Merge pull request #42 from multimeric/2025-06-regen

2025-06 Regenerate Code

Author: multimeric

CHANGELOG.md

@@ -1,6 +1,12 @@
 
 ## Changelog
 
+### Master (unreleased)
+
+#### Changed
+
+* Regenerated the generated code. For the detailed changes please refer to the [git diff](https://github.com/multimeric/Unipressed/commit/6ff916761afe9801f75b28d6bd21ec141109ea62).
+
 ### 1.4.0
 
 #### Added

unipressed/dataset/generated_types/arba.py

@@ -14,33 +14,25 @@ class ArbaQueryDict(TypedDict):
     not_: NotRequired[Iterable["ArbaQuery"]]
     "Negate a filter"
     protein_name: NotRequired[str]
-    "Protein Name [DE]\ne.g. mas5"
-    organism: NotRequired[str]
-    "Organism [OS]\ne.g. saccharomyces"
+    "Protein Name [DE]\ne.g. Elastin"
     taxonomy: NotRequired[str]
     "Taxonomy [OC]\ne.g. human"
     ec: NotRequired[str]
-    "Enzyme classification [EC]\ne.g. 1.1.2.3"
+    "Enzyme classification [EC]\ne.g. 2.3.2.5"
     cc_cofactor: NotRequired[str]
     "Cofactor\ne.g. 29105"
     cc_catalytic_activity: NotRequired[str]
     "Catalytic activity\ne.g. tyrosine"
-    cc_activity_regulation: NotRequired[str]
-    "Activity regulation\ne.g. inhibited"
     cc_pathway: NotRequired[str]
     "Pathway\ne.g. metabolism"
     cc_subcellular_location: NotRequired[str]
-    "Subcellular location term\ne.g. membrane"
-    cc_subcellular_location_note: NotRequired[str]
-    "Note\ne.g. membrane"
-    cc_domain: NotRequired[str]
-    "Domain comments [CC]\ne.g. conformation"
+    "Subcellular location [CC]\ne.g. membrane"
     family: NotRequired[str]
     "Protein family\ne.g. pa28"
     cc_similarity: NotRequired[str]
     "Comment similarity\ne.g. phosphatase"
     keyword: NotRequired[str]
-    "Keyword [KW]\ne.g. chromosomal"
+    "Keyword [KW]\ne.g. Tight junction"
 
 
 ArbaQuery: TypeAlias = Union[ArbaQueryDict, str]

unipressed/dataset/generated_types/citations.py

@@ -14,17 +14,17 @@ class CitationsQueryDict(TypedDict):
     not_: NotRequired[Iterable["CitationsQuery"]]
     "Negate a filter"
     title: NotRequired[str]
-    "Title\ne.g. sample title"
+    "Title\ne.g. VEGF is required for growth and survival in neonatal mice."
     author: NotRequired[str]
-    "Author\ne.g. sample author name"
+    "Author\ne.g. Smith"
     journal: NotRequired[str]
-    "Journal\ne.g. sample journal"
+    "Journal\ne.g. Biochemistry"
     published: NotRequired[str]
-    "Year published\ne.g. sample"
+    "Year published\ne.g. 2024"
     id: NotRequired[str]
     "Citation Id\ne.g. 15772651"
     doi: NotRequired[str]
-    "DOI\ne.g. 10.1007/s11882-009-0055-9"
+    "DOI\ne.g. 10.1016/j.burns.2017.03.013"
 
 
 CitationsQuery: TypeAlias = Union[CitationsQueryDict, str]

unipressed/dataset/generated_types/diseases.py

@@ -16,7 +16,7 @@ class DiseasesQueryDict(TypedDict):
     name: NotRequired[str]
     "Name\ne.g. alzheimer disease"
     id: NotRequired[str]
-    "Disease [AC]\ne.g. DI-12345"
+    "Disease [AC]\ne.g. DI-00086"
 
 
 DiseasesQuery: TypeAlias = Union[DiseasesQueryDict, str]

unipressed/dataset/generated_types/proteomes.py

@@ -31,7 +31,7 @@ class ProteomesQueryDict(TypedDict):
     genome_accession: NotRequired[str]
     "Genome Accession\ne.g. CM000663"
     genome_assembly: NotRequired[str]
-    "Genome Assembly\ne.g. GCA_000001405.27"
+    "Genome Assembly\ne.g. GCA_000005845.2"
     cpd: NotRequired[Cpd]
     "CPD (Complete Proteome Detector)\ne.g. 1\n* 1: Standard\n* 2: Close to standard (high value)\n* 3: Close to standard (low value)\n* 4: Outlier (high value)\n* 5: Outlier (low value)\n* 6: Unknown"
     busco: NotRequired[
@@ -46,7 +46,7 @@ class ProteomesQueryDict(TypedDict):
             ],
         ]
     ]
-    "BUSCO (Complete %)\ne.g. 97"
+    "BUSCO (Complete %)\ne.g. [97-100]"
 
 
 ProteomesQuery: TypeAlias = Union[ProteomesQueryDict, str]

unipressed/dataset/generated_types/taxonomy.py

@@ -52,15 +52,15 @@ class TaxonomyQueryDict(TypedDict):
     scientific: NotRequired[str]
     "Scientific name\ne.g. 16SrII"
     common: NotRequired[str]
-    "Common name\ne.g. sample name"
+    "Common name\ne.g. mouse"
     mnemonic: NotRequired[str]
-    "Mnemonic\ne.g. sample mnemonic"
+    "Mnemonic\ne.g. 9BACT"
     rank: NotRequired[Rank]
     "Rank\ne.g. SPECIES_GROUP\n* SUPERKINGDOM: Superkingdom\n* KINGDOM: Kingdom\n* SUBKINGDOM: Subkingdom\n* SUPERPHYLUM: Superphylum\n* PHYLUM: Phylum\n* SUBPHYLUM: Subphylum\n* SUPERCLASS: Superclass\n* CLASS: Class\n* SUBCLASS: Subclass\n* INFRACLASS: Infraclass\n* COHORT: Cohort\n* SUBCOHORT: Subcohort\n* SUPERORDER: Superorder\n* ORDER: Order\n* SUBORDER: Suborder\n* INFRAORDER: Infraorder\n* PARVORDER: Parvorder\n* SUPERFAMILY: Superfamily\n* FAMILY: Family\n* SUBFAMILY: Subfamily\n* TRIBE: Tribe\n* SUBTRIBE: Subtribe\n* GENUS: Genus\n* SUBGENUS: Subgenus\n* SPECIES_GROUP: Species group\n* SPECIES_SUBGROUP: Species subgroup\n* SPECIES: Species\n* SUBSPECIES: Subspecies\n* VARIETAS: Varietas\n* FORMA: Forma\n* NO_RANK: No rank"
     strain: NotRequired[str]
-    "Strain\ne.g. SPECIES_GROUP"
+    "Strain\ne.g. UA858"
     host: NotRequired[int]
-    "Virus host\ne.g. 85621"
+    "Virus host\ne.g. 9606"
     linked: NotRequired[bool]
     "With external info\ne.g. true"
     parent: NotRequired[str]

unipressed/dataset/generated_types/uniparc.py

@@ -92,17 +92,19 @@ class UniparcQueryDict(TypedDict):
     uniprotkb: NotRequired[str]
     "UniProtKB AC\ne.g. P12345"
     isoform: NotRequired[str]
-    "UniProtKB isoform ID\ne.g. P12345"
-    upid: NotRequired[str]
-    "Proteome ID\ne.g. UP123456789"
+    "UniProtKB isoform ID\ne.g. O60260-2"
+    proteome: NotRequired[str]
+    "Proteome ID\ne.g. UP000005640"
+    organism_id: NotRequired[int]
+    "Organism\ne.g. 10254"
     taxonomy_name: NotRequired[str]
-    "Taxonomy [OC]\ne.g. Human"
+    "Taxonomy [OC]\ne.g. Mammalia"
     taxonomy_id: NotRequired[str]
     "Taxonomy id"
     gene: NotRequired[str]
     "Gene name [GN]\ne.g. PROZ"
-    protein: NotRequired[str]
-    "Protein name\ne.g. Protein Z"
+    protein_name: NotRequired[str]
+    "Protein name\ne.g. Elastin"
     database: NotRequired[Database]
     "Database\ne.g. Gene3D\n* EnsemblBacteria: EnsemblBacteria\n* EnsemblFungi: EnsemblFungi\n* EnsemblMetazoa: EnsemblMetazoa\n* EnsemblPlants: EnsemblPlants\n* EnsemblProtists: EnsemblProtists\n* embl-cds: EMBL CDS\n* EMBL_CON: EMBL_CON\n* EMBL_TPA: EMBL_TPA\n* EMBL_TSA: EMBL_TSA\n* EMBLWGS: EMBLWGS\n* Ensembl: Ensembl\n* EnsemblRapid: EnsemblRapid\n* EPO: EPO\n* FlyBase: FlyBase\n* FusionGDB: FusionGDB\n* H-InvDB: H-InvDB\n* IPI: IPI\n* JPO: JPO\n* KIPO: KIPO\n* PATRIC: PATRIC\n* PDB: PDB\n* PIR: PIR\n* PIRARC: PIRARC\n* PRF: PRF\n* RefSeq: RefSeq\n* REMTREMBL: REMTREMBL\n* SEED: SEED\n* SGD: SGD\n* UniProt: UniProtKB\n* isoforms: UniProtKB/Swiss-Prot isoforms\n* TAIR: TAIR\n* TREMBLNEW: TREMBLNEW\n* TREMBL_VARSPLIC: TREMBL_VARSPLIC\n* TROME: TROME\n* UNIMES: UNIMES\n* USPTO: USPTO\n* VectorBase: VectorBase\n* VEGA: VEGA\n* WBParaSite: WBParaSite\n* WormBase: WormBase"
     active: NotRequired[Active]
@@ -121,20 +123,25 @@ class UniparcQueryDict(TypedDict):
             ],
         ]
     ]
-    "Sequence length\ne.g. [100 TO 300]"
+    "Sequence length\ne.g. [50 TO 100]"
     dbid: NotRequired[str]
     "Database ID\ne.g. AAC02967"
     feature_id: NotRequired[str]
     "Feature ID\ne.g. IPR004251"
     proteomecomponent: NotRequired[str]
     "Proteome Component\ne.g. chromosome"
-    organism_id: NotRequired[int]
-    "Organism ID\ne.g. 10254"
 
 
 UniparcQuery: TypeAlias = Union[UniparcQueryDict, str]
 UniparcNamesTaxonomy: TypeAlias = Literal[
-    "upi", "gene", "organism_id", "organism", "protein", "proteome"
+    "upi",
+    "gene",
+    "organism_id",
+    "organism",
+    "protein",
+    "proteome",
+    "common_taxons",
+    "common_taxon_ids",
 ]
 UniparcSequences: TypeAlias = Literal["checksum", "length", "sequence"]
 UniparcMiscellaneous: TypeAlias = Literal["accession",]
@@ -152,6 +159,7 @@ class UniparcQueryDict(TypedDict):
     "SMART",
     "SUPFAM",
     "NCBIfam",
+    "FunFam",
 ]
 UniparcFields: TypeAlias = Literal[
     UniparcNamesTaxonomy,

unipressed/dataset/generated_types/uniprotkb.py

@@ -31,16 +31,18 @@ class UniprotkbQueryDict(TypedDict):
     "UniProtKB AC\ne.g. P12345"
     id: NotRequired[str]
     "Entry Name [ID]\ne.g. P53_HUMAN"
+    sec_acc: NotRequired[str]
+    "Secondary Accession\ne.g. B2R5V1"
     protein_name: NotRequired[str]
-    "Protein Name [DE]\ne.g. mas5"
+    "Protein Name [DE]\ne.g. Elastin"
     gene: NotRequired[str]
-    "Gene Name [GN]\ne.g. ydj1"
+    "Gene Name [GN]\ne.g. YDJ1"
     organism_name: NotRequired[str]
     "Organism [OS]\ne.g. saccharomyces"
     organism_id: NotRequired[str]
     "Organism id"
     taxonomy_name: NotRequired[str]
-    "Taxonomy [OC]\ne.g. human"
+    "Taxonomy [OC]\ne.g. mammalia"
     taxonomy_id: NotRequired[str]
     "Taxonomy id"
     virus_host_name: NotRequired[str]
@@ -136,17 +138,17 @@ class UniprotkbQueryDict(TypedDict):
     cc_scl_note_exp: NotRequired[str]
     "Cc scl note exp\ne.g. membrane"
     ft_transmem: NotRequired[str]
-    "Ft transmem\ne.g. forming"
+    "Ft transmem\ne.g. helical"
     ft_transmem_exp: NotRequired[str]
-    "Ft transmem exp\ne.g. forming"
+    "Ft transmem exp\ne.g. helical"
     ft_topo_dom: NotRequired[str]
-    "Ft topo dom\ne.g. forming"
+    "Ft topo dom\ne.g. cytoplasmic"
     ft_topo_dom_exp: NotRequired[str]
-    "Ft topo dom exp\ne.g. forming"
+    "Ft topo dom exp\ne.g. cytoplasmic"
     ft_intramem: NotRequired[str]
-    "Ft intramem\ne.g. forming"
+    "Ft intramem\ne.g. helical"
     ft_intramem_exp: NotRequired[str]
-    "Ft intramem exp\ne.g. forming"
+    "Ft intramem exp\ne.g. helical"
     cc_disease: NotRequired[str]
     "Cc disease\ne.g. nephrotic"
     cc_disease_exp: NotRequired[str]
@@ -188,9 +190,9 @@ class UniprotkbQueryDict(TypedDict):
     ft_lipid_exp: NotRequired[str]
     "Ft lipid exp\ne.g. cysteine"
     ft_carbohyd: NotRequired[str]
-    "Ft carbohyd\ne.g. cysteine"
+    "Ft carbohyd\ne.g. GlcNAc"
     ft_carbohyd_exp: NotRequired[str]
-    "Ft carbohyd exp\ne.g. cysteine"
+    "Ft carbohyd exp\ne.g. GlcNAc"
     ft_disulfid: NotRequired[str]
     "Ft disulfid\ne.g. reversible"
     ft_disulfid_exp: NotRequired[str]
@@ -275,7 +277,7 @@ class UniprotkbQueryDict(TypedDict):
             ],
         ]
     ]
-    "Mass(Da)\ne.g. [441126 TO 441126]"
+    "Mass(Da)\ne.g. [10000 TO 11000]"
     length: NotRequired[
         tuple[
             Union[
@@ -318,7 +320,7 @@ class UniprotkbQueryDict(TypedDict):
     cc_sc_einit: NotRequired[str]
     "Erroneous initiation\ne.g. extended"
     cc_sc_eterm: NotRequired[str]
-    "Erroneous termination\ne.g. translated"
+    "Erroneous termination\ne.g. truncated"
     cc_sc_epred: NotRequired[str]
     "Erroneous gene model prediction\ne.g. *"
     cc_sc_etran: NotRequired[str]
@@ -447,7 +449,7 @@ class UniprotkbQueryDict(TypedDict):
             ],
         ]
     ]
-    "Date Of Creation\ne.g. [2018-03-04 TO 2018-03-08]"
+    "Date Of Creation\ne.g. [2023-05-13 TO 2024-05-13]"
     date_modified: NotRequired[
         tuple[
             Union[
@@ -460,7 +462,7 @@ class UniprotkbQueryDict(TypedDict):
             ],
         ]
     ]
-    "Date of last entry modification\ne.g. [2018-03-04 TO 2018-03-08]"
+    "Date of last entry modification\ne.g. [2023-05-13 TO 2024-05-13]"
     date_sequence_modified: NotRequired[
         tuple[
             Union[
@@ -473,7 +475,7 @@ class UniprotkbQueryDict(TypedDict):
             ],
         ]
     ]
-    "Date of last sequence modification\ne.g. [2018-03-04 TO 2018-03-08]"
+    "Date of last sequence modification\ne.g. [2023-05-13 TO 2024-05-13]"
     go: NotRequired[str]
     "Go\ne.g. 0009986"
     go_manual: NotRequired[str]
@@ -523,11 +525,11 @@ class UniprotkbQueryDict(TypedDict):
     go_iea: NotRequired[str]
     "go, inferred from electronic annotation [iea]"
     chebi: NotRequired[str]
-    "CHEBI ID\ne.g. 29105"
+    "Name or ID (CHEBI)\ne.g. Search by Name or ID (CHEBI)"
     inchikey: NotRequired[str]
     "InChIKey\ne.g. XLYOFNOQVPJJNP-UHFFFAOYSA-N"
     keyword: NotRequired[str]
-    "Keyword [KW]\ne.g. chromosomal"
+    "Keyword [KW]\ne.g. activator"
     lit_author: NotRequired[str]
     "Author\ne.g. smith"
     lit_journal: NotRequired[str]
@@ -548,19 +550,19 @@ class UniprotkbQueryDict(TypedDict):
     lit_pubmed: NotRequired[str]
     "PubMed ID\ne.g. 15165820"
     lit_title: NotRequired[str]
-    "Title\ne.g. protein"
+    "Title\ne.g. apoptosis"
     lit_citation_id: NotRequired[str]
     "Citation ID\ne.g. CI-6EPRJ6MFFS5LC"
     computational_pubmed_id: NotRequired[str]
-    "Computational PubMed ID\ne.g. 15165820"
+    "Computational PubMed ID\ne.g. 1697263"
     community_pubmed_id: NotRequired[str]
-    "Community PubMed ID\ne.g. 15165820"
+    "Community PubMed ID\ne.g. 30699149"
     proteome: NotRequired[str]
     "Proteome ID\ne.g. UP000005640"
     proteomecomponent: NotRequired[str]
     "Proteome Component\ne.g. chromosome"
     scope: NotRequired[str]
-    "Cited for\ne.g. microtubule"
+    "Cited for\ne.g. function"
     reviewed: NotRequired[bool]
     "Reviewed\ne.g. true"
     active: NotRequired[bool]
@@ -753,9 +755,7 @@ class UniprotkbQueryDict(TypedDict):
 UniprotkbPolymorphismAndMutation: TypeAlias = Literal[
     "xref_alzforum", "xref_biomuta", "xref_dmdm", "xref_dbsnp"
 ]
-UniprotkbTwodGel: TypeAlias = Literal[
-    "xref_compluyeast-2dpage", "xref_ogp", "xref_reproduction-2dpage"
-]
+UniprotkbTwodGel: TypeAlias = Literal["xref_ogp", "xref_reproduction-2dpage"]
 UniprotkbProteomic: TypeAlias = Literal[
     "xref_cptac",
     "xref_massive",
@@ -769,7 +769,7 @@ class UniprotkbQueryDict(TypedDict):
     "xref_jpost",
 ]
 UniprotkbProtocolsAndMaterials: TypeAlias = Literal[
-    "xref_abcd", "xref_antibodypedia", "xref_cptc", "xref_dnasu"
+    "xref_abcd", "xref_antibodypedia", "xref_cptc", "xref_dnasu", "xref_ycharos"
 ]
 UniprotkbGenomeAnnotation: TypeAlias = Literal[
     "xref_ensembl",
@@ -846,11 +846,13 @@ class UniprotkbQueryDict(TypedDict):
     "xref_reactome",
     "xref_sabio-rk",
     "xref_signor",
+    "xref_strenda-db",
     "xref_signalink",
     "xref_unipathway",
 ]
 UniprotkbOther: TypeAlias = Literal[
     "xref_biogrid-orcs",
+    "xref_cd-code",
     "xref_chitars",
     "xref_evolutionarytrace",
     "xref_genewiki",
@@ -868,8 +870,10 @@ class UniprotkbQueryDict(TypedDict):
     "xref_bgee", "xref_cleanex", "xref_collectf", "xref_expressionatlas"
 ]
 UniprotkbFamilyAndDomain: TypeAlias = Literal[
+    "xref_antifam",
     "xref_cdd",
     "xref_disprot",
+    "xref_funfam",
     "xref_gene3d",
     "xref_hamap",
     "xref_ideal",