ampliseq samplesheet

.github/workflows/linting.yml

@@ -11,12 +11,12 @@ jobs:
   pre-commit:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5
 
-      - name: Set up Python 3.13
-        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
+      - name: Set up Python 3.14
+        uses: actions/setup-python@e797f83bcb11b83ae66e0230d6156d7c80228e7c # v6
         with:
-          python-version: "3.13"
+          python-version: "3.14"
 
       - name: Install pre-commit
         run: pip install pre-commit
@@ -28,14 +28,14 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out pipeline code
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5
 
       - name: Install Nextflow
         uses: nf-core/setup-nextflow@v2
 
-      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
+      - uses: actions/setup-python@e797f83bcb11b83ae66e0230d6156d7c80228e7c # v6
         with:
-          python-version: "3.13"
+          python-version: "3.14"
           architecture: "x64"
 
       - name: read .nf-core.yml

.github/workflows/linting_comment.yml

@@ -21,7 +21,7 @@ jobs:
         run: echo "pr_number=$(cat linting-logs/PR_number.txt)" >> $GITHUB_OUTPUT
 
       - name: Post PR comment
-        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728 # v2
+        uses: marocchino/sticky-pull-request-comment@773744901bac0e8cbb5a0dc842800d45e9b2b405 # v2
         with:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           number: ${{ steps.pr_number.outputs.pr_number }}

.prettierignore

@@ -10,4 +10,5 @@ testing/
 testing*
 *.pyc
 bin/
+.nf-test/
 ro-crate-metadata.json

modules/local/aspera_cli/environment.yml

@@ -0,0 +1,7 @@
+name: aspera_cli
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - bioconda::aspera-cli=4.14.0

modules/local/sra_to_samplesheet/main.nf

@@ -44,6 +44,8 @@ process SRA_TO_SAMPLESHEET {
             pipeline_map << [ replicate: 1 ]
         } else if (pipeline == 'taxprofiler') {
             pipeline_map << [ fasta: '' ]
+        } else if (pipeline == 'ampliseq'){
+            pipeline_map << [ run: '']
         }
     }
     pipeline_map << meta_clone

nextflow_schema.json

@@ -38,7 +38,7 @@
                     "type": "string",
                     "fa_icon": "fab fa-apple",
                     "description": "Name of supported nf-core pipeline e.g. 'rnaseq'. A samplesheet for direct use with the pipeline will be created with the appropriate columns.",
-                    "enum": ["rnaseq", "atacseq", "viralrecon", "taxprofiler"]
+                    "enum": ["rnaseq", "atacseq", "viralrecon", "taxprofiler", "ampliseq"]
                 },
                 "nf_core_rnaseq_strandedness": {
                     "type": "string",

workflows/sra/tests/main.nf.test

@@ -15,9 +15,6 @@ nextflow_workflow {
     test("Parameters: default") {
 
         when {
-            params {
-                outdir = "$outputDir"
-            }
             workflow {
                 """
                 input[0] = Channel.from("DRX026011", "ERX1234253", "SRX6725035")
@@ -26,15 +23,29 @@ nextflow_workflow {
         }
 
         then {
+            assert workflow.success
+
             assertAll(
-                { assert workflow.success},
-                { assert snapshot(
-                    file(workflow.out.samplesheet[0]).name,
-                    workflow.out.mappings,
-                    workflow.out.sample_mappings,
-                    workflow.out.sra_metadata,
-                    workflow.out.versions
-                ).match() }
+                {
+                    with(workflow.out.samplesheet) {
+                        assert path(get(0)).readLines().size() == 4
+                        assert path(get(0)).readLines()*.split(',')[0].take(4) == ['"sample"', '"fastq_1"', '"fastq_2"', '"run_accession"']
+                        assert path(get(0)).readLines()*.split(',').collect { it[0] } == ['"sample"', '"DRX026011"', '"ERX1234253"', '"SRX6725035"']
+                        assert path(get(0)).text.contains('Illumina HiSeq 2500')
+                    }
+                },
+                {
+                    with(workflow.out.mappings) {
+                        assert path(get(0)).readLines().size() == 4
+                        assert path(get(0)).readLines()*.split(',').collect { it[0] } == ['"sample"', '"DRX026011"', '"ERX1234253"', '"SRX6725035"']
+                        assert path(get(0)).text.contains('Illumina HiSeq 2500')
+                    }
+                },
+                {
+                    with(workflow.out.sample_mappings) {
+                        assert path(get(0)[0]).md5 == "1ac06bb95b503703430e74660bbdd768"
+                    }
+                }
             )
         }
     }

workflows/sra/tests/sra_nf_core_pipeline_ampliseq.nf.test

@@ -0,0 +1,42 @@
+nextflow_workflow {
+
+    name "Test workflow: sra/main.nf"
+    script "../main.nf"
+    workflow "SRA"
+    tag "SRA_NF_CORE_PIPELINE_AMPLISEQ"
+
+    // Dependencies
+    tag "SRA_IDS_TO_RUNINFO"
+    tag "SRA_RUNINFO_TO_FTP"
+    tag "SRA_FASTQ_FTP"
+    tag "SRA_TO_SAMPLESHEET"
+    tag "MULTIQC_MAPPINGS_CONFIG"
+
+    test("Parameters: --nf_core_pipeline ampliseq") {
+
+        when {
+            params {
+                outdir = "$outputDir"
+                nf_core_pipeline = "ampliseq"
+            }
+            workflow {
+                """
+                input[0] = Channel.from("DRX026011", "ERX1234253", "SRX6725035")
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success},
+                { assert snapshot(
+                    file(workflow.out.samplesheet[0]).name,
+                    workflow.out.mappings,
+                    workflow.out.sample_mappings,
+                    workflow.out.sra_metadata,
+                    workflow.out.versions
+                ).match() }
+            )
+        }
+    }
+}

workflows/sra/tests/sra_nf_core_pipeline_ampliseq.nf.test.snap

@@ -0,0 +1,143 @@
+{
+    "Parameters: --nf_core_pipeline ampliseq": {
+        "content": [
+            "samplesheet.csv",
+            [
+                "id_mappings.csv:md5,3e41ce6ab19feb76f2b20fa77a910ad3"
+            ],
+            [
+                "multiqc_config.yml:md5,1ac06bb95b503703430e74660bbdd768"
+            ],
+            [
+                {
+                    "base_count": "194930",
+                    "experiment_accession": "DRX026011",
+                    "experiment_alias": "DRX026011",
+                    "experiment_title": "Illumina HiSeq 2500 paired end sequencing: Illumina HiSeq 2500 paired end sequencing of SAMD00024405",
+                    "fastq_1": "DRX026011_DRR028935_1.fastq.gz:md5,f9b4a5d25aa7d6ab4050dbe0764eb04d",
+                    "fastq_2": "DRX026011_DRR028935_2.fastq.gz:md5,dc0d2e1fc46f4d4581a477f87ec3ff15",
+                    "fastq_aspera": "fasp.sra.ebi.ac.uk:/vol1/fastq/DRR028/DRR028935/DRR028935_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/DRR028/DRR028935/DRR028935_2.fastq.gz",
+                    "fastq_bytes": "60275;61610",
+                    "fastq_ftp": "ftp.sra.ebi.ac.uk/vol1/fastq/DRR028/DRR028935/DRR028935_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/DRR028/DRR028935/DRR028935_2.fastq.gz",
+                    "fastq_galaxy": "ftp.sra.ebi.ac.uk/vol1/fastq/DRR028/DRR028935/DRR028935_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/DRR028/DRR028935/DRR028935_2.fastq.gz",
+                    "fastq_md5": "cc01df82a9354bb6b3be93483b20c35a;941c9998d746416dad53c94c480ddf30",
+                    "id": "DRX026011_DRR028935",
+                    "instrument_model": "Illumina HiSeq 2500",
+                    "instrument_platform": "ILLUMINA",
+                    "library_layout": "PAIRED",
+                    "library_name": "day0_BbSQE-I",
+                    "library_selection": "cDNA",
+                    "library_source": "TRANSCRIPTOMIC",
+                    "library_strategy": "RNA-Seq",
+                    "md5_1": "cc01df82a9354bb6b3be93483b20c35a",
+                    "md5_2": "941c9998d746416dad53c94c480ddf30",
+                    "read_count": "965",
+                    "run_accession": "DRR028935",
+                    "run_alias": "DRR028935",
+                    "sample_accession": "SAMD00024405",
+                    "sample_alias": "SAMD00024405",
+                    "sample_description": "Liquid culture",
+                    "sample_title": "Botryococcus braunii Showa at day 0 after inoculation into fresh culture medium",
+                    "scientific_name": "Botryococcus braunii Showa",
+                    "secondary_sample_accession": "DRS019431",
+                    "secondary_study_accession": "DRP002616",
+                    "single_end": false,
+                    "study_accession": "PRJDB3420",
+                    "study_alias": "DRP002616",
+                    "study_title": "Liquid culture of Botryococcus braunii, race B, Showa",
+                    "submission_accession": "DRA002949",
+                    "tax_id": "1202541"
+                },
+                {
+                    "base_count": "1996273",
+                    "experiment_accession": "SRX6725035",
+                    "experiment_alias": "Emb289P1_bin131",
+                    "experiment_title": "Illumina HiSeq 2500 sequencing: Binning of metagenomic reads from the P1 gut compartment of Embiratermes neotenicus",
+                    "fastq_1": "SRX6725035_SRR9984183.fastq.gz:md5,c9b4c2c4abf19da7082caf442fdefea7",
+                    "fastq_2": "",
+                    "fastq_aspera": "fasp.sra.ebi.ac.uk:/vol1/fastq/SRR998/003/SRR9984183/SRR9984183.fastq.gz",
+                    "fastq_bytes": "605358",
+                    "fastq_ftp": "ftp.sra.ebi.ac.uk/vol1/fastq/SRR998/003/SRR9984183/SRR9984183.fastq.gz",
+                    "fastq_galaxy": "ftp.sra.ebi.ac.uk/vol1/fastq/SRR998/003/SRR9984183/SRR9984183.fastq.gz",
+                    "fastq_md5": "0b512d2dc31685983456bd56fd836544",
+                    "id": "SRX6725035_SRR9984183",
+                    "instrument_model": "Illumina HiSeq 2500",
+                    "instrument_platform": "ILLUMINA",
+                    "library_layout": "SINGLE",
+                    "library_name": "Emb289P1_bin131",
+                    "library_selection": "RANDOM",
+                    "library_source": "METAGENOMIC",
+                    "library_strategy": "WGS",
+                    "md5_1": "0b512d2dc31685983456bd56fd836544",
+                    "md5_2": "",
+                    "read_count": "58",
+                    "run_accession": "SRR9984183",
+                    "run_alias": "Emb289P1_bin131.fastq",
+                    "sample_accession": "SAMN12581720",
+                    "sample_alias": "Emb289P1_bin131",
+                    "sample_description": "Keywords: GSC:MIxS MIMAG:5.0",
+                    "sample_title": "MIMAG Metagenome-assembled Genome sample from Defluviitaleaceae bacterium",
+                    "scientific_name": "Defluviitaleaceae bacterium",
+                    "secondary_sample_accession": "SRS5277011",
+                    "secondary_study_accession": "SRP218535",
+                    "single_end": true,
+                    "study_accession": "PRJNA560329",
+                    "study_alias": "PRJNA560329",
+                    "study_title": "Phylogenomic analysis of 589 metagenome-assembled genomes encompassing all major prokaryotic lineages from the gut of higher termites",
+                    "submission_accession": "SRA942061",
+                    "tax_id": "2660712"
+                },
+                {
+                    "base_count": "35658",
+                    "experiment_accession": "ERX1234253",
+                    "experiment_alias": "qiita_ptid_1263:10317.BLANK.93.3E.r22",
+                    "experiment_title": "Illumina HiSeq 2500 sequencing: qiita_ptid_1263:10317.BLANK.93.3E.r22",
+                    "fastq_1": "ERX1234253_ERR1160846.fastq.gz:md5,b1de59f829fbd2d60a1ed4bc3da55709",
+                    "fastq_2": "",
+                    "fastq_aspera": "fasp.sra.ebi.ac.uk:/vol1/fastq/ERR116/006/ERR1160846/ERR1160846.fastq.gz",
+                    "fastq_bytes": "18077",
+                    "fastq_ftp": "ftp.sra.ebi.ac.uk/vol1/fastq/ERR116/006/ERR1160846/ERR1160846.fastq.gz",
+                    "fastq_galaxy": "ftp.sra.ebi.ac.uk/vol1/fastq/ERR116/006/ERR1160846/ERR1160846.fastq.gz",
+                    "fastq_md5": "5924f20ef547ebdfed7cad795bbab6e6",
+                    "id": "ERX1234253_ERR1160846",
+                    "instrument_model": "Illumina HiSeq 2500",
+                    "instrument_platform": "ILLUMINA",
+                    "library_layout": "SINGLE",
+                    "library_name": "10317.BLANK.93.3E.r22",
+                    "library_selection": "PCR",
+                    "library_source": "METAGENOMIC",
+                    "library_strategy": "AMPLICON",
+                    "md5_1": "5924f20ef547ebdfed7cad795bbab6e6",
+                    "md5_2": "",
+                    "read_count": "283",
+                    "run_accession": "ERR1160846",
+                    "run_alias": "qiita_ppdid_706:10317.BLANK.93.3E.r22",
+                    "sample_accession": "SAMEA3687214",
+                    "sample_alias": "qiita_sid_10317:10317.BLANK.93.3E.r22",
+                    "sample_description": "American Gut control",
+                    "sample_title": "10317.BLANK.93.3E.r22",
+                    "scientific_name": "metagenome",
+                    "secondary_sample_accession": "ERS994363",
+                    "secondary_study_accession": "ERP012803",
+                    "single_end": true,
+                    "study_accession": "PRJEB11419",
+                    "study_alias": "qiita_sid_10317",
+                    "study_title": "American Gut Project",
+                    "submission_accession": "ERA541392",
+                    "tax_id": "256318"
+                }
+            ],
+            [
+                "versions.yml:md5,1496d1cbc9041e07ab8a0c25f0b054d9",
+                "versions.yml:md5,9b17045ca8bdc272cb3f9d349a81d206",
+                "versions.yml:md5,b52279f7d6b891a6523d9321f3f85b47",
+                "versions.yml:md5,c19fc0f920e57875881761cc944a46d7"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "25.10.0"
+        },
+        "timestamp": "2025-10-28T15:50:25.540511"
+    }
+}