-15 Ra Interleukin-15 receptor subunit alpha IL15RA +SeqId.2774-10 Q14005 IL-16 Interleukin-16 IL16 +SeqId.9170-24 Q16552 IL-17 Interleukin-17A IL17A +SeqId.3499-77 Q9UHF5 IL-17B Interleukin-17B IL17B +SeqId.9255-5 Q9P0M4 IL-17C Interleukin-17C IL17C +SeqId.4136-40 Q8TAD2 IL-17D Interleukin-17D IL17D +SeqId.14026-24 Q96PD4 IL-17F Interleukin-17F IL17F +SeqId.2992-59 Q96F46 IL-17 sR Interleukin-17 receptor A IL17RA +SeqId.6262-14 Q9NRM6 IL-17B R Interleukin-17 receptor B IL17RB +SeqId.5468-67 Q8NAC3 IL-17 RC Interleukin-17 receptor C IL17RC +SeqId.3376-49 Q8NFM7 IL-17 RD Interleukin-17 receptor D IL17RD +SeqId.5661-15 Q14116 IL-18 Interleukin-18 IL18 +SeqId.3073-51 O95998 IL-18 BPa Interleukin-18-binding protein IL18BP +SeqId.14079-14 Q13478 IL-18 Ra Interleukin-18 receptor 1 IL18R1 +SeqId.2993-1 O95256 IL-18 Rb Interleukin-18 receptor accessory protein IL18RAP +SeqId.3035-80 Q9UHD0 IL-19 Interleukin-19 IL19 +SeqId.4851-25 P01583 IL-1a Interleukin-1 alpha IL1A +SeqId.3037-62 P01584 IL-1b Interleukin-1 beta IL1B +SeqId.17356-34 Q8WWZ1 IL1FA Interleukin-1 family member 10 IL1F10 +SeqId.18375-28 Q9UBH0 IL-1F5 Interleukin-36 receptor antagonist protein IL1F5 +SeqId.2991-9 P14778 IL-1 sRI Interleukin-1 receptor type 1 IL1R1 +SeqId.14133-93 P27930 IL-1 sRII Interleukin-1 receptor type 2 IL1R2 +SeqId.14048-7 Q9NPH3 IL-1 R AcP Interleukin-1 Receptor accessory protein IL1RAP +SeqId.5082-51 Q9NP60 IL-1 sR9 X-linked interleukin-1 receptor accessory protein-like 2 IL1RAPL2 +SeqId.4234-8 Q01638 IL-1 R4 Interleukin-1 receptor-like 1 IL1RL1 +SeqId.2994-71 Q9HB29 IL-1Rrp2 Interleukin-1 receptor-like 2 IL1RL2 +SeqId.5353-89 P18510 IL-1Ra Interleukin-1 receptor antagonist protein IL1RN +SeqId.3070-1 P60568 IL-2 Interleukin-2 IL2 +SeqId.4138-25 Q9NYY1 IL-20 Interleukin-20 IL20 +SeqId.5085-18 Q9UHF4 IL-20 Ra Interleukin-20 receptor subunit alpha IL20RA +SeqId.13435-31 Q6UXL0 IL-20 Rb Interleukin-20 receptor subunit beta IL20RB +SeqId.7124-18 Q9HBE4 IL-21 Interleukin-21 IL21 +SeqId.9366-54 Q9HBE5 IL-21 sR Interleukin-21 receptor IL21R +SeqId.2778-10 Q9GZX6 IL-22 Interleukin-22 IL22 +SeqId.3620-67 Q8N6P7 IL22RA1 Interleukin-22 receptor subunit alpha-1 IL22RA1 +SeqId.5087-5 Q969J5 IL-22BP Interleukin-22 receptor subunit alpha-2 IL22RA2 +SeqId.5088-175 Q5VWK5 IL-23 R Interleukin-23 receptor IL23R +SeqId.3321-2 Q13007 IL24 Interleukin-24 IL24 +SeqId.4137-57 Q9H293 IL-17E Interleukin-25 IL25 +SeqId.16760-2 Q9NPH9 IL-26 Interleukin-26 IL26 +SeqId.2829-19 Q8NEV9 Q14213 IL-27 Interleukin-27 IL27 EBI3 +SeqId.2829-19 Q8NEV9 Q14213 IL-27 Interleukin-27 IL27 EBI3 +SeqId.5132-71 Q6UWB1 TCCR Interleukin-27 receptor subunit alpha IL27RA +SeqId.3151-6 P01589 IL-2 sRa Interleukin-2 receptor subunit alpha IL2RA +SeqId.9343-16 P14784 IL-2 sRb Interleukin-2 receptor subunit beta IL2RB +SeqId.2634-2 P31785 IL-2 sRg Cytokine receptor common subunit gamma IL2RG +SeqId.4717-55 P08700 IL-3 Interleukin-3 IL3 +SeqId.10455-196 Q6EBC2 IL-31 Interleukin-31 IL31 +SeqId.8273-84 Q8NI17 IL31R Interleukin-31 receptor subunit alpha IL31RA +SeqId.9051-13 P24001 IL32 Interleukin-32 IL32 +SeqId.4556-10 Q6ZMJ4 IL-34 Interleukin-34 IL34 +SeqId.14150-7 Q9UHA7 IL-1F6 Interleukin-36 alpha IL36A +SeqId.14149-9 Q9NZH7 IL-1F8 Interleukin-36 beta IL36B +SeqId.9117-4 Q9NZH8 IL-1F9 Interleukin-36 gamma IL36G +SeqId.2723-9 Q9NZH6 IL-1F7 Interleukin-37 IL37 +SeqId.13744-37 P26951 IL-3 Ra Interleukin-3 receptor subunit alpha IL3RA +SeqId.2906-55 P05112 IL-4 Interleukin-4 IL4 +SeqId.3055-54 P24394 IL-4 sR Interleukin-4 receptor subunit alpha IL4R +SeqId.11071-1 P05113 IL-5 Interleukin-5 IL5 +SeqId.13686-2 Q01344 IL-5 Ra Interleukin-5 receptor subunit alpha IL5RA +SeqId.4673-13 P05231 IL-6 Interleukin-6 IL6 +SeqId.15602-43 P08887 IL-6 sRa Interleukin-6 receptor subunit alpha IL6R +SeqId.2620-4 P40189 "gp130, soluble" Interleukin-6 receptor subunit beta IL6ST +SeqId.4140-3 P13232 IL-7 Interleukin-7 IL7 +SeqId.5089-11 P16871 IL-7 Ra Interleukin-7 receptor subunit alpha IL7R +SeqId.5834-18 P15248 IL-9 Interleukin-9 IL9 +SeqId.12665-16 Q12905 ILF2 Interleukin enhancer-binding factor 2 ILF2 +SeqId.12759-47 Q12906 DRBP76 Interleukin enhancer-binding factor 3 ILF3 +SeqId.10053-5 Q13418 ILK1 Integrin-linked protein kinase ILK +SeqId.17796-15 P29218 IMPA1 Inositol monophosphatase 1 IMPA1 +SeqId.12581-39 O14732 IMPA2 Inositol monophosphatase 2 IMPA2 +SeqId.9231-23 Q9NX62 IMPA3 Inositol monophosphatase 3 IMPAD1 +SeqId.5229-90 P20839 IMDH1 Inosine-5'-monophosphate dehydrogenase 1 IMPDH1 +SeqId.5250-53 P12268 IMDH2 Inosine-5'-monophosphate dehydrogenase 2 IMPDH2 +SeqId.11436-6 Q16352 AINX Alpha-internexin INA +SeqId.3888-8 Q9UK53 ING1 Inhibitor of growth protein 1 ING1 +SeqId.17671-58 Q9UNL4 ING4 Inhibitor of growth protein 4 ING4 +SeqId.19622-7 P08476 Activin A Activin A INHBA +SeqId.13738-8 P08476 Inhibin bA chain Inhibin beta A chain INHBA +SeqId.8467-9 P08476 P09529 Activin AB Inhibin beta A chain:Inhibin beta B chain heterodimer INHBA INHBB +SeqId.8467-9 P08476 P09529 Activin AB Inhibin beta A chain:Inhibin beta B chain heterodimer INHBA INHBB +SeqId.18814-21 P08476 P55103 Activin AC Inhibin beta A chain:Inhibin beta C chain heterodimer INHBA INHBC +SeqId.18814-21 P08476 P55103 Activin AC Inhibin beta A chain:Inhibin beta C chain heterodimer INHBA INHBC +SeqId.16746-12 P09529 Activin B Activin B INHBB +SeqId.13676-46 P09529 Inhibin bB chain Inhibin beta B chain INHBB +SeqId.15686-49 P55103 INHBC Inhibin beta C chain INHBC +SeqId.6408-2 P55103 INHBC Inhibin beta C chain INHBC +SeqId.12641-3 P32019 I5P2 "Type II inositol 1,4,5-trisphosphate 5-phosphatase" INPP5B +SeqId.11370-20 Q9NRR6 INP5E 72 kDa inositol polyphosphate 5-phosphatase INPP5E +SeqId.4883-56 P01308 Insulin Insulin INS +SeqId.10663-42 O15503 INSI1 Insulin-induced gene 1 protein INSIG1 +SeqId.5723-4 P51460 INSL3 Insulin-like 3 INSL3 +SeqId.6410-26 Q14641 INSL4 Early placenta insulin-like peptide INSL4 +SeqId.10462-14 Q9Y5Q6 INSL5 Insulin-like peptide INSL5 INSL5 +SeqId.5754-76 Q9Y581 INSL6 Insulin-like peptide INSL6 INSL6 +SeqId.3448-13 P06213 IR Insulin receptor INSR +SeqId.6352-8 P14616 INSRR Insulin receptor-related protein INSRR +SeqId.11934-9 Q68E01 INT3 Integrator complex subunit 3 INTS3 +SeqId.7991-54 Q8N6M8 IQCF1 IQ domain-containing protein F1 IQCF1 +SeqId.13439-6 P0C7M6 IQCF3 IQ domain-containing protein F3 IQCF3 +SeqId.18162-167 Q9NWZ3 IRAK4 Interleukin-1 receptor-associated kinase 4 IRAK4 +SeqId.17462-19 P10914 IRF1 Interferon regulatory factor 1 IRF1 +SeqId.12801-33 P14316 IRF2 Interferon regulatory factor 2 IRF2 +SeqId.17151-84 Q14653 IRF-3 Interferon regulatory factor 3 IRF3 +SeqId.19564-61 Q15306 IRF4 Interferon regulatory factor 4 IRF4 +SeqId.9999-1 O14896 IRF6 Interferon regulatory factor 6 IRF6 +SeqId.12439-67 Q00978 ISGF3 Interferon regulatory factor 9 IRF9 +SeqId.7201-5 Q9H1K1 ISCU "Iron-sulfur cluster assembly enzyme ISCU, mitochondrial" ISCU +SeqId.14151-4 P05161 UCRP Ubiquitin-like protein ISG15 ISG15 +SeqId.11549-6 P61371 ISL1 Insulin gene enhancer protein ISL-1 ISL1 +SeqId.13124-20 Q6UXK2 ISLR2 Immunoglobulin superfamily containing leucine-rich repeat protein 2 ISLR2 +SeqId.8355-80 B1AKI9 ISM1 Isthmin-1 ISM1 +SeqId.9816-37 Q96CN7 ISOC1 Isochorismatase domain-containing protein 1 ISOC1 +SeqId.12434-25 P53990 K0174 IST1 homolog IST1 +SeqId.12551-3 Q96J02 ITCH E3 ubiquitin-protein ligase Itchy homolog ITCH +SeqId.3503-4 "P56199, P05556" Integrin a1b1 Integrin alpha-I: beta-1 complex ITGA1 ITGB1 +SeqId.3503-4 "P56199, P05556" Integrin a1b1 Integrin alpha-I: beta-1 complex ITGA1 ITGB1 +SeqId.15603-20 P17301 Integrin alpha-2 Integrin alpha-2 ITGA2 +SeqId.19574-5 P08514 P05106 gpIIbIIIa Integrin alpha-IIb: beta-3 complex ITGA2B ITGB3 +SeqId.19574-5 P08514 P05106 gpIIbIIIa Integrin alpha-IIb: beta-3 complex ITGA2B ITGB3 +SeqId.6932-42 P08648 ITA5 Integrin alpha-5 ITGA5 +SeqId.11617-1 P20701 LFA-1 alpha-L chain Integrin alpha-L ITGAL +SeqId.4917-62 "P06756, P18084" Integrin aVb5 Integrin alpha-V: beta-5 complex ITGAV ITGB5 +SeqId.4917-62 "P06756, P18084" Integrin aVb5 Integrin alpha-V: beta-5 complex ITGAV ITGB5 +SeqId.12750-9 P05107 LFA-1 beta-2 Integrin beta-2 ITGB2 +SeqId.7755-37 P18084 ITB5 Integrin beta-5 ITGB5 +SeqId.7737-76 P18564 ITB6 Integrin beta-6 ITGB6 +SeqId.11205-10 P26010 Integrin beta-7 Integrin beta-7 ITGB7 +SeqId.7955-195 P19827 ITI heavy chain H1 Inter-alpha-trypsin inhibitor heavy chain H1 ITIH1 +SeqId.9326-33 P19823 ITI heavy chain H2 Inter-alpha-trypsin inhibitor heavy chain H2 ITIH2 +SeqId.7145-1 Q06033 ITIH3 Inter-alpha-trypsin inhibitor heavy chain H3 ITIH3 +SeqId.4811-33 Q14624 ITI heavy chain H4 Inter-alpha-trypsin inhibitor heavy chain H4 ITIH4 +SeqId.8233-2 Q86UX2 ITIH5 Inter-alpha-trypsin inhibitor heavy chain H5 ITIH5 +SeqId.18830-1 Q8WWA0 Omentin Intelectin-1 ITLN1 +SeqId.7765-15 O43736 ITM2A Integral membrane protein 2A ITM2A +SeqId.8086-49 Q9Y287 ITM2B Integral membrane protein 2B ITM2B +SeqId.10560-1 Q9NQX7 ITM2C Integral membrane protein 2C ITM2C +SeqId.9523-34 Q9NQX7 ITM2C Integral membrane protein 2C ITM2C +SeqId.18916-25 Q9BY32 Inosine triphosphatase Inosine triphosphate pyrophosphatase ITPA +SeqId.13473-55 P23677 IP3KA Inositol-trisphosphate 3-kinase A ITPKA +SeqId.12507-16 Q96DU7 IP3KC Inositol-trisphosphate 3-kinase C ITPKC +SeqId.9221-6 Q6GPH6 IPIL1 "Inositol 1,4,5-trisphosphate receptor-interacting protein-like 1" ITPRIPL1 +SeqId.14070-56 Q15811 ITSN1 Intersectin-1 ITSN1 +SeqId.17737-7 P26440 IVD "Isovaleryl-CoA dehydrogenase, mitochondrial" IVD +SeqId.5092-51 P78504 JAG1 Protein jagged-1 JAG1 +SeqId.7754-11 P78504 JAG1 Protein jagged-1 JAG1 +SeqId.5093-47 Q9Y219 JAG2 Protein jagged-2 JAG2 +SeqId.11816-84 O60674 JAK2 Tyrosine-protein kinase JAK2 JAK2 +SeqId.9068-17 Q5VZ66 JKIP3 Janus kinase and microtubule-interacting protein 3 JAKMIP3 +SeqId.2997-8 P57087 JAM-B Junctional adhesion molecule B JAM2 +SeqId.2998-53 Q9BX67 JAM-C Junctional adhesion molecule C JAM3 +SeqId.12623-84 Q92833 JARD2 Protein Jumonji JARID2 +SeqId.18322-15 Q6NYC1 JMJD6 Bifunctional arginine demethylase and lysyl-hydroxylase JMJD6 JMJD6 +SeqId.6940-18 Q9HDC5 JPH1 Junctophilin-1 JPH1 +SeqId.9089-77 Q8WXH2 JPH3 Junctophilin-3 JPH3 +SeqId.9111-40 Q96JJ6 JPH4 Junctophilin-4 JPH4 +SeqId.9038-12 O76095 JTB Protein JTB JTB +SeqId.10356-21 P05412 c-Jun Transcription factor AP-1 JUN +SeqId.19602-36 P17535 jun-D Transcription factor jun-D JUND +SeqId.16768-3 P14923 PLAK Junction plakoglobin JUP +SeqId.19492-5 Q9UBP8 KAAG1 Kidney-associated antigen 1 KAAG1 +SeqId.6603-18 P23352 KALM Anosmin-1 KAL1 +SeqId.19249-18 Q15046 SYK Lysine--tRNA ligase KARS +SeqId.19369-17 Q92830 GCNL2 Histone acetyltransferase KAT2A KAT2A +SeqId.12368-18 Q92831 PCAF Histone acetyltransferase KAT2B KAT2B +SeqId.7144-234 Q96I82 KAZD1 Kazal-type serine protease inhibitor domain-containing protein 1 KAZALD1 +SeqId.13042-7 Q16322 KCA10 Potassium voltage-gated channel subfamily A member 10 KCNA10 +SeqId.10015-119 Q13303 KCAB2 Voltage-gated potassium channel subunit beta-2 KCNAB2 +SeqId.8067-21 Q9Y6H6 KCNE3 Potassium voltage-gated channel subfamily E member 3 KCNE3 +SeqId.8756-41 Q9UJ90 KCE1L Potassium voltage-gated channel subfamily E regulatory beta subunit 5 KCNE5 +SeqId.8908-14 Q9UJ90 KCE1L Potassium voltage-gated channel subfamily E regulatory beta subunit 5 KCNE5 +SeqId.12834-3 Q9H3M0 KCNF1 Potassium voltage-gated channel subfamily F member 1 KCNF1 +SeqId.13525-17 Q8TDN1 KCNG4 Potassium voltage-gated channel subfamily G member 4 KCNG4 +SeqId.13650-11 Q9NZI2 KCIP1 Kv channel-interacting protein 1 KCNIP1 +SeqId.10513-13 Q9Y2W7 CSEN Calsenilin KCNIP3 +SeqId.7011-8 Q6PIL6 KCIP4 Kv channel-interacting protein 4 KCNIP4 +SeqId.8905-20 Q9NPA1 KCMB3 Calcium-activated potassium channel subunit beta-3 KCNMB3 +SeqId.13539-131 Q92952 KCNN1 Small conductance calcium-activated potassium channel protein 1 KCNN1 +SeqId.12473-48 Q9NXV2 KCTD5 BTB/POZ domain-containing protein KCTD5 KCTD5 +SeqId.6611-8 Q6UW63 KDEL1 KDEL motif-containing protein 1 KDELC1 +SeqId.8296-117 Q7Z4H8 KDEL2 KDEL motif-containing protein 2 KDELC2 +SeqId.3651-50 P35968 VEGF sR2 Vascular endothelial growth factor receptor 2 KDR +SeqId.19483-16 Q06136 KDSR 3-ketodihydrosphingosine reductase KDSR +SeqId.12568-14 Q14145 KEAP1 Kelch-like ECH-associated protein 1 KEAP1 +SeqId.8485-7 Q14145 KEAP1 Kelch-like ECH-associated protein 1 KEAP1 +SeqId.7070-25 P23276 KELL Kell blood group glycoprotein KEL +SeqId.10758-2 O60938 KERA Keratocan KERA +SeqId.14603-51 J3QR46 KIAA0040 Uncharacterized protein KIAA0040 KIAA0040 +SeqId.13698-28 Q8IZA0 K319L Dyslexia-associated protein KIAA0319-like protein KIAA0319L +SeqId.9075-121 Q9UPX6 K1024 UPF0258 protein KIAA1024 KIAA1024 +SeqId.8068-43 Q6NSJ0 K1161 Uncharacterized family 31 glucosidase KIAA1161 KIAA1161 +SeqId.8093-13 Q6NSJ0 K1161 Uncharacterized family 31 glucosidase KIAA1161 KIAA1161 +SeqId.12956-40 Q96EK5 KBP KIF1-binding protein KIAA1279 +SeqId.10637-50 Q6UXG2 K1324 UPF0577 protein KIAA1324 KIAA1324 +SeqId.9097-5 Q6UXG2 K1324 UPF0577 protein KIAA1324 KIAA1324 +SeqId.8363-18 A8MWY0 K132L UPF0577 protein KIAA1324-like KIAA1324L +SeqId.7892-132 A2RU67 K1467 Protein FAM234B KIAA1467 +SeqId.9981-18 A2RU67 K1467 Protein FAM234B KIAA1467 +SeqId.11145-72 Q6ZVL6 K154L UPF0606 protein KIAA1549L KIAA1549L +SeqId.10432-3 Q3SXP7 K1644 Uncharacterized protein KIAA1644 KIAA1644 +SeqId.6538-90 Q8IYS2 K2013 Uncharacterized protein KIAA2013 KIAA2013 +SeqId.11672-17 Q96L93 KI16B Kinesin-like protein KIF16B KIF16B +SeqId.9899-28 O43896 KIF1C Kinesin-like protein KIF1C KIF1C +SeqId.12734-112 Q14807 KIF22 Kinesin-like protein KIF22 KIF22 +SeqId.5228-25 Q02241 KIF23 Kinesin-like protein KIF23 KIF23 +SeqId.13961-18 Q9Y496 KIF3A Kinesin-like protein KIF3A KIF3A +SeqId.13476-16 O60870 KIN17 DNA/RNA-binding protein KIN17 KIN +SeqId.17200-50 P43626 KI2L1 Killer cell immunoglobulin-like receptor 2DL1 KIR2DL1 +SeqId.7773-20 P43627 KI2L2 Killer cell immunoglobulin-like receptor 2DL2 KIR2DL2 +SeqId.17153-46 P43628 KI2L3 Killer cell immunoglobulin-like receptor 2DL3 KIR2DL3 +SeqId.5095-21 Q99706 KI2L4 Killer cell immunoglobulin-like receptor 2DL4 KIR2DL4 +SeqId.8000-17 Q8N109 KI2LA Killer cell immunoglobulin-like receptor 2DL5A KIR2DL5A +SeqId.10428-1 P43631 KI2S2 Killer cell immunoglobulin-like receptor 2DS2 KIR2DS2 +SeqId.17152-10 P43632 KI2S4 Killer cell immunoglobulin-like receptor 2DS4 KIR2DS4 +SeqId.18907-97 P43629 KI3L1 Killer cell immunoglobulin-like receptor 3DL1 KIR3DL1 +SeqId.5096-51 P43630 KI3L2 Killer cell immunoglobulin-like receptor 3DL2 KIR3DL2 +SeqId.7944-1 Q8N743 KI3L3 Killer cell immunoglobulin-like receptor 3DL3 KIR3DL3 +SeqId.8045-3 Q8N743 KI3L3 Killer cell immunoglobulin-like receptor 3DL3 KIR3DL3 +SeqId.5097-14 Q14943 KI3S1 Killer cell immunoglobulin-like receptor 3DS1 KIR3DS1 +SeqId.16609-106 Q6UWL6 KIRR2 Kin of IRRE-like protein 2 KIRREL2 +SeqId.4557-61 Q8IZU9 KIRR3 Kin of IRRE-like protein 3 KIRREL3 +SeqId.6606-61 Q15726 KISS1 Metastasis-suppressor KiSS-1 KISS1 +SeqId.2475-1 P10721 SCF sR Mast/stem cell growth factor receptor Kit KIT +SeqId.9377-25 P21583 SCF Kit ligand KITLG +SeqId.15384-15 Q9UEF7 KLOTHO Klotho KL +SeqId.19557-3 Q86Z14 KLOTB Beta-klotho KLB +SeqId.12656-1 Q07866 KLC1 Kinesin light chain 1 KLC1 +SeqId.17850-42 O43474 KLF4 Krueppel-like factor 4 KLF4 +SeqId.12695-62 Q53G59 KLH12 Kelch-like protein 12 KLHL12 +SeqId.12463-7 Q9P2N7 KLH13 Kelch-like protein 13 KLHL13 +SeqId.12625-138 Q8IXQ5 KLHL7 Kelch-like protein 7 KLHL7 +SeqId.6227-1 O43240 kallikrein 10 Kallikrein-10 KLK10 +SeqId.2831-29 Q9UBX7 Kallikrein 11 Kallikrein-11 KLK11 +SeqId.3199-54 Q9UKR0 kallikrein 12 Kallikrein-12 KLK12 +SeqId.11152-46 Q9UKR3 kallikrein 13 Kallikrein-13 KLK13 +SeqId.15544-25 Q9P0G3 kallikrein 14 Kallikrein-14 KLK14 +SeqId.6491-59 Q9H2R5 kallikrein 15 Kallikrein-15 KLK15 +SeqId.8468-19 P07288 PSA Prostate-specific antigen KLK3 +SeqId.2833-20 Q9Y5K2 Kallikrein 4 Kallikrein-4 KLK4 +SeqId.14039-33 Q9Y337 kallikrein 5 Kallikrein-5 KLK5 +SeqId.3201-49 Q9Y337 kallikrein 5 Kallikrein-5 KLK5 +SeqId.3450-4 Q92876 Kallikrein 6 Kallikrein-6 KLK6 +SeqId.3378-49 P49862 Kallikrein 7 Kallikrein-7 KLK7 +SeqId.2834-54 O60259 kallikrein 8 Kallikrein-8 KLK8 +SeqId.5758-49 Q9UKQ9 kallikrein 9 Kallikrein-9 KLK9 +SeqId.4152-58 P03952 Prekallikrein Plasma kallikrein KLKB1 +SeqId.10809-14 Q12918 KLRB1 Killer cell lectin-like receptor subfamily B member 1 KLRB1 +SeqId.5629-58 P26715 NKG2A NKG2-A/NKG2-B type II integral membrane protein KLRC1 +SeqId.11571-75 Q07444 NKG2E NKG2-E type II integral membrane protein KLRC3 +SeqId.7795-14 Q07444 NKG2E NKG2-E type II integral membrane protein KLRC3 +SeqId.10552-88 O43908 NKG2F NKG2-F type II integral membrane protein KLRC4 +SeqId.5098-79 Q9NZS2 KLRF1 Killer cell lectin-like receptor subfamily F member 1 KLRF1 +SeqId.10693-43 A4D1S0 KLRG2 Killer cell lectin-like receptor subfamily G member 2 KLRG2 +SeqId.10762-2 A4D1S0 KLRG2 Killer cell lectin-like receptor subfamily G member 2 KLRG2 +SeqId.14095-1 P26718 NKG2D NKG2-D type II integral membrane protein KLRK1 +SeqId.11402-17 Q8NEZ4 KMT2C Histone-lysine N-methyltransferase 2C KMT2C +SeqId.19631-13 P01042 Kininostatin Kininostatin KNG1 +SeqId.15343-337 P01042 "Kininogen, HMW, Two Chain" "Kininogen, HMW, Two Chain" KNG1 +SeqId.7784-1 P01042 "Kininogen, HMW" Kininogen-1 KNG1 +SeqId.19587-12 P52294 IMA5 Importin subunit alpha-5 KPNA1 +SeqId.2860-19 P52292 Karyopherin-a2 Importin subunit alpha-1 KPNA2 +SeqId.12698-72 O00629 IMA4 Importin subunit alpha-3 KPNA4 +SeqId.13969-24 O60684 IMA7 Importin subunit alpha-7 KPNA6 +SeqId.3887-90 Q14974 IMB1 Importin subunit beta-1 KPNB1 +SeqId.17331-138 Q96MU8 KREM1 Kremen protein 1 KREMEN1 +SeqId.3202-28 Q8NCW0 KREM2 Kremen protein 2 KREMEN2 +SeqId.9931-20 P04264 Keratin-1 "Keratin, type II cytoskeletal 1" KRT1 +SeqId.18905-5 P08779 Keratin-16 "Keratin, type I cytoskeletal 16" KRT16 +SeqId.12923-51 Q04695 Keratin 17 "Keratin, type I cytoskeletal 17" KRT17 +SeqId.5354-11 P05783 Keratin 18 "Keratin, type I cytoskeletal 18" KRT18 +SeqId.15606-19 P08727 Keratin 19 "Keratin, type I cytoskeletal 19" KRT19 +SeqId.12975-11 P35900 Keratin 20 "Keratin, type I cytoskeletal 20" KRT20 +SeqId.11177-16 P13647 K2C5 "Keratin, type II cytoskeletal 5" KRT5 +SeqId.11383-41 P08729 Keratin 7 "Keratin, type II cytoskeletal 7" KRT7 +SeqId.11566-48 Q14CN4 Keratin 72 "Keratin, type II cytoskeletal 72" KRT72 +SeqId.14615-46 Q9BYR9 KRA24 Keratin-associated protein 2-4 KRTAP2-4 +SeqId.5739-75 P60985 KTDAP Keratinocyte differentiation-associated protein KRTDAP +SeqId.4559-64 Q16719 KYNU Kynureninase KYNU +SeqId.4246-40 P32004 NCAM-L1 Neural cell adhesion molecule L1 L1CAM +SeqId.12708-91 Q969R5 LMBL2 Lethal(3)malignant brain tumor-like protein 2 L3MBTL2 +SeqId.7163-26 Q9GZZ8 lacritin Extracellular glycoprotein lacritin LACRT +SeqId.6407-63 O00515 LAD1 Ladinin-1 LAD1 +SeqId.9950-229 P18627 LAG-3 Lymphocyte activation gene 3 protein LAG3 +SeqId.11284-24 Q6GTX8 LAIR1 Leukocyte-associated immunoglobulin-like receptor 1 LAIR1 +SeqId.7130-4 Q6ISS4 LAIR2 Leukocyte-associated immunoglobulin-like receptor 2 LAIR2 +SeqId.18347-15 P24043 P07942 P11047 Laminin-2 Laminin-2 LAMA2 LAMB1 LAMC1 +SeqId.18347-15 P24043 P07942 P11047 Laminin-2 Laminin-2 LAMA2 LAMB1 LAMC1 +SeqId.18347-15 P24043 P07942 P11047 Laminin-2 Laminin-2 LAMA2 LAMB1 LAMC1 +SeqId.6577-64 Q16363 LAMA4 Laminin subunit alpha-4 LAMA4 +SeqId.9580-5 Q13753 Laminin gamma-2 Laminin subunit gamma-2 LAMC2 +SeqId.16902-17 P11279 LAMP1 Lysosome-associated membrane glycoprotein 1 LAMP1 +SeqId.12490-92 Q9UHA4 LTOR3 Ragulator complex protein LAMTOR3 LAMTOR3 +SeqId.13986-6 O43813 LANC1 LanC-like protein 1 LANCL1 +SeqId.12628-31 Q9NS86 LANC2 LanC-like protein 2 LANCL2 +SeqId.13959-7 P28838 LAP Cytosol aminopeptidase LAP3 +SeqId.15610-72 P28838 LAP Cytosol aminopeptidase LAP3 +SeqId.7935-26 O95461 LARGE Glycosyltransferase-like protein LARGE1 LARGE +SeqId.10551-7 O43561 LAT Linker for activation of T-cells family member 1 LAT +SeqId.5613-75 Q9GZY6 NTAL Linker for activation of T-cells family member 2 LAT2 +SeqId.2635-61 Q6UX15 Layilin Layilin LAYN +SeqId.3074-6 P18428 LBP Lipopolysaccharide-binding protein LBP +SeqId.15413-3 P04180 LCAT Phosphatidylcholine-sterol acyltransferase LCAT +SeqId.3452-17 P06239 LCK Tyrosine-protein kinase Lck LCK +SeqId.4560-34 P06239 LCK Tyrosine-protein kinase Lck LCK +SeqId.4237-70 Q9UIC8 LCMT1 Leucine carboxyl methyltransferase 1 LCMT1 +SeqId.11708-2 P31025 LCN1 Lipocalin-1 LCN1 +SeqId.13007-66 Q6JVE6 LCN10 Epididymal-specific lipocalin-10 LCN10 +SeqId.2836-68 P80188 Lipocalin 2 Neutrophil gelatinase-associated lipocalin LCN2 +SeqId.5643-2 Q6JVE9 LCN8 Epididymal-specific lipocalin-8 LCN8 +SeqId.4304-18 Q8N3X6 "transcription factor MLR1, isoform CRA_b" Ligand-dependent nuclear receptor corepressor-like protein LCORL +SeqId.17231-1 P13796 L-plastin Plastin-2 LCP1 +SeqId.9017-58 P09848 LPH Lactase-phlorizin hydrolase LCT +SeqId.10890-135 Q6UWM7 LCTL Lactase-like protein LCTL +SeqId.15414-316 P00338 LDHA L-lactate dehydrogenase A chain LDHA +SeqId.3890-8 P07195 LDH-H 1 L-lactate dehydrogenase B chain LDHB +SeqId.9828-86 P07864 LDHC L-lactate dehydrogenase C chain LDHC +SeqId.13129-40 P01130 LDLR Low-density lipoprotein receptor LDLR +SeqId.9004-24 O15165 CR001 Low-density lipoprotein receptor class A domain-containing protein 4 LDLRAD4 +SeqId.18183-3 Q5SW96 ARH Low density lipoprotein receptor adapter protein 1 LDLRAP1 +SeqId.8378-3 O95751 LDOC1 Protein LDOC1 LDOC1 +SeqId.5708-1 Q969E1 LEAP2 Liver-expressed antimicrobial peptide 2 LEAP2 +SeqId.9928-125 O75829 LECT1 Leukocyte cell-derived chemotaxin 1 LECT1 +SeqId.16763-11 O14960 LECT2 Leukocyte cell-derived chemotaxin-2 LECT2 +SeqId.15503-15 O00292 Lefty-A Left-right determination factor 2 LEFTY2 +SeqId.15503-20 O00292 Lefty-A Left-right determination factor 2 LEFTY2 +SeqId.7154-92 Q6P5S2 CF058 Protein LEG1 homolog LEG1 +SeqId.8040-9 Q68G75 LEMD1 LEM domain-containing protein 1 LEMD1 +SeqId.8484-24 P41159 Leptin Leptin LEP +SeqId.5400-52 P48357 sLeptin R "Leptin receptor, soluble" LEPR +SeqId.6273-58 Q32P28 P3H1 Prolyl 3-hydroxylase 1 LEPRE1 +SeqId.5751-14 Q6P1Q0 HCCR-1 LETM1 domain-containing protein 1 LETMD1 +SeqId.8046-9 P09382 Galectin-1 Galectin-1 LGALS1 +SeqId.19147-6 Q9UHV8 PP13 Galactoside-binding soluble lectin 13 LGALS13 +SeqId.3033-57 P05162 Galectin-2 Galectin-2 LGALS2 +SeqId.3066-12 P17931 Galectin-3 Galectin-3 LGALS3 +SeqId.5000-52 Q08380 LG3BP Galectin-3-binding protein LGALS3BP +SeqId.2982-82 P56470 Galectin-4 Galectin-4 LGALS4 +SeqId.9196-8 P47929 Galectin-7 Galectin-7 LGALS7 +SeqId.4909-68 O00214 Galectin-8 Galectin-8 LGALS8 +SeqId.9197-4 O00182 LEG9 Galectin-9 LGALS9 +SeqId.8003-57 Q8N145 LGI3 Leucine-rich repeat LGI family member 3 LGI3 +SeqId.3622-33 Q99538 LGMN Legumain LGMN +SeqId.16304-6 Q9BXB1 LGR4 Leucine-rich repeat-containing G-protein coupled receptor 4 LGR4 +SeqId.16296-43 O75473 LGR5 Leucine-rich repeat-containing G-protein coupled receptor 5 LGR5 +SeqId.8376-25 P01229 LSHB Lutropin subunit beta LHB +SeqId.14634-13 P22888 LSHR Lutropin-choriogonadotropic hormone receptor LHCGR +SeqId.7790-21 P15018 LIF Leukemia inhibitory factor LIF +SeqId.5837-49 P42702 LIF sR Leukemia inhibitory factor receptor LIFR +SeqId.15614-168 Q8N149 LIRA2 Leukocyte immunoglobulin-like receptor subfamily A member 2 LILRA2 +SeqId.6391-52 Q8N6C8 LIRA3 Leukocyte immunoglobulin-like receptor subfamily A member 3 LILRA3 +SeqId.8299-66 P59901 LIRA4 Leukocyte immunoglobulin-like receptor subfamily A member 4 LILRA4 +SeqId.7787-25 A6NI73 LIRA5 Leukocyte immunoglobulin-like receptor subfamily A member 5 LILRA5 +SeqId.8766-29 A6NI73 LIRA5 Leukocyte immunoglobulin-like receptor subfamily A member 5 LILRA5 +SeqId.7059-14 Q6PI73 LIRA6 Leukocyte immunoglobulin-like receptor subfamily A member 6 LILRA6 +SeqId.5090-49 Q8NHL6 ILT-2 Leukocyte immunoglobulin-like receptor subfamily B member 1 LILRB1 +SeqId.5091-28 Q8N423 ILT-4 Leukocyte immunoglobulin-like receptor subfamily B member 2 LILRB2 +SeqId.11334-7 O75022 LIRB3 Leukocyte immunoglobulin-like receptor subfamily B member 3 LILRB3 +SeqId.15615-8 O75022 LIRB3 Leukocyte immunoglobulin-like receptor subfamily B member 3 LILRB3 +SeqId.6453-70 Q8NHJ6 LIRB4 Leukocyte immunoglobulin-like receptor subfamily B member 4 LILRB4 +SeqId.7015-8 O75023 LIRB5 Leukocyte immunoglobulin-like receptor subfamily B member 5 LILRB5 +SeqId.11543-84 Q9UHB6 LIMA1 LIM domain and actin-binding protein 1 LIMA1 +SeqId.18910-45 O14910 LIN7A Protein lin-7 homolog A LIN7A +SeqId.15612-5 Q9HAP6 LIN7B Protein lin-7 homolog B LIN7B +SeqId.12986-12 Q9NUP9 LIN7C Protein lin-7 homolog C LIN7C +SeqId.6620-82 Q96FE5 LIGO1 Leucine-rich repeat and immunoglobulin-like domain-containing nogo receptor-interacting protein 1 LINGO1 +SeqId.10827-67 P0C6S8 LIGO3 Leucine-rich repeat and immunoglobulin-like domain-containing nogo receptor-interacting protein 3 LINGO3 +SeqId.6413-79 Q5VXJ0 LIPK Lipase member K LIPK +SeqId.8097-77 Q5VXI9 LIPN Lipase member N LIPN +SeqId.15688-30 P49257 Mannose-binding lectin Protein ERGIC-53 LMAN1 +SeqId.7638-30 Q12907 "Lectin, mannose-binding 2" Vesicular integral-membrane protein VIP36 LMAN2 +SeqId.9468-8 Q12907 "Lectin, mannose-binding 2" Vesicular integral-membrane protein VIP36 LMAN2 +SeqId.8013-9 Q9H0V9 LMA2L VIP36-like protein LMAN2L +SeqId.3889-64 P20700 Lamin-B1 Lamin-B1 LMNB1 +SeqId.12504-26 P29536 LMOD1 Leiomodin-1 LMOD1 +SeqId.9936-27 Q8TBB1 LNX1 E3 ubiquitin-protein ligase LNX LNX1 +SeqId.6398-12 P36776 LONM "Lon protease homolog, mitochondrial" LONP1 +SeqId.6504-65 Q9Y4K0 Lysyl oxidase-like protein 2 Lysyl oxidase homolog 2 LOXL2 +SeqId.15427-35 P58215 LOXL3 Lysyl oxidase homolog 3 LOXL3 +SeqId.11175-45 Q7L5N7 PCAT2 Lysophosphatidylcholine acyltransferase 2 LPCAT2 +SeqId.4801-13 P22079 PERL Lactoperoxidase LPO +SeqId.11252-30 O75427 LRCH4 Leucine-rich repeat and calponin homology domain-containing protein 4 LRCH4 +SeqId.7910-41 Q9P244 LRFN1 Leucine-rich repeat and fibronectin type III domain-containing protein 1 LRFN1 +SeqId.7200-4 Q9ULH4 LRFN2 Leucine-rich repeat and fibronectin type-III domain-containing protein 2 LRFN2 +SeqId.6587-6 Q96NI6 LRFN5 Leucine-rich repeat and fibronectin type-III domain-containing protein 5 LRFN5 +SeqId.18831-6 Q96JA1 LRIG1 Leucine-rich repeats and immunoglobulin-like domains protein 1 LRIG1 +SeqId.3322-52 Q6UXM1 LRIG3 Leucine-rich repeats and immunoglobulin-like domains protein 3 LRIG3 +SeqId.11716-28 A6NDA9 LRIT2 "Leucine-rich repeat, immunoglobulin-like domain and transmembrane domain-containing protein 2" LRIT2 +SeqId.11534-6 Q3SXY7 LRIT3 "Leucine-rich repeat, immunoglobulin-like domain and transmembrane domain-containing protein 3" LRIT3 +SeqId.10704-91 Q12912 LRMP Lymphoid-restricted membrane protein LRMP +SeqId.8601-167 Q07954 sLRP1 "Low-density lipoprotein receptor-related protein 1, soluble" LRP1 +SeqId.10699-52 Q07954 LRP1 Prolow-density lipoprotein receptor-related protein 1 LRP1 +SeqId.9182-3 Q07954 sLRP1 "Low-density lipoprotein receptor-related protein 1, soluble" LRP1 +SeqId.16610-13 Q7Z4F1 LRP10 Low-density lipoprotein receptor-related protein 10 LRP10 +SeqId.15472-16 Q86VZ4 LRP11 Low-density lipoprotein receptor-related protein 11 LRP11 +SeqId.6713-4 Q86VZ4 LRP11 Low-density lipoprotein receptor-related protein 11 LRP11 +SeqId.15506-34 Q9Y561 LRP12 Low-density lipoprotein receptor-related protein 12 LRP12 +SeqId.11275-94 Q9NZR2 LRP1B Low-density lipoprotein receptor-related protein 1B LRP1B +SeqId.10618-190 P98164 megalin Low-density lipoprotein receptor-related protein 2 LRP2 +SeqId.19558-10 O75096 LRP4 Low-density lipoprotein receptor-related protein 4 LRP4 +SeqId.3323-37 Q14114 LRP8 Low-density lipoprotein receptor-related protein 8 LRP8 +SeqId.3640-14 P30533 RAP alpha-2-macroglobulin receptor-associated protein LRPAP1 +SeqId.6557-50 Q8TF66 LRC15 Leucine-rich repeat-containing protein 15 LRRC15 +SeqId.9989-12 Q50LG9 LRC24 Leucine-rich repeat-containing protein 24 LRRC24 +SeqId.9317-4 Q8N386 LRC25 Leucine-rich repeat-containing protein 25 LRRC25 +SeqId.6917-49 Q9BY71 LRRC3 Leucine-rich repeat-containing protein 3 LRRC3 +SeqId.7551-33 Q14392 LRC32 Leucine-rich repeat-containing protein 32 LRRC32 +SeqId.8897-3 A6NM11 L37A2 Leucine-rich repeat-containing protein 37A2 LRRC37A2 +SeqId.18947-3 Q96PB8 LRC3B Leucine-rich repeat-containing protein 3B LRRC3B +SeqId.11911-13 Q9NT99 LRC4B Leucine-rich repeat-containing protein 4B LRRC4B +SeqId.9916-146 Q9NT99 LRC4B Leucine-rich repeat-containing protein 4B LRRC4B +SeqId.9369-174 Q9HCJ2 NGL1 Leucine-rich repeat-containing protein 4C LRRC4C +SeqId.10785-8 Q8N7C0 LRC52 Leucine-rich repeat-containing protein 52 LRRC52 +SeqId.19163-26 Q96AG4 LRC59 Leucine-rich repeat-containing protein 59 LRRC59 +SeqId.8389-8 Q0VAA2 CN16B Leucine-rich repeat-containing protein 74A LRRC74A +SeqId.10990-21 Q5S007 LRRK2 Leucine-rich repeat serine/threonine-protein kinase 2 LRRK2 +SeqId.11293-14 Q6UXK5 LRRN1 Leucine-rich repeat neuronal protein 1 LRRN1 +SeqId.19360-22 Q86UE6 LRRT1 Leucine-rich repeat transmembrane neuronal protein 1 LRRTM1 +SeqId.6904-14 O43300 LRRT2 Leucine-rich repeat transmembrane neuronal protein 2 LRRTM2 +SeqId.4453-83 Q86VH5 LRRT3 Leucine-rich repeat transmembrane neuronal protein 3 LRRTM3 +SeqId.6572-10 Q86VH4 LRRT4 Leucine-rich repeat transmembrane neuronal protein 4 LRRTM4 +SeqId.8646-61 Q86VH4 LRRT4 Leucine-rich repeat transmembrane neuronal protein 4 LRRTM4 +SeqId.9368-64 Q9HBL6 LRTM1 Leucine-rich repeat and transmembrane domain-containing protein 1 LRTM1 +SeqId.8906-60 Q8N967 LRTM2 Leucine-rich repeat and transmembrane domain-containing protein 2 LRTM2 +SeqId.2999-6 Q13449 LSAMP Limbic system-associated membrane protein LSAMP +SeqId.17795-176 O15116 LSM1 U6 snRNA-associated Sm-like protein LSm1 LSM1 +SeqId.16854-17 Q9Y4Z0 LSM4 U6 snRNA-associated Sm-like protein LSm4 LSM4 +SeqId.9531-24 O00453 LST1 Leukocyte-specific transcript 1 protein LST1 +SeqId.4703-87 P01374 TNF-b Lymphotoxin-alpha LTA +SeqId.3506-49 "P01374, Q06643" Lymphotoxin a2/b1 Lymphotoxin alpha2:beta1 LTA LTB +SeqId.3506-49 "P01374, Q06643" Lymphotoxin a2/b1 Lymphotoxin alpha2:beta1 LTA LTB +SeqId.3505-6 "P01374, Q06643" Lymphotoxin a1/b2 Lymphotoxin alpha1:beta2 LTA LTB +SeqId.3505-6 "P01374, Q06643" Lymphotoxin a1/b2 Lymphotoxin alpha1:beta2 LTA LTB +SeqId.3204-2 P09960 LKHA4 Leukotriene A-4 hydrolase LTA4H +SeqId.13477-65 Q15722 LT4R1 Leukotriene B4 receptor 1 LTB4R +SeqId.13133-73 Q8N2S1 LTBP4 Latent-transforming growth factor beta-binding protein 4 LTBP4 +SeqId.2636-10 P36941 Lymphotoxin b R Tumor necrosis factor receptor superfamily member 3 LTBR +SeqId.2780-35 P02788 Lactoferrin Lactotransferrin LTF +SeqId.13114-50 P51884 Lumican Lumican LUM +SeqId.6256-9 O95867 LY66C Lymphocyte antigen 6 complex locus protein G6c LY6G6C +SeqId.6469-62 O95868 LY66D Lymphocyte antigen 6 complex locus protein G6d LY6G6D +SeqId.16620-26 O60449 LY75 Lymphocyte antigen 75 LY75 +SeqId.3623-84 O95711 LY86 Lymphocyte antigen 86 LY86 +SeqId.3324-51 Q9HBG7 LY9 T-lymphocyte surface antigen Ly-9 LY9 +SeqId.9243-10 Q8N1E2 LYG1 Lysozyme g-like protein 1 LYG1 +SeqId.15416-54 Q86SG7 LYG2 Lysozyme g-like protein 2 LYG2 +SeqId.3381-24 P07948 LYNB "Tyrosine-protein kinase Lyn, isoform B" LYN +SeqId.3453-87 P07948 LYN Tyrosine-protein kinase Lyn LYN +SeqId.9327-3 Q8N2G4 LYPD1 Ly6/PLAUR domain-containing protein 1 LYPD1 +SeqId.13107-9 O95274 LYPD3 Ly6/PLAUR domain-containing protein 3 LYPD3 +SeqId.12428-2 Q5VWZ2 LYPL1 Lysophospholipase-like protein 1 LYPLAL1 +SeqId.10563-13 Q7Z3D4 LYSM3 LysM and putative peptidoglycan-binding domain-containing protein 3 LYSMD3 +SeqId.9106-87 Q5XG99 LYSM4 LysM and putative peptidoglycan-binding domain-containing protein 4 LYSMD4 +SeqId.3206-4 Q9Y5Y7 LYVE1 Lymphatic vessel endothelial hyaluronic acid receptor 1 LYVE1 +SeqId.4920-10 P61626 Lysozyme Lysozyme C LYZ +SeqId.6377-54 Q7Z4W2 LYZL2 Lysozyme-like protein 2 LYZL2 +SeqId.19338-3 Q8WZA0 LZIC Protein LZIC LZIC +SeqId.13653-335 Q9BQ69 MACD1 O-acetyl-ADP-ribose deacetylase MACROD1 MACROD1 +SeqId.13618-15 Q9Y6D9 MD1L1 Mitotic spindle assembly checkpoint protein MAD1 MAD1L1 +SeqId.15313-28 Q13257 MD2L1 Mitotic spindle assembly checkpoint protein MAD2A MAD2L1 +SeqId.11258-41 Q13477 MAdCAM-1 Mucosal addressin cell adhesion molecule 1 MADCAM1 +SeqId.19281-86 O15525 MAFG Transcription factor MafG MAFG +SeqId.13610-9 P43363 MAGE-10 Melanoma-associated antigen 10 MAGEA10 +SeqId.12576-21 P43357 MAGE-3 Melanoma-associated antigen 3 MAGEA3 +SeqId.10485-56 P43358 MAGE-4 Melanoma-associated antigen 4 MAGEA4 +SeqId.18192-69 P43359 MAGE-5 Melanoma-associated antigen 5 MAGEA5 +SeqId.18205-123 P43360 MAGE-6 Melanoma-associated antigen 6 MAGEA6 +SeqId.18326-50 P43361 MAGA8 Melanoma-associated antigen 8 MAGEA8 +SeqId.11456-2 Q96LZ2 MAGBA Melanoma-associated antigen B10 MAGEB10 +SeqId.14066-49 Q86UL8 MAGI2 "Membrane-associated guanylate kinase, WW and PDZ domain-containing protein 2" MAGI2 +SeqId.16875-13 Q96A72 MGN2 Protein mago nashi homolog 2 MAGOHB +SeqId.6119-14 Q7Z304 MAMC2 MAM domain-containing protein 2 MAMDC2 +SeqId.9077-10 O60476 MA1A2 "Mannosyl-oligosaccharide 1,2-alpha-mannosidase IB" MAN1A2 +SeqId.7071-23 Q9UKM7 MA1B1 "Endoplasmic reticulum mannosyl-oligosaccharide 1,2-alpha-mannosidase" MAN1B1 +SeqId.13427-66 Q9NR34 MA1C1 "Mannosyl-oligosaccharide 1,2-alpha-mannosidase IC" MAN1C1 +SeqId.9251-28 Q9Y2E5 MA2B2 Epididymis-specific alpha-mannosidase MAN2B2 +SeqId.6382-17 O00462 MANBA Beta-mannosidase MANBA +SeqId.8014-359 Q5SRI9 MANEA "Glycoprotein endo-alpha-1,2-mannosidase" MANEA +SeqId.9223-11 P55145 ARMET Mesencephalic astrocyte-derived neurotrophic factor MANF +SeqId.9557-5 Q9H8J5 MANS1 MANSC domain-containing protein 1 MANSC1 +SeqId.9578-263 A6NHS7 MANS4 MANSC domain-containing protein 4 MANSC4 +SeqId.17781-191 Q9H492 MLP3A Microtubule-associated proteins 1A/1B light chain 3A MAP1LC3A +SeqId.11608-5 Q9GZQ8 MLP3B Microtubule-associated proteins 1A/1B light chain 3B MAP1LC3B +SeqId.2864-2 Q02750 MEK1 Dual specificity mitogen-activated protein kinase kinase 1 MAP2K1 +SeqId.3628-3 P36507 MP2K2 Dual specificity mitogen-activated protein kinase kinase 2 MAP2K2 +SeqId.6151-18 P46734 MP2K3 Dual specificity mitogen-activated protein kinase kinase 3 MAP2K3 +SeqId.5242-37 P45985 MP2K4 Dual specificity mitogen-activated protein kinase kinase 4 MAP2K4 +SeqId.17175-5 P52564 MP2K6 Dual specificity mitogen-activated protein kinase kinase 6 MAP2K6 +SeqId.12990-39 Q99759 MAP3K3 Mitogen-activated protein kinase kinase kinase 3 MAP3K3 +SeqId.5259-2 O43318 Q15750 TAK1-TAB1 Mitogen-activated protein kinase kinase kinase 7:TGF-beta-activated kinase 1 and MAP3K7-binding protein 1 fusion MAP3K7 TAB1 +SeqId.5259-2 O43318 Q15750 TAK1-TAB1 Mitogen-activated protein kinase kinase kinase 7:TGF-beta-activated kinase 1 and MAP3K7-binding protein 1 fusion MAP3K7 TAB1 +SeqId.8954-30 Q92918 M4K1 Mitogen-activated protein kinase kinase kinase kinase 1 MAP4K1 +SeqId.8978-30 Q8IVH8 M4K3 Mitogen-activated protein kinase kinase kinase kinase 3 MAP4K3 +SeqId.3115-64 P28482 MK01 Mitogen-activated protein kinase 1 MAPK1 +SeqId.15418-25 P53779 MK10 Mitogen-activated protein kinase 10 MAPK10 +SeqId.5004-69 Q15759 MK11 Mitogen-activated protein kinase 11 MAPK11 +SeqId.5005-4 P53778 MK12 Mitogen-activated protein kinase 12 MAPK12 +SeqId.5006-71 O15264 MK13 Mitogen-activated protein kinase 13 MAPK13 +SeqId.5007-1 Q16539 MAPK14 Mitogen-activated protein kinase 14 MAPK14 +SeqId.2855-49 P27361 ERK-1 Mitogen-activated protein kinase 3 MAPK3 +SeqId.3825-18 P45983 MK08 Mitogen-activated protein kinase 8 MAPK8 +SeqId.15604-18 P45984 JNK2 Mitogen-activated protein kinase 9 MAPK9 +SeqId.3820-68 P49137 MAPK2 MAP kinase-activated protein kinase 2 MAPKAPK2 +SeqId.3822-54 Q16644 MAPKAPK3 MAP kinase-activated protein kinase 3 MAPKAPK3 +SeqId.3821-28 Q8IW41 MAPK5 MAP kinase-activated protein kinase 5 MAPKAPK5 +SeqId.8382-47 Q8IW41 MAPK5 MAP kinase-activated protein kinase 5 MAPKAPK5 +SeqId.12469-19 Q15691 MARE1 Microtubule-associated protein RP/EB family member 1 MAPRE1 +SeqId.16856-79 Q15555 MARE2 Microtubule-associated protein RP/EB family member 2 MAPRE2 +SeqId.16885-49 Q9UPY8 MARE3 Microtubule-associated protein RP/EB family member 3 MAPRE3 +SeqId.5854-60 P10636 tau Microtubule-associated protein tau MAPT +SeqId.19175-18 P49006 MARCKSL1 MARCKS-related protein MARCKSL1 +SeqId.9003-99 Q9UEW3 MARCO Macrophage receptor MARCO MARCO +SeqId.9747-48 P27448 MARK3 MAP/microtubule affinity-regulating kinase 3 MARK3 +SeqId.3605-77 P48740 MASP3 Mannan-binding lectin serine protease 1 MASP1 +SeqId.9125-23 P48740 MASP3 Mannan-binding lectin serine protease 1 MASP1 +SeqId.18392-19 Q9NZL9 MAT2B Methionine adenosyltransferase 2 subunit beta MAT2B +SeqId.3823-9 P42679 MATK Megakaryocyte-associated tyrosine-protein kinase MATK +SeqId.3325-2 O00339 MATN2 Matrilin-2 MATN2 +SeqId.19361-78 O15232 MATN3 Matrilin-3 MATN3 +SeqId.7083-74 O95460 MATN4 Matrilin-4 MATN4 +SeqId.12411-60 P61244 MAX Protein max MAX +SeqId.13436-54 P56270 MAZ Myc-associated zinc finger protein MAZ +SeqId.3042-7 P02144 Myoglobin Myoglobin MB +SeqId.14294-61 Q9UIS9 MBD1 Methyl-CpG-binding domain protein 1 MBD1 +SeqId.3891-56 O95243 MBD4 Methyl-CpG-binding domain protein 4 MBD4 +SeqId.3000-66 P11226 MBL Mannose-binding protein C MBL2 +SeqId.7240-2 Q14703 MBTP1 Membrane-bound transcription factor site-1 protease MBTPS1 +SeqId.8032-23 P59942 MCCD1 Mitochondrial coiled-coil domain protein 1 MCCD1 +SeqId.9388-18 Q96PE7 MCEE "Methylmalonyl-CoA epimerase, mitochondrial" MCEE +SeqId.6283-60 Q8IX19 MCEM1 Mast cell-expressed membrane protein 1 MCEMP1 +SeqId.13934-3 O15068 MCF2L Guanine nucleotide exchange factor DBS MCF2L +SeqId.10396-6 Q07820 Mcl-1 Induced myeloid leukemia cell differentiation protein Mcl-1 MCL1 +SeqId.9819-110 Q07820 Mcl-1 Induced myeloid leukemia cell differentiation protein Mcl-1 MCL1 +SeqId.9897-9 Q14566 MCM6 DNA replication licensing factor MCM6 MCM6 +SeqId.12488-9 Q9ULC4 MCTS1 Malignant T-cell-amplified sequence 1 MCTS1 +SeqId.16900-29 Q8NFP4 MDGA1 MAM domain-containing glycosylphosphatidylinositol anchor protein 1 MDGA1 +SeqId.19372-7 Q7Z553 MDGA2 MAM domain-containing glycosylphosphatidylinositol anchor protein 2 MDGA2 +SeqId.3853-56 P40925 MDHC "Malate dehydrogenase, cytoplasmic" MDH1 +SeqId.15534-26 P40926 Malate dehydrogenase 2 "Malate dehydrogenase, mitochondrial" MDH2 +SeqId.2911-27 P21741 Midkine Midkine MDK +SeqId.7898-29 Q8TC05 MDM1 Nuclear protein MDM1 MDM1 +SeqId.13228-75 Q00987 MDM2 E3 ubiquitin-protein ligase Mdm2 MDM2 +SeqId.13229-20 O15151 MDM4 Protein Mdm4 MDM4 +SeqId.19108-50 P51608 MECP2 Methyl-CpG-binding protein 2 MECP2 +SeqId.3892-21 Q15648 MED-1 Mediator of RNA polymerase II transcription subunit 1 MED1 +SeqId.14021-81 Q9NPJ6 MED4 Mediator of RNA polymerase II transcription subunit 4 MED4 +SeqId.8933-84 Q06413 MEF2C Myocyte-specific enhancer factor 2C MEF2C +SeqId.11168-3 Q96KG7 MEG10 Multiple epidermal growth factor-like domains protein 10 MEGF10 +SeqId.19110-6 Q9Y316 MEMO1 Protein MEMO1 MEMO1 +SeqId.5744-12 Q9BUN1 CA056 Protein MENT MENT +SeqId.18259-15 P50222 MEOX2 Homeobox protein MOX-2 MEOX2 +SeqId.3209-69 Q9NQ76 MEPE Matrix extracellular phosphoglycoprotein MEPE +SeqId.15299-102 Q14696 MESD2 LDLR chaperone MESD MESDC2 +SeqId.2837-3 P08581 Met Hepatocyte growth factor receptor MET +SeqId.3210-1 P53582 METAP1 Methionine aminopeptidase 1 METAP1 +SeqId.3170-6 P50579 AMPM2 Methionine aminopeptidase 2 METAP2 +SeqId.12514-16 Q9UBP6 METTL1 tRNA (guanine-N(7)-)-methyltransferase METTL1 +SeqId.9470-15 Q5JXM2 MET24 Methyltransferase-like protein 24 METTL24 +SeqId.5606-24 P55081 MFAP1 Microfibrillar-associated protein 1 MFAP1 +SeqId.9294-45 P55001 MFAP2 Microfibrillar-associated protein 2 MFAP2 +SeqId.10569-28 P55001 MFAP2 Microfibrillar-associated protein 2 MFAP2 +SeqId.8837-8 O75121 MFA3L Microfibrillar-associated protein 3-like MFAP3L +SeqId.5636-10 P55083 MFAP4 Microfibril-associated glycoprotein 4 MFAP4 +SeqId.6440-31 Q13361 MFAP5 Microfibrillar-associated protein 5 MFAP5 +SeqId.4455-89 Q08431 MFGM Lactadherin MFGE8 +SeqId.11364-18 Q8IWA4 MFN1 Mitofusin-1 MFN1 +SeqId.5605-77 O00587 MFNG "Beta-1,3-N-acetylglucosaminyltransferase manic fringe" MFNG +SeqId.3685-53 Q9BY79 MFRP Membrane frizzled-related protein MFRP +SeqId.11587-5 Q8IWI9 MGAP MAX gene-associated protein MGA +SeqId.10571-14 P26572 MGAT1 "Alpha-1,3-mannosyl-glycoprotein 2-beta-N-acetylglucosaminyltransferase" MGAT1 +SeqId.6909-40 Q10469 MGAT2 "Alpha-1,6-mannosyl-glycoprotein 2-beta-N-acetylglucosaminyltransferase" MGAT2 +SeqId.9392-43 Q9UM21 MGT4A "Alpha-1,3-mannosyl-glycoprotein 4-beta-N-acetylglucosaminyltransferase A" MGAT4A +SeqId.7141-21 Q9UQ53 MGT4B "Alpha-1,3-mannosyl-glycoprotein 4-beta-N-acetylglucosaminyltransferase B" MGAT4B +SeqId.7208-60 Q9UBM8 MGT4C "Alpha-1,3-mannosyl-glycoprotein 4-beta-N-acetylglucosaminyltransferase C" MGAT4C +SeqId.6520-87 P08493 MGP Matrix Gla protein MGP +SeqId.2687-2 Q16674 MIA Melanoma-derived growth regulatory protein MIA +SeqId.2730-58 Q29983 MICA MHC class I polypeptide-related sequence A MICA +SeqId.12891-1 Q8IY33 MILK2 MICAL-like protein 2 MICALL2 +SeqId.5102-55 Q29980 MICB MHC class I polypeptide-related sequence B MICB +SeqId.14249-68 Q9UJV3 TRIM1 Probable E3 ubiquitin-protein ligase MID2 MID2 +SeqId.8221-19 P14174 MIF Macrophage migration inhibitory factor MIF +SeqId.11173-29 Q7Z6M3 MILR1 Allergin-1 MILR1 +SeqId.7956-11 Q5TGZ0 MOS1 MICOS complex subunit MIC10 MINOS1 +SeqId.5586-66 Q9UNW1 MINP1 Multiple inositol polyphosphate phosphatase 1 MINPP1 +SeqId.13498-1 Q9UGB7 MIOX Inositol oxygenase MIOX +SeqId.6285-71 Q14165 K0152 Malectin MLEC +SeqId.17820-170 P58340 MLF1 Myeloid leukemia factor 1 MLF1 +SeqId.13623-4 O14686 MLL2 Histone-lysine N-methyltransferase 2D MLL2 +SeqId.5631-83 P12872 MOTI Promotilin MLN +SeqId.11538-216 O95822 DCMC "Malonyl-CoA decarboxylase, mitochondrial" MLYCD +SeqId.17783-9 Q96EY8 MMAB "Cob(I)yrinic acid a,c-diamide adenosyltransferase, mitochondrial" MMAB +SeqId.3627-71 Q495T6 MMEL2 Membrane metallo-endopeptidase-like 1 MMEL1 +SeqId.7225-51 Q8N4V1 MMGT1 Membrane magnesium transporter 1 MMGT1 +SeqId.4924-32 P03956 MMP-1 Interstitial collagenase MMP1 +SeqId.8479-4 P09238 MMP-10 Stromelysin-2 MMP10 +SeqId.4496-60 P39900 MMP-12 Macrophage metalloelastase MMP12 +SeqId.4925-54 P45452 MMP-13 Collagenase 3 MMP13 +SeqId.5002-76 P50281 MMP-14 Matrix metalloproteinase-14 MMP14 +SeqId.5268-49 P51512 MMP-16 Matrix metalloproteinase-16 MMP16 +SeqId.9719-145 P51512 MMP-16 Matrix metalloproteinase-16 MMP16 +SeqId.2838-53 Q9ULZ9 MMP-17 Matrix metalloproteinase-17 MMP17 +SeqId.6425-87 Q99542 MMP19 Matrix metalloproteinase-19 MMP19 +SeqId.4160-49 P08253 MMP-2 72 kDa type IV collagenase MMP2 +SeqId.15419-15 O60882 MMP20 Matrix metalloproteinase-20 MMP20 +SeqId.2788-55 P08254 MMP-3 Stromelysin-1 MMP3 +SeqId.2789-26 P09237 MMP-7 Matrilysin MMP7 +SeqId.9172-69 P22894 MMP-8 Neutrophil collagenase MMP8 +SeqId.2579-17 P14780 MMP-9 Matrix metalloproteinase-9 MMP9 +SeqId.9723-105 Q9H8L6 EMILIN-3 Multimerin-2 MMRN2 +SeqId.9576-58 P50219 MNX1 Motor neuron and pancreas homeobox protein 1 MNX1 +SeqId.12426-19 Q9H8S9 MOL1B MOB kinase activator 1A MOB1A +SeqId.19177-7 Q7L9L4 MOL1A MOB kinase activator 1B MOBKL1A +SeqId.19332-1 Q9Y3A3 MOBL3 MOB-like protein phocein MOBKL3 +SeqId.14229-5 O95396 MOCS3 Adenylyltransferase and sulfurtransferase MOCS3 MOCS3 +SeqId.15619-49 Q16653 MOG Myelin-oligodendrocyte glycoprotein MOG +SeqId.18193-165 Q9UBU8 MO4L1 Mortality factor 4-like protein 1 MORF4L1 +SeqId.14036-116 O75970 MPDZ Multiple PDZ domain protein MPDZ +SeqId.12438-127 P29372 3MG DNA-3-methyladenine glycosylase MPG +SeqId.3473-78 P40238 Thrombopoietin Receptor Thrombopoietin Receptor MPL +SeqId.2580-83 P05164 Myeloperoxidase Myeloperoxidase MPO +SeqId.13490-1 Q9NZW5 MPP6 MAGUK p55 subfamily member 6 MPP6 +SeqId.12732-13 Q5T2T1 MPP7 MAGUK p55 subfamily member 7 MPP7 +SeqId.19153-53 Q15777 MPPD2 Metallophosphoesterase MPPED2 MPPED2 +SeqId.12686-15 P25325 THTM 3-mercaptopyruvate sulfurtransferase MPST +SeqId.10615-18 P25189 MYP0 Myelin protein P0 MPZ +SeqId.16845-15 O95297 MPZL1 Myelin protein zero-like protein 1 MPZL1 +SeqId.9372-157 O60487 MPZL2 Myelin protein zero-like protein 2 MPZL2 +SeqId.7895-108 Q8TCY5 MRAP Melanocortin-2 receptor accessory protein MRAP +SeqId.10889-2 Q96G30 MRAP2 Melanocortin-2 receptor accessory protein 2 MRAP2 +SeqId.18297-8 O14807 RASM Ras-related protein M-Ras MRAS +SeqId.2637-77 P22897 Macrophage mannose receptor Macrophage mannose receptor 1 MRC1 +SeqId.3041-55 Q9UBG0 MRC2 C-type mannose receptor 2 MRC2 +SeqId.11319-106 P49959 MRE11 Double-strand break repair protein MRE11 MRE11A +SeqId.19145-4 Q8N565 MREG Melanoregulin MREG +SeqId.8021-59 Q6P1L8 RM14 "39S ribosomal protein L14, mitochondrial" MRPL14 +SeqId.19132-1 Q5T653 RM02 "39S ribosomal protein L2, mitochondrial" MRPL2 +SeqId.8942-2 Q7Z2W9 RM21 "39S ribosomal protein L21, mitochondrial" MRPL21 +SeqId.7982-10 Q9BYC8 RM32 "39S ribosomal protein L32, mitochondrial" MRPL32 +SeqId.13453-2 O75394 RM33 "39S ribosomal protein L33, mitochondrial" MRPL33 +SeqId.6933-20 Q9BQ48 RM34 "39S ribosomal protein L34, mitochondrial" MRPL34 +SeqId.7123-25 Q86TS9 RM52 "39S ribosomal protein L52, mitochondrial" MRPL52 +SeqId.11135-5 Q7Z7F7 RM55 "39S ribosomal protein L55, mitochondrial" MRPL55 +SeqId.12355-223 Q96E11 RRFM "Ribosome-recycling factor, mitochondrial" MRRF +SeqId.8255-34 Q9Y6F6 MRVI1 Protein MRVI1 MRVI1 +SeqId.9739-4 P43246 MSH2 DNA mismatch repair protein Msh2 MSH2 +SeqId.3893-64 Q13421 Mesothelin Mesothelin MSLN +SeqId.10620-21 P08118 PSP-94 Beta-microseminoprotein MSMB +SeqId.8080-24 Q1L6U9 PSMP Prostate-associated microseminoprotein MSMP +SeqId.5009-11 P26038 Moesin Moesin MSN +SeqId.11207-3 P21757 Macrophage scavenger receptor Macrophage scavenger receptor types I and II MSR1 +SeqId.15533-97 P21757 Macrophage scavenger receptor Macrophage scavenger receptor types I and II MSR1 +SeqId.7137-8 Q9UJ68 MSRA Mitochondrial peptide methionine sulfoxide reductase MSRA +SeqId.16877-19 Q9Y3D2 MSRB2 "Methionine-R-sulfoxide reductase B2, mitochondrial" MSRB2 +SeqId.7824-88 Q8IXL7 MSRB3 Methionine-R-sulfoxide reductase B3 MSRB3 +SeqId.4407-10 P26927 MSP Hepatocyte growth factor-like protein MST1 +SeqId.2640-3 Q04912 MSP R Macrophage-stimulating protein receptor MST1R +SeqId.14583-49 O14793 Myostatin Growth/differentiation factor 8 MSTN +SeqId.9910-9 Q13126 MTAP S-methyl-5'-thioadenosine phosphorylase MTAP +SeqId.19374-72 P56278 MTCP1 Protein p13 MTCP-1 MTCP1 +SeqId.9095-5 Q15390 MTFR1 Mitochondrial fission regulator 1 MTFR1 +SeqId.12575-30 P11586 C1TC "C-1-tetrahydrofolate synthase, cytoplasmic" MTHFD1 +SeqId.18321-38 P13995 MTDC "Bifunctional methylenetetrahydrofolate dehydrogenase/cyclohydrolase, mitochondrial" MTHFD2 +SeqId.14107-1 P49914 MTHFS 5-formyltetrahydrofolate cyclo-ligase MTHFS +SeqId.19129-15 Q2M296 MTHFSD Methenyltetrahydrofolate synthase domain-containing protein MTHFSD +SeqId.7852-9 Q9H2K0 IF3M "Translation initiation factor IF-3, mitochondrial" MTIF3 +SeqId.11167-6 Q13613 MTMR1 Myotubularin-related protein 1 MTMR1 +SeqId.12536-46 Q9Y217 MTMR6 Myotubularin-related protein 6 MTMR6 +SeqId.9028-5 Q9NVV4 PAPD1 "Poly(A) RNA polymerase, mitochondrial" MTPAP +SeqId.11134-30 Q9UGC7 RF1ML "Peptide chain release factor 1-like, mitochondrial" MTRF1L +SeqId.8839-4 O75431 Metaxin-2 Metaxin-2 MTX2 +SeqId.10623-19 P15941 MUC1 Mucin-1 MUC1 +SeqId.9176-3 P15941 MUC1 Mucin-1 MUC1 +SeqId.15565-102 Q8WXI7 CA125 Mucin-16 MUC16 +SeqId.10975-59 Q96DR8 MUCL1 Mucin-like protein 1 MUCL1 +SeqId.9315-16 Q969V5 MUL1 Mitochondrial ubiquitin ligase activator of NFKB 1 MUL1 +SeqId.11547-84 O15146 MUSK "Muscle, skeletal receptor tyrosine-protein kinase" MUSK +SeqId.19116-1 Q8TDH9 MUTED Biogenesis of lysosome-related organelles complex 1 subunit 5 MUTED +SeqId.10030-8 Q9UIF7 MutY homolog Adenine DNA glycosylase MUTYH +SeqId.18422-41 P53602 ERG19 Diphosphomevalonate decarboxylase MVD +SeqId.11391-69 Q03426 MVK Mevalonate kinase MVK +SeqId.17460-51 P20591 Mx1 Interferon-induced GTP-binding protein Mx1 MX1 +SeqId.9035-2 P50539 MXI1 MAX-interacting protein 1 MXI1 +SeqId.8005-1 P84157 MXRA7 Matrix-remodeling-associated protein 7 MXRA7 +SeqId.10521-10 Q9BRK3 MXRA8 Matrix-remodeling-associated protein 8 MXRA8 +SeqId.11618-83 P10242 MYB Transcriptional activator Myb MYB +SeqId.7648-9 Q00872 MYPC1 "Myosin-binding protein C, slow-type" MYBPC1 +SeqId.10362-35 P01106 c-Myc Myc proto-oncogene protein MYC +SeqId.19250-50 Q99417 MYCBP C-Myc-binding protein MYCBP +SeqId.13541-1 Q8N699 MYCT1 Myc target protein 1 MYCT1 +SeqId.9248-36 Q969H8 CS010 Myeloid-derived growth factor MYDGF +SeqId.19373-3 P19105 MLRM Myosin regulatory light chain 12A MYL12A +SeqId.19122-47 O14950 ML12B Myosin regulatory light chain 12B MYL12B +SeqId.18376-19 P08590 Myosin light chain 1 Myosin light chain 3 MYL3 +SeqId.19286-30 Q02045 MLR5 Myosin light chain 5 MYL5 +SeqId.14227-21 P14649 MYL6B Myosin light chain 6B MYL6B +SeqId.19296-51 Q01449 MLRA "Myosin regulatory light chain 2, atrial isoform" MYL7 +SeqId.12455-48 Q9NPC7 MYNN Myoneurin MYNN +SeqId.9894-13 Q9UM54 MYO6 Unconventional myosin-VI MYO6 +SeqId.16558-2 Q99972 MYOC Myocilin MYOC +SeqId.13534-20 P54296 MYOM2 Myomesin-2 MYOM2 +SeqId.13966-30 Q5VTT5 MYOM3 Myomesin-3 MYOM3 +SeqId.8843-34 Q9Y2G1 MRF Myelin regulatory factor MYRF +SeqId.11536-9 Q5VVJ2 MYSM1 Histone H2A deubiquitinase MYSM1 MYSM1 +SeqId.9055-81 P0CAP1 MYZAP Myocardial zonula adherens protein MYZAP +SeqId.9964-10 P0CAP1 MYZAP Myocardial zonula adherens protein MYZAP +SeqId.14662-6 P28698 MZF1 Myeloid zinc finger 1 MZF1 +SeqId.11096-57 Q9Y5N5 HEMK2 HemK methyltransferase family member 2 N6AMT1 +SeqId.17854-33 P41227 NAA10 N-alpha-acetyltransferase 10 NAA10 +SeqId.3173-49 Q02083 ASAHL N-acylethanolamine-hydrolyzing acid amidase NAAA +SeqId.7986-98 Q9Y3Q0 NALD2 N-acetylated-alpha-linked acidic dipeptidase 2 NAALAD2 +SeqId.17505-125 Q9UQQ1 NALDL N-acetylated-alpha-linked acidic dipeptidase-like protein NAALADL1 +SeqId.13933-276 Q13506 NAB1 NGFI-A-binding protein 1 NAB1 +SeqId.13680-3 Q15742 NAB2 NGFI-A-binding protein 2 NAB2 +SeqId.3854-24 Q13765 NACA Nascent polypeptide-associated complex subunit alpha NACA +SeqId.13624-17 O95544 NADK NAD kinase NADK +SeqId.18177-49 Q13564 ULA1 NEDD8-activating enzyme E1 regulatory subunit NAE1 +SeqId.3894-15 Q9UJ70 NAGK N-acetyl-D-glucosamine kinase NAGK +SeqId.15509-2 P54802 NAG Alpha-N-acetylglucosaminidase NAGLU +SeqId.11208-15 Q9UK23 NAGPA N-acetylglucosamine-1-phosphodiester alpha-N-acetylglucosaminidase NAGPA +SeqId.11247-20 Q8N159 NAGS "N-acetylglutamate synthase, mitochondrial" NAGS +SeqId.18301-10 Q69YI7 NAIF1 Nuclear apoptosis-inducing factor 1 NAIF1 +SeqId.5011-11 P43490 PBEF Nicotinamide phosphoribosyltransferase NAMPT +SeqId.2732-58 Q9H9S0 NANOG Homeobox protein NANOG NANOG +SeqId.16863-47 Q8TBE9 NANP N-acylneuraminate-9-phosphatase NANP +SeqId.17802-4 Q9NR45 SIAS Sialic acid synthase NANS +SeqId.13636-20 P55209 NP1L1 Nucleosome assembly protein 1-like 1 NAP1L1 +SeqId.13529-39 Q9ULW6 NP1L2 Nucleosome assembly protein 1-like 2 NAP1L2 +SeqId.19188-21 Q99733 NAP2L nucleosome assembly protein 1-like 4 NAP1L4 +SeqId.4292-5 P54920 SNAA Alpha-soluble NSF attachment protein NAPA +SeqId.12655-30 Q9H115 SNAB Beta-soluble NSF attachment protein NAPB +SeqId.17773-26 Q99747 SNAG Gamma-soluble NSF attachment protein NAPG +SeqId.12632-14 P18440 ARY1 Arylamine N-acetyltransferase 1 NAT1 +SeqId.11120-49 Q8WUY8 NAT14 N-acetyltransferase 14 NAT14 +SeqId.18261-34 Q8N6N6 NATD1 Protein NATD1 NATD1 +SeqId.2944-66 P41271 DAN Neuroblastoma suppressor of tumorigenicity 1 NBL1 +SeqId.7696-3 Q14596 NBR1 Next to BRCA1 gene 1 protein NBR1 +SeqId.17816-58 P61601 NCALD Neurocalcin-delta NCALD +SeqId.4498-62 P13591 NCAM-120 "Neural cell adhesion molecule 1, 120 kDa isoform" NCAM1 +SeqId.6507-16 O15394 NCAM2 Neural cell adhesion molecule 2 NCAM2 +SeqId.15573-110 O14594 CSPG3 Neurocan core protein NCAN +SeqId.17766-5 P14598 NCF-1 Neutrophil cytosol factor 1 NCF1 +SeqId.10047-12 P19878 NCF-2 Neutrophil cytosol factor 2 NCF2 +SeqId.14060-67 Q15080 NCF4 Neutrophil cytosol factor 4 NCF4 +SeqId.5014-49 P16333 NCK1 Cytoplasmic protein NCK1 NCK1 +SeqId.13615-60 O43639 NCK2 Cytoplasmic protein NCK2 NCK2 +SeqId.13655-34 P19338 Nucleolin Nucleolin NCL +SeqId.14614-41 Q5T1S8 CA130 Noncompact myelin-associated protein NCMAP +SeqId.14045-12 Q15596 NCOA2 Nuclear receptor coactivator 2 NCOA2 +SeqId.8360-169 O76036 NKp46 Natural cytotoxicity triggering receptor 1 NCR1 +SeqId.2734-49 O95944 NKp44 Natural cytotoxicity triggering receptor 2 NCR2 +SeqId.3003-29 O14931 NKp30 Natural cytotoxicity triggering receptor 3 NCR3 +SeqId.7854-38 Q68D85 NR3L1 Natural cytotoxicity triggering receptor 3 ligand 1 NCR3LG1 +SeqId.12730-3 O14777 KNTC2 Kinetochore protein NDC80 homolog NDC80 +SeqId.9765-4 Q9NXR1 NDE1 Nuclear distribution protein nudE homolog 1 NDE1 +SeqId.6604-59 Q8TB73 CD031 Protein NDNF NDNF +SeqId.19215-7 Q92597 NDRG1 Protein NDRG1 NDRG1 +SeqId.18312-68 Q9UGV2 NDRG3 Protein NDRG3 NDRG3 +SeqId.7934-11 Q9ULP0 NDRG4 Protein NDRG4 NDRG4 +SeqId.6927-7 P52848 NDST1 Bifunctional heparan sulfate N-deacetylase/N-sulfotransferase 1 NDST1 +SeqId.19200-16 Q16718 NDUA5 NADH dehydrogenase [ubiquinone] 1 alpha subcomplex subunit 5 NDUFA5 +SeqId.7747-47 Q9NX14 NDUBB "NADH dehydrogenase [ubiquinone] 1 beta subcomplex subunit 11, mitochondrial" NDUFB11 +SeqId.10677-9 O95168 NDUB4 NADH dehydrogenase [ubiquinone] 1 beta subcomplex subunit 4 NDUFB4 +SeqId.9800-20 O95169 NDUB8 "NADH dehydrogenase [ubiquinone] 1 beta subcomplex subunit 8, mitochondrial" NDUFB8 +SeqId.10584-7 O43181 NDUS4 "NADH dehydrogenase [ubiquinone] iron-sulfur protein 4, mitochondrial" NDUFS4 +SeqId.7748-11 P19404 NDUV2 "NADH dehydrogenase [ubiquinone] flavoprotein 2, mitochondrial" NDUFV2 +SeqId.12862-14 Q14511 CASL Enhancer of filamentation 1 NEDD9 +SeqId.9900-36 P12036 NFH Neurofilament heavy polypeptide NEFH +SeqId.10082-251 P07196 NFL Neurofilament light polypeptide NEFL +SeqId.13109-82 Q7Z3B1 NEGR1 Neuronal growth regulator 1 NEGR1 +SeqId.7050-5 Q7Z3B1 NEGR1 Neuronal growth regulator 1 NEGR1 +SeqId.12703-6 Q8TDX7 NEK7 Serine/threonine-protein kinase Nek7 NEK7 +SeqId.6544-33 Q92832 NELL1 Protein kinase C-binding protein NELL1 NELL1 +SeqId.6022-57 Q99435 NELL2 Protein kinase C-binding protein NELL2 NELL2 +SeqId.9219-70 Q9UMX5 NENF Neudesin NENF +SeqId.8900-28 Q92859 NEO1 Neogenin NEO1 +SeqId.14260-112 Q7Z628 ARHG8 Neuroepithelial cell-transforming gene 1 protein NET1 +SeqId.15298-199 Q8TDF5 NETO1 Neuropilin and tolloid-like protein 1 NETO1 +SeqId.5639-49 Q8TDF5 NETO1 Neuropilin and tolloid-like protein 1 NETO1 +SeqId.10562-42 Q8NC67 NETO2 Neuropilin and tolloid-like protein 2 NETO2 +SeqId.15426-5 Q99519 NEUR1 Sialidase-1 NEU1 +SeqId.13604-27 O76050 NEUL1 E3 ubiquitin-protein ligase NEURL1 NEURL1 +SeqId.13468-5 Q96JN8 NEUL4 Neuralized-like protein 4 NEURL4 +SeqId.7179-69 O94856 NFASC Neurofascin NFASC +SeqId.14286-2 O95644 NF-ATc1 "Nuclear factor of activated T-cells, cytoplasmic 1" NFATC1 +SeqId.11560-76 Q14934 NFAC4 "Nuclear factor of activated T-cells, cytoplasmic 4" NFATC4 +SeqId.11154-3 Q14494 NF2L1 Nuclear factor erythroid 2-related factor 1 NFE2L1 +SeqId.9869-28 P19838 NF-kappa-B p105 Nuclear factor NF-kappa-B p105 subunit NFKB1 +SeqId.19209-6 P25963 IKB-alpha NF-kappa-B inhibitor alpha NFKBIA +SeqId.17387-27 Q15653 IKB-beta NF-kappa-B inhibitor beta NFKBIB +SeqId.19123-6 Q8NI38 IKBD NF-kappa-B inhibitor delta NFKBID +SeqId.7770-25 Q9UMS0 NFU1 "NFU1 iron-sulfur cluster scaffold homolog, mitochondrial" NFU1 +SeqId.5801-72 P01138 b-NGF beta-nerve growth factor NGF +SeqId.8374-5 P08138 NGF R Tumor necrosis factor receptor superfamily member 16 NGFR +SeqId.7153-66 Q9NPE2 NGRN Neugrin NGRN +SeqId.11351-233 Q9H9Q4 NHEJ1 Non-homologous end-joining factor 1 NHEJ1 +SeqId.9087-8 Q5JS37 NHLC3 NHL repeat-containing protein 3 NHLRC3 +SeqId.13602-6 P55769 NH2L1 NHP2-like protein 1 NHP2L1 +SeqId.3213-65 P14543 Nidogen Nidogen-1 NID1 +SeqId.16060-99 Q14112 NID2 Nidogen-2 NID2 +SeqId.12564-9 Q9Y221 NIP7 60S ribosome subunit biogenesis protein NIP7 homolog NIP7 +SeqId.12864-9 Q0D2K0 NIPA4 Magnesium transporter NIPA4 NIPAL4 +SeqId.12738-43 Q9Y2I1 NISCH Nischarin NISCH +SeqId.17808-37 Q9NQR4 NIT2 Omega-amidase NIT2 NIT2 +SeqId.15620-4 Q8N2Q7 NLGN1 Neuroligin-1 NLGN1 +SeqId.9027-10 Q8NFZ4 NLGN2 Neuroligin-2 NLGN2 +SeqId.9772-153 Q8NFZ4 NLGN2 Neuroligin-2 NLGN2 +SeqId.17427-26 Q9NZ94 NLGN3 Neuroligin-3 NLGN3 +SeqId.8941-4 Q9NZ94 NLGN3 Neuroligin-3 NLGN3 +SeqId.5357-60 Q8N0W4 NLGNX "Neuroligin-4, X-linked" NLGN4X +SeqId.11661-11 Q9C000 NALP1 "NACHT, LRR and PYD domains-containing protein 1" NLRP1 +SeqId.12821-6 Q86W26 NAL10 "NACHT, LRR and PYD domains-containing protein 10" NLRP10 +SeqId.12794-6 Q96MN2 NALP4 "NACHT, LRR and PYD domains-containing protein 4" NLRP4 +SeqId.9321-400 P08949 NMB Neuromedin-B NMB +SeqId.5909-51 P15531 Nucleoside diphosphate kinase A Nucleoside diphosphate kinase A NME1 +SeqId.4249-64 P22392 NDP kinase B Nucleoside diphosphate kinase B NME2 +SeqId.16809-1 O00746 NDKM "Nucleoside diphosphate kinase, mitochondrial" NME4 +SeqId.6406-3 Q9C002 NMES1 Normal mucosa of esophagus-specific gene 1 protein NMES1 +SeqId.17512-2 Q13287 NMI N-myc-interactor NMI +SeqId.18932-84 Q9HAN9 NMNA1 Nicotinamide/nicotinic acid mononucleotide adenylyltransferase 1 NMNAT1 +SeqId.13988-67 Q9HBL8 NMRL1 NmrA-like family domain-containing protein 1 NMRAL1 +SeqId.9503-1 Q5H8A3 NMS Neuromedin-S NMS +SeqId.5196-7 P30419 NMT1 Glycylpeptide N-tetradecanoyltransferase 1 NMT1 +SeqId.17821-20 O60551 NMT2 Glycylpeptide N-tetradecanoyltransferase 2 NMT2 +SeqId.8754-5 P48645 NMU Neuromedin-U NMU +SeqId.9374-24 Q16517 NNAT Neuronatin NNAT +SeqId.19376-74 P40261 NNMT Nicotinamide N-methyltransferase NNMT +SeqId.15692-300 Q96S42 NODAL Nodal homolog NODAL +SeqId.8778-3 Q13253 Noggin Noggin NOG +SeqId.18228-30 Q9Y3C1 NOP16 Nucleolar protein 16 NOP16 +SeqId.5107-7 P46531 Notch 1 Neurogenic locus notch homolog protein 1 NOTCH1 +SeqId.11297-54 Q04721 NOTC2 Neurogenic locus notch homolog protein 2 NOTCH2 +SeqId.5106-52 Q04721 NOTC2 Neurogenic locus notch homolog protein 2 NOTCH2 +SeqId.5108-72 Q9UM47 Notch-3 Neurogenic locus notch homolog protein 3 NOTCH3 +SeqId.8252-2 Q6P988 NOTUM Palmitoleoyl-protein carboxylesterase NOTUM NOTUM +SeqId.2737-22 P48745 NovH Protein NOV homolog NOV +SeqId.12557-18 P51513 NOVA1 RNA-binding protein Nova-1 NOVA1 +SeqId.10424-31 Q9NQX5 NPDC1 Neural proliferation differentiation and control protein 1 NPDC1 +SeqId.5617-41 O15130 NPFF Pro-FMRFamide-related neuropeptide FF NPFF +SeqId.9954-2 Q92617 NPPL3 Nuclear pore complex-interacting protein family member B3 NPIPB3 +SeqId.19496-1 Q9BXD5 NPL N-acetylneuraminate lyase NPL +SeqId.12993-21 Q8TAT6 NPL4 Nuclear protein localization protein 4 homolog NPLOC4 +SeqId.8870-38 P06748 NPM1 Nucleophosmin NPM1 +SeqId.6342-10 Q6UXI9 Nephronectin Nephronectin NPNT +SeqId.5443-62 P01160 ANP Atrial natriuretic factor NPPA +SeqId.3723-1 P16860 BNP-32 Brain natriuretic peptide 32 NPPB +SeqId.16751-15 P16860 BNP Natriuretic peptides B NPPB +SeqId.7655-11 P16860 N-terminal pro-BNP N-terminal pro-BNP NPPB +SeqId.6390-18 P0C0P6 NPS Neuropeptide S NPS +SeqId.7194-36 Q9Y639 NPTN Neuroplastin NPTN +SeqId.9256-78 Q15818 NPTX1 Neuronal pentraxin-1 NPTX1 +SeqId.6521-35 P47972 NPTX2 Neuronal pentraxin-2 NPTX2 +SeqId.15511-37 O95502 NPTXR Neuronal pentraxin receptor NPTXR +SeqId.9986-14 Q8N729 Neuropeptide W Neuropeptide W NPW +SeqId.9837-60 P15559 NAD(P)H dehydrogenase NAD(P)H dehydrogenase [quinone] 1 NQO1 +SeqId.9754-33 P16083 Quinone reductase 2 Ribosyldihydronicotinamide dehydrogenase [quinone] NQO2 +SeqId.5236-2 P20393 NR1D1 Nuclear receptor subfamily 1 group D member 1 NR1D1 +SeqId.12885-42 Q14995 NR1D2 Nuclear receptor subfamily 1 group D member 2 NR1D2 +SeqId.9016-12 P55055 NR1H2 Oxysterols receptor LXR-beta NR1H2 +SeqId.8946-38 Q96RI1 NR1H4 Bile acid receptor NR1H4 +SeqId.12931-16 P08235 MCR Mineralocorticoid receptor NR3C2 +SeqId.8089-173 P22736 NR4A1 Nuclear receptor subfamily 4 group A member 1 NR4A1 +SeqId.12444-39 O00482 NR5A2 Nuclear receptor subfamily 5 group A member 2 NR5A2 +SeqId.13464-8 Q8N912 NRAC Nutritionally-regulated adipose and cardiac enriched protein homolog NRAC +SeqId.10531-18 P01111 RASN GTPase NRas NRAS +SeqId.12616-45 Q9UHY1 NRBP Nuclear receptor-binding protein NRBP1 +SeqId.5109-24 Q92823 Nr-CAM Neuronal cell adhesion molecule NRCAM +SeqId.15446-25 Q02297 SMDF "Neuregulin-1, sensory and motor neuron-derived factor isoform" NRG1 +SeqId.9178-30 Q02297 NEUREGULIN-1 Neuregulin-1 NRG1 +SeqId.8060-7 O14511 NRG2 "Pro-neuregulin-2, membrane-bound isoform" NRG2 +SeqId.10981-56 P56975 NRG3 "Pro-neuregulin-3, membrane-bound isoform" NRG3 +SeqId.14139-16 Q8WWG1 NRG4 Neuregulin-4 NRG4 +SeqId.18303-39 Q92686 NEUG Neurogranin NRGN +SeqId.18237-29 Q9NQ35 NRIP3 Nuclear receptor-interacting protein 3 NRIP3 +SeqId.16853-5 Q9NWW6 NRK1 Nicotinamide riboside kinase 1 NRK1 +SeqId.5542-22 O14786 NRP1 Neuropilin-1 NRP1 +SeqId.15387-44 O60462 Neuropilin-2 Neuropilin-2 NRP2 +SeqId.11654-77 Q8IZ57 NRSN1 Neurensin-1 NRSN1 +SeqId.5110-84 P58400 NRX1B Neurexin-1-beta NRXN1 +SeqId.8971-9 Q9ULB1 NRX1A Neurexin-1 NRXN1 +SeqId.8876-51 P58401 NRX2B Neurexin-2-beta NRXN2 +SeqId.5111-15 Q9HDB5 NRX3B Neurexin-3-beta NRXN3 +SeqId.16323-8 Q9Y4C0 NRX3A Neurexin-3 NRXN3 +SeqId.8038-41 Q15738 NSDHL "Sterol-4-alpha-carboxylate 3-dehydrogenase, decarboxylating" NSDHL +SeqId.13992-12 P46459 NSF Vesicle-fusing ATPase NSF +SeqId.4250-23 Q9UNZ2 NSF1C NSFL1 cofactor p47 NSFL1C +SeqId.12560-9 Q8TCD5 NT5C "5'(3')-deoxyribonucleotidase, cytosolic type" NT5C +SeqId.11288-26 P49902 5NTC Cytosolic purine 5'-nucleotidase NT5C2 +SeqId.19615-213 Q9H0P0 5NT3 Cytosolic 5'-nucleotidase 3A NT5C3A +SeqId.19135-5 Q969T7 Cytosolic 5'-nucleotidase III-like protein 7-methylguanosine phosphate-specific 5'-nucleotidase NT5C3L +SeqId.9126-171 Q86UY8 NT5D3 5'-nucleotidase domain-containing protein 3 NT5DC3 +SeqId.15452-5 P21589 5'-Nucleotidase 5'-Nucleotidase NT5E +SeqId.17856-23 Q9NPB1 NT5M "5'(3')-deoxyribonucleotidase, mitochondrial" NT5M +SeqId.4145-58 P20783 Neurotrophin-3 Neurotrophin-3 NTF3 +SeqId.4146-58 P34130 Neurotrophin-5 Neurotrophin-4 NTF4 +SeqId.10907-116 Q9P121 NTRI Neurotrimin NTM +SeqId.8428-102 Q9P121 NTRI Neurotrimin NTM +SeqId.12454-105 Q9BV86 NTM1A N-terminal Xaa-Pro-Lys N-methyltransferase 1 NTMT1 +SeqId.6649-51 O95631 NET1 Netrin-1 NTN1 +SeqId.3327-27 Q9HB63 NET4 Netrin-4 NTN4 +SeqId.5637-81 Q9Y2I2 NTNG1 Netrin-G1 NTNG1 +SeqId.3477-63 P04629 TrkA High affinity nerve growth factor receptor NTRK1 +SeqId.4866-59 Q16620 TrkB BDNF/NT-3 growth factors receptor NTRK2 +SeqId.2658-27 Q16288 TrkC NT-3 growth factor receptor NTRK3 +SeqId.7857-22 P30990 NEUT Neurotensin/neuromedin N NTS +SeqId.10451-11 Q02818 NUCB1 Nucleobindin-1 NUCB1 +SeqId.8887-21 Q9Y266 NUDC Nuclear migration protein nudC NUDC +SeqId.4254-6 Q8IVD9 NUDC3 NudC domain-containing protein 3 NUDCD3 +SeqId.19206-20 P36639 8ODP "7,8-dihydro-8-oxoguanine triphosphatase" NUDT1 +SeqId.13947-371 Q9BQG2 NUD12 Peroxisomal NADH pyrophosphatase NUDT12 NUDT12 +SeqId.12497-29 Q9BRJ7 SDOS Tudor-interacting repair regulator protein NUDT16L1 +SeqId.16583-8 P50583 AP4A Bis(5'-nucleosyl)-tetraphosphatase [asymmetrical] NUDT2 +SeqId.12796-44 O95989 NUDT3 Diphosphoinositol polyphosphate phosphohydrolase 1 NUDT3 +SeqId.17761-2 Q9UKK9 NUDT5 ADP-sugar pyrophosphatase NUDT5 +SeqId.9482-110 Q9BW91 NUDT9 "ADP-ribose pyrophosphatase, mitochondrial" NUDT9 +SeqId.9606-4 Q5VU65 P210L Nuclear pore membrane glycoprotein 210-like NUP210L +SeqId.12772-8 P52948 NUP98 Nuclear pore complex protein Nup98-Nup96 NUP98 +SeqId.19219-71 P61970 NTF-2 Nuclear transport factor 2 NUTF2 +SeqId.12453-161 Q9UBU9 NXF1 Nuclear RNA export factor 1 NXF1 +SeqId.4562-1 P58417 NXPH1 Neurexophilin-1 NXPH1 +SeqId.9511-61 O95156 NXPH2 Neurexophilin-2 NXPH2 +SeqId.6054-6 O95157 NXPH3 Neurexophilin-3 NXPH3 +SeqId.9942-2 Q9UKK6 NXT1 NTF2-related export protein 1 NXT1 +SeqId.19255-124 Q9NPJ8 NXT2 NTF2-related export protein 2 NXT2 +SeqId.6414-8 Q86UD1 OAF Out at first protein homolog OAF +SeqId.10361-25 P00973 OAS1 2'-5'-oligoadenylate synthase 1 OAS1 +SeqId.9893-27 P54368 Ornithine decarboxylase antizyme Ornithine decarboxylase antizyme 1 OAZ1 +SeqId.6526-77 Q9NY56 OBP2A Odorant-binding protein 2a OBP2A +SeqId.5680-54 Q9NPH6 OBP2B Odorant-binding protein 2b OBP2B +SeqId.16802-31 Q9NX40 OCAD1 OCIA domain-containing protein 1 OCIAD1 +SeqId.10011-65 Q01968 OCRL Inositol polyphosphate 5-phosphatase OCRL-1 OCRL +SeqId.13689-2 P11926 Ornithine decarboxylase Ornithine decarboxylase ODC1 +SeqId.17224-12 P20774 MIME Mimecan OGN +SeqId.6296-36 Q8WWZ8 OIT3 Oncoprotein-induced transcript 3 protein OIT3 +SeqId.12659-13 Q9NTK5 GTPB9 Obg-like ATPase 1 OLA1 +SeqId.5703-26 Q99784 NOE1 Noelin OLFM1 +SeqId.19377-14 O95897 NOE2 Noelin-2 OLFM2 +SeqId.10643-16 Q96PB7 NOE3 Noelin-3 OLFM3 +SeqId.11143-32 Q96PB7 NOE3 Noelin-3 OLFM3 +SeqId.4769-10 Q6UX06 Olfactomedin-4 Olfactomedin-4 OLFM4 +SeqId.8815-1 Q6UWY5 OLFL1 Olfactomedin-like protein 1 OLFML1 +SeqId.8660-5 Q9NRN5 OLFL3 Olfactomedin-like protein 3 OLFML3 +SeqId.16049-43 P78380 OLR1 Oxidized low-density lipoprotein receptor 1 OLR1 +SeqId.5358-3 Q99983 OMD Osteomodulin OMD +SeqId.16908-5 P23515 OMGP Oligodendrocyte-myelin glycoprotein OMG +SeqId.18240-6 P47874 OMP Olfactory marker protein OMP +SeqId.7106-37 Q86WS3 PLACL Oocyte-secreted protein 2 OOSP2 +SeqId.7736-28 Q96PE5 OPALI Opalin OPALIN +SeqId.15622-13 Q14982 OBCAM Opioid-binding protein/cell adhesion molecule OPCML +SeqId.12591-27 O60890 Oligophrenin-1 Oligophrenin-1 OPHN1 +SeqId.15430-165 Q9UBM4 OPT Opticin OPTC +SeqId.18195-3 Q8WV07 ORAV1 Oral cancer-overexpressed protein 1 ORAOV1 +SeqId.12389-4 Q9Y5N6 ORC6 Origin recognition complex subunit 6 ORC6L +SeqId.12878-60 Q9BXB4 OSB11 Oxysterol-binding protein-related protein 11 OSBPL11 +SeqId.16899-59 Q96SU4 OSBL9 Oxysterol-binding protein-related protein 9 OSBPL9 +SeqId.7116-31 Q8IYS5 OSCAR Osteoclast-associated immunoglobulin-like receptor OSCAR +SeqId.14063-17 P13725 OSM Oncostatin-M OSM +SeqId.2693-20 P13725 OSM Oncostatin-M OSM +SeqId.10892-8 Q99650 OSMR Oncostatin-M-specific receptor subunit beta OSMR +SeqId.19118-47 Q92882 OSTF1 Osteoclast-stimulating factor 1 OSTF1 +SeqId.19353-25 Q86WC4 OSTM1 Osteopetrosis-associated transmembrane protein 1 OSTM1 +SeqId.7265-32 P61366 OSTN Osteocrin OSTN +SeqId.15431-31 P00480 OTCase "Ornithine carbamoyltransferase, mitochondrial" OTC +SeqId.15432-1 Q9NRC9 Otoraplin Otoraplin OTOR +SeqId.12493-42 Q96DC9 OTUB2 Ubiquitin thioesterase OTUB2 OTUB2 +SeqId.12480-9 Q96G74 OTUD5 OTU domain-containing protein 5 OTUD5 +SeqId.17697-2 Q8WZ82 OVCA2 Esterase OVCA2 OVCA2 +SeqId.18271-43 Q9NWU1 OXSM "3-oxoacyl-[acyl-carrier-protein] synthase, mitochondrial" OXSM +SeqId.8356-88 P01178 NEU1 Oxytocin-neurophysin 1 OXT +SeqId.7233-73 O15547 P2RX6 P2X purinoceptor 6 P2RX6 +SeqId.11645-9 P13674 P4HA1 Prolyl 4-hydroxylase subunit alpha-1 P4HA1 +SeqId.11348-132 O15460 P4HA2 Prolyl 4-hydroxylase subunit alpha-2 P4HA2 +SeqId.4278-14 P07237 Protein disulfide-isomerase Protein disulfide-isomerase P4HB +SeqId.4258-15 Q9UQ80 PA2G4 Proliferation-associated protein 2G4 PA2G4 +SeqId.10447-18 Q9H361 PABP3 Polyadenylate-binding protein 3 PABPC3 +SeqId.12603-87 Q13310 PABP4 Polyadenylate-binding protein 4 PABPC4 +SeqId.8921-139 Q86U42 PABP2 Polyadenylate-binding protein 2 PABPN1 +SeqId.16322-10 Q8WU39 PACAP Marginal zone B- and B1-cell-specific protein PACAP +SeqId.12676-1 Q9BY11 PACN1 Protein kinase C and casein kinase substrate in neurons protein 1 PACSIN1 +SeqId.14674-63 Q9UKS6 PACN3 Protein kinase C and casein kinase substrate in neurons protein 3 PACSIN3 +SeqId.8867-18 P09466 Glycodelin Glycodelin PAEP +SeqId.19158-1 Q15004 PAF PCNA-associated factor PAF +SeqId.2642-4 P68402 PAFAH beta subunit Platelet-activating factor acetylhydrolase IB subunit beta PAFAH1B2 +SeqId.12374-8 Q15102 PA1B3 Platelet-activating factor acetylhydrolase IB subunit gamma PAFAH1B3 +SeqId.18914-188 Q99487 PAFA2 "Platelet-activating factor acetylhydrolase 2, cytoplasmic" PAFAH2 +SeqId.9841-197 P22234 Multifunctional protein ADE2 Multifunctional protein ADE2 PAICS +SeqId.12430-78 Q9H074 PAIP1 Polyadenylate-binding protein-interacting protein 1 PAIP1 +SeqId.3387-1 O75914 PAK3 Serine/threonine-protein kinase PAK 3 PAK3 +SeqId.13719-19 O96013 PAK4 Serine/threonine-protein kinase PAK 4 PAK4 +SeqId.3827-22 Q9NQU5 PAK6 Serine/threonine-protein kinase PAK 6 PAK6 +SeqId.3388-58 Q9P286 PAK7 Serine/threonine-protein kinase PAK 5 PAK7 +SeqId.18306-1 O75781 PALM Paralemmin-1 PALM +SeqId.5620-13 P19021 AMD Peptidyl-glycine alpha-amidating monooxygenase PAM +SeqId.12658-72 Q9H999 PANK3 Pantothenate kinase 3 PANK3 +SeqId.8011-96 Q6ZNF0 PAPL Iron/zinc purple acid phosphatase-like protein PAPL +SeqId.11254-13 O95428 PPN Papilin PAPLN +SeqId.8343-224 Q9BWT3 PAPOG Poly(A) polymerase gamma PAPOLG +SeqId.4148-49 Q13219 PAPP-A Pappalysin-1 PAPPA +SeqId.5756-66 Q9BXP8 PAPP2 Pappalysin-2 PAPPA2 +SeqId.14007-22 O43252 PAPS1 Bifunctional 3'-phosphoadenosine 5'-phosphosulfate synthase 1 PAPSS1 +SeqId.13013-41 O60260 PRKN2 E3 ubiquitin-protein ligase parkin PARK2 +SeqId.19523-215 Q99497 PARK7 Protein DJ-1 PARK7 +SeqId.19545-145 Q99497 Oxidized PARK7 Oxidized Protein deglycase DJ-1 PARK7 +SeqId.10534-40 P09874 PARP Poly [ADP-ribose] polymerase 1 PARP1 +SeqId.8893-29 P09874 PARP Poly [ADP-ribose] polymerase 1 PARP1 +SeqId.12882-7 Q9NR21 PAR11 Poly [ADP-ribose] polymerase 11 PARP11 +SeqId.7881-244 Q8N5Y8 PAR16 Mono [ADP-ribose] polymerase PARP16 PARP16 +SeqId.13434-172 Q9NVD7 PARVA Alpha-parvin PARVA +SeqId.8386-11 Q8WXA2 PATE Prostate and testis expressed protein 1 PATE1 +SeqId.8065-245 P0C8F1 PATE4 Prostate and testis expressed protein 4 PATE4 +SeqId.9565-6 Q96IZ0 PAWR PRKC apoptosis WT1 regulator protein PAWR +SeqId.12398-15 O43316 PAX4 Paired box protein Pax-4 PAX4 +SeqId.12894-3 Q6ZW49 PAXI1 PAX-interacting protein 1 PAXIP1 +SeqId.17475-18 Q96KB5 TOPK Lymphokine-activated killer T-cell-originated protein kinase PBK +SeqId.12518-289 Q86U86 PB1 Protein polybromo-1 PBRM1 +SeqId.13990-1 P11498 pyruvate carboxylase "Pyruvate carboxylase, mitochondrial" PC +SeqId.11313-100 P61457 PHS Pterin-4-alpha-carbinolamine dehydratase PCBD1 +SeqId.6899-37 Q9H0N5 PHS2 Pterin-4-alpha-carbinolamine dehydratase 2 PCBD2 +SeqId.11458-30 Q15365 PCBP1 Poly(rC)-binding protein 1 PCBP1 +SeqId.8780-2 Q9P2E7 PCD10 Protocadherin-10 PCDH10 +SeqId.9018-38 Q9P2E7 PCD10 Protocadherin-10 PCDH10 +SeqId.6280-11 O95206 PCDH8 Protocadherin-8 PCDH8 +SeqId.10558-26 Q9HC56 PCDH9 Protocadherin-9 PCDH9 +SeqId.7157-22 Q9UN74 PCDA4 Protocadherin alpha-4 PCDHA4 +SeqId.8758-2 Q9UN72 PCDA7 Protocadherin alpha-7 PCDHA7 +SeqId.7193-98 Q9H158 PCDC1 Protocadherin alpha-C1 PCDHAC1 +SeqId.9361-7 Q9Y5I4 PCDC2 Protocadherin alpha-C2 PCDHAC2 +SeqId.9941-70 Q9Y5F3 PCDB1 Protocadherin beta-1 PCDHB1 +SeqId.9963-19 Q9UN67 PCDBA Protocadherin beta-10 PCDHB10 +SeqId.10748-216 Q9Y5E7 PCDB2 Protocadherin beta-2 PCDHB2 +SeqId.8071-114 Q9Y5E2 PCDB7 Protocadherin beta-7 PCDHB7 +SeqId.6457-50 Q9Y5H4 PCDG1 Protocadherin gamma-A1 PCDHGA1 +SeqId.6321-65 Q9Y5H3 PCDGA Protocadherin gamma-A10 PCDHGA10 +SeqId.6938-21 O60330 PCDGC Protocadherin gamma-A12 PCDHGA12 +SeqId.7175-4 Q9Y5H1 PCDG2 Protocadherin gamma-A2 PCDHGA2 +SeqId.11872-9 Q9Y5G3 PCDGD Protocadherin gamma-B1 PCDHGB1 +SeqId.7859-21 Q9UN70 PCDGK Protocadherin gamma-C3 PCDHGC3 +SeqId.7983-1 Q9Y5F6 PCDGM Protocadherin gamma-C5 PCDHGC5 +SeqId.18182-24 P35558 PCKGC "Phosphoenolpyruvate carboxykinase, cytosolic [GTP]" PCK1 +SeqId.18160-2 P22061 PIMT Protein-L-isoaspartate(D-aspartate) O-methyltransferase PCMT1 +SeqId.19364-163 P12004 PCNA Proliferating cell nuclear antigen PCNA +SeqId.17769-28 Q8WW12 PCNP PEST proteolytic signal-containing nuclear protein PCNP +SeqId.11237-49 Q15113 PCOC1 Procollagen C-endopeptidase enhancer 1 PCOLCE +SeqId.6081-52 Q9UKZ9 PCOC2 Procollagen C-endopeptidase enhancer 2 PCOLCE2 +SeqId.13388-57 P29120 NEC1 Neuroendocrine convertase 1 PCSK1 +SeqId.9391-60 Q9UHG2 PCSK1 ProSAAS PCSK1N +SeqId.15440-57 P16519 NEC2 Neuroendocrine convertase 2 PCSK2 +SeqId.6117-4 P16519 NEC2 Neuroendocrine convertase 2 PCSK2 +SeqId.4459-68 Q16549 PCSK7 Proprotein convertase subtilisin/kexin type 7 PCSK7 +SeqId.5231-79 Q8NBP7 PCSK9 Proprotein convertase subtilisin/kexin type 9 PCSK9 +SeqId.16867-76 Q00536 PCTK1 Cyclin-dependent kinase 16 PCTK1 +SeqId.6431-68 Q9UHG3 PCYOX Prenylcysteine oxidase 1 PCYOX1 +SeqId.5599-88 Q8NBM8 PCYXL Prenylcysteine oxidase-like PCYOX1L +SeqId.19240-265 Q13442 HAP28 28 kDa heat- and acid-stable phosphoprotein PDAP1 +SeqId.15623-1 Q15116 PD-1 Programmed cell death protein 1 PDCD1 +SeqId.3004-67 Q9BQ51 PD-L2 Programmed cell death 1 ligand 2 PDCD1LG2 +SeqId.17202-37 Q53EL6 PDCD4 Programmed cell death protein 4 PDCD4 +SeqId.12517-52 O14737 TFAR19 Programmed cell death protein 5 PDCD5 +SeqId.19488-1 O75340 PDCD6 Programmed cell death protein 6 PDCD6 +SeqId.18174-79 Q8WUM4 PDC6I Programmed cell death 6-interacting protein PDCD6IP +SeqId.14192-31 Q8N4E4 PDCL2 Phosducin-like protein 2 PDCL2 +SeqId.5252-33 Q9HCR9 PDE11 "Dual 3',5'-cyclic-AMP and -GMP phosphodiesterase 11A" PDE11A +SeqId.5253-1 P54750 PDE1A "Calcium/calmodulin-dependent 3',5'-cyclic nucleotide phosphodiesterase 1A" PDE1A +SeqId.5246-64 O00408 cGMP-stimulated PDE "cGMP-dependent 3',5'-cyclic phosphodiesterase" PDE2A +SeqId.5254-69 Q14432 PDE3A "cGMP-inhibited 3',5'-cyclic phosphodiesterase A" PDE3A +SeqId.18918-86 P27815 PDE4A "cAMP-specific 3',5'-cyclic phosphodiesterase 4A" PDE4A +SeqId.5255-22 Q08499 PDE4D "cAMP-specific 3',5'-cyclic phosphodiesterase 4D" PDE4D +SeqId.16805-5 O76074 PDE5A "cGMP-specific 3',5'-cyclic phosphodiesterase" PDE5A +SeqId.5256-86 O76074 PDE5A "cGMP-specific 3',5'-cyclic phosphodiesterase" PDE5A +SeqId.13491-40 O43924 PDE6D "Retinal rod rhodopsin-sensitive cGMP 3',5'-cyclic phosphodiesterase subunit delta" PDE6D +SeqId.5178-5 Q13946 PDE7A "High affinity cAMP-specific 3',5'-cyclic phosphodiesterase 7A" PDE7A +SeqId.5201-50 O76083 PDE9A "High affinity cGMP-specific 3',5'-cyclic phosphodiesterase 9A" PDE9A +SeqId.4499-21 P04085 PDGF-AA Platelet-derived growth factor subunit A PDGFA +SeqId.4149-8 P01127 PDGF-BB Platelet-derived growth factor subunit B PDGFB +SeqId.13658-31 Q9NRA1 PDGF-CC Platelet-derived growth factor C PDGFC +SeqId.17140-57 Q9GZP0 PDGFD Platelet-derived growth factor D PDGFD +SeqId.9341-1 Q9GZP0 PDGFD Platelet-derived growth factor D PDGFD +SeqId.10366-11 P16234 PDGFRA Platelet-derived growth factor receptor alpha PDGFRA +SeqId.3459-49 P09619 PDGF Rb Platelet-derived growth factor receptor beta PDGFRB +SeqId.9713-67 Q15198 PGFRL Platelet-derived growth factor receptor-like protein PDGFRL +SeqId.18319-7 O00330 ODPX "Pyruvate dehydrogenase protein X component, mitochondrial" PDHX +SeqId.4719-58 P30101 Protein disulfide isomerase A3 Protein disulfide-isomerase A3 PDIA3 +SeqId.7146-16 P13667 PDIA4 Protein disulfide-isomerase A4 PDIA4 +SeqId.5593-11 Q14554 PDIA5 Protein disulfide-isomerase A5 PDIA5 +SeqId.5650-9 Q15084 PDIA6 Protein disulfide-isomerase A6 PDIA6 +SeqId.7092-7 Q8N807 PDILT Protein disulfide-isomerase-like protein of the testis PDILT +SeqId.5227-60 Q15118 PDK1 "[Pyruvate dehydrogenase (acetyl-transferring)] kinase isozyme 1, mitochondrial" PDK1 +SeqId.12651-21 Q15119 PDK2 "[Pyruvate dehydrogenase (acetyl-transferring)] kinase isozyme 2, mitochondrial" PDK2 +SeqId.11428-31 O00151 PDLI1 PDZ and LIM domain protein 1 PDLIM1 +SeqId.12387-7 P50479 PDLI4 PDZ and LIM domain protein 4 PDLIM4 +SeqId.4460-8 O15530 PDPK1 3-phosphoinositide-dependent protein kinase 1 PDPK1 +SeqId.12593-33 Q9NUG6 PDRG1 p53 and DNA damage-regulated protein 1 PDRG1 +SeqId.11098-1 O00764 PDXK Pyridoxal kinase PDXK +SeqId.3897-61 Q96GD0 PLPP Pyridoxal phosphate phosphatase PDXP +SeqId.19638-9 P01213 Dynorphin A (1-17) Dynorphin A (1-17) PDYN +SeqId.6219-14 Q5EBL8 PDZ11 PDZ domain-containing protein 11 PDZD11 +SeqId.12391-27 Q9H5P4 PDZD7 PDZ domain-containing protein 7 PDZD7 +SeqId.16852-10 Q5T2W1 NHRF3 Na(+)/H(+) exchange regulatory cofactor NHE-RF3 PDZK1 +SeqId.18833-76 Q15121 PEA15 Astrocytic phosphoprotein PEA-15 PEA15 +SeqId.8275-31 Q5VY43 PEAR1 Platelet endothelial aggregation receptor 1 PEAR1 +SeqId.8892-14 Q5VY43 PEAR1 Platelet endothelial aggregation receptor 1 PEAR1 +SeqId.4276-10 P30086 prostatic binding protein Phosphatidylethanolamine-binding protein 1 PEBP1 +SeqId.2695-25 P16284 PECAM-1 Platelet endothelial cell adhesion molecule PECAM1 +SeqId.17776-15 Q9BY49 PECR Peroxisomal trans-2-enoyl-CoA reductase PECR +SeqId.19272-9 Q9UBV8 PEF1 Peflin PEF1 +SeqId.12702-13 Q9HAT8 PELI2 E3 ubiquitin-protein ligase pellino homolog 2 PELI2 +SeqId.12431-13 Q9BRX2 PELO Protein pelota homolog PELO +SeqId.9076-25 P01210 PENK Proenkephalin-A PENK +SeqId.4267-81 O00541 PESC Pescadillo homolog PES1 +SeqId.19303-64 Q6UWS5 PT117 "Protein PET117 homolog, mitochondrial" PET117 +SeqId.8300-82 O75381 PEX14 Peroxisomal membrane protein PEX14 PEX14 +SeqId.19366-8 Q7Z412 PEX26 Peroxisome assembly protein 26 PEX26 +SeqId.5915-58 P50542 PEX5 Peroxisomal targeting signal 1 receptor PEX5 +SeqId.2697-7 P02776 PF-4 Platelet factor 4 PF4 +SeqId.5663-18 P10720 PF4V Platelet factor 4 variant PF4V1 +SeqId.19242-21 O60925 PFD1 Prefoldin subunit 1 PFDN1 +SeqId.19243-2 Q9UHV9 PFD2 Prefoldin subunit 2 PFDN2 +SeqId.4271-75 Q99471 PFD5 Prefoldin subunit 5 PFDN5 +SeqId.12456-5 Q16875 F263 "6-phosphofructo-2-kinase/fructose-2,6-bisphosphatase 3" PFKFB3 +SeqId.17384-110 P08237 K6PF "ATP-dependent 6-phosphofructokinase, muscle type" PFKM +SeqId.16923-20 P35080 Profilin II Profilin-2 PFN2 +SeqId.3896-5 P18669 Phosphoglycerate mutase 1 Phosphoglycerate mutase 1 PGAM1 +SeqId.15524-30 P15259 PGAM2 Phosphoglycerate mutase 2 PGAM2 +SeqId.4187-49 P52209 6-Phosphogluconate dehydrogenase "6-phosphogluconate dehydrogenase, decarboxylating" PGD +SeqId.3078-1 P49763 PlGF Placenta growth factor PGF +SeqId.5020-50 P00558 phosphoglycerate kinase 1 Phosphoglycerate kinase 1 PGK1 +SeqId.13936-24 P07205 PGK2 Phosphoglycerate kinase 2 PGK2 +SeqId.17799-9 O95336 6PGL 6-phosphogluconolactonase PGLS +SeqId.3329-14 O75594 PGRP-S Peptidoglycan recognition protein 1 PGLYRP1 +SeqId.5601-2 Q96PD5 PGRP-L N-acetylmuramoyl-L-alanine amidase PGLYRP2 +SeqId.10561-5 Q96LB9 PGRP-I-alpha Peptidoglycan recognition protein 3 PGLYRP3 +SeqId.9173-21 P36871 PGM1 Phosphoglucomutase-1 PGM1 +SeqId.18330-7 Q96G03 PGM2 Phosphoglucomutase-2 PGM2 +SeqId.18235-16 A6NDG6 PGP Glycerol-3-phosphate phosphatase PGP +SeqId.15693-9 P06401 PgR Progesterone receptor PGR +SeqId.7863-50 O00264 PGRC1 Membrane-associated progesterone receptor component 1 PGRMC1 +SeqId.10506-53 O15173 PGRC2 Membrane-associated progesterone receptor component 2 PGRMC2 +SeqId.8681-93 O15173 PGRC2 Membrane-associated progesterone receptor component 2 PGRMC2 +SeqId.18921-30 P78562 PHEX Phosphate-regulating neutral endopeptidase PHEX +SeqId.11544-39 Q92576 PHF3 PHD finger protein 3 PHF3 +SeqId.15548-35 O43175 SERA D-3-phosphoglycerate dehydrogenase PHGDH +SeqId.16882-27 Q9NRX4 PHP14 14 kDa phosphohistidine phosphatase PHPT1 +SeqId.5745-64 O43692 PI15 Peptidase inhibitor 15 PI15 +SeqId.4982-54 P19957 Elafin Elafin PI3 +SeqId.14114-18 Q8IYJ0 PIANP PILR alpha-associated neural protein PIANP +SeqId.9599-6 Q8IYJ0 PIANP PILR alpha-associated neural protein PIANP +SeqId.13513-174 Q9Y6X2 PIAS3 E3 SUMO-protein ligase PIAS3 PIAS3 +SeqId.10342-55 Q8N2W9 PIAS4 E3 SUMO-protein ligase PIAS4 PIAS4 +SeqId.11838-130 Q92508 FA38A Piezo-type mechanosensitive ion channel component 1 PIEZO1 +SeqId.3216-2 P01833 PIGR Polymeric immunoglobulin receptor PIGR +SeqId.14028-22 O00443 P3C2A Phosphatidylinositol 4-phosphate 3-kinase C2 domain-containing subunit alpha PIK3C2A +SeqId.3390-72 P42336 P27986 PIK3CA/PIK3R1 PIK3CA/PIK3R1 PIK3CA PIK3R1 +SeqId.3390-72 P42336 P27986 PIK3CA/PIK3R1 PIK3CA/PIK3R1 PIK3CA PIK3R1 +SeqId.3391-10 P48736 PK3CG "Phosphatidylinositol 4,5-bisphosphate 3-kinase catalytic subunit gamma isoform" PIK3CG +SeqId.8863-3 P27986 P85A Phosphatidylinositol 3-kinase regulatory subunit alpha PIK3R1 +SeqId.10816-150 Q9UKJ1 PILRA isoform FDF03-M14 Paired immunoglobulin-like type 2 receptor alpha isoform FDF03-M14 PILRA +SeqId.6402-8 Q9UKJ1 PILRA isoform FDF03-deltaTM Paired immunoglobulin-like type 2 receptor alpha isoform FDF03-deltaTM PILRA +SeqId.8825-4 Q9UKJ1 PILRA Paired immunoglobulin-like type 2 receptor alpha PILRA +SeqId.5359-65 P11309 PIM1 Serine/threonine-protein kinase pim-1 PIM1 +SeqId.15474-7 Q13526 PIN1 Peptidyl-prolyl cis-trans isomerase NIMA-interacting 1 PIN1 +SeqId.12718-43 Q9Y237 PIN4 Peptidyl-prolyl cis-trans isomerase NIMA-interacting 4 PIN4 +SeqId.6060-2 P12273 PIP Prolactin-inducible protein PIP +SeqId.12697-30 P48426 PI42A Phosphatidylinositol 5-phosphate 4-kinase type-2 alpha PIP4K2A +SeqId.18232-42 P78356 PI42B Phosphatidylinositol 5-phosphate 4-kinase type-2 beta PIP4K2B +SeqId.13634-209 O00625 PIR Pirin PIR +SeqId.9934-29 Q00169 PIPNA Phosphatidylinositol transfer protein alpha isoform PITPNA +SeqId.12484-67 P48739 PIPNB Phosphatidylinositol transfer protein beta isoform PITPNB +SeqId.12793-4 Q96J94 PIWL1 Piwi-like protein 1 PIWIL1 +SeqId.13486-9 Q13563 PKD2 Polycystin-2 PKD2 +SeqId.13745-10 Q13563 PKD2 Polycystin-2 PKD2 +SeqId.8664-36 Q504Y2 PKDCC Extracellular tyrosine-protein kinase PKDCC PKDCC +SeqId.15607-56 P30613 KPYR Pyruvate kinase PKLR PKLR +SeqId.4240-31 P14618 M2-PK Pyruvate kinase PKM PKM2 +SeqId.12562-1 Q16512 PKN1 Serine/threonine-protein kinase N1 PKN1 +SeqId.14067-6 Q99959 PKP2 Plakophilin-2 PKP2 +SeqId.9518-95 Q53H76 PLA1A Phospholipase A1 member A PLA1A +SeqId.2949-6 O15496 GX Group 10 secretory phospholipase A2 PLA2G10 +SeqId.9380-2 Q9BX93 sPLA(2)-XIII Group XIIB secretory phospholipase A2-like protein PLA2G12B +SeqId.7865-126 P53816 HRSL3 HRAS-like suppressor 3 PLA2G16 +SeqId.4910-21 P04054 GIB Phospholipase A2 PLA2G1B +SeqId.2692-74 P14555 NPS-PLA2 "Phospholipase A2, membrane associated" PLA2G2A +SeqId.8850-5 Q5R387 PA2GC Putative inactive group IIC secretory phospholipase A2 PLA2G2C +SeqId.16298-84 Q9UNK4 sPLA(2)-IID Group IID secretory phospholipase A2 PLA2G2D +SeqId.2447-7 Q9NZK7 GIIE Group IIE secretory phospholipase A2 PLA2G2E +SeqId.2449-1 P39877 GV Calcium-dependent phospholipase A2 PLA2G5 +SeqId.5015-15 Q13093 PAFAH Platelet-activating factor acetylhydrolase PLA2G7 +SeqId.10916-44 Q13018 PLA2R Secretory phospholipase A2 receptor PLA2R1 +SeqId.2212-69 P00750 tPA Tissue-type plasminogen activator PLAT +SeqId.4158-54 P00749 uPA Urokinase-type plasminogen activator PLAU +SeqId.2652-15 Q03405 suPAR Urokinase plasminogen activator surface receptor PLAUR +SeqId.6315-58 Q6P4A8 PLBL1 Phospholipase B-like 1 PLBD1 +SeqId.6536-54 Q8NHP8 LAML2 Putative phospholipase B-like 2 PLBD2 +SeqId.11354-21 Q9NQ66 Phospholipase C-beta-1 "1-phosphatidylinositol 4,5-bisphosphate phosphodiesterase beta-1" PLCB1 +SeqId.4563-61 P19174 PLCG1 "1-phosphatidylinositol 4,5-bisphosphate phosphodiesterase gamma-1" PLCG1 +SeqId.10070-22 P16885 PLCG2 "1-phosphatidylinositol 4,5-bisphosphate phosphodiesterase gamma-2" PLCG2 +SeqId.10948-14 Q8IV08 PLD3 Phospholipase D3 PLD3 +SeqId.8081-55 Q8N7P1 PLD5 Inactive phospholipase D5 PLD5 +SeqId.7875-86 P08567 PLEK Pleckstrin PLEK +SeqId.12459-13 Q9HB21 PKHA1 Pleckstrin homology domain-containing family A member 1 PLEKHA1 +SeqId.10939-16 Q9H4M7 PKHA4 Pleckstrin homology domain-containing family A member 4 PLEKHA4 +SeqId.12731-12 Q6IQ23 PKHA7 Pleckstrin homology domain-containing family A member 7 PLEKHA7 +SeqId.4150-75 P00747 Plasmin Plasmin PLG +SeqId.3710-49 P00747 Angiostatin Angiostatin PLG +SeqId.4151-6 P00747 Plasminogen Plasminogen PLG +SeqId.14687-6 O60664 M6PBP Perilipin-3 PLIN3 +SeqId.3394-81 P53350 PLK-1 Serine/threonine-protein kinase PLK1 PLK1 +SeqId.6923-1 O00469 PLOD2 "Procollagen-lysine,2-oxoglutarate 5-dioxygenase 2" PLOD2 +SeqId.10612-18 O60568 PLOD3 "Procollagen-lysine,2-oxoglutarate 5-dioxygenase 3" PLOD3 +SeqId.12737-12 Q14651 PLSI Plastin-1 PLS1 +SeqId.11407-57 Q9NRY6 PLS3 Phospholipid scramblase 3 PLSCR3 +SeqId.15475-4 P55058 PLTP Phospholipid transfer protein PLTP +SeqId.8565-160 Q9BX97 PLVAP Plasmalemma vesicle-associated protein PLVAP +SeqId.9235-3 Q8IUK5 PXDC1 Plexin domain-containing protein 1 PLXDC1 +SeqId.11342-59 Q6UX71 PXDC2 Plexin domain-containing protein 2 PLXDC2 +SeqId.9005-16 Q9UIW2 PLXA1 Plexin-A1 PLXNA1 +SeqId.19560-23 Q9HCM2 PLXA4 Plexin-A4 PLXNA4 +SeqId.9216-100 O15031 PLXB2 Plexin-B2 PLXNB2 +SeqId.16922-53 Q9ULL4 PLXB3 Plexin-B3 PLXNB3 +SeqId.4564-2 O60486 PLXC1 Plexin-C1 PLXNC1 +SeqId.19561-216 Q9Y4D7 PLXD1 Plexin-D1 PLXND1 +SeqId.6472-40 P40967 GP100 Melanocyte protein PMEL PMEL +SeqId.6936-7 Q969W9 PMEPA Protein TMEPAI PMEPA1 +SeqId.17408-2 Q92871 PMM1 Phosphomannomutase 1 PMM1 +SeqId.17794-6 O15305 Phosphomannomutase 2 Phosphomannomutase 2 PMM2 +SeqId.15422-12 P02689 MYP2 Myelin P2 protein PMP2 +SeqId.11312-40 P54278 PMS2 Mismatch repair endonuclease PMS2 PMS2 +SeqId.12450-42 Q15126 PMVK Phosphomevalonate kinase PMVK +SeqId.13657-2 Q96T60 PNKP Bifunctional polynucleotide phosphatase/kinase PNKP +SeqId.15613-16 P16233 LIPP Pancreatic triacylglycerol lipase PNLIP +SeqId.6627-25 P54315 LIPR1 Inactive pancreatic lipase-related protein 1 PNLIPRP1 +SeqId.15471-29 P54317 LIPR2 Pancreatic lipase-related protein 2 PNLIPRP2 +SeqId.17204-17 P11086 PNMT Phenylethanolamine N-methyltransferase PNMT +SeqId.15434-5 Q13519 PNOC Prepronociceptin PNOC +SeqId.15435-4 P00491 PNP Purine nucleoside phosphorylase PNP +SeqId.9802-27 Q96AD5 PLPL2 Patatin-like phospholipase domain-containing protein 2 PNPLA2 +SeqId.17804-102 Q9NVS9 PNPO Pyridoxine-5'-phosphate oxidase PNPO +SeqId.10616-67 Q9NZ53 PDXL2 Podocalyxin-like protein 2 PODXL2 +SeqId.5634-39 Q9H488 OFUT1 GDP-fucose protein O-fucosyltransferase 1 POFUT1 +SeqId.6467-65 Q8NBL1 KTEL1 Protein O-glucosyltransferase 1 POGLUT1 +SeqId.19159-9 Q9HCU8 DNA polymerase subunit delta 4 DNA polymerase delta subunit 4 POLD4 +SeqId.11562-9 P56282 DPOE2 DNA polymerase epsilon subunit 2 POLE2 +SeqId.19170-25 Q9NRF9 DPOE3 DNA polymerase epsilon subunit 3 POLE3 +SeqId.10022-207 Q9Y253 POLH DNA polymerase eta POLH +SeqId.13536-56 Q9UNA4 POLI DNA polymerase iota POLI +SeqId.12851-5 Q9NP87 DPOLM DNA-directed DNA/RNA polymerase mu POLM +SeqId.12939-1 O15160 RPAC1 DNA-directed RNA polymerases I and III subunit RPAC1 POLR1C +SeqId.19199-3 P52435 RPB11 DNA-directed RNA polymerase II subunit RPB11-a POLR2J +SeqId.19134-66 P53803 RPAB4 "DNA-directed RNA polymerases I, II, and III subunit RPABC4" POLR2K +SeqId.11444-49 Q9H1D9 RPC6 DNA-directed RNA polymerase III subunit RPC6 POLR3F +SeqId.4890-10 P01189 ACTH Corticotropin POMC +SeqId.2558-51 P01189 b-Endorphin Beta-endorphin POMC +SeqId.9204-33 P01189 Corticotropin-lipotropin Pro-opiomelanocortin POMC +SeqId.8253-2 Q8WZA1 PMGT1 "Protein O-linked-mannose beta-1,2-N-acetylglucosaminyltransferase 1" POMGNT1 +SeqId.6359-50 Q8NAT1 AGO61 "Protein O-linked-mannose beta-1,4-N-acetylglucosaminyltransferase 2" POMGNT2 +SeqId.10582-36 Q9H5K3 SG196 Protein O-mannose kinase POMK +SeqId.4261-55 P27169 paraoxonase 1 Serum paraoxonase/arylesterase 1 PON1 +SeqId.2731-29 P16435 NADPH-P450 Oxidoreductase NADPH--cytochrome P450 reductase POR +SeqId.3457-57 Q15063 Periostin Periostin POSTN +SeqId.7960-53 Q6S5H5 POTEG POTE ankyrin domain family member G POTEG +SeqId.7967-38 A6NI47 POTEM Putative POTE ankyrin domain family member M POTEM +SeqId.11715-1 P14859 PO2F1 "POU domain, class 2, transcription factor 1" POU2F1 +SeqId.5021-13 Q15181 PPase Inorganic pyrophosphatase PPA1 +SeqId.18307-71 Q9H2U2 PPase 2 "Inorganic pyrophosphatase 2, mitochondrial" PPA2 +SeqId.13548-53 Q5VZY2 PPC1A Phosphatidate phosphatase PPAPDC1A PPAPDC1A +SeqId.12954-71 Q07869 PPARa Peroxisome proliferator-activated receptor alpha PPARA +SeqId.11825-27 Q9UBK2 PRGC1 Peroxisome proliferator-activated receptor gamma coactivator 1-alpha PPARGC1A +SeqId.2790-54 P02775 NAP-2 Neutrophil-activating peptide 2 PPBP +SeqId.16765-52 P02775 PBP Platelet basic protein PPBP +SeqId.17165-1 P02775 BTG Beta-thromboglobulin PPBP +SeqId.4544-4 P02775 CTAP-III Connective tissue-activating peptide III PPBP +SeqId.13996-16 Q96CD2 COAC Phosphopantothenoylcysteine decarboxylase PPCDC +SeqId.17843-30 Q9HAB8 PPCS Phosphopantothenate--cysteine ligase PPCS +SeqId.13975-56 Q13136 LIPA1 Liprin-alpha-1 PPFIA1 +SeqId.3844-2 P62937 Cyclophilin A Peptidyl-prolyl cis-trans isomerase A PPIA +SeqId.4718-5 P23284 PPIB Peptidyl-prolyl cis-trans isomerase B PPIB +SeqId.18819-21 P45877 PPIC Peptidyl-prolyl cis-trans isomerase C PPIC +SeqId.5202-4 Q08752 PPID Peptidyl-prolyl cis-trans isomerase D PPID +SeqId.5238-26 Q9UNP9 PPIE Peptidyl-prolyl cis-trans isomerase E PPIE +SeqId.5248-68 P30405 Cyclophilin F "Peptidyl-prolyl cis-trans isomerase F, mitochondrial" PPIF +SeqId.18449-33 Q13427 PPIG Peptidyl-prolyl cis-trans isomerase G PPIG +SeqId.12449-16 O43447 PPIH Peptidyl-prolyl cis-trans isomerase H PPIH +SeqId.9884-8 Q9Y3C6 PPIL1 Peptidyl-prolyl cis-trans isomerase-like 1 PPIL1 +SeqId.14314-6 Q13356 PPIL2 Peptidyl-prolyl cis-trans isomerase-like 2 PPIL2 +SeqId.12619-14 P35813 Protein phophatase 2Ca Protein phosphatase 1A PPM1A +SeqId.11315-148 O15297 PPM1D Protein phosphatase 1D PPM1D +SeqId.7187-3 Q5SGD2 PPM1L Protein phosphatase 1L PPM1L +SeqId.17852-5 Q9Y570 PPME1 Protein phosphatase methylesterase 1 PPME1 +SeqId.19295-32 P36873 PP1G Serine/threonine-protein phosphatase PP1-gamma catalytic subunit PPP1CC +SeqId.19117-3 Q96A00 PP14A Protein phosphatase 1 regulatory subunit 14A PPP1R14A +SeqId.17706-4 Q13522 PPR1A Protein phosphatase 1 regulatory subunit 1A PPP1R1A +SeqId.19152-4 P41236 IPP2 Protein phosphatase inhibitor 2 PPP1R2 +SeqId.12768-3 Q86XI6 PPR3B Protein phosphatase 1 regulatory subunit 3B PPP1R3B +SeqId.13039-1 Q12972 PP1R8 Nuclear inhibitor of protein phosphatase 1 PPP1R8 +SeqId.12621-55 P30153 PP2AAA Serine/threonine-protein phosphatase 2A 65 kDa regulatory subunit A alpha isoform PPP2R1A +SeqId.13665-35 Q06190 "PP2A, subunit B" Serine/threonine-protein phosphatase 2A regulatory subunit B'' subunit alpha PPP2R3A +SeqId.13622-16 Q15172 2A5A Serine/threonine-protein phosphatase 2A 56 kDa regulatory subunit alpha isoform PPP2R5A +SeqId.4903-72 Q08209 P63098 Calcineurin Calcineurin PPP3CA PPP3R1 +SeqId.4903-72 Q08209 P63098 Calcineurin Calcineurin PPP3CA PPP3R1 +SeqId.15545-13 P63098 Calcineurin B a Calcineurin subunit B type 1 PPP3R1 +SeqId.18866-8 Q96LZ3 CANB2 Calcineurin subunit B type 2 PPP3R2 +SeqId.9244-27 P50897 PPT1 Palmitoyl-protein thioesterase 1 PPT1 +SeqId.4588-1 P01298 PH Pancreatic hormone PPY +SeqId.11432-11 O60828 PQBP1 Polyglutamine-binding protein 1 PQBP1 +SeqId.7939-1 A1A4F0 CC055 Putative uncharacterized protein PQLC2L PQLC2L +SeqId.11591-43 O43663 PRC1 Protein regulator of cytokinesis 1 PRC1 +SeqId.15310-61 O43663 PRC1 Protein regulator of cytokinesis 1 PRC1 +SeqId.5722-78 P42785 Prolylcarboxypeptidase Lysosomal Pro-X carboxypeptidase PRCP +SeqId.14197-2 O75626 PRDM1 PR domain zinc finger protein 1 PRDM1 +SeqId.12779-30 Q9UKN5 PRDM4 PR domain zinc finger protein 4 PRDM4 +SeqId.3855-56 Q06830 Peroxiredoxin-1 Peroxiredoxin-1 PRDX1 +SeqId.8358-30 P30048 Peroxiredoxin-3 "Thioredoxin-dependent peroxide reductase, mitochondrial" PRDX3 +SeqId.7789-182 Q13162 PRDX4 Peroxiredoxin-4 PRDX4 +SeqId.5017-19 P30044 Peroxiredoxin-5 "Peroxiredoxin-5, mitochondrial" PRDX5 +SeqId.5018-68 P30041 Peroxiredoxin-6 Peroxiredoxin-6 PRDX6 +SeqId.14273-19 P48147 PPCE Prolyl endopeptidase PREP +SeqId.7258-5 P13727 EMBP Bone marrow proteoglycan PRG2 +SeqId.9015-1 Q9Y2Y8 PRG3 Proteoglycan 3 PRG3 +SeqId.13591-31 P49642 PRI1 DNA primase small subunit PRIM1 +SeqId.5183-53 Q13131 Q9Y478 P54619 AMPK a1b1g1 AMP Kinase (alpha1beta1gamma1) PRKAA1 PRKAB1 PRKAG1 +SeqId.5183-53 Q13131 Q9Y478 P54619 AMPK a1b1g1 AMP Kinase (alpha1beta1gamma1) PRKAA1 PRKAB1 PRKAG1 +SeqId.5183-53 Q13131 Q9Y478 P54619 AMPK a1b1g1 AMP Kinase (alpha1beta1gamma1) PRKAA1 PRKAB1 PRKAG1 +SeqId.5245-40 P54646 O43741 P54619 AMPK a2b2g1 AMP Kinase (alpha2beta2gamma1) PRKAA2 PRKAB2 PRKAG1 +SeqId.5245-40 P54646 O43741 P54619 AMPK a2b2g1 AMP Kinase (alpha2beta2gamma1) PRKAA2 PRKAB2 PRKAG1 +SeqId.5245-40 P54646 O43741 P54619 AMPK a2b2g1 AMP Kinase (alpha2beta2gamma1) PRKAA2 PRKAB2 PRKAG1 +SeqId.3466-8 P17612 PRKACA cAMP-dependent protein kinase catalytic subunit alpha PRKACA +SeqId.12479-50 P31321 KAP1 cAMP-dependent protein kinase type I-beta regulatory subunit PRKAR1B +SeqId.19125-26 P13861 KAP2 cAMP-dependent protein kinase type II-alpha regulatory subunit PRKAR2A +SeqId.2644-11 P17252 PKC-A Protein kinase C alpha type PRKCA +SeqId.5475-10 P05771 PKC-B-II Protein kinase C beta type (splice variant beta-II) PRKCB +SeqId.5476-66 P05129 PKC-G Protein kinase C gamma type PRKCG +SeqId.3379-29 P41743 KPCI Protein kinase C iota type PRKCI +SeqId.3817-18 Q04759 KPCT Protein kinase C theta type PRKCQ +SeqId.5687-5 P14314 GLU2B Glucosidase 2 subunit beta PRKCSH +SeqId.2645-54 Q05513 PKC-Z Protein kinase C zeta type PRKCZ +SeqId.13067-5 Q13976 KGP1B "cGMP-dependent protein kinase 1, beta isozyme" PRKG1 +SeqId.2585-2 P01236 PRL Prolactin PRL +SeqId.6543-182 P81277 PRRP Prolactin-releasing peptide PRLH +SeqId.5114-65 P16471 Prolactin Receptor Prolactin receptor PRLR +SeqId.12696-166 O60678 ANM3 Protein arginine N-methyltransferase 3 PRMT3 +SeqId.18231-147 Q9UKY0 PRND Prion-like protein doppel PRND +SeqId.6545-58 P04156 PRIO Major prion protein PRNP +SeqId.2961-1 P04070 Protein C Vitamin K-dependent protein C PROC +SeqId.3758-68 P04070 Activated Protein C Activated Protein C PROC +SeqId.2247-20 P58294 EG-VEGF Prokineticin-1 PROK1 +SeqId.10754-113 Q9HC23 Prokineticin-2 Prokineticin-2 PROK2 +SeqId.6530-63 Q99935 PROL1 Opiorphin prepropeptide PROL1 +SeqId.2700-56 P07225 Protein S Vitamin K-dependent protein S PROS1 +SeqId.9012-1 O94906 PRP6 Pre-mRNA-processing factor 6 PRPF6 +SeqId.9581-4 O94906 PRP6 Pre-mRNA-processing factor 6 PRPF6 +SeqId.11381-56 P60891 PRPS1 Ribose-phosphate pyrophosphokinase 1 PRPS1 +SeqId.18329-4 P11908 PRPS2 Ribose-phosphate pyrophosphokinase 2 PRPS2 +SeqId.9478-69 Q14558 KPRA Phosphoribosyl pyrophosphate synthase-associated protein 1 PRPSAP1 +SeqId.19150-20 O60256 KPRB Phosphoribosyl pyrophosphate synthase-associated protein 2 PRPSAP2 +SeqId.10621-26 Q569H4 PRR16 Protein Largen PRR16 +SeqId.9607-39 Q6MZM9 CD040 Proline-rich protein 27 PRR27 +SeqId.8306-54 O14668 TMG1 Transmembrane gamma-carboxyglutamic acid protein 1 PRRG1 +SeqId.9008-6 O14668 TMG1 Transmembrane gamma-carboxyglutamic acid protein 1 PRRG1 +SeqId.9579-59 Q9BZD6 TMG4 Transmembrane gamma-carboxyglutamic acid protein 4 PRRG4 +SeqId.3049-61 P07477 Trypsin Trypsin-1 PRSS1 +SeqId.5034-79 P07478 Trypsin 2 Trypsin-2 PRSS2 +SeqId.4534-10 Q9GZN4 BSSP4 Brain-specific serine protease 4 PRSS22 +SeqId.15535-3 Q9BQR3 Marapsin Serine protease 27 PRSS27 +SeqId.18864-7 P35030 TRY3 Trypsin-3 PRSS3 +SeqId.9983-97 Q8N3Z0 PRS35 Inactive serine protease 35 PRSS35 +SeqId.5653-23 A4D1T9 PRS37 Probable inactive serine protease 37 PRSS37 +SeqId.8351-17 Q6UWY2 PRS57 Serine protease 57 PRSS57 +SeqId.15513-108 Q16651 Prostasin Prostasin PRSS8 +SeqId.13720-95 P24158 Proteinase-3 Myeloblastin PRTN3 +SeqId.6207-10 P07602 prosaposin Prosaposin PSAP +SeqId.8814-33 Q6NUJ1 SAPL1 Proactivator polypeptide-like 1 PSAPL1 +SeqId.18342-2 Q9Y617 SERC Phosphoserine aminotransferase PSAT1 +SeqId.13055-53 A5PKW4 PSD1 PH and SEC7 domain-containing protein 1 PSD +SeqId.9118-7 Q9BQI7 PSD2 PH and SEC7 domain-containing protein 2 PSD2 +SeqId.15631-18 P11464 PSG1 Pregnancy-specific beta-1-glycoprotein 1 PSG1 +SeqId.7846-44 Q9UQ72 PSG11 Pregnancy-specific beta-1-glycoprotein 11 PSG11 +SeqId.6405-74 P11465 PSG2 Pregnancy-specific beta-1-glycoprotein 2 PSG2 +SeqId.6444-15 Q16557 PSG3 Pregnancy-specific beta-1-glycoprotein 3 PSG3 +SeqId.5649-83 Q00888 PSG4 Pregnancy-specific beta-1-glycoprotein 4 PSG4 +SeqId.9314-9 Q15238 PSG5 Pregnancy-specific beta-1-glycoprotein 5 PSG5 +SeqId.6456-17 Q00889 PSG6 Pregnancy-specific beta-1-glycoprotein 6 PSG6 +SeqId.5651-50 Q13046 PSG7 Putative pregnancy-specific beta-1-glycoprotein 7 PSG7 +SeqId.6238-55 Q9UQ74 PSG8 Pregnancy-specific beta-1-glycoprotein 8 PSG8 +SeqId.9335-28 Q00887 PSG9 Pregnancy-specific beta-1-glycoprotein 9 PSG9 +SeqId.17176-13 O75475 PSIP1 PC4 and SFRS1-interacting protein PSIP1 +SeqId.3859-50 P25786 PSA1 Proteasome subunit alpha type-1 PSMA1 +SeqId.7880-9 P25786 PSA1 Proteasome subunit alpha type-1 PSMA1 +SeqId.4280-47 P25787 PSA2 Proteasome subunit alpha type-2 PSMA2 +SeqId.18926-7 P25788 PSA3 Proteasome subunit alpha type-3 PSMA3 +SeqId.14099-20 P25789 PSA4 Proteasome subunit alpha type-4 PSMA4 +SeqId.18925-24 P28066 Proteasome subunit alpha type 5 Proteasome subunit alpha type-5 PSMA5 +SeqId.3860-7 P60900 PSA6 Proteasome subunit alpha type-6 PSMA6 +SeqId.12460-18 O14818 PSA7 Proteasome subunit alpha type-7 PSMA7 +SeqId.12612-37 P20618 PSB1 Proteasome subunit beta type-1 PSMB1 +SeqId.19252-67 P49721 PSB2 Proteasome subunit beta type-2 PSMB2 +SeqId.18339-207 P49720 PSB3 Proteasome subunit beta type-3 PSMB3 +SeqId.18340-2 P28070 Proteasome beta chain Proteasome subunit beta type-4 PSMB4 +SeqId.12580-7 P28074 PSB5 Proteasome subunit beta type-5 PSMB5 +SeqId.10530-8 P28072 PSB6 Proteasome subunit beta type-6 PSMB6 +SeqId.18942-11 P28065 PSB9 Proteasome subunit beta type-9 PSMB9 +SeqId.18385-4 O75832 PSD10 26S proteasome non-ATPase regulatory subunit 10 PSMD10 +SeqId.13572-43 O00231 PSD11 26S proteasome non-ATPase regulatory subunit 11 PSMD11 +SeqId.13568-30 P55036 PSMD4 26S proteasome non-ATPase regulatory subunit 4 PSMD4 +SeqId.10716-35 Q16401 PSMD5 26S proteasome non-ATPase regulatory subunit 5 PSMD5 +SeqId.3898-5 P51665 PSD7 26S proteasome non-ATPase regulatory subunit 7 PSMD7 +SeqId.13931-22 O00233 PSMD9 26S proteasome non-ATPase regulatory subunit 9 PSMD9 +SeqId.5918-5 Q06323 PSME1 Proteasome activator complex subunit 1 PSME1 +SeqId.17694-32 Q9UL46 PSME2 Proteasome activator complex subunit 2 PSME2 +SeqId.5204-13 P61289 PSME3 Proteasome activator complex subunit 3 PSME3 +SeqId.12729-12 Q9BT73 PSMG3 Proteasome assembly chaperone 3 PSMG3 +SeqId.2696-87 O60542 Persephin Persephin PSPN +SeqId.19168-71 O43586 PPIP1 Proline-serine-threonine phosphatase-interacting protein 1 PSTPIP1 +SeqId.13517-3 Q3KNS1 PTHD3 Patched domain-containing protein 3 PTCHD3 +SeqId.3831-21 P60484 pTEN "Phosphatidylinositol 3,4,5-trisphosphate 3-phosphatase and dual-specificity protein phosphatase PTEN" PTEN +SeqId.10514-5 P41222 PGD2 synthase Prostaglandin-H2 D-isomerase PTGDS +SeqId.18458-4 Q9H7Z7 PGES2 Prostaglandin E synthase 2 PTGES2 +SeqId.17154-2 Q15185 TEBP Prostaglandin E synthase 3 PTGES3 +SeqId.12727-7 Q9P2B2 FPRP Prostaglandin F2 receptor negative regulator PTGFRN +SeqId.19617-5 Q14914 LTB4DH Prostaglandin reductase 1 PTGR1 +SeqId.18943-4 Q8N8N7 PTGR2 Prostaglandin reductase 2 PTGR2 +SeqId.3761-4 P35354 COX-2 Prostaglandin G/H synthase 2 PTGS2 +SeqId.19640-2 P01270 Parathyroid Hormone1-34 Parathyroid Hormone1-34 PTH +SeqId.5954-62 P01270 PTH Parathyroid hormone PTH +SeqId.13470-43 Q03431 PTH1R Parathyroid hormone/parathyroid hormone-related peptide receptor PTH1R +SeqId.7257-18 Q96A98 TIP39 Tuberoinfundibular peptide of 39 residues PTH2 +SeqId.2962-50 P12272 PTHrP Parathyroid hormone-related protein PTHLH +SeqId.4986-59 Q05397 FAK1 Focal adhesion kinase 1 PTK2 +SeqId.11395-5 Q14289 FAK2 Protein-tyrosine kinase 2-beta PTK2B +SeqId.8918-64 Q14289 FAK2 Protein-tyrosine kinase 2-beta PTK2B +SeqId.3832-51 Q13882 PTK6 Protein-tyrosine kinase 6 PTK6 +SeqId.9525-1 Q13308 PTK7 Inactive tyrosine-protein kinase 7 PTK7 +SeqId.3045-72 P21246 PTN Pleiotrophin PTN +SeqId.17812-2 Q93096 TP4A1 Protein tyrosine phosphatase type IVA 1 PTP4A1 +SeqId.11699-16 Q12974 TP4A2 Protein tyrosine phosphatase type IVA 2 PTP4A2 +SeqId.19231-22 O75365 PRL-3 Protein tyrosine phosphatase type IVA 3 PTP4A3 +SeqId.3005-5 P18031 PTP-1B Tyrosine-protein phosphatase non-receptor type 1 PTPN1 +SeqId.3397-7 Q06124 SHP-2 Tyrosine-protein phosphatase non-receptor type 11 PTPN11 +SeqId.12664-19 Q12923 PTN13 Tyrosine-protein phosphatase non-receptor type 13 PTPN13 +SeqId.3401-8 P17706 TCPTP Tyrosine-protein phosphatase non-receptor type 2 PTPN2 +SeqId.14254-27 P29074 PTN4 Tyrosine-protein phosphatase non-receptor type 4 PTPN4 +SeqId.4318-12 P29350 PTP-1C Tyrosine-protein phosphatase non-receptor type 6 PTPN6 +SeqId.14688-6 P35236 PTN7 Tyrosine-protein phosphatase non-receptor type 7 PTPN7 +SeqId.12633-3 P43378 PTN9 Tyrosine-protein phosphatase non-receptor type 9 PTPN9 +SeqId.9296-15 P23468 PTPRD Receptor-type tyrosine-protein phosphatase delta PTPRD +SeqId.11988-24 Q9HD43 PTPRH Receptor-type tyrosine-protein phosphatase H PTPRH +SeqId.8250-2 Q12913 PTPRJ Receptor-type tyrosine-protein phosphatase eta PTPRJ +SeqId.6361-49 Q15256 PTPRR Receptor-type tyrosine-protein phosphatase R PTPRR +SeqId.6049-64 Q13332 PTPRS Receptor-type tyrosine-protein phosphatase S PTPRS +SeqId.8337-65 Q92729 PTPRU Receptor-type tyrosine-protein phosphatase U PTPRU +SeqId.16887-29 Q9Y3E5 PTH2 "Peptidyl-tRNA hydrolase 2, mitochondrial" PTRH2 +SeqId.12014-19 Q03393 PTPS 6-pyruvoyl tetrahydrobiopterin synthase PTS +SeqId.17727-1 O95997 Securin Securin PTTG1 +SeqId.6447-73 P26022 PTX3 Pentraxin-related protein PTX3 PTX3 +SeqId.10575-31 Q9UHX1 PUF60 Poly(U)-binding-splicing factor PUF60 PUF60 +SeqId.12537-88 Q00577 PURA Transcriptional activator protein Pur-alpha PURA +SeqId.18300-39 Q96QR8 PURB Transcriptional activator protein Pur-beta PURB +SeqId.11201-19 Q9Y606 TRUA "tRNA pseudouridine synthase A, mitochondrial" PUS1 +SeqId.8064-125 P15151 Poliovirus receptor Poliovirus receptor PVR +SeqId.6464-40 Q6DKI7 PVRIG Transmembrane protein PVRIG PVRIG +SeqId.8803-61 Q15223 nectin-1 gamma "Nectin-1, isoform gamma" PVRL1 +SeqId.6245-4 Q92692 Nectin-2 Nectin-2 PVRL2 +SeqId.13557-3 Q9NQS3 Nectin 3 Nectin-3 PVRL3 +SeqId.5734-13 Q96NY8 nectin-4 Nectin-4 PVRL4 +SeqId.13463-1 Q92626 PXDN Peroxidasin homolog PXDN +SeqId.11324-3 A1KZ92 PXDNL Peroxidasin-like protein PXDNL +SeqId.18170-46 P32322 P5CR1 "Pyrroline-5-carboxylate reductase 1, mitochondrial" PYCR1 +SeqId.18328-36 Q96C36 P5CR2 Pyrroline-5-carboxylate reductase 2 PYCR2 +SeqId.12835-101 Q8WXC3 PYDC1 Pyrin domain-containing protein 1 PYDC1 +SeqId.11441-11 P06737 PYGL "Glycogen phosphorylase, liver form" PYGL +SeqId.3727-35 P10082 PYY Peptide YY PYY +SeqId.6580-29 P20742 Pregnancy zone protein Pregnancy zone protein PZP +SeqId.11257-1 P09417 DHPR Dihydropteridine reductase QDPR +SeqId.7253-6 Q96PU8 QKI Protein quaking QKI +SeqId.7849-3 Q16769 Glutaminyl cyclase Glutaminyl-peptide cyclotransferase QPCT +SeqId.8866-53 Q9NXS2 QPCTL Glutaminyl-peptide cyclotransferase-like protein QPCTL +SeqId.17789-1 Q15274 NADC Nicotinate-nucleotide pyrophosphorylase [carboxylating] QPRT +SeqId.6463-59 P83859 OX26 Orexigenic neuropeptide QRFP QRFP +SeqId.8397-147 Q6ZRP7 QSOX2 Sulfhydryl oxidase 2 QSOX2 +SeqId.17744-31 P62491 RB11A Ras-related protein Rab-11A RAB11A +SeqId.19282-3 P51153 RAB13 Ras-related protein Rab-13 RAB13 +SeqId.14283-12 P61106 RAB14 Ras-related protein Rab-14 RAB14 +SeqId.11118-107 Q9H0T7 RAB17 Ras-related protein Rab-17 RAB17 +SeqId.12945-33 Q9NP72 RAB18 Ras-related protein Rab-18 RAB18 +SeqId.19223-6 P62820 RAB1A Ras-related protein Rab-1A RAB1A +SeqId.19278-19 Q9H0U4 RAB1B Ras-related protein Rab-1B RAB1B +SeqId.17514-48 Q9UL25 RAB21 Ras-related protein Rab-21 RAB21 +SeqId.12408-333 Q9UL26 RB22A Ras-related protein Rab-22A RAB22A +SeqId.6997-32 Q9ULW5 RAB26 Ras-related protein Rab-26 RAB26 +SeqId.9504-19 P51159 RB27A Ras-related protein Rab-27A RAB27A +SeqId.13596-3 O00194 RB27B Ras-related protein Rab-27B RAB27B +SeqId.16857-2 P61019 RAB2A Ras-related protein Rab-2A RAB2A +SeqId.19253-82 Q8WUD1 RAB2B Ras-related protein Rab-2B RAB2B +SeqId.13597-20 Q13636 RAB31 Ras-related protein Rab-31 RAB31 +SeqId.17778-19 Q13637 RAB32 Ras-related protein Rab-32 RAB32 +SeqId.13514-121 Q15286 Rab-1C Ras-related protein Rab-35 RAB35 +SeqId.12403-30 Q96DA2 RB39B Ras-related protein Rab-39B RAB39B +SeqId.17516-7 P20336 Rab3A Ras-related protein Rab-3A RAB3A +SeqId.16847-39 P20337 RAB3B Ras-related protein Rab-3B RAB3B +SeqId.19586-89 Q96E17 RAB3C Ras-related protein Rab-3C RAB3C +SeqId.19379-154 O95716 RAB3D Ras-related protein Rab-3D RAB3D +SeqId.16883-57 P20338 RAB4A Ras-related protein Rab-4A RAB4A +SeqId.17205-21 P20339 RAB5A Ras-related protein Rab-5A RAB5A +SeqId.19222-124 P61020 RAB5B Ras-related protein Rab-5B RAB5B +SeqId.14287-6 P51148 RAB5C Ras-related protein Rab-5C RAB5C +SeqId.14271-23 Q9NRW1 RAB6B Ras-related protein Rab-6B RAB6B +SeqId.12409-90 Q96AH8 RAB7B Ras-related protein Rab-7b RAB7B +SeqId.13599-15 Q7Z6M1 RABEK Rab9 effector protein with kelch motifs RABEPK +SeqId.18483-36 P47224 MSS4 Guanine nucleotide exchange factor MSS4 RABIF +SeqId.2870-29 P63000 RAC1 Ras-related C3 botulinum toxin substrate 1 RAC1 +SeqId.18950-13 P15153 RAC2 Ras-related C3 botulinum toxin substrate 2 RAC2 +SeqId.16769-20 P60763 RAC3 Ras-related C3 botulinum toxin substrate 3 RAC3 +SeqId.13587-10 Q9H0H5 RGAP1 Rac GTPase-activating protein 1 RACGAP1 +SeqId.12670-15 O60671 RAD1 Cell cycle checkpoint protein RAD1 RAD1 +SeqId.10058-1 P54725 RD23A UV excision repair protein RAD23 homolog A RAD23A +SeqId.12522-6 P54727 RD23B UV excision repair protein RAD23 homolog B RAD23B +SeqId.2871-73 Q06609 RAD51 DNA repair protein RAD51 homolog 1 RAD51 +SeqId.12554-10 O75771 RA51D DNA repair protein RAD51 homolog 4 RAD51L3 +SeqId.18927-14 Q6H3X3 RET1G Retinoic acid early transcript 1G protein RAET1G +SeqId.10589-7 Q5VY80 RET1L Retinoic acid early transcript 1L protein RAET1L +SeqId.10001-7 P04049 c-Raf RAF proto-oncogene serine/threonine-protein kinase RAF1 +SeqId.11311-79 P15918 RAG-1 V(D)J recombination-activating protein 1 RAG1 +SeqId.14332-3 P11233 RALA Ras-related protein Ral-A RALA +SeqId.18432-32 P11234 RALB Ras-related protein Ral-B RALB +SeqId.15436-40 O60894 RAMP1 Receptor activity-modifying protein 1 RAMP1 +SeqId.15437-11 O60896 RAMP3 Receptor activity-modifying protein 3 RAMP3 +SeqId.4282-3 P62826 RAN GTP-binding nuclear protein Ran RAN +SeqId.18191-23 P43487 RANG Ran-specific GTPase-activating protein RANBP1 +SeqId.14037-18 Q9H6Z4 RANB3 Ran-binding protein 3 RANBP3 +SeqId.13735-1 P47736 RPGP1 Rap1 GTPase-activating protein 1 RAP1GAP +SeqId.14106-46 P52306 GDP/GTP exchange protein Rap1 GTPase-GDP dissociation stimulator 1 RAP1GDS1 +SeqId.9885-41 P10114 RAP2A Ras-related protein Rap-2a RAP2A +SeqId.9059-14 Q92565 RPGF5 Rap guanine nucleotide exchange factor 5 RAPGEF5 +SeqId.8398-277 P49788 RAR-responsive protein TIG1 Retinoic acid receptor responder protein 1 RARRES1 +SeqId.3079-62 Q99969 TIG2 Retinoic acid receptor responder protein 2 RARRES2 +SeqId.10961-15 Q9UL19 TIG3 Retinoic acid receptor responder protein 3 RARRES3 +SeqId.5481-16 P20936 RASA1 Ras GTPase-activating protein 1 RASA1 +SeqId.5024-67 P06400 Rb Retinoblastoma-associated protein RB1 +SeqId.15331-47 Q09028 RBBP4 Histone-binding protein RBBP4 RBBP4 +SeqId.13631-1 Q15291 RB binding protein 5 Retinoblastoma-binding protein 5 RBBP5 +SeqId.9887-40 Q7Z6E9 RBBP6 E3 ubiquitin-protein ligase RBBP6 RBBP6 +SeqId.10064-12 O75884 RBBP9 Putative hydrolase RBBP9 RBBP9 +SeqId.11462-8 O43251 RBM9 RNA binding protein fox-1 homolog 2 RBFOX2 +SeqId.19467-3 Q9H477 RBSK Ribokinase RBKS +SeqId.12879-5 P28749 p107 Retinoblastoma-like protein 1 RBL1 +SeqId.13565-2 Q08999 p130 Retinoblastoma-like protein 2 RBL2 +SeqId.17391-10 Q96I25 SPF45 Splicing factor 45 RBM17 +SeqId.11468-15 Q9Y4C8 RBM19 Probable RNA-binding protein 19 RBM19 +SeqId.12980-31 Q9NW64 RBM22 Pre-mRNA-splicing factor RBM22 RBM22 +SeqId.11590-5 Q86U06 RBM23 Probable RNA-binding protein 23 RBM23 +SeqId.11380-84 Q9BX46 RBM24 RNA-binding protein 24 RBM24 +SeqId.12747-89 P98179 RBM3 RNA-binding protein 3 RBM3 +SeqId.4284-18 Q14498 RBM39 RNA-binding protein 39 RBM39 +SeqId.13958-5 Q8TBY0 RBM46 Probable RNA-binding protein 46 RBM46 +SeqId.19279-42 P09455 CRBP Retinol-binding protein 1 RBP1 +SeqId.15633-6 P02753 RBP Retinol-binding protein 4 RBP4 +SeqId.19241-31 P82980 RBP-III Retinol-binding protein 5 RBP5 +SeqId.14208-3 Q96R05 RET7 Retinoid-binding protein 7 RBP7 +SeqId.13465-5 P53805 CCP1 Calcipressin-1 RCAN1 +SeqId.17785-11 O43598 RCL 2'-deoxynucleoside 5'-phosphate N-hydrolase 1 RCL +SeqId.9322-15 Q15293 RCN1 Reticulocalbin-1 RCN1 +SeqId.16858-384 Q96D15 RCN3 Reticulocalbin-3 RCN3 +SeqId.14334-3 P35243 RECO Recoverin RCVRN +SeqId.12881-17 O75452 RDH16 Retinol dehydrogenase 16 RDH16 +SeqId.18373-13 P35241 Radixin Radixin RDX +SeqId.11431-235 P46063 RECQ1 ATP-dependent DNA helicase Q1 RECQL +SeqId.13095-51 P05451 PSP Lithostathine-1-alpha REG1A +SeqId.16770-3 P48304 REG1B Lithostathine-1-beta REG1B +SeqId.15304-1 Q06141 PAP1 Regenerating islet-derived protein 3-alpha REG3A +SeqId.15476-6 Q6UW15 REG3G Regenerating islet-derived protein 3-gamma REG3G +SeqId.11102-22 Q9BYZ8 REG4 Regenerating islet-derived protein 4 REG4 +SeqId.11464-9 Q01201 RELB Transcription factor RelB RELB +SeqId.13399-33 Q8IUW5 RELL1 RELT-like protein 1 RELL1 +SeqId.6600-70 Q8NC24 RELL2 RELT-like protein 2 RELL2 +SeqId.14112-40 Q969Z4 RELT Tumor necrosis factor receptor superfamily member 19L RELT +SeqId.3396-54 P00797 Renin Renin REN +SeqId.13554-78 Q9BWE0 REPI1 Replication initiator 1 REPIN1 +SeqId.17822-57 Q96A58 RERG Ras-related and estrogen-regulated growth inhibitor RERG +SeqId.3220-40 P07949 RET Proto-oncogene tyrosine-protein kinase receptor Ret RET +SeqId.3046-31 Q9HD89 resistin Resistin RETN +SeqId.13590-1 Q9Y3B8 ORN "Oligoribonuclease, mitochondrial" REXO2 +SeqId.13603-7 Q8TAC1 RFESD Rieske domain-containing protein RFESD +SeqId.14186-13 Q8WZ73 RFFL E3 ubiquitin-protein ligase rififylin RFFL +SeqId.13059-33 Q969G6 RIFK Riboflavin kinase RFK +SeqId.7203-125 Q9Y644 RFNG "Beta-1,3-N-acetylglucosaminyltransferase radical fringe" RFNG +SeqId.12726-3 O00287 RFXAP Regulatory factor X-associated protein RFXAP +SeqId.5483-1 Q96B86 RGMA Repulsive guidance molecule A RGMA +SeqId.3331-8 Q6NW40 RGMB RGM domain family member B RGMB +SeqId.18945-11 Q08116 RGS1 Regulator of G-protein signaling 1 RGS1 +SeqId.11634-32 O43665 RGS10 Regulator of G-protein signaling 10 RGS10 +SeqId.13982-33 Q9NS28 RGS18 Regulator of G-protein signaling 18 RGS18 +SeqId.12713-365 P49795 RGS19 Regulator of G-protein signaling 19 RGS19 +SeqId.19381-7 Q2M5E4 RGS21 Regulator of G-protein signaling 21 RGS21 +SeqId.12827-37 P49796 RGS3 Regulator of G-protein signaling 3 RGS3 +SeqId.17855-28 P49798 RGS4 Regulator of G-protein signaling 4 RGS4 +SeqId.16850-5 O15539 RGS5 Regulator of G-protein signaling 5 RGS5 +SeqId.12538-19 P49802 RGS7 Regulator of G-protein signaling 7 RGS7 +SeqId.11666-72 P57771 RGS8 Regulator of G-protein signaling 8 RGS8 +SeqId.9855-10 P61586 Rho A Transforming protein RhoA RHOA +SeqId.18166-4 P62745 RHOB Rho-related GTP-binding protein RhoB RHOB +SeqId.17764-108 P08134 RHOC Rho-related GTP-binding protein RhoC RHOC +SeqId.12442-4 O00212 RHOD Rho-related GTP-binding protein RhoD RHOD +SeqId.12540-25 P84095 RHOG Rho-related GTP-binding protein RhoG RHOG +SeqId.11439-88 Q8IUC4 RHPN2 Rhophilin-2 RHPN2 +SeqId.11228-37 Q7Z5B4 RIC3 Protein RIC-3 RIC3 +SeqId.8970-9 O43353 RIPK2 Receptor-interacting serine/threonine-protein kinase 2 RIPK2 +SeqId.8993-151 O43353 RIPK2 Receptor-interacting serine/threonine-protein kinase 2 RIPK2 +SeqId.9767-22 Q0D2K3 RIPP1 Protein ripply1 RIPPLY1 +SeqId.12936-38 P12271 RLBP1 Retinaldehyde-binding protein 1 RLBP1 +SeqId.6621-10 P04090 REL2 Prorelaxin H2 RLN2 +SeqId.6027-31 Q8WXF3 REL3 Relaxin-3 RLN3 +SeqId.7096-30 Q96DB5 RMD1 Regulator of microtubule dynamics protein 1 RMDN1 +SeqId.9290-8 Q96TC7 RMD3 Regulator of microtubule dynamics protein 3 RMDN3 +SeqId.13926-1 Q9H9A7 RMI1 RecQ-mediated genome instability protein 1 RMI1 +SeqId.7211-2 P07998 RNase 1 Ribonuclease pancreatic RNASE1 +SeqId.5602-62 Q5GAN6 RNS10 Inactive ribonuclease-like protein 10 RNASE10 +SeqId.6424-2 Q5GAN3 RNS13 Probable inactive ribonuclease-like protein 13 RNASE13 +SeqId.8394-56 P10153 RNase 2 Non-secretory ribonuclease RNASE2 +SeqId.15576-158 P12724 ECP Eosinophil cationic protein RNASE3 +SeqId.5644-60 P34096 RNAS4 Ribonuclease 4 RNASE4 +SeqId.5646-20 Q93091 RNAS6 Ribonuclease K6 RNASE6 +SeqId.8470-213 O60930 RNase H1 Ribonuclease H1 RNASEH1 +SeqId.16913-8 O00584 RNT2 Ribonuclease T2 RNASET2 +SeqId.13574-50 Q92730 RND1 Rho-related GTP-binding protein Rho6 RND1 +SeqId.15439-21 P61587 RND3 Rho-related GTP-binding protein RhoE RND3 +SeqId.9957-9 Q9Y508 RN114 E3 ubiquitin-protein ligase RNF114 RNF114 +SeqId.11160-56 Q9H9V4 RN122 RING finger protein 122 RNF122 +SeqId.6510-56 Q8TEB7 RN128 E3 ubiquitin-protein ligase RNF128 RNF128 +SeqId.8633-18 Q8TEB7 RN128 E3 ubiquitin-protein ligase RNF128 RNF128 +SeqId.8087-250 O43567 RNF13 E3 ubiquitin-protein ligase RNF13 RNF13 +SeqId.11401-181 Q9NTX7 RN146 E3 ubiquitin-protein ligase RNF146 RNF146 +SeqId.7742-11 Q8N7C7 RN148 RING finger protein 148 RNF148 +SeqId.9955-40 Q8N7C7 RN148 RING finger protein 148 RNF148 +SeqId.9773-15 Q8NC42 RN149 E3 ubiquitin-protein ligase RNF149 RNF149 +SeqId.9774-59 Q9ULK6 RN150 RING finger protein 150 RNF150 +SeqId.7758-217 Q9Y6U7 RN215 RING finger protein 215 RNF215 +SeqId.9064-12 Q9Y6U7 RN215 RING finger protein 215 RNF215 +SeqId.9583-17 Q9Y225 RNF24 RING finger protein 24 RNF24 +SeqId.13386-248 Q969K3 RNF34 E3 ubiquitin-protein ligase RNF34 RNF34 +SeqId.13411-21 Q9H4P4 RNF41 E3 ubiquitin-protein ligase NRDP1 RNF41 +SeqId.14120-2 Q68DV7 RNF43 E3 ubiquitin-protein ligase RNF43 RNF43 +SeqId.14663-44 O76064 RNF8 E3 ubiquitin-protein ligase RNF8 RNF8 +SeqId.12847-27 O60942 MCE1 mRNA-capping enzyme RNGTT +SeqId.12814-17 Q96LT9 RBM40 RNA-binding protein 40 RNPC3 +SeqId.12386-11 Q9H4A4 AMPB Aminopeptidase B RNPEP +SeqId.15329-167 Q9Y2Q5 MAPIP Ragulator complex protein LAMTOR2 ROBLD3 +SeqId.5740-17 Q9Y6N7 ROBO1 Roundabout homolog 1 ROBO1 +SeqId.5116-62 Q9HCK4 ROBO2 Roundabout homolog 2 ROBO2 +SeqId.5117-14 Q96MS0 ROBO3 Roundabout homolog 3 ROBO3 +SeqId.16297-14 Q8WZ75 ROBO4 Roundabout homolog 4 ROBO4 +SeqId.13654-1 O75116 ROCK2 Rho-associated protein kinase 2 ROCK2 +SeqId.2590-69 Q01973 ROR1 Inactive tyrosine-protein kinase transmembrane receptor ROR1 ROR1 +SeqId.7861-9 Q01974 ROR2 Tyrosine-protein kinase transmembrane receptor ROR2 ROR2 +SeqId.12483-62 Q92753 RORB Nuclear receptor ROR-beta RORB +SeqId.11827-7 P51449 RORG Nuclear receptor ROR-gamma RORC +SeqId.9032-30 P08922 ROS1 Proto-oncogene tyrosine-protein kinase ROS ROS1 +SeqId.19264-6 P15927 RFA2 Replication protein A 32 kDa subunit RPA2 +SeqId.12646-2 Q96AT9 RPE Ribulose-phosphate 3-epimerase RPE +SeqId.12333-87 P49247 RPIA Ribose-5-phosphate isomerase RPIA +SeqId.19183-164 P30050 RL12 60S ribosomal protein L12 RPL12 +SeqId.12478-15 P62888 RL30 60S ribosomal protein L30 RPL30 +SeqId.10949-59 P05387 RLA2 60S acidic ribosomal protein P2 RPLP2 +SeqId.10490-3 P04843 RPN1 Dolichyl-diphosphooligosaccharide--protein glycosyltransferase subunit 1 RPN1 +SeqId.6458-6 P04843 RPN1 Dolichyl-diphosphooligosaccharide--protein glycosyltransferase subunit 1 RPN1 +SeqId.17511-10 P78346 RPP30 Ribonuclease P protein subunit p30 RPP30 +SeqId.13515-8 Q96P16 RPR1A Regulation of nuclear pre-mRNA domain-containing protein 1A RPRD1A +SeqId.19126-4 Q9NQG5 C20orf77 Regulation of nuclear pre-mRNA domain-containing protein 1B RPRD1B +SeqId.13011-20 P46783 RS10 40S ribosomal protein S10 RPS10 +SeqId.19166-15 P39019 RS19 40S ribosomal protein S19 RPS19 +SeqId.2846-24 P62979 Ubiquitin+1 "Ubiquitin+1, truncated mutation for UbB" RPS27A +SeqId.4474-19 P62979 Ubiquitin Ubiquitin RPS27A +SeqId.5026-66 P23396 RS3 40S ribosomal protein S3 RPS3 +SeqId.5484-63 P61247 RS3A 40S ribosomal protein S3a RPS3A +SeqId.9758-17 P62701 RS4X "40S ribosomal protein S4, X isoform" RPS4X +SeqId.19195-85 P46782 RS5 40S ribosomal protein S5 RPS5 +SeqId.12329-21 Q15418 KS6A1 Ribosomal protein S6 kinase alpha-1 RPS6KA1 +SeqId.3469-74 P51812 RPS6KA3 Ribosomal protein S6 kinase alpha-3 RPS6KA3 +SeqId.12688-115 Q9UK32 KS6A6 Ribosomal protein S6 kinase alpha-6 RPS6KA6 +SeqId.15608-5 P23443 KS6B1 Ribosomal protein S6 kinase beta-1 RPS6KB1 +SeqId.8962-48 P23443 KS6B1 Ribosomal protein S6 kinase beta-1 RPS6KB1 +SeqId.3864-5 P62081 RS7 40S ribosomal protein S7 RPS7 +SeqId.19623-26 P08865 40S ribosomal protein SA 40S ribosomal protein SA RPSA +SeqId.8975-26 Q92600 RCD1 Cell differentiation protein RCD1 homolog RQCD1 +SeqId.12548-75 Q9HB90 RRAGC Ras-related GTP-binding protein C RRAGC +SeqId.17742-2 P10301 RRAS Ras-related protein R-Ras RRAS +SeqId.12361-102 P62070 RRAS2 Ras-related protein R-Ras2 RRAS2 +SeqId.9913-4 Q9P2E9 RRBP1 Ribosome-binding protein 1 RRBP1 +SeqId.11360-39 P23921 RRM1 Ribonucleoside-diphosphate reductase large subunit RRM1 +SeqId.17750-8 P31350 RIR2 Ribonucleoside-diphosphate reductase subunit M2 RRM2 +SeqId.8925-25 Q7LG56 RIR2B Ribonucleoside-diphosphate reductase subunit M2 B RRM2B +SeqId.6497-10 O15537 XLRS1 Retinoschisin RS1 +SeqId.16614-27 Q2MKA7 RSPO1 R-spondin-1 RSPO1 +SeqId.6240-70 Q2MKA7 RSPO1 R-spondin-1 RSPO1 +SeqId.4566-24 Q6UXX9 RSPO2 R-spondin-2 RSPO2 +SeqId.8409-3 Q6UXX9 RSPO2 R-spondin-2 RSPO2 +SeqId.13094-75 Q9BXY4 RSPO3 R-spondin-3 RSPO3 +SeqId.8427-118 Q9BXY4 RSPO3 R-spondin-3 RSPO3 +SeqId.8464-31 Q2I0M5 RSPO4 R-spondin-4 RSPO4 +SeqId.9050-170 Q9BUV0 CA063 Arginine/serine-rich protein 1 RSRP1 +SeqId.7741-111 Q92541 RTF1 RNA polymerase-associated protein RTF1 homolog RTF1 +SeqId.18180-58 Q8WWV3 RT4I1 "Reticulon-4-interacting protein 1, mitochondrial" RTN4IP1 +SeqId.5105-2 Q9BZR6 Nogo Receptor Reticulon-4 receptor RTN4R +SeqId.18315-38 Q96DX8 RTP4 Receptor-transporting protein 4 RTP4 +SeqId.11425-31 Q96T51 RUFY1 RUN and FYVE domain-containing protein 1 RUFY1 +SeqId.11138-16 Q13761 RUNX3 Runt-related transcription factor 3 RUNX3 +SeqId.12365-108 Q9Y265 RUVB1 RuvB-like 1 RUVBL1 +SeqId.14135-3 Q9HBX9 RXFP1 Relaxin receptor 1 RXFP1 +SeqId.5583-62 P34925 RYK Tyrosine-protein kinase RYK RYK +SeqId.15318-75 P60903 Calpactin I light chain Protein S100-A10 S100A10 +SeqId.14011-17 P31949 S100A11 Protein S100-A11 S100A11 +SeqId.5852-6 P80511 S100A12 Protein S100-A12 S100A12 +SeqId.7223-60 Q99584 S100A13 Protein S100-A13 S100A13 +SeqId.17828-3 Q9HCY8 S100A14 Protein S100-A14 S100A14 +SeqId.17836-17 Q96FQ6 S100A16 Protein S100-A16 S100A16 +SeqId.11969-5 P29034 S100A2 Protein S100-A2 S100A2 +SeqId.15297-3 P33764 S100A3 Protein S100-A3 S100A3 +SeqId.14116-129 P26447 S100A4 Protein S100-A4 S100A4 +SeqId.15303-63 P33763 S100A5 Protein S100-A5 S100A5 +SeqId.13090-17 P06703 S100A6 Protein S100-A6 S100A6 +SeqId.7916-10 P31151 S100A7 Protein S100-A7 S100A7 +SeqId.17145-1 "P05109, P06702" S100A8/S100A9 Protein S100-A8/A9 heterodimer S100A8 S100A9 +SeqId.17145-1 "P05109, P06702" S100A8/S100A9 Protein S100-A8/A9 heterodimer S100A8 S100A9 +SeqId.5339-49 P06702 calgranulin B Protein S100-A9 S100A9 +SeqId.9926-4 P25815 S100P Protein S100-P S100P +SeqId.18928-10 Q8WXG8 S100Z Protein S100-Z S100Z +SeqId.15515-2 P0DJI8 SAA Serum amyloid A-1 protein SAA1 +SeqId.18832-65 P0DJI9 SAA2 Serum amyloid A-2 protein SAA2 +SeqId.15516-12 P35542 SAA-4 Serum amyloid A-4 protein SAA4 +SeqId.11303-7 Q9Y3Z3 SAMH1 Deoxynucleoside triphosphate triphosphohydrolase SAMHD1 SAMHD1 +SeqId.12830-4 O00422 SAP18 Histone deacetylase complex subunit SAP18 SAP18 +SeqId.12888-18 O75446 SAP30 Histone deacetylase complex subunit SAP30 SAP30 +SeqId.17726-3 Q9NR31 SAR1A GTP-binding protein SAR1a SAR1A +SeqId.18178-13 P49591 SYSC "Serine--tRNA ligase, cytoplasmic" SARS +SeqId.12348-46 Q9NP81 SYSM "Serine--tRNA ligase, mitochondrial" SARS2 +SeqId.9859-180 P21673 SSAT-1 Diamine acetyltransferase 1 SAT1 +SeqId.12524-18 Q96F10 SAT2 Diamine acetyltransferase 2 SAT2 +SeqId.13511-29 Q01826 SATB1 DNA-binding protein SATB1 SATB1 +SeqId.10081-17 Q9UPW6 SATB2 DNA-binding protein SATB2 SATB2 +SeqId.6594-64 Q9NPB0 SMDC1 SAYSvFN domain-containing protein 1 SAYSD1 +SeqId.3866-7 Q9Y3A5 SBDS Ribosome maturation protein SBDS SBDS +SeqId.5724-58 Q6UWP8 SBSN Suprabasin SBSN +SeqId.13509-5 Q8TAC9 SCAM5 Secretory carrier-associated membrane protein 5 SCAMP5 +SeqId.17800-33 P57086 SCAND1 SCAN domain-containing protein 1 SCAND1 +SeqId.11292-13 Q6AZY7 SCAR3 Scavenger receptor class A member 3 SCARA3 +SeqId.10419-1 Q6ZMJ2 SCAR5 Scavenger receptor class A member 5 SCARA5 +SeqId.5100-53 Q14108 LIMP II Lysosome membrane protein 2 SCARB2 +SeqId.5129-12 Q14162 SREC-I Scavenger receptor class F member 1 SCARF1 +SeqId.8956-96 Q96GP6 SREC-II Scavenger receptor class F member 2 SCARF2 +SeqId.9925-56 Q96GP6 SREC-II Scavenger receptor class F member 2 SCARF2 +SeqId.7957-2 Q8WXD2 SCG3 Secretogranin-3 SCG3 +SeqId.15358-28 P05408 7B2 Neuroendocrine protein 7B2 SCG5 +SeqId.6508-68 O95969 SG1D2 Secretoglobin family 1D member 2 SCGB1D2 +SeqId.5001-6 O75556 Mammaglobin 2 Mammaglobin-B SCGB2A1 +SeqId.6252-62 Q96QR1 Secretoglobin family 3A member 1 Secretoglobin family 3A member 1 SCGB3A1 +SeqId.15305-7 O76038 Secretagogin Secretagogin SCGN +SeqId.10510-62 Q6UWF3 SCIMP SLP adapter and CSK-interacting membrane protein SCIMP +SeqId.12684-5 Q9Y6U3 ADSV Adseverin SCIN +SeqId.12604-16 Q96GD3 SCMH1 Polycomb protein SCMH1 SCMH1 +SeqId.8353-15 O60939 SCN2B Sodium channel subunit beta-2 SCN2B +SeqId.7911-29 Q8IWT1 SCN4B Sodium channel subunit beta-4 SCN4B +SeqId.7853-19 O75880 SCO1 "Protein SCO1 homolog, mitochondrial" SCO1 +SeqId.16851-50 O43819 SCO2 "Protein SCO2 homolog, mitochondrial" SCO2 +SeqId.14175-78 Q9UJQ7 SCP2D SCP2 sterol-binding domain-containing protein 1 SCP2D1 +SeqId.3728-52 P09683 Secretin Secretin SCT +SeqId.8989-40 Q8IWY4 SCUB1 "Signal peptide, CUB and EGF-like domain-containing protein 1" SCUBE1 +SeqId.16773-29 Q8IX30 SCUB3 "Signal peptide, CUB and EGF-like domain-containing protein 3" SCUBE3 +SeqId.16612-28 O75056 SDC3 Syndecan-3 SDC3 +SeqId.17806-6 O00560 Syntenin 1 Syntenin-1 SDCBP +SeqId.19261-12 Q9H190 SDCB2 Syntenin-2 SDCBP2 +SeqId.15333-11 Q99470 SDF2 Stromal cell-derived factor 2 SDF2 +SeqId.6990-44 Q9HCN8 SDF2L Stromal cell-derived factor 2-like protein 1 SDF2L1 +SeqId.6420-4 Q9NX18 SDHF2 "Succinate dehydrogenase assembly factor 2, mitochondrial" SDHAF2 +SeqId.17777-31 Q96GA7 SDSL Serine dehydratase-like SDSL +SeqId.14689-3 P55735 SEC13 Protein SEC13 homolog SEC13 +SeqId.13713-164 Q96IW7 SC22A Vesicle-trafficking protein SEC22a SEC22A +SeqId.7878-2 P60468 SC61B Protein transport protein Sec61 subunit beta SEC61B +SeqId.8872-1 P60059 SC61G Protein transport protein Sec61 subunit gamma SEC61G +SeqId.13093-6 Q8WVN6 SECTM1 Secreted and transmembrane protein 1 SECTM1 +SeqId.9082-25 Q5TEA6 SE1L2 Protein sel-1 homolog 2 SEL1L2 +SeqId.3470-1 P16581 sE-Selectin E-selectin SELE +SeqId.17319-1 Q8IZQ5 SELH Selenoprotein H SELH +SeqId.4831-4 P14151 sL-Selectin L-Selectin SELL +SeqId.15336-7 Q8WWX9 SELM Selenoprotein M SELM +SeqId.4154-57 P16109 P-Selectin P-selectin SELP +SeqId.11266-8 Q14242 SELPL P-selectin glycoprotein ligand 1 SELPLG +SeqId.3222-11 Q14563 Semaphorin 3A Semaphorin-3A SEMA3A +SeqId.5667-3 Q13214 SEM3B Semaphorin-3B SEMA3B +SeqId.6448-36 Q99985 Sema E Semaphorin-3C SEMA3C +SeqId.5363-51 O15041 Semaphorin 3E Semaphorin-3E SEMA3E +SeqId.5628-21 Q9NS98 SEM3G Semaphorin-3G SEMA3G +SeqId.16915-153 Q9H3S1 SEM4A Semaphorin-4A SEMA4A +SeqId.9805-51 Q9NPR2 SEM4B Semaphorin-4B SEMA4B +SeqId.7923-41 Q9C0C4 SEM4C Semaphorin-4C SEMA4C +SeqId.5737-61 Q92854 SEM4D Semaphorin-4D SEMA4D +SeqId.9932-49 O95754 SEM4F Semaphorin-4F SEMA4F +SeqId.13132-14 Q13591 SEM5A Semaphorin-5A SEMA5A +SeqId.7945-10 Q9H2E6 Semaphorin-6A Semaphorin-6A SEMA6A +SeqId.5121-3 Q9H3T3 SEM6B Semaphorin-6B SEMA6B +SeqId.14597-5 Q9H3T2 SEM6C "Semaphorin-6C, cytoplasmic" SEMA6C +SeqId.7202-107 Q9H3T2 SEMA6C Semaphorin-6C SEMA6C +SeqId.7019-13 O75326 Semaphorin-7A Semaphorin-7A SEMA7A +SeqId.7115-5 P04279 Semenogelin Semenogelin-1 SEMG1 +SeqId.12626-6 Q9BQF6 SENP7 Sentrin-specific protease 7 SENP7 +SeqId.14083-25 P49903 SPS1 "Selenide, water dikinase 1" SEPHS1 +SeqId.17357-33 Q9HD40 SPCS O-phosphoseryl-tRNA(Sec) selenium transferase SEPSECS +SeqId.12690-33 Q9P0V9 Septin-10 Septin-10 SEPT10 +SeqId.12620-3 Q9NVA2 Septin-11 Septin-11 SEPT11 +SeqId.18316-75 Q9UH03 Septin-3 Neuronal-specific septin-3 SEPT3 +SeqId.17693-2 Q14141 Septin-6 Septin-6 SEPT6 +SeqId.18310-26 P63302 SELW Selenoprotein W SEPW1 +SeqId.8985-13 Q96JX3 SRAC1 Protein SERAC1 SERAC1 +SeqId.7842-52 O75920 SERF1 Small EDRK-rich factor 1 SERF1A +SeqId.18274-2 P84101 SERF2 Small EDRK-rich factor 2 SERF2 +SeqId.3580-25 P01009 a1-Antitrypsin Alpha-1-antitrypsin SERPINA1 +SeqId.13119-26 Q9UK55 protein Z inhibitor Protein Z-dependent protease inhibitor SERPINA10 +SeqId.9002-36 Q86U17 SPA11 Serpin A11 SERPINA11 +SeqId.6551-94 Q8IW75 Vaspin Serpin A12 SERPINA12 +SeqId.2879-9 P01011 a1-Antichymotrypsin Alpha-1-antichymotrypsin SERPINA3 +SeqId.4153-11 P01011 alpha-1-antichymotrypsin complex Alpha-1-antichymotrypsin complex SERPINA3 +SeqId.3449-58 P29622 Kallistatin Kallistatin SERPINA4 +SeqId.3389-7 P05154 PCI Plasma serine protease inhibitor SERPINA5 +SeqId.4785-30 P08185 CBG Corticosteroid-binding globulin SERPINA6 +SeqId.2706-69 P05543 Thyroxine-Binding Globulin Thyroxine-binding globulin SERPINA7 +SeqId.7266-4 Q86WD7 SPA9 Serpin A9 SERPINA9 +SeqId.10737-96 P30740 Serpin B1 Leukocyte elastase inhibitor SERPINB1 +SeqId.18841-1 Q9UIV8 SPB13 Serpin B13 SERPINB13 +SeqId.15444-45 P48594 SCCA2 Serpin B4 SERPINB4 +SeqId.15417-3 P36952 Maspin Serpin B5 SERPINB5 +SeqId.19130-81 P50452 SPB8 Serpin B8 SERPINB8 +SeqId.3344-60 P01008 Antithrombin III Antithrombin-III SERPINC1 +SeqId.3316-58 P05546 Heparin cofactor II Heparin cofactor 2 SERPIND1 +SeqId.2925-9 P05121 PAI-1 Plasminogen activator inhibitor 1 SERPINE1 +SeqId.19154-41 P07093 Protease nexin I Glia-derived nexin SERPINE2 +SeqId.9211-19 P36955 PEDF Pigment epithelium-derived factor SERPINF1 +SeqId.3024-18 P08697 a2-Antiplasmin Alpha-2-antiplasmin SERPINF2 +SeqId.4479-14 P05155 C1-Esterase Inhibitor Plasma protease C1 inhibitor SERPING1 +SeqId.10800-15 P50454 Collagen-binding protein Serpin H1 SERPINH1 +SeqId.7117-21 O75830 SPI2 Serpin I2 SERPINI2 +SeqId.5364-7 Q01105 SET Protein SET SET +SeqId.12647-52 Q9BYW2 SETD2 Histone-lysine N-methyltransferase SETD2 SETD2 +SeqId.12462-20 Q53H47 SETMR Histone-lysine N-methyltransferase SETMAR SETMAR +SeqId.19563-3 Q9BYH1 SEZ6L Seizure 6-like protein SEZ6L +SeqId.3867-49 Q6UXD5 SE6L2 Seizure 6-like protein 2 SEZ6L2 +SeqId.12777-11 Q15637 SF01 Splicing factor 1 SF1 +SeqId.13449-25 Q15427 SF3B4 Splicing factor 3B subunit 4 SF3B4 +SeqId.4829-43 P31947 STRATIFIN 14-3-3 protein sigma SFN +SeqId.3221-54 Q8N474 SARP-2 Secreted frizzled-related protein 1 SFRP1 +SeqId.7751-121 Q96HF1 SARP-1 Secreted frizzled-related protein 2 SFRP2 +SeqId.17447-52 Q6FHJ7 SFRP4 Secreted frizzled-related protein 4 SFRP4 +SeqId.10580-14 Q6UW10 SFTA2 Surfactant-associated protein 2 SFTA2 +SeqId.10672-75 P07988 SP-B Pulmonary surfactant-associated protein B SFTPB +SeqId.19590-46 P35247 SP-D Pulmonary surfactant-associated protein D SFTPD +SeqId.13729-26 Q8TD22 SFXN5 Sideroflexin-5 SFXN5 +SeqId.10042-8 Q96BR1 SGK3 Serine/threonine-protein kinase Sgk3 SGK3 +SeqId.3868-8 O43765 SGTA Small glutamine-rich tetratricopeptide repeat-containing protein alpha SGTA +SeqId.18837-9 Q96EQ0 SGTB Small glutamine-rich tetratricopeptide repeat-containing protein beta SGTB +SeqId.4567-82 O60880 SH21A SH2 domain-containing protein 1A SH2D1A +SeqId.18840-205 O14796 SH21B SH2 domain-containing protein 1B SH2D1B +SeqId.12704-26 Q8N5H7 SH2D3 SH2 domain-containing protein 3C SH2D3C +SeqId.12693-2 O75368 SH3L1 SH3 domain-binding glutamic acid-rich-like protein SH3BGRL +SeqId.19113-66 Q9UJC5 SH3L2 SH3 domain-binding glutamic acid-rich-like protein 2 SH3BGRL2 +SeqId.17490-4 Q9H299 SH3BGRL3-like protein SH3 domain-binding glutamic acid-rich-like protein 3 SH3BGRL3 +SeqId.7769-29 P78314 3BP2 SH3 domain-binding protein 2 SH3BP2 +SeqId.12499-108 Q99962 SH3G2 Endophilin-A1 SH3GL2 +SeqId.18318-98 Q99963 SH3G3 Endophilin-A3 SH3GL3 +SeqId.16859-100 Q9Y371 SHLB1 Endophilin-B1 SH3GLB1 +SeqId.18222-34 Q9NR46 SHLB2 Endophilin-B2 SH3GLB2 +SeqId.13240-170 Q9Y566 SHAN1 SH3 and multiple ankyrin repeat domains protein 1 SHANK1 +SeqId.13242-134 Q9BYB0 SHAN3 SH3 and multiple ankyrin repeat domains protein 3 SHANK3 +SeqId.4929-55 P04278 SHBG Sex hormone-binding globulin SHBG +SeqId.16043-30 P29353 SHC1 SHC-transforming protein 1 SHC1 +SeqId.5272-55 P29353 SHC1 SHC-transforming protein 1 SHC1 +SeqId.14074-2 P98077 SHC2 SHC-transforming protein 2 SHC2 +SeqId.11692-21 Q6S5L8 SHC4 SHC-transforming protein 4 SHC4 +SeqId.2743-5 Q15465 Sonic Hedgehog Sonic hedgehog protein SHH +SeqId.10449-31 Q6UWI4 TMM46 Protein shisa-2 homolog SHISA2 +SeqId.12334-25 P34896 cSHMT "Serine hydroxymethyltransferase, cytosolic" SHMT1 +SeqId.12691-44 P34897 GLYM "Serine hydroxymethyltransferase, mitochondrial" SHMT2 +SeqId.9263-57 Q9HAT2 SIAE Sialate O-acetylesterase SIAE +SeqId.8326-63 Q6IA17 SIGIRR Single Ig IL-1-related receptor SIGIRR +SeqId.4464-10 Q9BZZ2 Sialoadhesin Sialoadhesin SIGLEC1 +SeqId.8913-22 Q96RL6 SIG11 Sialic acid-binding Ig-like lectin 11 SIGLEC11 +SeqId.10037-98 Q96PQ1 SIG12 Sialic acid-binding Ig-like lectin 12 SIGLEC12 +SeqId.8352-26 Q96PQ1 SIG12 Sialic acid-binding Ig-like lectin 12 SIGLEC12 +SeqId.8248-222 Q08ET2 SIG14 Sialic acid-binding Ig-like lectin 14 SIGLEC14 +SeqId.10847-1 Q6ZMC9 SIG15 Sialic acid-binding Ig-like lectin 15 SIGLEC15 +SeqId.16792-4 O15389 Siglec-5 Sialic acid-binding Ig-like lectin 5 SIGLEC5 +SeqId.9275-2 O15389 Siglec-5 Sialic acid-binding Ig-like lectin 5 SIGLEC5 +SeqId.2741-22 O43699 Siglec-6 Sialic acid-binding Ig-like lectin 6 SIGLEC6 +SeqId.2742-68 Q9Y286 Siglec-7 Sialic acid-binding Ig-like lectin 7 SIGLEC7 +SeqId.7864-3 Q9NYZ4 SIGL8 Sialic acid-binding Ig-like lectin 8 SIGLEC8 +SeqId.3007-7 Q9Y336 Siglec-9 Sialic acid-binding Ig-like lectin 9 SIGLEC9 +SeqId.5430-66 P78324 SHPS1 Tyrosine-protein phosphatase non-receptor type substrate 1 SIRPA +SeqId.6247-9 O00241 SIRB1 Signal-regulatory protein beta-1 SIRPB1 +SeqId.5669-26 Q5JXA9 SIRB2 Signal-regulatory protein beta-2 SIRPB2 +SeqId.9241-40 Q9P1W8 SIRPG Signal-regulatory protein gamma SIRPG +SeqId.5030-52 Q8IXJ6 SIRT2 NAD-dependent protein deacetylase sirtuin-2 SIRT2 +SeqId.17495-141 Q9NTG7 SIR3 "NAD-dependent protein deacetylase sirtuin-3, mitochondrial" SIRT3 +SeqId.12461-8 Q9NXA8 SIRT5 "NAD-dependent protein deacylase sirtuin-5, mitochondrial" SIRT5 +SeqId.11194-6 Q9Y3P8 SIT1 Signaling threshold-regulating transmembrane adapter 1 SIT1 +SeqId.14670-1 P12757 SKIL Ski-like protein SKIL +SeqId.3902-21 P63208 SKP1 S-phase kinase-associated protein 1 SKP1 +SeqId.7953-20 Q13291 SLAF1 Signaling lymphocytic activation molecule SLAMF1 +SeqId.5128-53 Q96DU3 SLAF6 SLAM family member 6 SLAMF6 +SeqId.5487-7 Q9NQ25 SLAF7 SLAM family member 7 SLAMF7 +SeqId.8994-65 Q9P0V8 SLAMF8 SLAM family member 8 SLAMF8 +SeqId.13430-50 Q13336 UT1 Urea transporter 1 SLC14A1 +SeqId.12818-159 Q15849 UT2 Urea transporter 2 SLC14A2 +SeqId.9049-2 O15427 MOT4 Monocarboxylate transporter 4 SLC16A3 +SeqId.9969-8 Q86VW1 S22AG Solute carrier family 22 member 16 SLC22A16 +SeqId.5280-68 Q9H1K4 GHC2 Mitochondrial glutamate carrier 2 SLC25A18 +SeqId.13502-2 Q86WA9 S2611 Sodium-independent sulfate anion transporter SLC26A11 +SeqId.9127-4 P58743 S26A5 Prestin SLC26A5 +SeqId.13979-3 Q8TE54 S26A7 Anion exchange transporter SLC26A7 +SeqId.9045-3 O14975 S27A2 Very long-chain acyl-CoA synthetase SLC27A2 +SeqId.9081-39 Q99726 ZNT3 Zinc transporter 3 SLC30A3 +SeqId.9594-30 Q8TAD4 ZNT5 Zinc transporter 5 SLC30A5 +SeqId.13501-10 Q8TBE7 S35G2 Solute carrier family 35 member G2 SLC35G2 +SeqId.9000-177 Q07837 SLC31 Neutral and basic amino acid transport protein rBAT SLC3A1 +SeqId.10430-31 P08195 4F2 4F2 cell-surface antigen heavy chain SLC3A2 +SeqId.12511-83 Q96JW4 S41A2 Solute carrier family 41 member 2 SLC41A2 +SeqId.12798-46 Q2Y0W8 S4A8 Electroneutral sodium bicarbonate exchanger 1 SLC4A8 +SeqId.12826-5 Q92911 SC5A5 Sodium/iodide cotransporter SLC5A5 +SeqId.13691-10 Q8N695 SC5A8 Sodium-coupled monocarboxylate transporter 1 SLC5A8 +SeqId.13053-6 Q9UN76 S6A14 Sodium- and chloride-dependent neutral and basic amino acid transporter B(0+) SLC6A14 +SeqId.13056-18 Q9GZN6 S6A16 Orphan sodium- and chloride-dependent neurotransmitter transporter NTT5 SLC6A16 +SeqId.11653-69 P48067 SC6A9 Sodium- and chloride-dependent glycine transporter 1 SLC6A9 +SeqId.11669-39 Q9H2Y9 SO5A1 Solute carrier organic anion transporter family member 5A1 SLCO5A1 +SeqId.15634-139 O75093 SLIT1 Slit homolog 1 protein SLIT1 +SeqId.18930-28 O94813 SLIT2 Slit homolog 2 protein SLIT2 +SeqId.18931-40 O75094 SLIT3 Slit homolog 3 protein SLIT3 +SeqId.15539-15 Q96PX8 SLIK1 SLIT and NTRK-like protein 1 SLITRK1 +SeqId.10565-19 O94933 SLIK3 SLIT and NTRK-like protein 3 SLITRK3 +SeqId.7139-14 Q8IW52 SLIK4 SLIT and NTRK-like protein 4 SLITRK4 +SeqId.4568-17 O94991 SLIK5 SLIT and NTRK-like protein 5 SLITRK5 +SeqId.16916-19 Q9H5Y7 SLIK6 SLIT and NTRK-like protein 6 SLITRK6 +SeqId.7191-32 Q14BN4 SLMAP Sarcolemmal membrane-associated protein SLMAP +SeqId.4413-3 P03973 SLPI Antileukoproteinase SLPI +SeqId.8320-5 Q9NWH9 SLTM SAFB-like transcription modulator SLTM +SeqId.9838-4 Q15797 SMAD1 Mothers against decapentaplegic homolog 1 SMAD1 +SeqId.10364-6 Q15796 SMAD2 Mothers against decapentaplegic homolog 2 SMAD2 +SeqId.10363-13 P84022 SMAD3 Mothers against decapentaplegic homolog 3 SMAD3 +SeqId.12022-12 Q13485 SMAD4 Mothers against decapentaplegic homolog 4 SMAD4 +SeqId.11649-3 Q8IYB5 SMAP1 Stromal membrane-associated protein 1 SMAP1 +SeqId.11180-17 Q92922 SMRC1 SWI/SNF complex subunit SMARCC1 SMARCC1 +SeqId.14324-52 Q9UQE7 CSPG6 Structural maintenance of chromosomes protein 3 SMC3 +SeqId.7925-18 A6NFE2 CL070 Single-pass membrane and coiled-coil domain-containing protein 2 SMCO2 +SeqId.10866-60 Q6IN85 P4R3A Serine/threonine-protein phosphatase 4 regulatory subunit 3A SMEK1 +SeqId.9379-248 Q96HG1 CX069 Small integral membrane protein 10 SMIM10 +SeqId.13452-113 P0DJ93 SIM13 Small integral membrane protein 13 SMIM13 +SeqId.7108-7 O75264 CS077 Small integral membrane protein 24 SMIM24 +SeqId.8888-33 A6NGZ8 CX068 Small integral membrane protein 9 SMIM9 +SeqId.17805-35 O75940 SPF30 Survival of motor neuron-related-splicing factor 30 SMNDC1 +SeqId.13118-5 Q9H4F8 SMOC1 SPARC-related modular calcium-binding protein 1 SMOC1 +SeqId.15635-4 Q9H3U7 SMOC2 SPARC-related modular calcium-binding protein 2 SMOC2 +SeqId.10818-36 P17405 ASM Sphingomyelin phosphodiesterase SMPD1 +SeqId.4771-10 Q92484 ASM3A Acid sphingomyelinase-like phosphodiesterase 3a SMPDL3A +SeqId.7838-27 Q99954 SMR3A Submaxillary gland androgen-regulated protein 3A SMR3A +SeqId.18179-56 P52788 SPSY Spermine synthase SMS +SeqId.12546-1 P53814 SMTN Smoothelin SMTN +SeqId.11557-3 Q9HCE7 SMUF1 E3 ubiquitin-protein ligase SMURF1 SMURF1 +SeqId.13985-12 Q9HAU4 SMUF2 E3 ubiquitin-protein ligase SMURF2 SMURF2 +SeqId.12636-113 Q9NRG4 SMYD2 N-lysine methyltransferase SMYD2 SMYD2 +SeqId.10014-31 O43623 SLUG Zinc finger protein SNAI2 SNAI2 +SeqId.13105-7 P60880 SNP25 Synaptosomal-associated protein 25 SNAP25 +SeqId.12357-41 O95721 SNP29 Synaptosomal-associated protein 29 SNAP29 +SeqId.6975-52 O95295 SNAPN SNARE-associated protein Snapin SNAPIN +SeqId.8458-111 P37840 a-Synuclein Alpha-synuclein SNCA +SeqId.7762-30 O75324 SNN Stannin SNN +SeqId.17343-6 O15079 SNPH Syntaphilin SNPH +SeqId.12678-66 P09012 SNRPA U1 small nuclear ribonucleoprotein A SNRPA +SeqId.17364-8 P08579 RU2B U2 small nuclear ribonucleoprotein B'' SNRPB2 +SeqId.17823-40 P62316 SMD2 Small nuclear ribonucleoprotein Sm D2 SNRPD2 +SeqId.17774-38 P62318 SMD3 Small nuclear ribonucleoprotein Sm D3 SNRPD3 +SeqId.5494-52 P62306 RUXF Small nuclear ribonucleoprotein F SNRPF +SeqId.19276-124 P62308 RUXG Small nuclear ribonucleoprotein G SNRPG +SeqId.19274-80 Q13424 Alpha-1-syntrophin Alpha-1-syntrophin SNTA1 +SeqId.9078-207 Q13884 SNTB1 Beta-1-syntrophin SNTB1 +SeqId.17765-3 O95149 SPN1 Snurportin-1 SNUPN +SeqId.6955-68 Q13596 SNX1 Sorting nexin-1 SNX1 +SeqId.8807-13 Q13596 SNX1 Sorting nexin-1 SNX1 +SeqId.12845-18 Q15036 SNX17 Sorting nexin-17 SNX17 +SeqId.19503-2 O60493 SNX3 Sorting nexin-3 SNX3 +SeqId.3903-49 O95219 Sorting nexin 4 Sorting nexin-4 SNX4 +SeqId.18327-6 Q9Y5X3 SNX5 Sorting nexin-5 SNX5 +SeqId.14245-195 Q9UNH6 SNX7 Sorting nexin-7 SNX7 +SeqId.6925-26 Q9Y5X2 SNX8 Sorting nexin-8 SNX8 +SeqId.11440-58 O14543 SOCS-3 Suppressor of cytokine signaling 3 SOCS3 +SeqId.11657-86 O14512 SOCS7 Suppressor of cytokine signaling 7 SOCS7 +SeqId.2794-60 P00441 SOD Superoxide dismutase [Cu-Zn] SOD1 +SeqId.5008-51 P04179 Mn SOD "Superoxide dismutase [Mn], mitochondrial" SOD2 +SeqId.5660-51 P08294 SOD3 Extracellular superoxide dismutase [Cu-Zn] SOD3 +SeqId.12976-49 O60504 Vinexin b Vinexin b SORBS3 +SeqId.15636-49 Q8WY21 SORC1 VPS10 domain-containing receptor SorCS1 SORCS1 +SeqId.4569-52 Q96PQ0 SORC2 VPS10 domain-containing receptor SorCS2 SORCS2 +SeqId.15637-38 Q9UPU3 SORC3 VPS10 domain-containing receptor SorCS3 SORCS3 +SeqId.15447-45 Q00796 Sorbitol dehydrogenase Sorbitol dehydrogenase SORD +SeqId.11300-32 Q99523 SORT Sortilin SORT1 +SeqId.9923-6 Q07889 SOS1 Son of sevenless homolog 1 SOS1 +SeqId.13101-60 Q9BQB4 SOST Sclerostin SOST +SeqId.8237-56 Q6X4U4 SOSD1 Sclerostin domain-containing protein 1 SOSTDC1 +SeqId.18294-26 P48431 SOX2 Transcription factor SOX-2 SOX2 +SeqId.18242-8 Q15506 Sperm protein 17 Sperm surface protein Sp17 SPA17 +SeqId.6228-58 Q9HBV2 sperm acrosome associated 1 Sperm acrosome membrane-associated protein 1 SPACA1 +SeqId.8076-4 Q8IXA5 SACA3 Sperm acrosome membrane-associated protein 3 SPACA3 +SeqId.6494-60 Q96QH8 sperm acrosome associated 5 Sperm acrosome-associated protein 5 SPACA5 +SeqId.5726-49 Q6PDA7 SG11A Sperm-associated antigen 11A SPAG11A +SeqId.5762-35 Q08648 Sperm-associated antigen 11 Sperm-associated antigen 11B SPAG11B +SeqId.3043-49 P09486 ON SPARC SPARC +SeqId.4467-49 Q14515 SPARCL1 SPARC-like protein 1 SPARCL1 +SeqId.8388-24 Q9UBP0 Spastin Spastin SPAST +SeqId.11117-2 Q8TB22 SPT20 Spermatogenesis-associated protein 20 SPATA20 +SeqId.9524-46 Q6ZUB0 S31D4 Putative spermatogenesis-associated protein 31D4 SPATA31D4 +SeqId.7809-22 Q9BWV2 SPAT9 Spermatogenesis-associated protein 9 SPATA9 +SeqId.10012-5 O95238 SPDEF SAM pointed domain-containing Ets transcription factor SPDEF +SeqId.12876-39 Q9Y4P9 SPEF1 Sperm flagellar protein 1 SPEF1 +SeqId.11161-5 Q8N0X7 SPG20 Spartin SPG20 +SeqId.11122-97 Q9NZD8 SPG21 Maspardin SPG21 +SeqId.4294-16 Q9NYA1 Sphingosine kinase 1 Sphingosine kinase 1 SPHK1 +SeqId.4468-21 Q9NRA0 SPHK2 Sphingosine kinase 2 SPHK2 +SeqId.18210-12 Q9Y657 SPIN1 Spindlin-1 SPIN1 +SeqId.8243-55 P00995 TATI Serine protease inhibitor Kazal-type 1 SPINK1 +SeqId.10624-45 Q1W4C9 ISK13 Serine protease inhibitor Kazal-type 13 SPINK13 +SeqId.8587-21 Q6IE38 ISK52 Serine protease inhibitor Kazal-type 14 SPINK14 +SeqId.13405-61 P20155 ISK2 Serine protease inhibitor Kazal-type 2 SPINK2 +SeqId.19213-1 O60575 ISK4 Serine protease inhibitor Kazal-type 4 SPINK4 +SeqId.8028-22 Q9NQ38 SPINK5 Serine protease inhibitor Kazal-type 5 SPINK5 +SeqId.5731-1 Q6UWN8 ISK6 Serine protease inhibitor Kazal-type 6 SPINK6 +SeqId.10974-20 P58062 ISK7 Serine protease inhibitor Kazal-type 7 SPINK7 +SeqId.7962-11 P0C7L1 ISK8 Serine protease inhibitor Kazal-type 8 SPINK8 +SeqId.8042-88 Q5DT21 ISK9 Serine protease inhibitor Kazal-type 9 SPINK9 +SeqId.2828-82 O43278 HAI-1 Kunitz-type protease inhibitor 1 SPINT1 +SeqId.2843-13 O43291 SPINT2 Kunitz-type protease inhibitor 2 SPINT2 +SeqId.7926-13 P49223 SPIT3 Kunitz-type protease inhibitor 3 SPINT3 +SeqId.12873-11 P16150 LEUK Leukosialin SPN +SeqId.5490-53 Q08629 Testican-1 Testican-1 SPOCK1 +SeqId.5491-12 Q92563 Testican-2 Testican-2 SPOCK2 +SeqId.9906-21 Q9BQ16 TICN3 Testican-3 SPOCK3 +SeqId.4297-62 Q9HCB6 Spondin-1 Spondin-1 SPON1 +SeqId.8099-42 Q9BUD6 SPON2 Spondin-2 SPON2 +SeqId.13727-44 O43791 SPOP Speckle-type POZ protein SPOP +SeqId.13113-7 P10451 Osteopontin Osteopontin SPP1 +SeqId.9287-6 P35270 SPRE Sepiapterin reductase SPR +SeqId.8318-13 Q7Z699 SPRE1 "Sprouty-related, EVH1 domain-containing protein 1" SPRED1 +SeqId.13447-42 Q5BIV9 SPRN Shadow of prion protein SPRN +SeqId.13942-140 Q96BD6 SPSB1 SPRY domain-containing SOCS box protein 1 SPSB1 +SeqId.5031-10 Q13813 SPTA2 "Spectrin alpha chain, non-erythrocytic 1" SPTAN1 +SeqId.7886-26 O15269 SPTC1 Serine palmitoyltransferase 1 SPTLC1 +SeqId.7267-2 O15270 LCB2 Serine palmitoyltransferase 2 SPTLC2 +SeqId.15448-47 Q13501 SQSTM Sequestosome-1 SQSTM1 +SeqId.18220-141 Q9HD15 SRA1 Steroid receptor RNA activator 1 SRA1 +SeqId.15433-4 P12931 p60-Src Proto-oncogene tyrosine-protein kinase Src SRC +SeqId.5488-74 P12931 SRCN1 Proto-oncogene tyrosine-protein kinase Src isoform 2 SRC +SeqId.19251-56 P10124 Platelet proteoglycan Serglycin SRGN +SeqId.12356-65 P30626 Sorcin Sorcin SRI +SeqId.10940-25 Q86TD4 SRCA Sarcalumenin SRL +SeqId.17510-7 P37108 SRP14 Signal recognition particle 14 kDa protein SRP14 +SeqId.18257-64 P09132 SRP19 Signal recognition particle 19 kDa protein SRP19 +SeqId.11573-3 Q13247 SRSF6 Serine/arginine-rich splicing factor 6 SRSF6 +SeqId.12987-12 Q16629 SRSF7 Serine/arginine-rich splicing factor 7 SRSF7 +SeqId.14268-4 Q9BYN0 SRXN1 Sulfiredoxin-1 SRXN1 +SeqId.13526-5 P05455 LA Lupus La protein SSB +SeqId.13625-19 P05455 LA Lupus La protein SSB +SeqId.8298-8 Q8WWF3 CG045 Serine-rich single-pass membrane protein 1 SSMEM1 +SeqId.8106-15 P43307 SSRA Translocon-associated protein subunit alpha SSR1 +SeqId.5032-64 Q08945 SSRP1 FACT complex subunit SSRP1 SSRP1 +SeqId.5957-30 P61278 Somatostatin-28 Somatostatin-28 SST +SeqId.13566-2 Q9NP77 SSU72 RNA polymerase II subunit A C-terminal domain phosphatase SSU72 SSU72 +SeqId.18387-7 P50502 suppression of tumorigenicity 13 Hsc70-interacting protein ST13 +SeqId.5657-28 Q11201 SIA4A "CMP-N-acetylneuraminate-beta-galactosamide-alpha-2,3-sialyltransferase 1" ST3GAL1 +SeqId.6281-51 Q16842 SIA4B "CMP-N-acetylneuraminate-beta-galactosamide-alpha-2,3-sialyltransferase 2" ST3GAL2 +SeqId.10588-39 Q9UNP4 SIAT9 "Lactosylceramide alpha-2,3-sialyltransferase" ST3GAL5 +SeqId.6947-4 Q9Y274 SIA10 "Type 2 lactosamine alpha-2,3-sialyltransferase" ST3GAL6 +SeqId.6035-2 P15907 SIAT1 "Beta-galactoside alpha-2,6-sialyltransferase 1" ST6GAL1 +SeqId.7867-154 Q9NSC7 SIA7A "Alpha-N-acetylgalactosaminide alpha-2,6-sialyltransferase 1" ST6GALNAC1 +SeqId.7823-22 Q9UJ37 SIA7B "Alpha-N-acetylgalactosaminide alpha-2,6-sialyltransferase 2" ST6GALNAC2 +SeqId.10705-14 Q8NDV1 SIA7C "Alpha-N-acetylgalactosaminide alpha-2,6-sialyltransferase 3" ST6GALNAC3 +SeqId.7927-16 Q9BVH7 SIA7E "Alpha-N-acetylgalactosaminide alpha-2,6-sialyltransferase 5" ST6GALNAC5 +SeqId.7228-2 Q969X2 SIA7F "Alpha-N-acetylgalactosaminide alpha-2,6-sialyltransferase 6" ST6GALNAC6 +SeqId.7920-30 Q92186 SIA8B "Alpha-2,8-sialyltransferase 8B" ST8SIA2 +SeqId.6929-10 O43173 SIA8C "Sia-alpha-2,3-Gal-beta-1,4-GlcNAc-R:alpha 2,8-sialyltransferase" ST8SIA3 +SeqId.7038-45 Q92187 SIA8D "CMP-N-acetylneuraminate-poly-alpha-2,8-sialyltransferase" ST8SIA4 +SeqId.6930-95 P61647 SIA8F "Alpha-2,8-sialyltransferase 8F" ST8SIA6 +SeqId.14599-18 Q9NY15 STAB1 Stabilin-1 STAB1 +SeqId.3399-31 Q8WWQ8 STAB2 Stabilin-2 STAB2 +SeqId.19187-21 O95630 STABP STAM-binding protein STAMBP +SeqId.12401-3 Q96FJ0 STALP AMSH-like protease STAMBPL1 +SeqId.12510-3 Q9ULZ2 STAP1 Signal-transducing adaptor protein 1 STAP1 +SeqId.10085-25 P49675 STAR "Steroidogenic acute regulatory protein, mitochondrial" STAR +SeqId.17383-4 Q9NSY2 STAR5 StAR-related lipid transfer protein 5 STARD5 +SeqId.10370-21 P42224 STAT1 Signal transducer and activator of transcription 1-alpha/beta STAT1 +SeqId.10346-5 P40763 STAT3 Signal transducer and activator of transcription 3 STAT3 +SeqId.16551-14 P51692 STA5B Signal transducer and activator of transcription 5B STAT5B +SeqId.10372-18 P42226 STAT6 Signal transducer and activator of transcription 6 STAT6 +SeqId.17172-19 P02808 STAT Statherin STATH +SeqId.12471-47 O95793 STAU1 Double-stranded RNA-binding protein Staufen homolog 1 STAU1 +SeqId.12970-35 Q9NUL3 STAU2 Double-stranded RNA-binding protein Staufen homolog 2 STAU2 +SeqId.4930-21 P52823 Stanniocalcin-1 Stanniocalcin-1 STC1 +SeqId.6231-46 O76061 STC2 Stanniocalcin-2 STC2 +SeqId.8916-32 Q13586 STIM1 Stromal interaction molecule 1 STIM1 +SeqId.9271-101 Q13586 STIM1 Stromal interaction molecule 1 STIM1 +SeqId.5489-18 P31948 Stress-induced-phosphoprotein 1 Stress-induced-phosphoprotein 1 STIP1 +SeqId.3471-49 O75716 STK16 Serine/threonine-protein kinase 16 STK16 +SeqId.5249-31 O94768 DRAK2 Serine/threonine-protein kinase 17B STK17B +SeqId.8399-6 O94768 DRAK2 Serine/threonine-protein kinase 17B STK17B +SeqId.12617-2 Q9Y6E0 STK24 Serine/threonine-protein kinase 24 STK24 +SeqId.17367-5 P16949 Stathmin Stathmin STMN1 +SeqId.10900-272 Q93045 STMN2 Stathmin-2 STMN2 +SeqId.8019-73 Q9NZ72 STMN3 Stathmin-3 STMN3 +SeqId.6267-51 Q9H169 STMN4 Stathmin-4 STMN4 +SeqId.8261-51 P27105 STOM Erythrocyte band 7 integral membrane protein STOM +SeqId.17344-23 Q9UBI4 STML1 Stomatin-like protein 1 STOML1 +SeqId.6555-58 Q9UJZ1 Stomatin-like protein 2 "Stomatin-like protein 2, mitochondrial" STOML2 +SeqId.10336-3 Q9UNE7 CHIP E3 ubiquitin-protein ligase CHIP STUB1 +SeqId.11350-30 Q9UNE7 CHIP E3 ubiquitin-protein ligase CHIP STUB1 +SeqId.12842-43 O60499 STX10 Syntaxin-10 STX10 +SeqId.10418-36 Q86Y82 STX12 Syntaxin-12 STX12 +SeqId.9037-1 Q9P2W9 STX18 Syntaxin-18 STX18 +SeqId.19553-14 Q16623 STX1a Syntaxin-1A STX1A +SeqId.6966-144 P61266 STX1B Syntaxin-1B STX1B +SeqId.7738-299 P32856 STX2 Syntaxin-2 STX2 +SeqId.7186-111 Q13277 STX3 Syntaxin-3 STX3 +SeqId.10668-5 Q12846 STX4 Syntaxin-4 STX4 +SeqId.10945-11 O43752 Syntaxin-6 Syntaxin-6 STX6 +SeqId.8274-64 O15400 Syntaxin-7 Syntaxin-7 STX7 +SeqId.10903-50 Q9UNK0 STX8 Syntaxin-8 STX8 +SeqId.18308-30 Q8NFX7 STXB6 Syntaxin-binding protein 6 STXBP6 +SeqId.19236-24 P53999 TCP4 Activated RNA polymerase II transcriptional coactivator p15 SUB1 +SeqId.10703-203 Q9H7L9 SDS3 Sin3 histone deacetylase corepressor complex component SDS3 SUDS3 +SeqId.17468-1 Q9UMX1 SUFU Suppressor of fused homolog SUFU +SeqId.17818-22 Q9Y2Z0 SUGT1 Protein SGT1 homolog SUGT1 +SeqId.8305-18 Q8IWU5 SULF2 Extracellular sulfatase Sulf-2 SULF2 +SeqId.13944-3 P0DMM9 SULT 1A3 Sulfotransferase 1A3 SULT1A3 +SeqId.12671-35 O43704 ST1B1 Sulfotransferase family cytosolic 1B member 1 SULT1B1 +SeqId.17811-78 O00338 ST1C2 Sulfotransferase 1C2 SULT1C2 +SeqId.16932-5 P49888 SULT 1E Estrogen sulfotransferase SULT1E1 +SeqId.9829-91 Q06520 SULT 2A1 Bile salt sulfotransferase SULT2A1 +SeqId.17209-27 O00204 ST2B1 Sulfotransferase family cytosolic 2B member 1 SULT2B1 +SeqId.8357-43 Q9BR01 ST4A1 Sulfotransferase 4A1 SULT4A1 +SeqId.6941-11 Q8NBK3 SUMF1 Sulfatase-modifying factor 1 SUMF1 +SeqId.6069-71 Q8NBJ7 SUMF2 Sulfatase-modifying factor 2 SUMF2 +SeqId.19555-1 P61956 SUMO2 Small ubiquitin-related modifier 2 SUMO2 +SeqId.14623-26 P55854 SUMO3 Small ubiquitin-related modifier 3 SUMO3 +SeqId.8852-10 Q8TAQ9 SUN3 SUN domain-containing protein 3 SUN3 +SeqId.11260-47 Q8TC36 SPA4L SUN domain-containing protein 5 SUN5 +SeqId.18324-61 P51687 SUOX "Sulfite oxidase, mitochondrial" SUOX +SeqId.8009-121 Q15526 SURF1 Surfeit locus protein 1 SURF1 +SeqId.9582-93 Q6UWL2 SUSD1 Sushi domain-containing protein 1 SUSD1 +SeqId.5752-63 Q96L08 SUSD3 Sushi domain-containing protein 3 SUSD3 +SeqId.12452-32 Q86Y97 SV422 Histone-lysine N-methyltransferase SUV420H2 SUV420H2 +SeqId.12880-1 Q7L0J3 SV2A Synaptic vesicle glycoprotein 2A SV2A +SeqId.11109-56 Q4LDE5 SVEP1 "Sushi, von Willebrand factor type A, EGF and pentraxin domain-containing protein 1" SVEP1 +SeqId.11178-21 Q4LDE5 SVEP1 "Sushi, von Willebrand factor type A, EGF and pentraxin domain-containing protein 1" SVEP1 +SeqId.18285-6 Q8NHG7 SVIP Small VCP/p97-interacting protein SVIP +SeqId.13552-7 Q9UH65 SWP70 Switch-associated protein 70 SWAP70 +SeqId.19438-68 O95926 SYF2 Pre-mRNA-splicing factor SYF2 SYF2 +SeqId.10722-13 P43405 KSYK Tyrosine-protein kinase SYK SYK +SeqId.11378-37 P43405 KSYK Tyrosine-protein kinase SYK SYK +SeqId.7199-3 O14994 SYN3 Synapsin-3 SYN3 +SeqId.4224-7 O60506 HNRPQ Heterogeneous nuclear ribonucleoprotein Q SYNCRIP +SeqId.9789-52 Q8WXH0 Nesprin-2 Nesprin-2 SYNE2 +SeqId.13375-48 O43761 SNG3 Synaptogyrin-3 SYNGR3 +SeqId.17348-5 P57105 SYJ2B Synaptojanin-2-binding protein SYNJ2BP +SeqId.7089-42 Q9BT88 SYT11 Synaptotagmin-11 SYT11 +SeqId.9110-2 Q9BSW7 SYT17 Synaptotagmin-17 SYT17 +SeqId.9577-26 Q8N9I0 SYT2 Synaptotagmin-2 SYT2 +SeqId.17355-56 Q9H2B2 SYT4 Synaptotagmin-4 SYT4 +SeqId.9099-19 O00445 SYT5 Synaptotagmin-5 SYT5 +SeqId.7121-2 O43581 SYT7 Synaptotagmin-7 SYT7 +SeqId.7932-23 Q8NBV8 SYT8 Synaptotagmin-8 SYT8 +SeqId.8066-38 Q86SS6 SYT9 Synaptotagmin-9 SYT9 +SeqId.12892-10 Q8IYJ3 SYTL1 Synaptotagmin-like protein 1 SYTL1 +SeqId.11563-51 Q96C24 SYTL4 Synaptotagmin-like protein 4 SYTL4 +SeqId.9090-9 Q96C24 SYTL4 Synaptotagmin-like protein 4 SYTL4 +SeqId.9337-43 P20366 TKN1 Protachykinin-1 TAC1 +SeqId.6468-37 Q86UU9 TKN4 Tachykinin-4 TAC4 +SeqId.9257-14 Q9BSH4 TACO1 Translational activator of cytochrome c oxidase 1 TACO1 +SeqId.14034-22 P09758 GA733-1 protein Tumor-associated calcium signal transducer 2 TACSTD2 +SeqId.2619-72 P09758 GA733-1 protein Tumor-associated calcium signal transducer 2 TACSTD2 +SeqId.18270-10 Q12962 TAF10 Transcription initiation factor TFIID subunit 10 TAF10 +SeqId.16865-62 Q92804 RBP56 TATA-binding protein-associated factor 2N TAF15 +SeqId.15640-54 Q01995 TAGL Transgelin TAGLN +SeqId.11636-33 P37802 Transgelin-2 Transgelin-2 TAGLN2 +SeqId.9201-13 P37802 Transgelin-2 Transgelin-2 TAGLN2 +SeqId.17775-8 Q9UI15 TAGL3 Transgelin-3 TAGLN3 +SeqId.11347-9 P37837 Transaldolase Transaldolase TALDO1 +SeqId.14013-11 Q92844 TANK TRAF family member-associated NF-kappa-B activator TANK +SeqId.12378-71 O15533 TPSN Tapasin TAPBP +SeqId.6364-7 Q9BX59 TPSNR Tapasin-related protein TAPBPL +SeqId.12781-2 Q15633 TRBP2 RISC-loading complex subunit TARBP2 TARBP2 +SeqId.12046-51 Q13148 TADBP TAR DNA-binding protein 43 TARDBP +SeqId.18186-15 P26639 SYTC "Threonine--tRNA ligase, cytoplasmic" TARS +SeqId.12721-4 Q86VP1 TAXB1 Tax1-binding protein 1 TAX1BP1 +SeqId.12498-12 O14907 TX1B3 Tax1-binding protein 3 TAX1BP3 +SeqId.9960-2 Q92609 TBCD5 TBC1 domain family member 5 TBC1D5 +SeqId.12501-10 O75347 TBCA Tubulin-specific chaperone A TBCA +SeqId.17686-27 Q99426 TBCB Tubulin-folding cofactor B TBCB +SeqId.11211-7 Q15813 TBCE Tubulin-specific chaperone E TBCE +SeqId.3400-49 Q9UHD2 TBK1 Serine/threonine-protein kinase TBK1 TBK1 +SeqId.11227-31 Q9Y4P3 TBL2 Transducin beta-like protein 2 TBL2 +SeqId.2875-15 P20226 TBP TATA-box-binding protein TBP +SeqId.18434-141 P62380 TBPL1 TATA box-binding protein-like protein 1 TBPL1 +SeqId.11146-4 Q9Y458 TBX22 T-box transcription factor TBX22 TBX22 +SeqId.13978-122 O15119 Tbx3 T-box transcription factor TBX3 TBX3 +SeqId.11202-70 Q99593 TBX5 T-box transcription factor TBX5 TBX5 +SeqId.8098-37 P24557 THAS Thromboxane-A synthase TBXAS1 +SeqId.18204-1 P23193 TCEA1 Transcription elongation factor A protein 1 TCEA1 +SeqId.13481-24 Q15560 TCEA2 Transcription elongation factor A protein 2 TCEA2 +SeqId.19112-2 Q969E4 TCAL3 Transcription elongation factor A protein-like 3 TCEAL3 +SeqId.19109-32 Q8IYN2 TCAL8 Transcription elongation factor A protein-like 8 TCEAL8 +SeqId.19144-9 P15884 ITF2 Transcription factor 4 TCF4 +SeqId.17210-2 P56279 TCL1A T-cell leukemia/lymphoma protein 1A TCL1A +SeqId.18276-34 O95988 TCL1B T-cell leukemia/lymphoma protein 1B TCL1B +SeqId.19614-8 P20061 Holo-TC I Transcobalamin-1 TCN1 +SeqId.15560-52 P20062 Apo-TC II Transcobalamin-2 TCN2 +SeqId.5584-21 P20062 Holo-TC II Holo-Transcobalamin-2 TCN2 +SeqId.19265-9 P17987 TCPA T-complex protein 1 subunit alpha TCP1 +SeqId.8334-65 Q8WWU5 TCP11 T-complex protein 11 homolog TCP11 +SeqId.11433-11 Q96GX1 TECT2 Tectonic-2 TCTN2 +SeqId.5810-25 P13385 Cripto Teratocarcinoma-derived growth factor 1 TDGF1 +SeqId.9880-33 P48775 T23O "Tryptophan 2,3-dioxygenase" TDO2 +SeqId.10073-22 Q9NUW8 TYDP1 Tyrosyl-DNA phosphodiesterase 1 TDP1 +SeqId.12854-3 Q99594 TEAD3 Transcriptional enhancer factor TEF-5 TEAD3 +SeqId.12516-13 Q15561 TEAD4 Transcriptional enhancer factor TEF-3 TEAD4 +SeqId.16079-2 P42680 TEC Tyrosine-protein kinase Tec TEC +SeqId.3773-15 Q02763 sTie-2 "Angiopoietin-1 receptor, soluble" TEK +SeqId.11164-7 Q9NT68 TEN2 Teneurin-2 TENM2 +SeqId.11107-25 Q9P273 TEN3 Teneurin-3 TENM3 +SeqId.11365-17 Q6N022 TEN4 Teneurin-4 TENM4 +SeqId.10049-112 P54274 TERF1 Telomeric repeat-binding factor 1 TERF1 +SeqId.17419-17 Q9UGI8 TES Testin TES +SeqId.12831-21 Q96BS2 TESC Calcineurin B homologous protein 3 TESC +SeqId.10557-6 Q8N6K0 TEX29 Testis-expressed sequence 29 protein TEX29 +SeqId.4162-54 P02787 Transferrin Serotransferrin TF +SeqId.9952-57 Q00059 TFAM "Transcription factor A, mitochondrial" TFAM +SeqId.9185-15 P04155 TFF1 Trefoil factor 1 TFF1 +SeqId.9191-8 Q03403 Trefoil factor 2 Trefoil factor 2 TFF2 +SeqId.4721-54 Q07654 TFF3 Trefoil factor 3 TFF3 +SeqId.8323-163 Q07654 TFF3 Trefoil factor 3 TFF3 +SeqId.9043-7 Q9UBB9 TFP11 Tuftelin-interacting protein 11 TFIP11 +SeqId.3336-50 P10646 TFPI Tissue factor pathway inhibitor TFPI +SeqId.9233-71 P48307 TFPI -2 Tissue factor pathway inhibitor 2 TFPI2 +SeqId.11537-12 Q9UP52 TFR2 Transferrin receptor protein 2 TFR2 +SeqId.6895-1 P02786 TR Transferrin receptor protein 1 TFRC +SeqId.8795-48 P02786 TR Transferrin receptor protein 1 TFRC +SeqId.18839-24 P01266 Thyroglobulin Thyroglobulin TG +SeqId.2333-72 P01137 TGF-b1 Transforming growth factor beta-1 TGFB1 +SeqId.4156-74 P61812 TGF-b2 Transforming growth factor beta-2 TGFB2 +SeqId.3520-58 P10600 TGF-b3 Transforming growth factor beta-3 TGFB3 +SeqId.3283-21 Q15582 BGH3 Transforming growth factor-beta-induced protein ig-h3 TGFBI +SeqId.5133-17 P37173 TGF-b R II TGF-beta receptor type-2 TGFBR2 +SeqId.3009-3 Q03167 TGF-b R III Transforming growth factor beta receptor type 3 TGFBR3 +SeqId.9847-21 Q9GZN2 TGIF2 Homeobox protein TGIF2 TGIF2 +SeqId.11242-33 P22735 TGM1 Protein-glutamine gamma-glutamyltransferase K TGM1 +SeqId.18934-50 P21980 Tissue transglutaminase Protein-glutamine gamma-glutamyltransferase 2 TGM2 +SeqId.4471-50 Q08188 TGM3 Protein-glutamine gamma-glutamyltransferase E TGM3 +SeqId.18933-4 P49221 TGM4 Protein-glutamine gamma-glutamyltransferase 4 TGM4 +SeqId.3474-19 P07996 Thrombospondin-1 Thrombospondin-1 THBS1 +SeqId.14111-15 P35442 TSP2 Thrombospondin-2 THBS2 +SeqId.3339-33 P35442 TSP2 Thrombospondin-2 THBS2 +SeqId.8982-65 P49746 TSP3 Thrombospondin-3 THBS3 +SeqId.3340-53 P35443 TSP4 Thrombospondin-4 THBS4 +SeqId.18215-5 Q9NWX6 THG1 Probable tRNA(His) guanylyltransferase THG1L +SeqId.9875-107 Q96FV9 THOC1 THO complex subunit 1 THOC1 +SeqId.5947-90 P40225 Tpo Thrombopoietin THPO +SeqId.8059-1 P40225 Tpo Thrombopoietin THPO +SeqId.12527-50 P10827 THA Thyroid hormone receptor alpha THRA +SeqId.5621-64 Q9NS62 THSD1 Thrombospondin type-1 domain-containing protein 1 THSD1 +SeqId.11174-8 Q9UPZ6 THS7A Thrombospondin type-1 domain-containing protein 7A THSD7A +SeqId.9600-55 Q9UPZ6 THS7A Thrombospondin type-1 domain-containing protein 7A THSD7A +SeqId.13595-20 Q9BU02 THTPA Thiamine-triphosphatase THTPA +SeqId.12424-107 Q9P016 THYN1 Thymocyte nuclear protein 1 THYN1 +SeqId.19131-184 Q01085 TIAR Nucleolysin TIAR TIAL1 +SeqId.14035-13 Q13009 TIAM1 T-lymphoma invasion and metastasis-inducing protein 1 TIAM1 +SeqId.17696-1 Q86XR7 TIRP TIR domain-containing adapter molecule 2 TICAM2 +SeqId.2844-53 P35590 sTie-1 "Tyrosine-protein kinase receptor Tie-1, soluble" TIE1 +SeqId.12476-50 Q9NQ88 TIGAR "Fructose-2,6-bisphosphatase TIGAR" TIGAR +SeqId.16299-13 Q495A1 TIGIT T-cell immunoreceptor with Ig and ITIM domains TIGIT +SeqId.9638-2 Q495A1 TIGIT T-cell immunoreceptor with Ig and ITIM domains TIGIT +SeqId.15449-33 Q96H15 TIM-4 T-cell immunoglobulin and mucin domain-containing protein 4 TIMD4 +SeqId.17699-43 Q9UNS1 TIMELESS Protein timeless homolog TIMELESS +SeqId.9058-1 Q9BVV7 TIM21 Mitochondrial import inner membrane translocase subunit Tim21 TIMM21 +SeqId.7743-5 Q3ZCQ8 TIM50 Mitochondrial import inner membrane translocase subunit TIM50 TIMM50 +SeqId.19148-58 O60220 TIM8A Mitochondrial import inner membrane translocase subunit Tim8 A TIMM8A +SeqId.2211-9 P01033 TIMP-1 Metalloproteinase inhibitor 1 TIMP1 +SeqId.2278-61 P16035 TIMP-2 Metalloproteinase inhibitor 2 TIMP2 +SeqId.2480-58 P35625 TIMP-3 Metalloproteinase inhibitor 3 TIMP3 +SeqId.6462-12 Q99727 TIMP-4 Metalloproteinase inhibitor 4 TIMP4 +SeqId.11192-168 Q9GZM7 TINAL Tubulointerstitial nephritis antigen-like TINAGL1 +SeqId.10638-1 Q9BSI4 TINF2 TERF1-interacting nuclear factor 2 TINF2 +SeqId.9839-148 P58753 Tirap Toll/interleukin-1 receptor domain-containing adapter protein TIRAP +SeqId.12001-7 Q07157 ZO1 Tight junction protein ZO-1 TJP1 +SeqId.4301-58 P04183 Thymidine kinase "Thymidine kinase, cytosolic" TK1 +SeqId.19114-8 O00142 KITM "Thymidine kinase 2, mitochondrial" TK2 +SeqId.4306-4 P29401 Transketolase Transketolase TKT +SeqId.6383-90 O43897 TLL1 Tolloid-like protein 1 TLL1 +SeqId.14082-56 Q9Y4G6 TLN2 Talin-2 TLN2 +SeqId.11149-3 Q15399 TLR1 Toll-like receptor 1 TLR1 +SeqId.16324-38 Q15399 TLR1 Toll-like receptor 1 TLR1 +SeqId.3835-11 O60603 TLR2 Toll-like receptor 2 TLR2 +SeqId.16918-198 O15455 TLR3 Toll-like receptor 3 TLR3 +SeqId.11101-18 O00206 TLR4 Toll-like receptor 4 TLR4 +SeqId.3647-49 O00206 Q9Y6Y9 TLR4:MD-2 complex Toll-like receptor 4:Lymphocyte antigen 96 complex TLR4 LY96 +SeqId.3647-49 O00206 Q9Y6Y9 TLR4:MD-2 complex Toll-like receptor 4:Lymphocyte antigen 96 complex TLR4 LY96 +SeqId.18935-14 O60602 TLR5 Toll-like receptor 5 TLR5 +SeqId.8922-4 Q9ULS5 TMCC3 Transmembrane and coiled-coil domains protein 3 TMCC3 +SeqId.6907-17 Q8N6Q1 TMC5A Transmembrane and coiled-coil domain-containing protein 5A TMCO5A +SeqId.6506-54 P49755 TMEDA Transmembrane emp24 domain-containing protein 10 TMED10 +SeqId.10761-5 Q15363 TMED2 Transmembrane emp24 domain-containing protein 2 TMED2 +SeqId.9319-59 Q7Z7H5 TMED4 Transmembrane emp24 domain-containing protein 4 TMED4 +SeqId.15641-20 Q8IYR6 TEFF1 Tomoregulin-1 TMEFF1 +SeqId.10499-1 Q96A25 T106A Transmembrane protein 106A TMEM106A +SeqId.8687-26 Q9NUM4 T106B Transmembrane protein 106B TMEM106B +SeqId.10583-1 Q6UXF1 TM108 Transmembrane protein 108 TMEM108 +SeqId.11110-4 Q4V9L6 TM119 Transmembrane protein 119 TMEM119 +SeqId.7871-16 Q24JP5 T132A Transmembrane protein 132A TMEM132A +SeqId.8890-9 Q14DG7 T132B Transmembrane protein 132B TMEM132B +SeqId.11128-29 Q8N3T6 T132C Transmembrane protein 132C TMEM132C +SeqId.7173-141 Q8N3T6 T132C Transmembrane protein 132C TMEM132C +SeqId.13416-8 Q14C87 T132D Transmembrane protein 132D TMEM132D +SeqId.11223-1 Q6P9G4 TM154 Transmembrane protein 154 TMEM154 +SeqId.11112-18 Q8TBQ9 KISHA Protein kish-A TMEM167A +SeqId.13421-17 Q9NRX6 KISHB Protein kish-B TMEM167B +SeqId.14633-26 Q8NFB2 T185A Transmembrane protein 185A TMEM185A +SeqId.10442-1 Q8WZ59 TM190 Transmembrane protein 190 TMEM190 +SeqId.8992-1 Q9UHN6 TMEM2 Transmembrane protein 2 TMEM2 +SeqId.11542-11 Q96A57 TM230 Transmembrane protein 230 TMEM230 +SeqId.8107-12 Q8WY98 TM234 Transmembrane protein 234 TMEM234 +SeqId.12856-14 Q96Q45 TM237 Transmembrane protein 237 TMEM237 +SeqId.9014-18 Q86YD3 TMM25 Transmembrane protein 25 TMEM25 +SeqId.9509-4 Q9NVV0 TM38B Trimeric intracellular cation channel type B TMEM38B +SeqId.11186-12 Q8NDY8 TMM52 Transmembrane protein 52 TMEM52 +SeqId.9778-45 Q4KMG9 TM52B Transmembrane protein 52B TMEM52B +SeqId.12367-52 Q8N5G2 MACOI Macoilin TMEM57 +SeqId.9959-60 Q9UK28 TM59L Transmembrane protein 59-like TMEM59L +SeqId.8074-32 Q9BUB7 TMM70 "Transmembrane protein 70, mitochondrial" TMEM70 +SeqId.13485-20 Q96K49 TM87B Transmembrane protein 87B TMEM87B +SeqId.12742-160 A6NDV4 TMM8B Transmembrane protein 8B TMEM8B +SeqId.8597-1 Q9P0T7 TMEM9 Transmembrane protein 9 TMEM9 +SeqId.9249-17 Q9P0T7 TMEM9 Transmembrane protein 9 TMEM9 +SeqId.12595-11 P28289 TMOD1 Tropomodulin-1 TMOD1 +SeqId.12853-112 Q9NZR1 TMOD2 Tropomodulin-2 TMOD2 +SeqId.12861-13 Q9NYL9 TMOD3 Tropomodulin-3 TMOD3 +SeqId.8265-225 P42167 LAP2B "Lamina-associated polypeptide 2, isoforms beta/gamma" TMPO +SeqId.7231-37 Q6ZMR5 TM11A Transmembrane protease serine 11A TMPRSS11A +SeqId.10895-28 Q86T26 TM11B Transmembrane protease serine 11B TMPRSS11B +SeqId.6547-83 O60235 TM11D Transmembrane protease serine 11D TMPRSS11D +SeqId.3189-61 P98073 Enterokinase Enteropeptidase TMPRSS15 +SeqId.8002-27 Q9H3S3 Spinesin Transmembrane protease serine 5 TMPRSS5 +SeqId.11239-49 Q8IU80 TMPS6 Transmembrane protease serine 6 TMPRSS6 +SeqId.9226-6 Q71RG4 TMUB2 Transmembrane and ubiquitin-like domain-containing protein 2 TMUB2 +SeqId.10675-223 Q9Y320 TMX2 Thioredoxin-related transmembrane protein 2 TMX2 +SeqId.5654-70 Q96JJ7 TMX3 Protein disulfide-isomerase TMX3 TMX3 +SeqId.4155-3 P24821 Tenascin Tenascin TNC +SeqId.5936-53 P01375 TNF-a Tumor necrosis factor TNF +SeqId.14009-65 P21580 TNFAIP3 Tumor necrosis factor alpha-induced protein 3 TNFAIP3 +SeqId.5036-50 P98066 TSG-6 Tumor necrosis factor-inducible gene 6 protein TNFAIP6 +SeqId.12563-2 O95379 TFIP8 Tumor necrosis factor alpha-induced protein 8 TNFAIP8 +SeqId.4832-75 O00220 TRAIL R1 Tumor necrosis factor receptor superfamily member 10A TNFRSF10A +SeqId.5534-49 O14763 TRAIL R2 Tumor necrosis factor receptor superfamily member 10B TNFRSF10B +SeqId.8529-1 O14763 TRAIL R2 Tumor necrosis factor receptor superfamily member 10B TNFRSF10B +SeqId.14121-24 Q9UBN6 TRAIL R4 Tumor necrosis factor receptor superfamily member 10D TNFRSF10D +SeqId.8304-50 O00300 OPG Tumor necrosis factor receptor superfamily member 11B TNFRSF11B +SeqId.5138-50 Q9NP84 TWEAKR Tumor necrosis factor receptor superfamily member 12A TNFRSF12A +SeqId.2704-74 O14836 TACI Tumor necrosis factor receptor superfamily member 13B TNFRSF13B +SeqId.5383-14 Q96RJ3 BAFF Receptor Tumor necrosis factor receptor superfamily member 13C TNFRSF13C +SeqId.5352-11 Q92956 HVEM Tumor necrosis factor receptor superfamily member 14 TNFRSF14 +SeqId.2665-26 Q02223 BCMA Tumor necrosis factor receptor superfamily member 17 TNFRSF17 +SeqId.11837-7 Q9Y5U5 GITR Tumor necrosis factor receptor superfamily member 18 TNFRSF18 +SeqId.5526-53 Q9Y5U5 GITR Tumor necrosis factor receptor superfamily member 18 TNFRSF18 +SeqId.5131-15 Q9NS68 TAJ Tumor necrosis factor receptor superfamily member 19 TNFRSF19 +SeqId.2654-19 P19438 TNF sR-I Tumor necrosis factor receptor superfamily member 1A TNFRSF1A +SeqId.3152-57 P20333 TNF sR-II Tumor necrosis factor receptor superfamily member 1B TNFRSF1B +SeqId.8368-102 P20333 TNF sR-II Tumor necrosis factor receptor superfamily member 1B TNFRSF1B +SeqId.5404-53 O75509 DR6 Tumor necrosis factor receptor superfamily member 21 TNFRSF21 +SeqId.3730-81 P43489 TNR4 Tumor necrosis factor receptor superfamily member 4 TNFRSF4 +SeqId.5070-76 O95407 DcR3 Tumor necrosis factor receptor superfamily member 6B TNFRSF6B +SeqId.2605-49 P28908 CD30 Tumor necrosis factor receptor superfamily member 8 TNFRSF8 +SeqId.14025-18 Q07011 4-1BB Tumor necrosis factor receptor superfamily member 9 TNFRSF9 +SeqId.8833-20 P50591 TRAIL Tumor necrosis factor ligand superfamily member 10 TNFSF10 +SeqId.14061-48 O14788 sRANKL Tumor necrosis factor ligand superfamily member 11 TNFSF11 +SeqId.5939-42 O43508 TWEAK Tumor necrosis factor ligand superfamily member 12 TNFSF12 +SeqId.3059-50 Q9Y275 BAFF Tumor necrosis factor ligand superfamily member 13B TNFSF13B +SeqId.5355-69 O43557 LIGHT Tumor necrosis factor ligand superfamily member 14 TNFSF14 +SeqId.5988-49 O43557 LIGHT Tumor necrosis factor ligand superfamily member 14 TNFSF14 +SeqId.2968-61 O95150 TNFSF15 Tumor necrosis factor ligand superfamily member 15 TNFSF15 +SeqId.2708-54 Q9UNG2 TNFSF18 Tumor necrosis factor ligand superfamily member 18 TNFSF18 +SeqId.2839-2 P23510 OX40 Ligand Tumor necrosis factor ligand superfamily member 4 TNFSF4 +SeqId.3421-54 P32971 CD30 Ligand Tumor necrosis factor ligand superfamily member 8 TNFSF8 +SeqId.2599-51 P41273 4-1BB ligand Tumor necrosis factor ligand superfamily member 9 TNFSF9 +SeqId.9907-216 O95271 Tankyrase-1 Tankyrase-1 TNKS +SeqId.6578-29 Q9H2S6 TNMD Tenomodulin TNMD +SeqId.5440-26 P48788 "Troponin I, skeletal, fast twitch" "Troponin I, fast skeletal muscle" TNNI2 +SeqId.5441-67 P19429 Troponin I "Troponin I, cardiac muscle" TNNI3 +SeqId.5315-22 P45379 Troponin T "Troponin T, cardiac muscle" TNNT2 +SeqId.16807-35 P45378 TNNT3 "Troponin T, fast skeletal muscle" TNNT3 +SeqId.11302-237 Q92752 TENR Tenascin-R TNR +SeqId.9808-41 Q9UPQ9 TNR6B Trinucleotide repeat-containing gene 6B protein TNRC6B +SeqId.11667-29 Q63HR2 TENC1 Tensin-2 TNS2 +SeqId.9927-96 Q8IZW8 TENS4 Tensin-4 TNS4 +SeqId.5698-60 P22105 Tenascin-X Tenascin-X TNXB +SeqId.13963-7 Q9H0E2 tollip Toll-interacting protein TOLLIP +SeqId.13652-2 O75674 TM1L1 TOM1-like protein 1 TOM1L1 +SeqId.19356-20 Q6ZVM7 TM1L2 TOM1-like protein 2 TOM1L2 +SeqId.10817-26 Q6UXN7 TO20L TOMM20-like protein 1 TOMM20L +SeqId.2876-74 P11387 Topoisomerase I DNA topoisomerase 1 TOP1 +SeqId.9947-22 Q92547 TOPB1 DNA topoisomerase 2-binding protein 1 TOPBP1 +SeqId.10606-34 Q5JTV8 TOIP1 Torsin-1A-interacting protein 1 TOR1AIP1 +SeqId.9039-47 Q5JTV8 TOIP1 Torsin-1A-interacting protein 1 TOR1AIP1 +SeqId.10553-8 Q8NFQ8 TOIP2 Torsin-1A-interacting protein 2 TOR1AIP2 +SeqId.13459-30 Q9NXH8 CI167 Torsin-4A TOR4A +SeqId.12717-65 O15405 TOX3 TOX high mobility group box family member 3 TOX3 +SeqId.6123-69 P04637 p53 Cellular tumor antigen p53 TP53 +SeqId.6168-11 P04637 p53 R175H Cellular tumor antigen p53 R175H mutant TP53 +SeqId.13022-20 O14683 P5I11 Tumor protein p53-inducible protein 11 TP53I11 +SeqId.6400-33 Q8NBR0 P5I13 Tumor protein p53-inducible protein 13 TP53I13 +SeqId.17748-21 Q53FA7 QORX Quinone oxidoreductase PIG3 TP53I3 +SeqId.10040-63 Q9H3D4 P73L Tumor protein 63 TP63 +SeqId.17710-40 Q16890 TPD53 Tumor protein D53 TPD52L1 +SeqId.4309-59 P60174 Triosephosphate isomerase Triosephosphate isomerase TPI1 +SeqId.12018-84 Q9H3S4 TPK1 Thiamin pyrophosphokinase 1 TPK1 +SeqId.5033-27 P09493 Tropomyosin 1 alpha chain Tropomyosin alpha-1 chain TPM1 +SeqId.4472-5 P07951 Tropomyosin 2 Tropomyosin beta chain TPM2 +SeqId.9863-1 P67936 Tropomyosin 4 Tropomyosin alpha-4 chain TPM4 +SeqId.11218-84 P51580 TPMT Thiopurine S-methyltransferase TPMT +SeqId.3873-51 P07202 TMA Thyroid peroxidase TPO +SeqId.17691-1 O14773 TPP1 Tripeptidyl-peptidase 1 TPP1 +SeqId.12800-5 P59282 TPPP2 Tubulin polymerization-promoting protein family member 2 TPPP2 +SeqId.12417-46 Q9Y3C4 TPRKB EKC/KEOPS complex subunit TPRKB TPRKB +SeqId.9409-11 Q15661 TRYB1 Tryptase beta-1 TPSAB1 +SeqId.3403-1 P20231 TPSB2 Tryptase beta-2 TPSB2 +SeqId.3404-51 Q9NRR2 TPSG1 Tryptase gamma TPSG1 +SeqId.7928-183 O60507 TPST1 Protein-tyrosine sulfotransferase 1 TPST1 +SeqId.8024-64 O60704 TPST2 Protein-tyrosine sulfotransferase 2 TPST2 +SeqId.3872-2 P13693 TCTP Translationally-controlled tumor protein TPT1 +SeqId.12373-73 P62995 TRA2B Transformer-2 protein homolog beta TRA2B +SeqId.11262-39 Q9H4I3 TRABD TraB domain-containing protein TRABD +SeqId.9401-57 Q86V40 CB089 Metalloprotease TIKI1 TRABD2A +SeqId.13507-51 Q15628 TRADD Tumor necrosis factor receptor type 1-associated DEATH domain protein TRADD +SeqId.17747-45 Q13077 TRAF1 TNF receptor-associated factor 1 TRAF1 +SeqId.13041-47 Q9BUZ4 TRAF4 TNF receptor-associated factor 4 TRAF4 +SeqId.14337-1 O43617 TPPC3 Trafficking protein particle complex subunit 3 TRAPPC3 +SeqId.7007-24 Q9Y296 TRAPPC4 Trafficking protein particle complex subunit 4 TRAPPC4 +SeqId.8671-378 Q8IUR0 TPPC5 Trafficking protein particle complex subunit 5 TRAPPC5 +SeqId.7224-11 Q6PIZ9 TRAT1 T-cell receptor-associated transmembrane adapter 1 TRAT1 +SeqId.12635-9 O14717 TRDMT tRNA (cytosine(38)-C(5))-methyltransferase TRDMT1 +SeqId.9266-1 Q9NP99 sTREM-1 Triggering receptor expressed on myeloid cells 1 TREM1 +SeqId.16300-4 Q9NZC2 TREM2 Triggering receptor expressed on myeloid cells 2 TREM2 +SeqId.11147-17 Q86YW5 TRML1 Trem-like transcript 1 protein TREML1 +SeqId.9329-28 Q86YW5 TRML1 Trem-like transcript 1 protein TREML1 +SeqId.5736-1 Q5T2D2 TRML2 Trem-like transcript 2 protein TREML2 +SeqId.17829-2 Q9BQ50 TREX2 Three prime repair exonuclease 2 TREX2 +SeqId.5659-11 P20396 TRH Pro-Thyrotropin-releasing hormone TRH +SeqId.18277-28 O43715 TRIA1 TP53-regulated inhibitor of apoptosis 1 TRIAP1 +SeqId.12363-70 Q92519 TRIB2 Tribbles homolog 2 TRIB2 +SeqId.6527-1 Q7L0X0 TRIL TLR4 interactor with leucine rich repeats TRIL +SeqId.12573-80 O75382 TRIM3 Tripartite motif-containing protein 3 TRIM3 +SeqId.11126-102 O75962 TRIO Triple functional domain protein TRIO +SeqId.17676-13 Q15642 CIP4 Cdc42-interacting protein 4 TRIP10 +SeqId.13044-5 Q99816 TS101 Tumor susceptibility gene 101 protein TSG101 +SeqId.3010-53 Q969D9 TSLP Thymic stromal lymphopoietin TSLP +SeqId.12477-42 Q15631 TSN Translin TSN +SeqId.7069-9 Q96NA8 TSNA1 t-SNARE domain-containing protein 1 TSNARE1 +SeqId.10546-2 Q8WU66 TSEAR Thrombospondin-type laminin G domain and EAR repeat-containing protein TSPEAR +SeqId.7018-10 Q9UJK0 TSR3 Ribosome biogenesis protein TSR3 homolog TSR3 +SeqId.18181-2 Q9Y5U2 TSSC4 Protein TSSC4 TSSC4 +SeqId.11179-7 Q9BXA7 TSSK1 Testis-specific serine/threonine-protein kinase 1 TSSK1B +SeqId.7873-32 Q96PF2 TSSK2 Testis-specific serine/threonine-protein kinase 2 TSSK2 +SeqId.12663-1 Q16762 THTR Thiosulfate sulfurtransferase TST +SeqId.12657-2 Q13630 FCL GDP-L-fucose synthase TSTA3 +SeqId.19277-4 Q8NFU3 KAT Thiosulfate sulfurtransferase/rhodanese-like domain-containing protein 1 TSTD1 +SeqId.9864-38 Q99614 TTC1 Tetratricopeptide repeat protein 1 TTC1 +SeqId.8800-14 Q96AE7 TTC17 Tetratricopeptide repeat protein 17 TTC17 +SeqId.9550-153 Q96AE7 TTC17 Tetratricopeptide repeat protein 17 TTC17 +SeqId.9386-42 Q8N6N2 TTC9B Tetratricopeptide repeat protein 9B TTC9B +SeqId.13973-62 Q8NG68 TTL Tubulin--tyrosine ligase TTL +SeqId.11352-42 Q8WZ42 TITIN Titin TTN +SeqId.5690-49 Q9NNX1 TUFT1 Tuftelin TUFT1 +SeqId.12871-10 Q12792 TWF1 Twinfilin-1 TWF1 +SeqId.9234-8 Q9GZX9 TWSG1 Twisted gastrulation protein homolog 1 TWSG1 +SeqId.15698-6 P40222 TXLNA Alpha-taxilin TXLNA +SeqId.8813-160 P10599 Thioredoxin Thioredoxin TXN +SeqId.9573-108 Q6PKC3 TXD11 Thioredoxin domain-containing protein 11 TXNDC11 +SeqId.19334-62 O95881 TXD12 Thioredoxin domain-containing protein 12 TXNDC12 +SeqId.6366-38 Q96J42 TXD15 Thioredoxin domain-containing protein 15 TXNDC15 +SeqId.11212-7 Q8NBS9 TXND5 Thioredoxin domain-containing protein 5 TXNDC5 +SeqId.11682-7 Q9H3M7 TXNIP Thioredoxin-interacting protein TXNIP +SeqId.15316-262 Q9NX01 TXN4B Thioredoxin-like protein 4B TXNL4B +SeqId.13967-14 Q16881 Thioredoxin reductase 1 "Thioredoxin reductase 1, cytoplasmic" TXNRD1 +SeqId.5260-80 P29597 TYK2 Non-receptor tyrosine-protein kinase TYK2 TYK2 +SeqId.11361-73 P19971 TP Thymidine phosphorylase TYMP +SeqId.5035-7 P04818 TS Thymidylate synthase TYMS +SeqId.8263-64 Q8TAI1 CR056 TYMS opposite strand protein TYMSOS +SeqId.2611-72 Q06418 Dtk Tyrosine-protein kinase receptor TYRO3 TYRO3 +SeqId.13577-25 P26368 U2AF2 Splicing factor U2AF 65 kDa subunit U2AF2 +SeqId.13580-2 Q16222 Sperm-associated antigen 2 UDP-N-acetylhexosamine pyrophosphorylase UAP1 +SeqId.12500-88 Q9UBT2 SAE2 SUMO-activating enzyme subunit 2 UBA2 +SeqId.12558-3 Q8TF42 UBS3B Ubiquitin-associated and SH3 domain-containing protein B UBASH3B +SeqId.6641-60 P0CG47 PolyUbiquitin K48 PolyUbiquitin K48-linked UBB +SeqId.6651-74 P0CG47 PolyUbiquitin K48 PolyUbiquitin K48-linked UBB +SeqId.6647-55 P0CG48 PolyUbiquitin K63 PolyUbiquitin K63-linked UBC +SeqId.17772-7 O15205 UBD Ubiquitin D UBD +SeqId.17743-14 P49459 UBE2A Ubiquitin-conjugating enzyme E2 A UBE2A +SeqId.9865-40 P63146 UBE2B Ubiquitin-conjugating enzyme E2 B UBE2B +SeqId.12556-7 O00762 UBE2C Ubiquitin-conjugating enzyme E2 C UBE2C +SeqId.19247-1 P51668 UB2D1 Ubiquitin-conjugating enzyme E2 D1 UBE2D1 +SeqId.18842-24 P62837 UB2D2 Ubiquitin-conjugating enzyme E2 D2 UBE2D2 +SeqId.19280-29 P61077 UB2D3 Ubiquitin-conjugating enzyme E2 D3 UBE2D3 +SeqId.13475-10 Q9Y2X8 UB2D4 Ubiquitin-conjugating enzyme E2 D4 UBE2D4 +SeqId.14326-4 P51965 UB2E1 Ubiquitin-conjugating enzyme E2 E1 UBE2E1 +SeqId.18213-30 Q969M7 UBE2F NEDD8-conjugating enzyme UBE2F UBE2F +SeqId.17158-17 P62253 UB2G1 Ubiquitin-conjugating enzyme E2 G1 UBE2G1 +SeqId.9199-6 P60604 UB2G2 Ubiquitin-conjugating enzyme E2 G2 UBE2G2 +SeqId.2877-3 P63279 UBC9 SUMO-conjugating enzyme UBC9 UBE2I +SeqId.6900-30 Q9Y385 UB2J1 Ubiquitin-conjugating enzyme E2 J1 UBE2J1 +SeqId.17380-2 P61086 UBE2K Ubiquitin-conjugating enzyme E2 K UBE2K +SeqId.3874-8 P68036 UB2L3 Ubiquitin-conjugating enzyme E2 L3 UBE2L3 +SeqId.19190-4 O14933 UB2L6 Ubiquitin/ISG15-conjugating enzyme E2 L6 UBE2L6 +SeqId.19111-10 P61081 UBC12 NEDD8-conjugating enzyme Ubc12 UBE2M +SeqId.3905-62 P61088 UBE2N Ubiquitin-conjugating enzyme E2 N UBE2N +SeqId.17729-20 Q16763 UBE2S Ubiquitin-conjugating enzyme E2 S UBE2S +SeqId.12400-25 Q9NPD8 UBE2T Ubiquitin-conjugating enzyme E2 T UBE2T +SeqId.11626-7 Q13404 UB2V1 Ubiquitin-conjugating enzyme E2 variant 1 UBE2V1 +SeqId.18165-181 Q15819 UB2V2 Ubiquitin-conjugating enzyme E2 variant 2 UBE2V2 +SeqId.11226-16 Q05086 UBE3A Ubiquitin-protein ligase E3A UBE3A +SeqId.11490-42 P11441 UBL4A Ubiquitin-like protein 4A UBL4A +SeqId.19124-9 Q8WVY7 UBCP1 Ubiquitin-like domain-containing CTD phosphatase 1 UBLCP1 +SeqId.19121-3 Q9UHD9 UBQL2 Ubiquilin-2 UBQLN2 +SeqId.12720-71 Q9NRR5 UBQL4 Ubiquilin-4 UBQLN4 +SeqId.12875-28 Q8WUN7 UBTD2 Ubiquitin domain-containing protein 2 UBTD2 +SeqId.18435-40 Q14CS0 UBX2B UBX domain-containing protein 2B UBXN2B +SeqId.9970-7 Q92575 UBXN4 UBX domain-containing protein 4 UBXN4 +SeqId.9997-12 Q92575 UBXN4 UBX domain-containing protein 4 UBXN4 +SeqId.5019-16 P09936 PGP9.5 Ubiquitin carboxyl-terminal hydrolase isozyme L1 UCHL1 +SeqId.17405-2 Q9Y5K5 UCHL5 Ubiquitin carboxyl-terminal hydrolase isozyme L5 UCHL5 +SeqId.12515-45 Q9BZX2 UCK2 Uridine-cytidine kinase 2 UCK2 +SeqId.10977-55 Q8WVF2 UCMA Unique cartilage matrix-associated protein UCMA +SeqId.10756-34 Q969E3 UCN3 Urocortin-3 UCN3 +SeqId.3405-6 Q9Y3C8 UFC1 Ubiquitin-fold modifier-conjugating enzyme 1 UFC1 +SeqId.17411-55 Q92890 UFD1 Ubiquitin recognition factor in ER-associated degradation protein 1 UFD1L +SeqId.3836-51 P61960 UFM1 Ubiquitin-fold modifier 1 UFM1 +SeqId.17755-5 O60701 UGDH UDP-glucose 6-dehydrogenase UGDH +SeqId.13939-14 Q16851 UGPA1 UTP--glucose-1-phosphate uridylyltransferase UGP2 +SeqId.17702-53 P22309 UGT 1A1 UDP-glucuronosyltransferase 1-1 UGT1A1 +SeqId.7891-45 P19224 UGT 1A6 UDP-glucuronosyltransferase 1-6 UGT1A6 +SeqId.8899-75 Q9HAW9 UD18 UDP-glucuronosyltransferase 1-8 UGT1A8 +SeqId.8907-11 Q9Y4X1 UD2A1 UDP-glucuronosyltransferase 2A1 UGT2A1 +SeqId.3081-70 Q9BZM6 ULBP-1 NKG2D ligand 1 ULBP1 +SeqId.3082-9 Q9BZM5 ULBP-2 NKG2D ligand 2 ULBP2 +SeqId.2747-3 Q9BZM4 ULBP-3 NKG2D ligand 3 ULBP3 +SeqId.12437-18 Q6PHR2 ULK3 Serine/threonine-protein kinase ULK3 ULK3 +SeqId.9451-20 P07911 Uromodulin Uromodulin UMOD +SeqId.9114-84 Q5DID0 UROL1 Uromodulin-like 1 UMODL1 +SeqId.14052-26 Q9UPW8 UN13A Protein unc-13 homolog A UNC13A +SeqId.13082-9 Q9H3U1 UN45A Protein unc-45 homolog A UNC45A +SeqId.7975-97 Q6ZN44 UNC5A Netrin receptor UNC5A UNC5A +SeqId.15394-79 Q8IZJ1 UNC5B Netrin receptor UNC5B UNC5B +SeqId.7776-20 Q8IZJ1 UNC5B Netrin receptor UNC5B UNC5B +SeqId.5139-32 O95185 UNC5H3 Netrin receptor UNC5C UNC5C +SeqId.16307-22 Q6UXZ4 UNC5H4 Netrin receptor UNC5D UNC5D +SeqId.13487-24 Q9H1C4 UN93B Protein unc-93 homolog B1 UNC93B1 +SeqId.6633-43 B0FP48 UPK3L Uroplakin-3b-like protein UPK3BL +SeqId.19448-104 Q16831 UPP1 Uridine phosphorylase 1 UPP1 +SeqId.12957-62 P14927 UCR6 Cytochrome b-c1 complex subunit 7 UQCRB +SeqId.19289-29 P06132 DCUP Uroporphyrinogen decarboxylase UROD +SeqId.11248-43 P10746 HEM4 Uroporphyrinogen-III synthase UROS +SeqId.11328-9 Q9BQ65 USB1 U6 snRNA phosphodiesterase USB1 +SeqId.17725-37 Q9Y6N9 USH1C Harmonin USH1C +SeqId.13639-101 O60763 USO1 General vesicular transport factor p115 USO1 +SeqId.19189-2 P54578 UBP14 Ubiquitin carboxyl-terminal hydrolase 14 USP14 +SeqId.19161-1 Q9Y4E8 UBP15 Ubiquitin carboxyl-terminal hydrolase 15 USP15 +SeqId.12681-63 Q9UK80 UBP21 Ubiquitin carboxyl-terminal hydrolase 21 USP21 +SeqId.9215-117 Q9UHP3 UBP25 Ubiquitin carboxyl-terminal hydrolase 25 USP25 +SeqId.19562-8 Q96RU2 UBP28 Ubiquitin carboxyl-terminal hydrolase 28 USP28 +SeqId.13450-49 P40818 UBP8 Ubiquitin carboxyl-terminal hydrolase 8 USP8 +SeqId.8364-74 Q9Y2C2 UST Uronyl 2-sulfotransferase UST +SeqId.6020-52 O95399 Urotensin-II Urotensin-2 UTS2 +SeqId.6290-3 Q765I0 UTS2B Urotensin-2B UTS2B +SeqId.13530-5 Q9UKP6 UR2R Urotensin-2 receptor UTS2R +SeqId.8258-22 Q8NBZ7 UXS1 UDP-glucuronic acid decarboxylase 1 UXS1 +SeqId.17711-13 P23763 VAMP1 Vesicle-associated membrane protein 1 VAMP1 +SeqId.17335-18 P63027 VAMP2 Vesicle-associated membrane protein 2 VAMP2 +SeqId.7903-18 Q15836 VAMP3 Vesicle-associated membrane protein 3 VAMP3 +SeqId.7732-45 O75379 VAMP4 Vesicle-associated membrane protein 4 VAMP4 +SeqId.19357-11 P51809 VAMP7 Vesicle-associated membrane protein 7 VAMP7 +SeqId.7064-2 Q9BV40 VAMP8 Vesicle-associated membrane protein 8 VAMP8 +SeqId.7167-102 Q9P0L0 VAPA Vesicle-associated membrane protein-associated protein A VAPA +SeqId.7181-17 O95292 VAPB Vesicle-associated membrane protein-associated protein B/C VAPB +SeqId.13083-18 P26640 SYVC Valine--tRNA ligase VARS +SeqId.5682-13 Q6EMK4 VASN Vasorin VASN +SeqId.9762-14 P50552 VASP Vasodilator-stimulated phosphoprotein VASP +SeqId.18175-65 Q99536 VAT1 Synaptic vesicle membrane protein VAT-1 homolog VAT1 +SeqId.5275-28 P15498 VAV Proto-oncogene vav VAV1 +SeqId.9830-109 Q9UKW4 VAV3 Guanine nucleotide exchange factor VAV3 VAV3 +SeqId.19193-18 P61758 PFD3 Prefoldin subunit 3 VBP1 +SeqId.2967-8 P19320 VCAM-1 Vascular cell adhesion protein 1 VCAM1 +SeqId.9561-21 P13611 CSPG2 Versican core protein VCAN +SeqId.8750-46 P18206 Vinculin Vinculin VCL +SeqId.10023-32 P11473 VDR Vitamin D3 receptor VDR +SeqId.2597-8 P15692 VEGF Vascular endothelial growth factor A VEGFA +SeqId.19437-61 P15692 L-VEGF165 Isoform L-VEGF165 VEGFA +SeqId.4867-15 P15692 VEGF121 "Vascular endothelial growth factor A, isoform 121" VEGFA +SeqId.9453-12 P49765 VEGF-B Vascular endothelial growth factor B VEGFB +SeqId.3132-1 P49767 VEGF-C Vascular endothelial growth factor C VEGFC +SeqId.17362-5 P40337 VHL Von Hippel-Lindau disease tumor suppressor VHL +SeqId.15540-6 P08670 Vimentin Vimentin VIM +SeqId.11286-78 Q9BQE4 SELS Selenoprotein S VIMP +SeqId.3522-57 P01282 Vasoactive Intestinal Peptide Vasoactive Intestinal Peptide VIP +SeqId.6234-74 Q6UXI7 VITRN Vitrin VIT +SeqId.18938-3 P98155 VLDLR Very low-density lipoprotein receptor VLDLR +SeqId.15480-2 O95498 VNN2 Vascular non-inflammatory molecule 2 VNN2 +SeqId.14618-26 Q96AW1 ECOP "Vesicular, overexpressed in cancer, prosurvival protein 1" VOPP1 +SeqId.12508-9 Q9Y3E7 CHMP3 Charged multivesicular body protein 3 VPS24 +SeqId.18189-12 Q9BRG1 VPS25 Vacuolar protein-sorting-associated protein 25 VPS25 +SeqId.19293-6 O75436 VP26A Vacuolar protein sorting-associated protein 26A VPS26A +SeqId.17155-1 Q9UK41 VPS28 protein homolog Vacuolar protein sorting-associated protein 28 homolog VPS28 +SeqId.14318-1 Q9UBQ0 VPS29 Vacuolar protein sorting-associated protein 29 VPS29 +SeqId.11476-43 Q9UN37 VPS4A Vacuolar protein sorting-associated protein 4A VPS4A +SeqId.12668-7 O75351 VPS4B Vacuolar protein sorting-associated protein 4B VPS4B +SeqId.12553-5 Q99986 VRK1 Serine/threonine-protein kinase VRK1 VRK1 +SeqId.8367-142 Q86XK7 VSIG1 V-set and immunoglobulin domain-containing protein 1 VSIG1 +SeqId.10825-12 Q8N0Z9 VSI10 V-set and immunoglobulin domain-containing protein 10 VSIG10 +SeqId.8018-43 Q96IQ7 VSIG2 V-set and immunoglobulin domain-containing protein 2 VSIG2 +SeqId.13522-20 P62760 VISL1 Visinin-like protein 1 VSNL1 +SeqId.6549-60 Q96N03 VTM2L V-set and transmembrane domain-containing protein 2-like protein VSTM2L +SeqId.7242-14 Q8IW00 CJ072 V-set and transmembrane domain-containing protein 4 VSTM4 +SeqId.4209-60 Q9NP79 DRG-1 Vacuolar protein sorting-associated protein VTA1 homolog VTA1 +SeqId.7952-2 Q96AJ9 VTI1A Vesicle transport through interaction with t-SNAREs homolog 1A VTI1A +SeqId.8963-8 Q9UEU0 Vti1-rp1 Vesicle transport through interaction with t-SNAREs homolog 1B VTI1B +SeqId.13125-45 P04004 Vitronectin Vitronectin VTN +SeqId.6385-63 Q6PCB0 VWA1 von Willebrand factor A domain-containing protein 1 VWA1 +SeqId.7128-9 Q5GFL6 VWA2 von Willebrand factor A domain-containing protein 2 VWA2 +SeqId.15308-108 Q2TAL6 VWC2 Brorin VWC2 +SeqId.7995-16 B2RUY7 VWC2L von Willebrand factor C domain-containing protein 2-like VWC2L +SeqId.3050-7 P04275 vWF von Willebrand factor VWF +SeqId.9870-17 P23381 SYWC "Tryptophan--tRNA ligase, cytoplasmic" WARS +SeqId.9532-5 Q9NX94 WBP1L WW domain binding protein 1-like WBP1L +SeqId.17698-15 Q969T9 WBP2 WW domain-binding protein 2 WBP2 +SeqId.17760-128 P61964 WDR5 WD repeat-containing protein 5 WDR5 +SeqId.9316-67 Q9HC57 WFDC1 WAP four-disulfide core domain protein 1 WFDC1 +SeqId.13429-3 Q9H1F0 WF10A WAP four-disulfide core domain protein 10A WFDC10A +SeqId.10695-12 Q8IUB3 WF10B Protein WFDC10B WFDC10B +SeqId.7969-163 Q8NEX6 WFD11 Protein WFDC11 WFDC11 +SeqId.9345-436 Q8IUB5 WFD13 WAP four-disulfide core domain protein 13 WFDC13 +SeqId.11388-75 Q14508 HE4 WAP four-disulfide core domain protein 2 WFDC2 +SeqId.6384-19 Q8IUB2 WFDC3 WAP four-disulfide core domain protein 3 WFDC3 +SeqId.6969-14 Q8TCV5 WFDC5 WAP four-disulfide core domain protein 5 WFDC5 +SeqId.13412-5 Q9BQY6 WFDC6 WAP four-disulfide core domain protein 6 WFDC6 +SeqId.7147-35 Q8IUA0 WFDC8 WAP four-disulfide core domain protein 8 WFDC8 +SeqId.3191-50 Q96NZ8 WFKN1 "WAP, kazal, immunoglobulin, kunitz and NTR domain-containing protein 1" WFIKKN1 +SeqId.3235-50 Q8TEU8 WFKN2 "WAP, Kazal, immunoglobulin, Kunitz and NTR domain-containing protein 2" WFIKKN2 +SeqId.16070-7 Q9Y5W5 WIF-1 Wnt inhibitory factor 1 WIF1 +SeqId.13692-154 O95388 WISP-1 WNT1-inducible-signaling pathway protein 1 WISP1 +SeqId.3057-55 O95388 WISP-1 WNT1-inducible-signaling pathway protein 1 WISP1 +SeqId.6392-7 O76076 WISP-2 WNT1-inducible-signaling pathway protein 2 WISP2 +SeqId.5927-4 O95389 WISP-3 WNT1-inducible-signaling pathway protein 3 WISP3 +SeqId.5493-17 Q9BYP7 WNK3 Serine/threonine-protein kinase WNK3 WNK3 +SeqId.10044-12 Q9GZT5 WN10A Protein Wnt-10a WNT10A +SeqId.6624-94 O96014 WNT11 Protein Wnt-11 WNT11 +SeqId.13236-25 P56704 WNT3A Protein Wnt-3a WNT3A +SeqId.13268-45 P41221 WNT5A Protein Wnt-5a WNT5A +SeqId.4889-82 O00755 WNT7A Protein Wnt-7a WNT7A +SeqId.12528-40 Q96S55 WRIP1 ATPase WRNIP1 WRNIP1 +SeqId.6274-15 Q2TBF2 WSCD2 WSC domain-containing protein 2 WSCD2 +SeqId.18284-77 Q8IX03 WWC1 Protein KIBRA WWC1 +SeqId.17724-3 Q9NZC7 WWOX WW domain-containing oxidoreductase WWOX +SeqId.11307-33 Q9H0M0 WWP1 NEDD4-like E3 ubiquitin-protein ligase WWP1 WWP1 +SeqId.4143-74 P47992 Lymphotactin Lymphotactin XCL1 +SeqId.15617-8 Q9UBD3 lymphotactin beta Cytokine SCM-1 beta XCL2 +SeqId.11264-33 P47989 XDH Xanthine dehydrogenase/oxidase XDH +SeqId.8044-90 P55808 XG Glycoprotein Xg XG +SeqId.3481-87 Q9NQW7 XPNPEP1 Xaa-Pro aminopeptidase 1 XPNPEP1 +SeqId.12535-2 P18887 XRCC1 DNA repair protein XRCC1 XRCC1 +SeqId.9886-28 Q13426 XRCC4 DNA repair protein XRCC4 XRCC4 +SeqId.2835-1 P12956 Ku70 X-ray repair cross-complementing protein 6 XRCC6 +SeqId.6375-75 Q8NBI6 XXLT1 Xyloside xylosyltransferase 1 XXYLT1 +SeqId.19270-26 P54577 SYYC "Tyrosine--tRNA ligase, cytoplasmic" YARS +SeqId.9751-72 P67809 NSEP1 Nuclease-sensitive element-binding protein 1 YBX1 +SeqId.6372-7 Q9Y2T7 YBOX2 Y-box-binding protein 2 YBX2 +SeqId.17474-106 O95619 YETS4 YEATS domain-containing protein 4 YEATS4 +SeqId.2878-66 P07947 YES Tyrosine-protein kinase Yes YES1 +SeqId.9984-12 Q96EC8 YIPF6 Protein YIPF6 YIPF6 +SeqId.11190-129 Q96TA2 YMEL1 ATP-dependent zinc metalloprotease YME1L1 YME1L1 +SeqId.8878-48 Q96MU7 YTDC1 YTH domain-containing protein 1 YTHDC1 +SeqId.14156-33 P31946 14-3-3 protein beta/alpha 14-3-3 protein beta/alpha YWHAB +SeqId.14157-21 P62258 14-3-3E 14-3-3 protein epsilon YWHAE +SeqId.4179-57 P61981 14-3-3 protein gamma 14-3-3 protein gamma YWHAG +SeqId.4179-57 P61981 14-3-3 protein gamma 14-3-3 protein gamma YWHAG +SeqId.4179-57 P61981 14-3-3 protein gamma 14-3-3 protein gamma YWHAG +SeqId.4179-57 P61981 14-3-3 protein gamma 14-3-3 protein gamma YWHAG +SeqId.4179-57 P61981 14-3-3 protein gamma 14-3-3 protein gamma YWHAG +SeqId.4179-57 P61981 14-3-3 protein gamma 14-3-3 protein gamma YWHAG +SeqId.4179-57 P61981 14-3-3 protein gamma 14-3-3 protein gamma YWHAG +SeqId.4707-50 Q04917 14-3-3 eta 14-3-3 protein eta YWHAH +SeqId.4707-50 Q04917 14-3-3 eta 14-3-3 protein eta YWHAH +SeqId.4707-50 Q04917 14-3-3 eta 14-3-3 protein eta YWHAH +SeqId.4707-50 Q04917 14-3-3 eta 14-3-3 protein eta YWHAH +SeqId.4707-50 Q04917 14-3-3 eta 14-3-3 protein eta YWHAH +SeqId.4707-50 Q04917 14-3-3 eta 14-3-3 protein eta YWHAH +SeqId.4707-50 Q04917 14-3-3 eta 14-3-3 protein eta YWHAH +SeqId.7625-27 P27348 14-3-3 protein theta 14-3-3 protein theta YWHAQ +SeqId.5858-6 P63104 14-3-3 protein zeta/delta 14-3-3 protein zeta/delta YWHAZ +SeqId.17337-1 P25490 TYY1 Transcriptional repressor protein YY1 YY1 +SeqId.17345-12 Q8N4Q0 ZADH2 Prostaglandin reductase 3 ZADH2 +SeqId.3837-6 P43403 ZAP70 Tyrosine-protein kinase ZAP-70 ZAP70 +SeqId.4476-22 P43403 ZAP70 Tyrosine-protein kinase ZAP-70 ZAP70 +SeqId.12785-49 Q86T24 KAISO Transcriptional regulator Kaiso ZBTB33 +SeqId.11677-17 Q8IZN3 ZDH14 Probable palmitoyltransferase ZDHHC14 ZDHHC14 +SeqId.19173-5 Q8TCF1 ZFAN1 AN1-type zinc finger protein 1 ZFAND1 +SeqId.18317-111 O76080 ZFAN5 AN1-type zinc finger protein 5 ZFAND5 +SeqId.13651-54 Q96JP5 ZFP91 E3 ubiquitin-protein ligase ZFP91 ZFP91 +SeqId.9102-28 Q5T4F4 ZFY27 Protrudin ZFYVE27 +SeqId.8219-14 O60844 ZG16 Zymogen granule membrane protein 16 ZG16 +SeqId.8310-6 Q96DA0 U773 Zymogen granule protein 16 homolog B ZG16B +SeqId.12751-26 Q9UKY1 ZHX1 Zinc fingers and homeoboxes protein 1 ZHX1 +SeqId.10036-201 Q9H4I2 ZHX3 Zinc fingers and homeoboxes protein 3 ZHX3 +SeqId.11567-23 P21506 ZNF10 Zinc finger protein 10 ZNF10 +SeqId.12787-47 P52741 ZN134 Zinc finger protein 134 ZNF134 +SeqId.11486-26 Q15697 ZN174 Zinc finger protein 174 ZNF174 +SeqId.12716-3 Q9Y473 ZN175 Zinc finger protein 175 ZNF175 +SeqId.11372-2 P17022 ZNF18 Zinc finger protein 18 ZNF18 +SeqId.12771-19 Q9UJW8 ZN180 Zinc finger protein 180 ZNF180 +SeqId.11565-58 P17027 ZNF23 Zinc finger protein 23 ZNF23 +SeqId.9993-11 O43296 ZN264 Zinc finger protein 264 ZNF264 +SeqId.9609-25 Q9NSD4 ZN275 Zinc finger protein 275 ZNF275 +SeqId.14692-3 Q8N554 ZN276 Zinc finger protein 276 ZNF276 +SeqId.12803-9 Q86UD4 ZN329 Zinc finger protein 329 ZNF329 +SeqId.12763-69 Q9HCZ1 ZN334 Zinc finger protein 334 ZNF334 +SeqId.18265-18 Q8IZ26 ZNF34 Zinc finger protein 34 ZNF34 +SeqId.14616-16 Q96SR6 ZN382 Zinc finger protein 382 ZNF382 +SeqId.10003-15 P51814 ZNF41 Zinc finger protein 41 ZNF41 +SeqId.12843-6 Q86VK4 ZN410 Zinc finger protein 410 ZNF410 +SeqId.12811-55 Q09FC8 ZN415 Zinc finger protein 415 ZNF415 +SeqId.14619-8 Q8TF50 ZN526 Zinc finger protein 526 ZNF526 +SeqId.12543-76 Q96MR9 ZN560 Zinc finger protein 560 ZNF560 +SeqId.12795-2 Q969W8 ZN566 Zinc finger protein 566 ZNF566 +SeqId.11596-47 P51815 ZN75D Zinc finger protein 75D ZNF75D +SeqId.12760-34 Q6NX45 ZN774 Zinc finger protein 774 ZNF774 +SeqId.8321-27 Q8N446 ZN843 Zinc finger protein 843 ZNF843 +SeqId.10390-21 Q9ULT6 ZNRF3 E3 ubiquitin-protein ligase ZNRF3 ZNRF3 +SeqId.14122-132 Q9ULT6 ZNRF3 E3 ubiquitin-protein ligase ZNRF3 ZNRF3 +SeqId.7766-25 Q12836 ZP4 Zona pellucida sperm-binding protein 4 ZP4 +SeqId.8635-283 Q9BS86 ZPBP1 Zona pellucida-binding protein 1 ZPBP +SeqId.10710-23 Q6X784 ZPBP2 Zona pellucida-binding protein 2 ZPBP2 +SeqId.5590-11 Q8TCW7 ZPLD1 Zona pellucida-like domain-containing protein 1 ZPLD1 +SeqId.18302-204 Q9H900 ZWILC Protein zwilch homolog ZWILCH +SeqId.18286-3 O95229 ZWINT ZW10 interactor ZWINT +SeqId.13632-10 Q15942 Zyxin Zyxin ZYX diff --git a/tests/gentropy/data_samples/decode/raw/manifest/_SUCCESS b/tests/gentropy/data_samples/decode/raw/manifest/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/tests/gentropy/data_samples/decode/raw/manifest/part-00000-2c81f5b6-bf1b-407b-b876-439825f3ddaf-c000.snappy.parquet b/tests/gentropy/data_samples/decode/raw/manifest/part-00000-2c81f5b6-bf1b-407b-b876-439825f3ddaf-c000.snappy.parquet new file mode 100644 index 000000000..f3860a9f7 Binary files /dev/null and b/tests/gentropy/data_samples/decode/raw/manifest/part-00000-2c81f5b6-bf1b-407b-b876-439825f3ddaf-c000.snappy.parquet differ diff --git a/tests/gentropy/data_samples/decode/raw/raw_index.txt b/tests/gentropy/data_samples/decode/raw/raw_index.txt new file mode 100644 index 000000000..d109f2990 --- /dev/null +++ b/tests/gentropy/data_samples/decode/raw/raw_index.txt @@ -0,0 +1 @@ +2024-05-29 22:07:59 925.8 MiB some_prefix/Proteomics_PC0_9999_1_GENE_PROTEIN_07082019.txt.gz diff --git a/tests/gentropy/data_samples/decode/raw/raw_summary_statistics/studyId=deCODE-some_prefix_Proteomics_PC0_9999_1_GENE_PROTEIN_07082019/_SUCCESS b/tests/gentropy/data_samples/decode/raw/raw_summary_statistics/studyId=deCODE-some_prefix_Proteomics_PC0_9999_1_GENE_PROTEIN_07082019/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/tests/gentropy/data_samples/decode/raw/raw_summary_statistics/studyId=deCODE-some_prefix_Proteomics_PC0_9999_1_GENE_PROTEIN_07082019/part-00000-1d5fae52-417d-4c9e-812e-b6f81fb21ff0-c000.snappy.parquet b/tests/gentropy/data_samples/decode/raw/raw_summary_statistics/studyId=deCODE-some_prefix_Proteomics_PC0_9999_1_GENE_PROTEIN_07082019/part-00000-1d5fae52-417d-4c9e-812e-b6f81fb21ff0-c000.snappy.parquet new file mode 100644 index 000000000..d8e2c8425 Binary files /dev/null and b/tests/gentropy/data_samples/decode/raw/raw_summary_statistics/studyId=deCODE-some_prefix_Proteomics_PC0_9999_1_GENE_PROTEIN_07082019/part-00000-1d5fae52-417d-4c9e-812e-b6f81fb21ff0-c000.snappy.parquet differ diff --git a/tests/gentropy/data_samples/example_s3_config.json b/tests/gentropy/data_samples/example_s3_config.json new file mode 100644 index 000000000..a8c8eafd7 --- /dev/null +++ b/tests/gentropy/data_samples/example_s3_config.json @@ -0,0 +1,7 @@ +{ + "bucket_name": "my_bucket", + "access_key_id": "my_access_key", + "secret_access_key": "my_secret_access", + "s3_host_url": "https://some_host_url.com", + "s3_host_port": 1234 +} diff --git a/tests/gentropy/dataset/test_variant_direction.py b/tests/gentropy/dataset/test_variant_direction.py index ddc6abaf6..560450d7f 100644 --- a/tests/gentropy/dataset/test_variant_direction.py +++ b/tests/gentropy/dataset/test_variant_direction.py @@ -84,6 +84,7 @@ def test_from_variant_index( exp_data = [ Row( chromosome="1", + rangeId=0, originalVariantId="1_100_A_C", type=1, variantId="1_100_A_C", @@ -97,6 +98,7 @@ def test_from_variant_index( ), Row( chromosome="1", + rangeId=0, originalVariantId="1_100_A_C", type=1, variantId="1_100_C_A", @@ -110,6 +112,7 @@ def test_from_variant_index( ), Row( chromosome="1", + rangeId=0, originalVariantId="1_100_A_C", type=1, variantId="1_100_T_G", @@ -123,6 +126,7 @@ def test_from_variant_index( ), Row( chromosome="1", + rangeId=0, originalVariantId="1_100_A_C", type=1, variantId="1_100_G_T", @@ -136,6 +140,7 @@ def test_from_variant_index( ), Row( chromosome="1", + rangeId=0, originalVariantId="1_100_ACT_G", type=3, variantId="1_100_ACT_G", @@ -149,6 +154,7 @@ def test_from_variant_index( ), Row( chromosome="1", + rangeId=0, originalVariantId="1_100_ACT_G", type=3, variantId="1_100_G_ACT", @@ -162,6 +168,7 @@ def test_from_variant_index( ), Row( chromosome="1", + rangeId=0, originalVariantId="1_100_ACT_G", type=3, variantId="1_100_AGT_C", @@ -175,6 +182,7 @@ def test_from_variant_index( ), Row( chromosome="1", + rangeId=0, originalVariantId="1_100_ACT_G", type=3, variantId="1_100_C_AGT", @@ -188,6 +196,7 @@ def test_from_variant_index( ), Row( chromosome="1", + rangeId=0, originalVariantId="1_100_A_T", type=1, variantId="1_100_A_T", @@ -201,6 +210,7 @@ def test_from_variant_index( ), Row( chromosome="1", + rangeId=0, originalVariantId="1_100_A_T", type=1, variantId="1_100_T_A", @@ -214,6 +224,5 @@ def test_from_variant_index( ), ] exp_df = session.spark.createDataFrame(exp_data, VariantDirection.get_schema()) - assert ( - variant_direction.df.select(exp_df.columns).collect() == exp_df.collect() - ), "data does not match expected" + asserted = variant_direction.df.select(exp_df.columns).collect() + assert exp_df.collect() == asserted, "should collect expected rows" diff --git a/tests/gentropy/datasource/complex_portal/test_complex_tab.py b/tests/gentropy/datasource/complex_portal/test_complex_tab.py new file mode 100644 index 000000000..c05281b6c --- /dev/null +++ b/tests/gentropy/datasource/complex_portal/test_complex_tab.py @@ -0,0 +1,244 @@ +"""Unit tests for the ComplexTab protein-complex datasource.""" + +from __future__ import annotations + +from pyspark.sql import functions as f +from pyspark.sql import types as t + +from gentropy.common.session import Session +from gentropy.dataset.molecular_complex import MolecularComplex +from gentropy.datasource.complex_portal import ComplexTab + +# Paths to bundled sample ComplexTAB files +_EXPERIMENTAL_TSV = "tests/gentropy/data_samples/complex_tab/9606.tsv" +_PREDICTED_TSV = "tests/gentropy/data_samples/complex_tab/9606_predicted.tsv" + + +class TestComplexTabSchema: + """Tests for ComplexTab.get_schema().""" + + def test_returns_struct_type(self) -> None: + """get_schema() must return a StructType.""" + assert isinstance(ComplexTab.get_schema(), t.StructType) + + def test_has_required_fields(self) -> None: + """get_schema() must contain the core ComplexTAB column names.""" + field_names = set(ComplexTab.get_schema().fieldNames()) + assert "#Complex ac" in field_names + assert "Taxonomy identifier" in field_names + assert "Expanded participant list" in field_names + assert "Evidence Code" in field_names + assert "Cross references" in field_names + assert "Source" in field_names + + def test_taxonomy_identifier_is_integer(self) -> None: + """The Taxonomy identifier column must be IntegerType.""" + schema = ComplexTab.get_schema() + taxonomy_field = next( + field for field in schema.fields if field.name == "Taxonomy identifier" + ) + assert isinstance(taxonomy_field.dataType, t.IntegerType) + + +class TestParseSource: + """Tests for ComplexTab._parse_source().""" + + def test_extracts_id_and_source(self, session: Session) -> None: + """_parse_source should extract PSI-MI id and human-readable source name.""" + df = session.spark.createDataFrame( + [('psi-mi:"MI:0469"(IntAct)',)], "raw STRING" + ) + result = df.select(ComplexTab._parse_source(f.col("raw")).alias("s")) + row = result.collect()[0].s + assert row.id == "MI:0469" + assert row.source == "IntAct" + + def test_empty_string_gives_empty_fields(self, session: Session) -> None: + """_parse_source on an empty string should produce empty id and source.""" + df = session.spark.createDataFrame([("",)], "raw STRING") + result = df.select(ComplexTab._parse_source(f.col("raw")).alias("s")) + row = result.collect()[0].s + assert row.id == "" + assert row.source == "" + + +class TestParseEvidenceCode: + """Tests for ComplexTab._parse_evidence_code().""" + + def test_single_eco_code(self, session: Session) -> None: + """A single ECO term should produce a one-element array.""" + df = session.spark.createDataFrame([("ECO:0000353",)], "raw STRING") + result = df.select(ComplexTab._parse_evidence_code(f.col("raw")).alias("codes")) + codes = result.collect()[0].codes + assert codes == ["ECO:0000353"] + + def test_multiple_eco_codes_pipe_separated(self, session: Session) -> None: + """Pipe-separated ECO codes should produce a multi-element array.""" + df = session.spark.createDataFrame([("ECO:0000353|ECO:0005543",)], "raw STRING") + result = df.select(ComplexTab._parse_evidence_code(f.col("raw")).alias("codes")) + codes = result.collect()[0].codes + assert codes == ["ECO:0000353", "ECO:0005543"] + + def test_extra_text_around_eco_code_ignored(self, session: Session) -> None: + """Extra surrounding text should be stripped; only the ECO: accession is kept.""" + df = session.spark.createDataFrame( + [("pubmed:12345(ECO:0000353)",)], "raw STRING" + ) + result = df.select(ComplexTab._parse_evidence_code(f.col("raw")).alias("codes")) + codes = result.collect()[0].codes + assert codes == ["ECO:0000353"] + + +class TestParseCrossReferences: + """Tests for ComplexTab._parse_cross_references().""" + + def test_single_cross_reference(self, session: Session) -> None: + """A single cross-reference entry should produce a one-element array.""" + df = session.spark.createDataFrame( + [("reactome:R-HSA-9736938(identity)",)], "raw STRING" + ) + result = df.select( + ComplexTab._parse_cross_references(f.col("raw")).alias("xrefs") + ) + xrefs = result.collect()[0].xrefs + assert len(xrefs) == 1 + assert xrefs[0].source == "reactome" + assert xrefs[0].id == "R-HSA-9736938" + + def test_multiple_cross_references(self, session: Session) -> None: + """Pipe-separated entries should each map to a {source, id} struct.""" + df = session.spark.createDataFrame( + [("reactome:R-HSA-9736938(identity)|wwpdb:1U7V(subset)",)], "raw STRING" + ) + result = df.select( + ComplexTab._parse_cross_references(f.col("raw")).alias("xrefs") + ) + xrefs = result.collect()[0].xrefs + assert len(xrefs) == 2 + sources = {x.source for x in xrefs} + assert "reactome" in sources + assert "wwpdb" in sources + + +class TestParseComponents: + """Tests for ComplexTab._parse_components().""" + + def test_single_component(self, session: Session) -> None: + """A single UniProt entry should produce a one-element component array.""" + df = session.spark.createDataFrame([("P04637(2)",)], "raw STRING") + result = df.select(ComplexTab._parse_components(f.col("raw")).alias("comps")) + comps = result.collect()[0].comps + assert len(comps) == 1 + assert comps[0].id == "P04637" + assert comps[0].stoichiometry == "2" + assert comps[0].source == "uniprot" + + def test_multiple_components(self, session: Session) -> None: + """Pipe-separated entries should produce one struct per component.""" + df = session.spark.createDataFrame([("P04637(2)|Q9Y6K9(1)",)], "raw STRING") + result = df.select(ComplexTab._parse_components(f.col("raw")).alias("comps")) + comps = result.collect()[0].comps + assert len(comps) == 2 + ids = {c.id for c in comps} + assert ids == {"P04637", "Q9Y6K9"} + + def test_source_is_always_uniprot(self, session: Session) -> None: + """The source field must always be 'uniprot' regardless of the input.""" + df = session.spark.createDataFrame([("P04637(2)|Q9Y6K9(1)",)], "raw STRING") + result = df.select(ComplexTab._parse_components(f.col("raw")).alias("comps")) + comps = result.collect()[0].comps + assert all(c.source == "uniprot" for c in comps) + + def test_hyphenated_uniprot_id(self, session: Session) -> None: + """Hyphenated UniProt isoform IDs (e.g. P12345-1) should be parsed correctly.""" + df = session.spark.createDataFrame([("P12345-1(3)",)], "raw STRING") + result = df.select(ComplexTab._parse_components(f.col("raw")).alias("comps")) + comps = result.collect()[0].comps + assert comps[0].id == "P12345-1" + assert comps[0].stoichiometry == "3" + + +class TestFromComplexTab: + """Integration tests for ComplexTab.from_complex_tab() using bundled sample TSVs.""" + + def test_returns_molecular_complex(self, session: Session) -> None: + """from_complex_tab should return a MolecularComplex instance.""" + result = ComplexTab.from_complex_tab( + session, experimental=_EXPERIMENTAL_TSV, predicted=_PREDICTED_TSV + ) + assert isinstance(result, MolecularComplex) + + def test_output_has_rows(self, session: Session) -> None: + """The output dataset should contain at least one row.""" + result = ComplexTab.from_complex_tab( + session, experimental=_EXPERIMENTAL_TSV, predicted=_PREDICTED_TSV + ) + assert result.df.count() > 0 + + def test_output_schema_matches_molecular_complex(self, session: Session) -> None: + """The output DataFrame schema should match MolecularComplex.get_schema().""" + result = ComplexTab.from_complex_tab( + session, experimental=_EXPERIMENTAL_TSV, predicted=_PREDICTED_TSV + ) + assert result.df.schema == MolecularComplex.get_schema() + + def test_all_rows_are_human(self, session: Session) -> None: + """from_complex_tab must filter to human complexes only (taxonomy 9606).""" + # The sample TSVs are already human-only, so the row count should be + # equal to the total count before filtering – a non-zero count proves + # the filter is not discarding everything. + result = ComplexTab.from_complex_tab( + session, experimental=_EXPERIMENTAL_TSV, predicted=_PREDICTED_TSV + ) + assert result.df.count() > 0 + + def test_experimental_and_predicted_are_unioned(self, session: Session) -> None: + """Rows from both input files should appear in the output.""" + exp_only = ComplexTab.from_complex_tab( + session, experimental=_EXPERIMENTAL_TSV, predicted=_PREDICTED_TSV + ) + ComplexTab.from_complex_tab( + session, experimental=_PREDICTED_TSV, predicted=_EXPERIMENTAL_TSV + ) + # With both files the union should have at least as many rows as either alone + combined = ComplexTab.from_complex_tab( + session, experimental=_EXPERIMENTAL_TSV, predicted=_PREDICTED_TSV + ) + assert combined.df.count() >= exp_only.df.count() + + def test_id_field_is_populated(self, session: Session) -> None: + """Every row in the output must have a non-null id.""" + result = ComplexTab.from_complex_tab( + session, experimental=_EXPERIMENTAL_TSV, predicted=_PREDICTED_TSV + ) + null_ids = result.df.filter(f.col("id").isNull()).count() + assert null_ids == 0 + + def test_components_are_arrays(self, session: Session) -> None: + """The components column should be an array type in the schema.""" + result = ComplexTab.from_complex_tab( + session, experimental=_EXPERIMENTAL_TSV, predicted=_PREDICTED_TSV + ) + components_field = next( + field for field in result.df.schema.fields if field.name == "components" + ) + assert isinstance(components_field.dataType, t.ArrayType) + + def test_evidence_codes_contain_eco_accessions(self, session: Session) -> None: + """EvidenceCodes values should look like ECO accessions.""" + result = ComplexTab.from_complex_tab( + session, experimental=_EXPERIMENTAL_TSV, predicted=_PREDICTED_TSV + ) + # Collect a sample and verify at least one ECO code is present + rows = result.df.filter(f.col("evidenceCodes").isNotNull()).limit(5).collect() + assert any( + any(code.startswith("ECO:") for code in row.evidenceCodes) for row in rows + ) + + def test_known_complex_id_present(self, session: Session) -> None: + """CPX-1 from the experimental sample file must appear in the output.""" + result = ComplexTab.from_complex_tab( + session, experimental=_EXPERIMENTAL_TSV, predicted=_PREDICTED_TSV + ) + ids = {row.id for row in result.df.select("id").collect()} + assert "CPX-1" in ids diff --git a/tests/gentropy/datasource/decode/conftest.py b/tests/gentropy/datasource/decode/conftest.py new file mode 100644 index 000000000..dc35069d3 --- /dev/null +++ b/tests/gentropy/datasource/decode/conftest.py @@ -0,0 +1,78 @@ +"""Shared fixtures for deCODE datasource tests.""" + +from __future__ import annotations + +from datetime import datetime + +import pytest +from pyspark.sql import Row + +from gentropy.common.session import Session +from gentropy.dataset.molecular_complex import MolecularComplex +from gentropy.datasource.decode.aptamer_metadata import AptamerMetadata +from gentropy.datasource.decode.manifest import deCODEManifest + + +@pytest.fixture() +def sample_manifest(session: Session) -> deCODEManifest: + """A two-row deCODEManifest (one SMP, one RAW) for reuse across decode tests.""" + rows = [ + Row( + projectId="deCODE-proteomics-smp", + studyId="deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001", + hasSumstats=True, + summarystatsLocation="s3a://my_bucket/some_folder/Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001.txt.gz", + size="927.2 MiB", + accessionTimestamp=datetime(2022, 5, 29, 9, 27, 28), + ), + Row( + projectId="deCODE-proteomics-raw", + studyId="deCODE-proteomics-raw_Proteomics_PC0_10001_1_GENE2__SOME_PROTEIN_2_00000001", + hasSumstats=True, + summarystatsLocation="s3a://my_bucket/some_folder/Proteomics_PC0_10001_1_GENE2__SOME_PROTEIN_2_00000001.txt.gz", + size="926.0 MiB", + accessionTimestamp=datetime(2022, 5, 29, 9, 27, 35), + ), + ] + df = session.spark.createDataFrame(rows, schema=deCODEManifest.get_schema()) + return deCODEManifest(_df=df) + + +@pytest.fixture() +def sample_aptamer_metadata(session: Session) -> AptamerMetadata: + """A small AptamerMetadata dataset covering single-target and complex cases.""" + rows = [ + Row( + aptamerId="10000-2", + targetName="GENE1", + targetFullName="Gene 1 Full Name", + isProteinComplex=False, + targetMetadata=[Row(geneSymbol="GENE1", proteinId="P12345")], + ), + Row( + aptamerId="10001-1", + targetName="GENE2", + targetFullName="Gene 2 Full Name", + isProteinComplex=False, + targetMetadata=[Row(geneSymbol="GENE2", proteinId="Q99999")], + ), + Row( + aptamerId="20000-1", + targetName="COMPLEX1", + targetFullName="Complex Protein 1", + isProteinComplex=True, + targetMetadata=[ + Row(geneSymbol="GENEA", proteinId="P11111"), + Row(geneSymbol="GENEB", proteinId="P22222"), + ], + ), + ] + df = session.spark.createDataFrame(rows, schema=AptamerMetadata.get_schema()) + return AptamerMetadata(_df=df) + + +@pytest.fixture() +def empty_molecular_complex(session: Session) -> MolecularComplex: + """An empty MolecularComplex for use when no complex annotation is needed.""" + df = session.spark.createDataFrame([], schema=MolecularComplex.get_schema()) + return MolecularComplex(_df=df) diff --git a/tests/gentropy/datasource/decode/test_decode_aptamer_metadata.py b/tests/gentropy/datasource/decode/test_decode_aptamer_metadata.py new file mode 100644 index 000000000..fcdd54f87 --- /dev/null +++ b/tests/gentropy/datasource/decode/test_decode_aptamer_metadata.py @@ -0,0 +1,164 @@ +"""Unit tests for AptamerMetadata.""" + +from __future__ import annotations + +import csv +from pathlib import Path + +import pytest +from pyspark.sql import types as t + +from gentropy.common.session import Session +from gentropy.datasource.decode.aptamer_metadata import AptamerMetadata + + +class TestAptamerMetadataSchema: + """Tests for AptamerMetadata schema.""" + + def test_get_schema_returns_struct_type(self) -> None: + """get_schema() should return a StructType.""" + schema = AptamerMetadata.get_schema() + assert isinstance(schema, t.StructType) + + def test_get_schema_field_names(self) -> None: + """get_schema() must contain all expected field names.""" + expected_fields = { + "aptamerId", + "targetName", + "targetFullName", + "isProteinComplex", + "targetMetadata", + } + assert set(AptamerMetadata.get_schema().fieldNames()) == expected_fields + + def test_aptamer_id_is_non_nullable(self) -> None: + """AptamerId and targetName must be non-nullable.""" + schema = AptamerMetadata.get_schema() + fields = {f.name: f for f in schema.fields} + assert fields["aptamerId"].nullable is False + assert fields["targetName"].nullable is False + + +class TestAptamerMetadataTransform: + """Tests for AptamerMetadata._transform_source.""" + + def test_strips_seqid_prefix(self, session: Session) -> None: + """SeqId. prefix must be stripped; hyphens in the numeric suffix are preserved.""" + raw = session.spark.createDataFrame( + [("SeqId.10000-2", "GENE1", "Full name", "GENE1", "P12345")], + "seqid STRING, target_name STRING, target_full_name STRING, gene_name STRING, uniprot STRING", + ) + result = AptamerMetadata._transform_source(raw) + rows = result.df.collect() + assert len(rows) == 1 + assert rows[0].aptamerId == "10000-2" + + def test_single_target_not_complex(self, session: Session) -> None: + """A single-gene aptamer should have isProteinComplex=False and one targetMetadata entry.""" + raw = session.spark.createDataFrame( + [("SeqId.1111-1", "GENE1", "Gene 1", "GENE1", "P12345")], + "seqid STRING, target_name STRING, target_full_name STRING, gene_name STRING, uniprot STRING", + ) + result = AptamerMetadata._transform_source(raw) + rows = result.df.collect() + assert rows[0].isProteinComplex is False + assert len(rows[0].targetMetadata) == 1 + assert rows[0].targetMetadata[0].geneSymbol == "GENE1" + assert rows[0].targetMetadata[0].proteinId == "P12345" + + def test_multi_target_is_complex(self, session: Session) -> None: + """A comma-separated gene list should yield isProteinComplex=True and multiple targets.""" + raw = session.spark.createDataFrame( + [ + ( + "SeqId.2222_3", + "COMPLEX", + "Complex protein", + "GENEA,GENEB", + "P111,P222", + ) + ], + "seqid STRING, target_name STRING, target_full_name STRING, gene_name STRING, uniprot STRING", + ) + result = AptamerMetadata._transform_source(raw) + rows = result.df.collect() + assert rows[0].isProteinComplex is True + assert len(rows[0].targetMetadata) == 2 + + @pytest.mark.parametrize( + "gene_name,uniprot", + [ + ("GENE1", "P12345"), + ("GENE1,GENE2", "P12345,P67890"), + ], + ) + def test_target_metadata_gene_and_protein_id( + self, session: Session, gene_name: str, uniprot: str + ) -> None: + """TargetMetadata entries should carry geneSymbol and proteinId.""" + raw = session.spark.createDataFrame( + [("SeqId.9999-1", "TNAME", "Full", gene_name, uniprot)], + "seqid STRING, target_name STRING, target_full_name STRING, gene_name STRING, uniprot STRING", + ) + result = AptamerMetadata._transform_source(raw) + rows = result.df.collect() + gene_list = gene_name.split(",") + protein_list = uniprot.split(",") + for i, (gene, protein) in enumerate(zip(gene_list, protein_list)): + assert rows[0].targetMetadata[i].geneSymbol == gene + assert rows[0].targetMetadata[i].proteinId == protein + + def test_distinct_rows_deduplicated(self, session: Session) -> None: + """Duplicate rows in the source should be deduplicated.""" + raw = session.spark.createDataFrame( + [ + ("SeqId.1-1", "G", "FN", "G", "P1"), + ("SeqId.1-1", "G", "FN", "G", "P1"), + ], + "seqid STRING, target_name STRING, target_full_name STRING, gene_name STRING, uniprot STRING", + ) + result = AptamerMetadata._transform_source(raw) + assert result.df.count() == 1 + + +class TestAptamerMetadataFromSource: + """Tests for AptamerMetadata.from_source.""" + + def test_from_source_returns_aptamer_metadata( + self, session: Session, tmp_path: Path + ) -> None: + """from_source should return an AptamerMetadata instance.""" + tsv_path = tmp_path / "aptamers.tsv" + rows = [ + { + "seqid": "SeqId.10000_2", + "target_name": "GENE1", + "target_full_name": "Gene 1", + "gene_name": "GENE1", + "uniprot": "P12345", + }, + { + "seqid": "SeqId.10001_1", + "target_name": "GENE2", + "target_full_name": "Gene 2", + "gene_name": "GENE2", + "uniprot": "Q99999", + }, + ] + with tsv_path.open("w", newline="") as fh: + writer = csv.DictWriter(fh, fieldnames=rows[0].keys(), delimiter="\t") + writer.writeheader() + writer.writerows(rows) + + result = AptamerMetadata.from_source(session, str(tsv_path)) + assert isinstance(result, AptamerMetadata), "Should return AptamerMetadata" + assert result.df.count() == 2 + + def test_from_source_uses_sample_file(self, session: Session) -> None: + """from_source should parse the repository sample file without errors.""" + sample_path = ( + "tests/gentropy/data_samples/decode/decode_2023_aptamer_mapping.tsv" + ) + result = AptamerMetadata.from_source(session, sample_path) + assert isinstance(result, AptamerMetadata) + assert result.df.count() > 0 diff --git a/tests/gentropy/datasource/decode/test_decode_manifest.py b/tests/gentropy/datasource/decode/test_decode_manifest.py new file mode 100644 index 000000000..5af43186f --- /dev/null +++ b/tests/gentropy/datasource/decode/test_decode_manifest.py @@ -0,0 +1,69 @@ +"""Test manifest generation.""" + +from datetime import datetime +from pathlib import Path + +from pyspark.sql import Row + +from gentropy import Session +from gentropy.datasource.decode.manifest import deCODEManifest + + +class TestdeCODEManifest: + """Test methods of deCODEManifest.""" + + listing_path = "tests/gentropy/data_samples/aws_bucket_listing.txt" + s3_config_path = "tests/gentropy/data_samples/example_s3_config.json" + expected_rows = [ + Row( + projectId="deCODE-proteomics-smp", + studyId="deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001", + hasSumstats=True, + summarystatsLocation="s3a://my_bucket/some_folder/Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001.txt.gz", + size="927.2 MiB", + accessionTimestamp=datetime(2022, 5, 29, 9, 27, 28), + ), + Row( + projectId="deCODE-proteomics-raw", + studyId="deCODE-proteomics-raw_Proteomics_PC0_10001_1_GENE2__SOME_PROTEIN_2_00000001", + hasSumstats=True, + summarystatsLocation="s3a://my_bucket/some_folder/Proteomics_PC0_10001_1_GENE2__SOME_PROTEIN_2_00000001.txt.gz", + size="926.0 MiB", + accessionTimestamp=datetime(2022, 5, 29, 9, 27, 35), + ), + ] + + def test_manifest_from_bucket_listing(self, session: Session) -> None: + """Test building manifest from bucket listing.""" + manifest = deCODEManifest.from_bucket_listing( + session, self.listing_path, self.s3_config_path + ) + assert isinstance(manifest, deCODEManifest), "should return deCODEManifest" + assert manifest.df.count() == 2, "should have 2 entries" + + assert manifest.df.collect() == self.expected_rows, ( + "should collect expected rows" + ) + + def test_from_parquet(self, session: Session, tmp_path: Path) -> None: + """Test round-trip: write expected rows to parquet and reload via from_parquet.""" + manifest_path = (tmp_path / "manifest").as_posix() + session.spark.createDataFrame( + self.expected_rows, schema=deCODEManifest.get_schema() + ).write.mode("overwrite").parquet(manifest_path) + manifest = deCODEManifest.from_parquet(session, manifest_path) + assert isinstance(manifest, deCODEManifest), "should return deCODEManifest" + assert manifest.df.count() == 2, "should have 2 entries" + assert manifest.df.collect() == self.expected_rows, ( + "should collect expected rows" + ) + + def test_get_summary_statistics_paths(self, session: Session) -> None: + """get_summary_statistics_paths should return all summarystatsLocation values.""" + df = session.spark.createDataFrame( + self.expected_rows, schema=deCODEManifest.get_schema() + ) + manifest = deCODEManifest(_df=df) + paths = manifest.get_summary_statistics_paths() + expected_paths = [row.summarystatsLocation for row in self.expected_rows] + assert sorted(paths) == sorted(expected_paths) diff --git a/tests/gentropy/datasource/decode/test_decode_study_index.py b/tests/gentropy/datasource/decode/test_decode_study_index.py new file mode 100644 index 000000000..14aca986f --- /dev/null +++ b/tests/gentropy/datasource/decode/test_decode_study_index.py @@ -0,0 +1,426 @@ +"""Unit tests for deCODE study index.""" + +from __future__ import annotations + +import pytest +from pyspark.sql import Row +from pyspark.sql import functions as f +from pyspark.sql import types as t + +from gentropy.common.session import Session +from gentropy.dataset.molecular_complex import MolecularComplex +from gentropy.dataset.study_index import ProteinQuantitativeTraitLocusStudyIndex +from gentropy.datasource.decode.aptamer_metadata import AptamerMetadata +from gentropy.datasource.decode.manifest import deCODEManifest +from gentropy.datasource.decode.study_index import ( + deCODEStudyIdParts, + deCODEStudyIndex, +) + + +class TestdeCODEStudyIdParts: + """Tests for the deCODEStudyIdParts regex-based ID parsing.""" + + @pytest.mark.parametrize( + "study_id,expected_project,expected_datasource,expected_aptamer,expected_gene,expected_protein", + [ + ( + "deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001", + "deCODE-proteomics-smp", + "Proteomics_SMP_PC0", + "10000-2", + "GENE1", + "PROTEIN1", + ), + ( + "deCODE-proteomics-raw_Proteomics_PC0_10001_1_GENEXY_PROTEINY_99999999", + "deCODE-proteomics-raw", + "Proteomics_PC0", + "10001-1", + "GENEXY", + "PROTEINY", + ), + ], + ) + def test_extract_study_id_parts( + self, + session: Session, + study_id: str, + expected_project: str, + expected_datasource: str, + expected_aptamer: str, + expected_gene: str, + expected_protein: str, + ) -> None: + """extract_study_id_parts should correctly parse each component of a studyId.""" + df = session.spark.createDataFrame([(study_id,)], "studyId STRING") + id_parts = deCODEStudyIdParts.extract_study_id_parts(f.col("studyId")) + row = df.select(*id_parts).collect()[0] + assert row.projectId == expected_project + assert row.datasourceType == expected_datasource + assert row.aptamerId == expected_aptamer + assert row.geneSymbolFromStudyId == expected_gene + assert row.proteinNameFromStudyId == expected_protein + + def test_extract_study_id_parts_invalid_pattern_returns_empty( + self, session: Session + ) -> None: + """An unrecognised studyId should return empty strings for all parts.""" + df = session.spark.createDataFrame( + [("not-a-valid-study-id",)], "studyId STRING" + ) + id_parts = deCODEStudyIdParts.extract_study_id_parts(f.col("studyId")) + row = df.select(*id_parts).collect()[0] + assert row.projectId == "" + + def test_mark_missing_gene_id_na_becomes_null(self, session: Session) -> None: + """A gene symbol of 'NA' should be converted to null.""" + df = session.spark.createDataFrame([("NA",), ("REAL_GENE",)], "gene STRING") + result = df.select( + deCODEStudyIdParts._mark_missing_gene_id(f.col("gene")).alias("out") + ).collect() + assert result[0].out is None + assert result[1].out == "REAL_GENE" + + @pytest.mark.parametrize("protein", ["Deprecated", "No_Protein"]) + def test_mark_missing_protein_deprecated_becomes_null( + self, session: Session, protein: str + ) -> None: + """'Deprecated' and 'No_Protein' protein names should be nulled out.""" + df = session.spark.createDataFrame([(protein,)], "protein STRING") + result = df.select( + deCODEStudyIdParts._mark_missing_protein(f.col("protein")).alias("out") + ).collect() + assert result[0].out is None + + def test_trait_property_concatenates_parts(self, session: Session) -> None: + """The trait property should concat datasourceType, aptamerId, geneSymbol, proteinName.""" + study_id = ( + "deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001" + ) + df = session.spark.createDataFrame([(study_id,)], "studyId STRING") + id_parts = deCODEStudyIdParts.extract_study_id_parts(f.col("studyId")) + row = df.select(id_parts.trait).collect()[0] + assert row.traitFromSource == "Proteomics_SMP_PC0_10000-2_GENE1_PROTEIN1" + + +class TestdeCODEStudyIndexSampleSizes: + """Tests for sample-size helper methods.""" + + @pytest.mark.parametrize( + "project_id,expected_n", + [ + ("deCODE-proteomics-raw", 36_136), + ("deCODE-proteomics-smp", 35_892), + ], + ) + def test_get_n_samples_by_project( + self, session: Session, project_id: str, expected_n: int + ) -> None: + """get_n_samples should return the correct integer sample count per project.""" + from gentropy.datasource.decode import deCODEPublicationMetadata + + pub = deCODEPublicationMetadata() + df = session.spark.createDataFrame([(project_id,)], "projectId STRING") + row = df.select( + deCODEStudyIndex.get_n_samples(f.col("projectId"), pub) + ).collect()[0] + assert row.nSamples == expected_n + + @pytest.mark.parametrize( + "project_id,expected_text", + [ + ("deCODE-proteomics-raw", "36,136 Icelandic individuals"), + ("deCODE-proteomics-smp", "35,892 Icelandic individuals"), + ], + ) + def test_get_initial_sample_text( + self, session: Session, project_id: str, expected_text: str + ) -> None: + """get_initial_sample should return a readable string with correct count.""" + from gentropy.datasource.decode import deCODEPublicationMetadata + + pub = deCODEPublicationMetadata() + df = session.spark.createDataFrame([(project_id,)], "projectId STRING") + row = df.select( + deCODEStudyIndex.get_initial_sample(f.col("projectId"), pub) + ).collect()[0] + assert row.initialSampleSize == expected_text + + +class TestdeCODEStudyIndexUpdateStudyId: + """Tests for deCODEStudyIndex.update_study_id.""" + + def test_update_study_id_single_target(self, session: Session) -> None: + """update_study_id should reconstruct studyId using gene/protein from targets.""" + study_id = ( + "deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001" + ) + targets_type = t.ArrayType( + t.StructType( + [ + t.StructField("geneSymbol", t.StringType()), + t.StructField("proteinId", t.StringType()), + ] + ) + ) + schema = t.StructType( + [ + t.StructField("studyId", t.StringType()), + t.StructField("targets", targets_type), + ] + ) + df = session.spark.createDataFrame( + [(study_id, [Row(geneSymbol="GENE1", proteinId="PROTEIN1")])], + schema=schema, + ) + row = df.select( + deCODEStudyIndex.update_study_id(f.col("studyId"), f.col("targets")) + ).collect()[0] + assert ( + row.updatedStudyId + == "deCODE-proteomics-smp_Proteomics_SMP_PC0_10000-2_GENE1_PROTEIN1" + ) + + def test_update_study_id_multi_target(self, session: Session) -> None: + """Multi-target studyId should comma-join geneSymbols and proteinNames.""" + study_id = ( + "deCODE-proteomics-smp_Proteomics_SMP_PC0_20000_1_GENEA_PROTEINA_00000001" + ) + targets_type = t.ArrayType( + t.StructType( + [ + t.StructField("geneSymbol", t.StringType()), + t.StructField("proteinId", t.StringType()), + ] + ) + ) + schema = t.StructType( + [ + t.StructField("studyId", t.StringType()), + t.StructField("targets", targets_type), + ] + ) + df = session.spark.createDataFrame( + [ + ( + study_id, + [ + Row(geneSymbol="GENEA", proteinId="PROTEINA"), + Row(geneSymbol="GENEB", proteinId="PROTEINB"), + ], + ) + ], + schema=schema, + ) + row = df.select( + deCODEStudyIndex.update_study_id(f.col("studyId"), f.col("targets")) + ).collect()[0] + assert "GENEA,GENEB" in row.updatedStudyId + assert "PROTEINA,PROTEINB" in row.updatedStudyId + + +class TestdeCODEStudyIndexFromManifest: + """Tests for deCODEStudyIndex.from_manifest.""" + + def test_from_manifest_returns_pqtl_study_index( + self, + sample_manifest: deCODEManifest, + sample_aptamer_metadata: AptamerMetadata, + empty_molecular_complex: MolecularComplex, + ) -> None: + """from_manifest should return a ProteinQuantitativeTraitLocusStudyIndex.""" + result = deCODEStudyIndex.from_manifest( + manifest=sample_manifest, + aptamer_metadata=sample_aptamer_metadata, + molecular_complex=empty_molecular_complex, + ) + assert isinstance(result, ProteinQuantitativeTraitLocusStudyIndex) + + def test_from_manifest_inner_joins_on_aptamer_id( + self, + session: Session, + sample_manifest: deCODEManifest, + empty_molecular_complex: MolecularComplex, + ) -> None: + """Rows without a matching aptamerId should be excluded (inner join).""" + # Only provide aptamer for the first (SMP) study → only 1 output row + single_aptamer_df = session.spark.createDataFrame( + [ + Row( + aptamerId="10000-2", + targetName="GENE1", + targetFullName="Gene 1", + isProteinComplex=False, + targetMetadata=[Row(geneSymbol="GENE1", proteinId="P12345")], + ) + ], + schema=AptamerMetadata.get_schema(), + ) + single_aptamer = AptamerMetadata(_df=single_aptamer_df) + result = deCODEStudyIndex.from_manifest( + manifest=sample_manifest, + aptamer_metadata=single_aptamer, + molecular_complex=empty_molecular_complex, + ) + assert result.df.count() == 1 + + def test_from_manifest_drops_missing_gene_or_protein( + self, + session: Session, + empty_molecular_complex: MolecularComplex, + ) -> None: + """Rows where the gene symbol is 'NA' (→ null) are dropped before the join.""" + from datetime import datetime + + from gentropy.datasource.decode import deCODEDataSource + + bad_rows = [ + Row( + projectId=deCODEDataSource.DECODE_PROTEOMICS_SMP.value, + studyId="deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_NA_PROTEIN1_00000001", + hasSumstats=True, + summarystatsLocation="s3a://bucket/file.txt.gz", + size="1 MiB", + accessionTimestamp=datetime(2022, 1, 1), + ), + ] + manifest = deCODEManifest( + _df=session.spark.createDataFrame( + bad_rows, schema=deCODEManifest.get_schema() + ) + ) + aptamer_df = session.spark.createDataFrame( + [ + Row( + aptamerId="10000-2", + targetName="GENE1", + targetFullName="Full", + isProteinComplex=False, + targetMetadata=[Row(geneSymbol="GENE1", proteinId="P12345")], + ) + ], + schema=AptamerMetadata.get_schema(), + ) + aptamer = AptamerMetadata(_df=aptamer_df) + result = deCODEStudyIndex.from_manifest( + manifest=manifest, + aptamer_metadata=aptamer, + molecular_complex=empty_molecular_complex, + ) + assert result.df.count() == 0 + + def test_from_manifest_publication_metadata( + self, + session: Session, + empty_molecular_complex: MolecularComplex, + ) -> None: + """Output rows should carry hardcoded publication metadata.""" + from datetime import datetime + + from gentropy.datasource.decode import deCODEDataSource + + rows = [ + Row( + projectId=deCODEDataSource.DECODE_PROTEOMICS_SMP.value, + studyId="deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001", + hasSumstats=True, + summarystatsLocation="s3a://bucket/f.txt.gz", + size="1 MiB", + accessionTimestamp=datetime(2022, 1, 1), + ) + ] + manifest = deCODEManifest( + _df=session.spark.createDataFrame(rows, schema=deCODEManifest.get_schema()) + ) + aptamer_df = session.spark.createDataFrame( + [ + Row( + aptamerId="10000-2", + targetName="GENE1", + targetFullName="Full", + isProteinComplex=False, + targetMetadata=[Row(geneSymbol="GENE1", proteinId="P12345")], + ) + ], + schema=AptamerMetadata.get_schema(), + ) + aptamer = AptamerMetadata(_df=aptamer_df) + result = deCODEStudyIndex.from_manifest( + manifest=manifest, + aptamer_metadata=aptamer, + molecular_complex=empty_molecular_complex, + ) + row = result.df.select( + "pubmedId", + "publicationJournal", + "biosampleFromSourceId", + "studyType", + "nSamples", + "initialSampleSize", + ).collect()[0] + assert row.pubmedId == "37794188" + assert row.publicationJournal == "Nature" + assert row.biosampleFromSourceId == "UBERON_0001969" + assert row.studyType == "pqtl" + assert row.nSamples == 35_892 + assert row.initialSampleSize == "35,892 Icelandic individuals" + + def test_from_manifest_molecular_complex_annotated( + self, + session: Session, + ) -> None: + """A matched molecular complex should populate molecularComplexId.""" + from datetime import datetime + + from gentropy.datasource.decode import deCODEDataSource + + rows = [ + Row( + projectId=deCODEDataSource.DECODE_PROTEOMICS_SMP.value, + studyId="deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001", + hasSumstats=True, + summarystatsLocation="s3a://bucket/f.txt.gz", + size="1 MiB", + accessionTimestamp=datetime(2022, 1, 1), + ) + ] + manifest = deCODEManifest( + _df=session.spark.createDataFrame(rows, schema=deCODEManifest.get_schema()) + ) + aptamer_df = session.spark.createDataFrame( + [ + Row( + aptamerId="10000-2", + targetName="GENE1", + targetFullName="Full", + isProteinComplex=False, + targetMetadata=[Row(geneSymbol="GENE1", proteinId="P12345")], + ) + ], + schema=AptamerMetadata.get_schema(), + ) + aptamer = AptamerMetadata(_df=aptamer_df) + mc_df = session.spark.createDataFrame( + [ + Row( + id="COMPLEX_001", + description="desc", + properties=None, + assembly=None, + components=[Row(id="P12345", stoichiometry="1", source="intact")], + evidenceCodes=None, + crossReferences=None, + source=Row(id="intact", source="intact"), + ) + ], + schema=MolecularComplex.get_schema(), + ) + mc = MolecularComplex(_df=mc_df) + result = deCODEStudyIndex.from_manifest( + manifest=manifest, + aptamer_metadata=aptamer, + molecular_complex=mc, + ) + row = result.df.select("molecularComplexId").collect()[0] + assert row.molecularComplexId == "COMPLEX_001" diff --git a/tests/gentropy/datasource/decode/test_decode_summary_statistics.py b/tests/gentropy/datasource/decode/test_decode_summary_statistics.py new file mode 100644 index 000000000..728981096 --- /dev/null +++ b/tests/gentropy/datasource/decode/test_decode_summary_statistics.py @@ -0,0 +1,342 @@ +"""Test summary statistics.""" + +from pathlib import Path +from unittest.mock import MagicMock, patch + +import pytest +from pyspark.sql import Row +from pyspark.sql import functions as f +from pyspark.sql import types as t + +from gentropy.common.session import Session +from gentropy.dataset.study_index import ProteinQuantitativeTraitLocusStudyIndex +from gentropy.dataset.summary_statistics import SummaryStatistics +from gentropy.datasource.decode.summary_statistics import ( + deCODEHarmonisationConfig, + deCODESummaryStatistics, +) + + +def assert_sumstat_equal(l1: list[Row], l2: list[Row]) -> bool: + """Compare two lists of Rows for equality, ignoring order.""" + sorted_l1 = sorted(l1, key=lambda row: (row.studyId, row.variantId)) + sorted_l2 = sorted(l2, key=lambda row: (row.studyId, row.variantId)) + i = 0 + for row1, row2 in zip(sorted_l1, sorted_l2, strict=True): + for field in SummaryStatistics.get_schema().fieldNames(): + if isinstance(row1[field], float) and isinstance(row2[field], float): + cmp = row1[field] - row2[field] == pytest.approx(0, abs=1e-5) + else: + cmp = row1[field] == row2[field] + assert cmp, ( + f"Row: {i}: Field '{field}' does not match: {row1[field]} != {row2[field]}" + ) + i += 1 + return True + + +class TestdeCODESummaryStatistics: + """Test methods of deCODESummaryStatistics.""" + + raw_data = [ + Row( + # Retained variant, but flipped due to variant direction + Chrom="chr1", + Pos=1111, + Name="chr1:1111:C:T", + rsids=None, + effectAllele="C", # Expected alt = C + otherAllele="T", # Expected ref = T + Beta=-0.0077, # Expected beta is 0.0077 + Pval=0.7945, + minus_log10_pval=0.1, + SE=0.012345, + N=35678, + impMAF=0.07662, + studyId="deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001", + ), + Row( + # Row filtered out due to low N (N = 20000) + Chrom="chr1", + Pos=152835, + Name="chr1:152835:A:T", + rsids="rs1446209547", + effectAllele="A", + otherAllele="T", + Beta=-0.05, + Pval=0.7945, + minus_log10_pval=0.1, + SE=0.438241, + N=20000, + impMAF=0.01, + studyId="deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001", + ), + Row( + # Row filtered out due to low MAC (MAC = 6) + Chrom="chr1", + Pos=201430, + Name="chr1:201430:TTC:T", + rsids="rs1205330954", + effectAllele="TTC", + otherAllele="T", + Beta=-0.0077, + Pval=0.7945, + minus_log10_pval=0.1, + SE=0.015984, + N=30000, + impMAF=0.00001, + studyId="deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001", + ), + Row( + # Row retained, but EAF is 1 - MAF + Chrom="chr1", + Pos=455948, + Name="chr1:455948:G:C", + rsids="rs1363653182", + effectAllele="G", + otherAllele="C", + Beta=0.1027, + Pval=0.7945, + minus_log10_pval=0.1, + SE=0.012345, + N=34567, + impMAF=0.95, # Expected EAF is 0.05 + studyId="deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001", + ), + Row( + # Row retained, missing from gnomAD + Chrom="chr1", + Pos=455949, + Name="chr1:455949:G:C", + rsids=None, + effectAllele="G", + otherAllele="C", + Beta=0.1027, + Pval=0.7945, + minus_log10_pval=0.1, + SE=0.012345, + N=34567, + impMAF=0.05, + studyId="deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001", + ), + ] + + vd_data = [ + Row( + chromosome="1", + rangeId=0, + originalVariantId="1_1111_T_C", + variantId="1_1111_C_T", + direction=-1, + originalAlleleFrequencies=[ + Row(populationName="nfe_adj", alleleFrequency=0.07662) + ], + strand=1, + ), + Row( + chromosome="1", + rangeId=0, + originalVariantId="1_1111_T_C", + variantId="1_1111_T_C", + direction=1, + originalAlleleFrequencies=[ + Row(populationName="nfe_adj", alleleFrequency=0.07662) + ], + strand=1, + ), + Row( + chromosome="1", + rangeId=15, + originalVariantId="1_152835_A_T", + variantId="1_152835_A_T", + direction=1, + originalAlleleFrequencies=[ + Row(populationName="nfe_adj", alleleFrequency=0.07662) + ], + strand=1, + ), + Row( + chromosome="1", + rangeId=20, + originalVariantId="1_201430_TTC_T", + variantId="1_201430_TTC_T", + direction=1, + originalAlleleFrequencies=[ + Row(populationName="nfe_adj", alleleFrequency=0.07662) + ], + strand=1, + ), + Row( + chromosome="1", + rangeId=45, + originalVariantId="1_455948_G_C", + variantId="1_455948_G_C", + direction=1, + originalAlleleFrequencies=[ + Row(populationName="nfe_adj", alleleFrequency=0.07662) + ], + strand=1, + ), + ] + + expected_harm_rows = [ + # This allele is flipped with regards to source (variantId + beta sign) + Row( + studyId="deCODE-proteomics-smp_Proteomics_SMP_PC0_10000-2_GENE1_P12345", + variantId="1_1111_T_C", + chromosome="1", + position=1111, + beta=0.0077, + sampleSize=35678, + pValueMantissa=7.943282, + pValueExponent=-1, + effectAlleleFrequencyFromSource=0.07662, + standardError=0.012345, + ), + # This allele does not have anything changed, is found in variant direction + Row( + studyId="deCODE-proteomics-smp_Proteomics_SMP_PC0_10000-2_GENE1_P12345", + variantId="1_455948_G_C", + chromosome="1", + position=455948, + beta=0.1027, + sampleSize=34567, + pValueMantissa=7.943282, + pValueExponent=-1, + effectAlleleFrequencyFromSource=0.05, + standardError=0.012345, + ), + # This allele does not have anything changed, is not found in variant direction + Row( + studyId="deCODE-proteomics-smp_Proteomics_SMP_PC0_10000-2_GENE1_P12345", + variantId="1_455949_G_C", + chromosome="1", + position=455949, + beta=0.1027, + sampleSize=34567, + pValueMantissa=7.943282, + pValueExponent=-1, + effectAlleleFrequencyFromSource=0.05, + standardError=0.012345, + ), + ] + + @patch("gentropy.datasource.decode.summary_statistics.VariantDirection") + def test_from_source( + self, mock_variant_direction: MagicMock, session: Session + ) -> None: + """Test building summary statistics from source — filters, flips, and EAF inference.""" + raw = session.spark.createDataFrame(self.raw_data) + vd_df = session.spark.createDataFrame(self.vd_data) + vd_instance = MagicMock(df=vd_df) + mock_variant_direction.return_value = vd_instance + + # Build a minimal pQTL study index DF with the required non-nullable columns + source_study_id = ( + "deCODE-proteomics-smp_Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001" + ) + targets_schema = t.ArrayType( + t.StructType( + [ + t.StructField("geneSymbol", t.StringType(), nullable=True), + t.StructField("proteinId", t.StringType(), nullable=True), + t.StructField("geneId", t.StringType(), nullable=True), + t.StructField("proteinName", t.StringType(), nullable=True), + ] + ), + containsNull=True, + ) + si_schema = t.StructType( + [ + t.StructField("studyId", t.StringType(), nullable=False), + t.StructField("projectId", t.StringType(), nullable=False), + t.StructField("studyType", t.StringType(), nullable=False), + t.StructField("targetsFromSource", targets_schema, nullable=True), + ] + ) + si_df = session.spark.createDataFrame( + [ + ( + source_study_id, + "deCODE-proteomics-smp", + "pqtl", + [ + Row( + geneSymbol="GENE1", + proteinId="P12345", + geneId=None, + proteinName="PROTEIN1", + ) + ], + ) + ], + schema=si_schema, + ) + mock_si = MagicMock() + mock_si.df = si_df + + config = deCODEHarmonisationConfig( + min_mac=10, + min_sample_size=30000, + flipping_window_size=10000, + ) + result = deCODESummaryStatistics.from_source( + raw_summary_statistics=raw, + variant_direction=vd_instance, + decode_study_index=mock_si, + config=config, + ) + harm, pqtl_si = result + assert isinstance(harm, SummaryStatistics), ( + "first element should be SummaryStatistics" + ) + assert isinstance(pqtl_si, ProteinQuantitativeTraitLocusStudyIndex), ( + "second element should be ProteinQuantitativeTraitLocusStudyIndex" + ) + assert harm.df.count() == 3 + assert_sumstat_equal(harm.df.collect(), self.expected_harm_rows) + + def test_txtgz_to_parquet(self, tmp_path: Path, session: Session) -> None: + """Test converting txt.gz summary statistics to parquet.""" + input_path = ( + tmp_path / "Proteomics_SMP_PC0_10000_2_GENE1_PROTEIN1_00000001.txt.gz" + ) + output_path = tmp_path / "harmonised_sumstats" + session.spark.createDataFrame(self.expected_harm_rows).toPandas().to_csv( + input_path, sep="\t", compression="gzip" + ) + assert input_path.exists(), "Parquet file should be created" + deCODESummaryStatistics.txtgz_to_parquet( + session, [input_path.as_posix()], output_path.as_posix(), n_threads=1 + ) + + @pytest.mark.parametrize( + "imp_maf,eur_af,expected_eaf", + [ + # eur_af is null → use imp_maf directly + (0.01, None, 0.01), + # |eur_af - imp_maf| <= |eur_af - (1 - imp_maf)| → use imp_maf + (0.01, 0.02, 0.01), + # |eur_af - (1 - imp_maf)| < |eur_af - imp_maf| → use 1 - imp_maf + (0.01, 0.60, 0.99), + ], + ) + def test_infer_allele_frequency( + self, + session: Session, + imp_maf: float, + eur_af: float | None, + expected_eaf: float, + ) -> None: + """_infer_allele_frequency should pick imp_maf or 1-imp_maf based on proximity to EUR_AF.""" + df = session.spark.createDataFrame( + [(imp_maf, eur_af)], "impMAF DOUBLE, EUR_AF DOUBLE" + ) + row = df.select( + deCODESummaryStatistics._infer_allele_frequency( + f.col("impMAF"), f.col("EUR_AF") + ) + ).collect()[0] + assert row.effectAlleleFrequencyFromSource == pytest.approx( + expected_eaf, abs=1e-6 + ) diff --git a/tests/gentropy/step/test_decode_step.py b/tests/gentropy/step/test_decode_step.py new file mode 100644 index 000000000..a28f20bb3 --- /dev/null +++ b/tests/gentropy/step/test_decode_step.py @@ -0,0 +1,264 @@ +"""Test deCODE ingestion steps.""" + +import datetime +from pathlib import Path +from unittest.mock import MagicMock, patch + +import pytest +from pyspark.sql import DataFrame, Row + +from gentropy import Session +from gentropy.decode_ingestion import ( + deCODEManifestGenerationStep, + deCODESummaryStatisticsHarmonisationStep, +) + + +@pytest.fixture +def decode_manifest_df(session: Session) -> DataFrame: + """Manifest example DataFrame fixture.""" + data = [ + Row( + projectId="deCODE-proteomics-raw", + studyId="deCODE-proteomics-raw_Proteomics_PC0_10006_7_RAF1_c_Raf_05314415", + hasSumstats=True, + summarystatsLocation="s3a://some_bucket/some_folder/Proteomics_PC0_10006_7_RAF1_c_Raf_05314415.txt.gz", + size="925.8 MiB", + accessionTimestamp=datetime.datetime(2024, 5, 29, 7, 39, 17), + ), + Row( + projectId="deCODE-proteomics-raw", + studyId="deCODE-proteomics-raw_Proteomics_PC0_10003_15_ZNF41_ZNF41_05242112", + hasSumstats=True, + summarystatsLocation="s3a://some_bucket/some_folder/Proteomics_PC0_10003_15_ZNF41_ZNF41_05242112.txt.gz", + size="926.9 MiB", + accessionTimestamp=datetime.datetime(2024, 5, 29, 7, 39, 21), + ), + ] + return session.spark.createDataFrame(data) + + +@pytest.fixture() +def decode_study_index_df(session: Session) -> DataFrame: + """StudyIndex example mock.""" + data = [ + Row( + studyId="deCODE-proteomics-raw_Proteomics_PC0_10006_7_RAF1_c_Raf_05314415", + projectId="deCODE-proteomics-raw", + studyType="pqtl", + traitFromSource="Proteomics_PC0_10006_7_RAF1_c_Raf", + geneId="ENSG00000132155", + biosampleFromSourceId="UBERON_0001969", + pubmedId="37794188", + publicationTitle="Large-scale plasma proteomics comparisons through genetics and disease associations", + publicationFirstAuthor="Eldjarn GH, Ferkingstad E", + publicationDate="2024", + publicationJournal="Nature", + initialSampleSize="36,136 Icelandic individuals", + nSamples=36136, + cohorts=["deCODE"], + ldPopulationStructure=[Row(ldPopulation="nfe", relativeSampleSize=1.0)], + discoverySamples=[Row(sampleSize=36136, ancestry="Icelandic")], + summarystatsLocation="s3a://some_bucket/some_folder/Proteomics_PC0_10001_7_RAF1_c_Raf_07082019.txt.gz", + hasSumstats=True, + ), + Row( + studyId="deCODE-proteomics-raw_Proteomics_PC0_10003_15_ZNF41_ZNF41_05242112", + projectId="deCODE-proteomics-raw", + studyType="pqtl", + traitFromSource="Proteomics_PC0_10003_15_ZNF41_ZNF41", + geneId="ENSG00000147124", + biosampleFromSourceId="UBERON_0001969", + pubmedId="37794188", + publicationTitle="Large-scale plasma proteomics comparisons through genetics and disease associations", + publicationFirstAuthor="Eldjarn GH, Ferkingstad E", + publicationDate="2024", + publicationJournal="Nature", + initialSampleSize="36,136 Icelandic individuals", + nSamples=36136, + cohorts=["deCODE"], + ldPopulationStructure=[Row(ldPopulation="nfe", relativeSampleSize=1.0)], + discoverySamples=[Row(sampleSize=36136, ancestry="Icelandic")], + summarystatsLocation="s3a://some_bucket/some_folder/Proteomics_PC0_10003_15_ZNF41_ZNF41_07082019.txt.gz", + hasSumstats=True, + ), + ] + return session.spark.createDataFrame(data) + + +@pytest.fixture +def decode_summary_statistics_df(session: Session) -> DataFrame: + """SummaryStatistics example DataFrame fixture.""" + data = [ + Row( + studyId="deCODE-proteomics-raw_Proteomics_PC0_10006_7_RAF1_c_Raf_05314415", + variantId="1_100_A_G", + chromosome="1", + position=100, + beta=0.5, + standardError=0.1, + pValueMantissa=1.5, + pValueExponent=-8, + effectAlleleFrequencyFromSource=0.3, + ), + Row( + studyId="deCODE-proteomics-raw_Proteomics_PC0_10003_15_ZNF41_ZNF41_05242112", + variantId="2_200_C_T", + chromosome="2", + position=200, + beta=-0.3, + standardError=0.15, + pValueMantissa=2.5, + pValueExponent=-7, + effectAlleleFrequencyFromSource=0.45, + ), + ] + return session.spark.createDataFrame(data) + + +class TestdeCODEIngestionStep: + """Test deCODEManifestGenerationStep.""" + + @patch("gentropy.decode_ingestion.deCODEManifest") + def test_decode_manifest_generation_step( + self, + manifest_mock: MagicMock, + session: Session, + tmp_path: Path, + decode_manifest_df: DataFrame, + ) -> None: + """Test deCODEManifestGenerationStep.""" + s3_config_path = (tmp_path / "s3_config.json").as_posix() + bucket_listing_path = (tmp_path / "bucket_listing.txt").as_posix() + output_path = (tmp_path / "manifest_output").as_posix() + + # Mock the manifest instance returned by from_bucket_listing + manifest_instance = MagicMock() + manifest_instance.df = decode_manifest_df + manifest_mock.from_bucket_listing.return_value = manifest_instance + + deCODEManifestGenerationStep( + session=session, + s3_config_path=s3_config_path, + bucket_listing_path=bucket_listing_path, + output_path=output_path, + ) + + manifest_mock.from_bucket_listing.assert_called_once_with( + session=session, + s3_config_path=s3_config_path, + path=bucket_listing_path, + ) + assert Path(output_path).exists() + + +class TestdeCODESummaryStatisticsHarmonisationStep: + """Test deCODESummaryStatisticsHarmonisationStep.""" + + @patch("gentropy.decode_ingestion.SummaryStatisticsQC") + @patch("gentropy.decode_ingestion.deCODEStudyIndex") + @patch("gentropy.decode_ingestion.AptamerMetadata") + @patch("gentropy.decode_ingestion.MolecularComplex") + @patch("gentropy.decode_ingestion.deCODESummaryStatistics") + @patch("gentropy.decode_ingestion.VariantDirection") + @patch("gentropy.decode_ingestion.deCODEManifest") + def test_decode_summary_statistics_harmonisation_step( + self, + manifest_mock: MagicMock, + variant_direction_mock: MagicMock, + summary_statistics_mock: MagicMock, + molecular_complex_mock: MagicMock, + aptamer_metadata_mock: MagicMock, + study_index_mock: MagicMock, + qc_mock: MagicMock, + session: Session, + tmp_path: Path, + decode_summary_statistics_df: DataFrame, + ) -> None: + """Test deCODESummaryStatisticsHarmonisationStep.""" + raw_summary_statistics_path = ( + tmp_path / "raw_summary_statistics.parquet" + ).as_posix() + manifest_path = (tmp_path / "manifest.parquet").as_posix() + aptamer_metadata_path = (tmp_path / "aptamer_metadata.tsv").as_posix() + variant_direction_path = (tmp_path / "variant_direction.parquet").as_posix() + molecular_complex_path = (tmp_path / "molecular_complex.parquet").as_posix() + harmonised_summary_statistics_path = ( + tmp_path / "harmonised_summary_statistics" + ).as_posix() + protein_qtl_study_index_path = (tmp_path / "protein_qtl_study_index").as_posix() + qc_summary_statistics_path = (tmp_path / "qc_summary_statistics").as_posix() + + # Write raw summary statistics parquet (step reads it via spark.read.parquet) + decode_summary_statistics_df.write.mode("overwrite").parquet( + raw_summary_statistics_path + ) + + # Mock deCODEManifest + manifest_instance = MagicMock() + manifest_instance.persist.return_value = manifest_instance + manifest_mock.from_parquet.return_value = manifest_instance + + # Mock MolecularComplex + mc_instance = MagicMock() + mc_instance.persist.return_value = mc_instance + molecular_complex_mock.from_parquet.return_value = mc_instance + + # Mock AptamerMetadata + am_instance = MagicMock() + am_instance.persist.return_value = am_instance + aptamer_metadata_mock.from_source.return_value = am_instance + + # Mock deCODEStudyIndex + si_instance = MagicMock() + si_instance.persist.return_value = si_instance + study_index_mock.from_manifest.return_value = si_instance + + # Mock VariantDirection + vd_instance = MagicMock() + vd_instance.persist.return_value = vd_instance + variant_direction_mock.from_parquet.return_value = vd_instance + + # Mock deCODESummaryStatistics.from_source — returns (hss, pqtl_si) tuple + harmonised_instance = MagicMock() + harmonised_instance.df = decode_summary_statistics_df + harmonised_instance.persist.return_value = harmonised_instance + + pqtl_si_instance = MagicMock() + pqtl_si_instance.persist.return_value = pqtl_si_instance + pqtl_si_instance.annotate_sumstats_qc.return_value.df = ( + decode_summary_statistics_df + ) + summary_statistics_mock.from_source.return_value = ( + harmonised_instance, + pqtl_si_instance, + ) + + # Mock SummaryStatisticsQC + qc_instance = MagicMock() + qc_instance.df = decode_summary_statistics_df + qc_instance.persist.return_value = qc_instance + qc_mock.from_summary_statistics.return_value = qc_instance + + deCODESummaryStatisticsHarmonisationStep( + session=session, + raw_summary_statistics_path=raw_summary_statistics_path, + manifest_path=manifest_path, + aptamer_metadata_path=aptamer_metadata_path, + variant_direction_path=variant_direction_path, + molecular_complex_path=molecular_complex_path, + harmonised_summary_statistics_path=harmonised_summary_statistics_path, + protein_qtl_study_index_path=protein_qtl_study_index_path, + qc_summary_statistics_path=qc_summary_statistics_path, + min_mac_threshold=50, + min_sample_size_threshold=30_000, + flipping_window_size=10_000_000, + ) + + variant_direction_mock.from_parquet.assert_called_once_with( + session, variant_direction_path + ) + summary_statistics_mock.from_source.assert_called_once() + assert Path(harmonised_summary_statistics_path).exists() + assert Path(protein_qtl_study_index_path).exists() + assert Path(qc_summary_statistics_path).exists() diff --git a/uv.lock b/uv.lock index cd0fdd297..9a8a913df 100644 --- a/uv.lock +++ b/uv.lock @@ -1012,6 +1012,7 @@ dependencies = [ { name = "numpy" }, { name = "omegaconf" }, { name = "pandas", extra = ["gcp", "parquet"] }, + { name = "pydantic" }, { name = "pyliftover" }, { name = "pyspark", extra = ["pandas-on-spark"] }, { name = "scikit-learn" }, @@ -1073,6 +1074,7 @@ requires-dist = [ { name = "numpy", specifier = ">=2.3.0" }, { name = "omegaconf", specifier = ">=2.3.0,<2.4.0" }, { name = "pandas", extras = ["gcp", "parquet"], specifier = ">=2.2.3,<2.4.0" }, + { name = "pydantic", specifier = ">=2.12.4" }, { name = "pyliftover", specifier = ">=0.4.1,<0.5.0" }, { name = "pyspark", extras = ["pandas-on-spark"], specifier = ">=3.5.0,<3.6" }, { name = "scikit-learn", specifier = ">=1.6.1,<1.8.0" },