Enhanced pipeline logic to support user-defined sample_name input

.github/workflows/linting.yml

@@ -14,13 +14,12 @@ jobs:
   pre-commit:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4
+      - uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
 
-      - name: Set up Python 3.11
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5
+      - name: Set up Python 3.12
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
         with:
-          python-version: 3.11
-          cache: "pip"
+          python-version: "3.12"
 
       - name: Install pre-commit
         run: pip install pre-commit
@@ -32,14 +31,14 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out pipeline code
-        uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4
+        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
 
       - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v1
+        uses: nf-core/setup-nextflow@v2
 
-      - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5
+      - uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
         with:
-          python-version: "3.11"
+          python-version: "3.12"
           architecture: "x64"
 
       - name: Install dependencies
@@ -60,7 +59,7 @@ jobs:
 
       - name: Upload linting log file artifact
         if: ${{ always() }}
-        uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4
+        uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4
         with:
           name: linting-logs
           path: |

.github/workflows/linting_comment.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Download lint results
-        uses: dawidd6/action-download-artifact@f6b0bace624032e30a85a8fd9c1a7f8f611f5737 # v3
+        uses: dawidd6/action-download-artifact@09f2f74827fd3a8607589e5ad7f9398816f540fe # v3
         with:
           workflow: linting.yml
           workflow_conclusion: completed

assets/samplesheet.csv

@@ -1,4 +1,4 @@
-sample,fastq_1,fastq_2
-SAMPLE1,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R1.fastq.gz,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R2.fastq.gz
-SAMPLE2,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_sample2_R1.fastq.gz,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_sample2_R2.fastq.gz
-SAMPLE3,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R1.fastq.gz,
+sample,sample_name,fastq_1,fastq_2
+SAMPLE1,A1,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R1.fastq.gz,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R2.fastq.gz
+SAMPLE2,B2,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_sample2_R1.fastq.gz,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_sample2_R2.fastq.gz
+SAMPLE3,C3,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R1.fastq.gz,

assets/schema_input.json

@@ -10,10 +10,15 @@
             "sample": {
                 "type": "string",
                 "pattern": "^\\S+$",
-                "meta": ["id"],
+                "meta": ["irida_id"],
                 "unique": true,
                 "errorMessage": "Sample name must be provided and cannot contain spaces"
             },
+            "sample_name": {
+                "type": "string",
+                "meta": ["id"],
+                "errorMessage": "Sample name must be provided"
+            },
             "fastq_1": {
                 "type": "string",
                 "pattern": "^\\S+\\.f(ast)?q(\\.gz)?$",

conf/iridanext.config

@@ -4,6 +4,7 @@ iridanext {
         path = "${params.outdir}/iridanext.output.json.gz"
         overwrite = true
         files {
+            idkey = "irida_id"
             global = [
                 "**/failure/failures_report.csv"
             ]

conf/test.config

@@ -20,6 +20,6 @@ params {
     max_time   = '1.h'
 
     // Input data
-    input  = 'https://raw.githubusercontent.com/phac-nml/speciesabundance/dev/assets/samplesheet.csv'
+    input  = "${projectDir}/assets/samplesheet.csv"
     database = "${projectDir}/tests/data/minidb"
 }

modules/local/topN/main.nf

@@ -38,7 +38,7 @@ process TOP_N {
     ${abundances} \\
     ${args} \\
     -n ${top_n} \\
-    -s ${meta.id} \\
+    -s ${meta.irida_id} \\
     > ${meta.id}_${taxonomic_level}_top_${top_n}.csv
 
     cat <<-END_VERSIONS > versions.yml

tests/data/error_samplesheet.csv

@@ -1,5 +1,5 @@
-sample,fastq_1,fastq_2
-SAMPLE1,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R1.fastq.gz,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_sample2_R2.fastq.gz
-SAMPLE2,https://raw.githubusercontent.com/phac-nml/speciesabundance/dev/tests/data/fastq/test-kraken_R1_001.fastq.gz,https://raw.githubusercontent.com/phac-nml/speciesabundance/dev/tests/data/fastq/test-kraken_R2_001.fastq.gz
-SAMPLE3,https://raw.githubusercontent.com/phac-nml/speciesabundance/dev/tests/data/fastq/test-bracken_R1_001.fastq.gz,https://raw.githubusercontent.com/phac-nml/speciesabundance/dev/tests/data/fastq/test-bracken_R2_001.fastq.gz
-SAMPLE4,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R1.fastq.gz,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R2.fastq.gz
+sample,sample_name,fastq_1,fastq_2
+SAMPLE1,A1,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R1.fastq.gz,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_sample2_R2.fastq.gz
+SAMPLE2,B2,https://raw.githubusercontent.com/phac-nml/speciesabundance/dev/tests/data/fastq/test-kraken_R1_001.fastq.gz,https://raw.githubusercontent.com/phac-nml/speciesabundance/dev/tests/data/fastq/test-kraken_R2_001.fastq.gz
+SAMPLE3,C3,https://raw.githubusercontent.com/phac-nml/speciesabundance/dev/tests/data/fastq/test-bracken_R1_001.fastq.gz,https://raw.githubusercontent.com/phac-nml/speciesabundance/dev/tests/data/fastq/test-bracken_R2_001.fastq.gz
+SAMPLE4,D4,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R1.fastq.gz,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R2.fastq.gz

tests/data/fail_samplesheet.csv

@@ -1,2 +1,2 @@
-sample,fastq_1,fastq_2
-SAMPLE1,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R1.fastq.gz,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_sample2_R2.fastq.gz
+sample,sample_name,fastq_1,fastq_2
+SAMPLE1,A1,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R1.fastq.gz,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_sample2_R2.fastq.gz

tests/data/samplename.test_iridanext.output.json

@@ -0,0 +1,167 @@
+{
+    "files": {
+        "global": [
+            {
+                "path": "failure/failures_report.csv"
+            }
+        ],
+        "samples": {
+            "SAMPLE2": [
+                {
+                    "path": "krona/B2_.krona.html"
+                },
+                {
+                    "path": "adjust/B2__S_bracken_abundances.csv"
+                },
+                {
+                    "path": "fastp/B2_.fastp.html"
+                }
+            ],
+            "SAMPLE3": [
+                {
+                    "path": "krona/B2__SAMPLE3.krona.html"
+                },
+                {
+                    "path": "adjust/B2__SAMPLE3_S_bracken_abundances.csv"
+                },
+                {
+                    "path": "fastp/B2__SAMPLE3.fastp.html"
+                }
+            ],
+            "SAMPLE4": [
+                {
+                    "path": "krona/SAMPLE4.krona.html"
+                },
+                {
+                    "path": "adjust/SAMPLE4_S_bracken_abundances.csv"
+                },
+                {
+                    "path": "fastp/SAMPLE4.fastp.html"
+                }
+            ],
+            "SAMPLE1": [
+                {
+                    "path": "krona/A1__sample1.krona.html"
+                },
+                {
+                    "path": "adjust/A1__sample1_S_bracken_abundances.csv"
+                },
+                {
+                    "path": "fastp/A1__sample1.fastp.html"
+                }
+            ]
+        }
+    },
+    "metadata": {
+        "samples": {
+            "SAMPLE4": {
+                "taxonomy_level": "S",
+                "abundance_1_name": "Bacteroides fragilis",
+                "abundance_1_ncbi_taxonomy_id": "817",
+                "abundance_1_num_assigned_reads": "28877",
+                "abundance_1_fraction_total_reads": "0.577702",
+                "abundance_2_name": "Escherichia coli",
+                "abundance_2_ncbi_taxonomy_id": "562",
+                "abundance_2_num_assigned_reads": "21065",
+                "abundance_2_fraction_total_reads": "0.421418",
+                "abundance_3_name": "",
+                "abundance_3_ncbi_taxonomy_id": "",
+                "abundance_3_num_assigned_reads": "",
+                "abundance_3_fraction_total_reads": "",
+                "abundance_4_name": "",
+                "abundance_4_ncbi_taxonomy_id": "",
+                "abundance_4_num_assigned_reads": "",
+                "abundance_4_fraction_total_reads": "",
+                "abundance_5_name": "",
+                "abundance_5_ncbi_taxonomy_id": "",
+                "abundance_5_num_assigned_reads": "",
+                "abundance_5_fraction_total_reads": "",
+                "unclassified_name": "unclassified",
+                "unclassified_ncbi_taxonomy_id": "0",
+                "unclassified_num_assigned_reads": "44",
+                "unclassified_fraction_total_reads": "0.00088"
+            },
+            "SAMPLE2": {
+                "taxonomy_level": "S",
+                "abundance_1_name": "Escherichia coli",
+                "abundance_1_ncbi_taxonomy_id": "562",
+                "abundance_1_num_assigned_reads": "631",
+                "abundance_1_fraction_total_reads": "0.025253",
+                "abundance_2_name": "Bacteroides fragilis",
+                "abundance_2_ncbi_taxonomy_id": "817",
+                "abundance_2_num_assigned_reads": "22",
+                "abundance_2_fraction_total_reads": "0.00088",
+                "abundance_3_name": "",
+                "abundance_3_ncbi_taxonomy_id": "",
+                "abundance_3_num_assigned_reads": "",
+                "abundance_3_fraction_total_reads": "",
+                "abundance_4_name": "",
+                "abundance_4_ncbi_taxonomy_id": "",
+                "abundance_4_num_assigned_reads": "",
+                "abundance_4_fraction_total_reads": "",
+                "abundance_5_name": "",
+                "abundance_5_ncbi_taxonomy_id": "",
+                "abundance_5_num_assigned_reads": "",
+                "abundance_5_fraction_total_reads": "",
+                "unclassified_name": "unclassified",
+                "unclassified_ncbi_taxonomy_id": "0",
+                "unclassified_num_assigned_reads": "24334",
+                "unclassified_fraction_total_reads": "0.973866"
+            },
+            "SAMPLE3": {
+                "taxonomy_level": "S",
+                "abundance_1_name": "Bacteroides fragilis",
+                "abundance_1_ncbi_taxonomy_id": "817",
+                "abundance_1_num_assigned_reads": "28877",
+                "abundance_1_fraction_total_reads": "0.577702",
+                "abundance_2_name": "Escherichia coli",
+                "abundance_2_ncbi_taxonomy_id": "562",
+                "abundance_2_num_assigned_reads": "21065",
+                "abundance_2_fraction_total_reads": "0.421418",
+                "abundance_3_name": "",
+                "abundance_3_ncbi_taxonomy_id": "",
+                "abundance_3_num_assigned_reads": "",
+                "abundance_3_fraction_total_reads": "",
+                "abundance_4_name": "",
+                "abundance_4_ncbi_taxonomy_id": "",
+                "abundance_4_num_assigned_reads": "",
+                "abundance_4_fraction_total_reads": "",
+                "abundance_5_name": "",
+                "abundance_5_ncbi_taxonomy_id": "",
+                "abundance_5_num_assigned_reads": "",
+                "abundance_5_fraction_total_reads": "",
+                "unclassified_name": "unclassified",
+                "unclassified_ncbi_taxonomy_id": "0",
+                "unclassified_num_assigned_reads": "44",
+                "unclassified_fraction_total_reads": "0.00088"
+            },
+            "SAMPLE1": {
+                "taxonomy_level": "S",
+                "abundance_1_name": "Bacteroides fragilis",
+                "abundance_1_ncbi_taxonomy_id": "817",
+                "abundance_1_num_assigned_reads": "28799",
+                "abundance_1_fraction_total_reads": "0.578328",
+                "abundance_2_name": "Escherichia coli",
+                "abundance_2_ncbi_taxonomy_id": "562",
+                "abundance_2_num_assigned_reads": "20997",
+                "abundance_2_fraction_total_reads": "0.421652",
+                "abundance_3_name": "",
+                "abundance_3_ncbi_taxonomy_id": "",
+                "abundance_3_num_assigned_reads": "",
+                "abundance_3_fraction_total_reads": "",
+                "abundance_4_name": "",
+                "abundance_4_ncbi_taxonomy_id": "",
+                "abundance_4_num_assigned_reads": "",
+                "abundance_4_fraction_total_reads": "",
+                "abundance_5_name": "",
+                "abundance_5_ncbi_taxonomy_id": "",
+                "abundance_5_num_assigned_reads": "",
+                "abundance_5_fraction_total_reads": "",
+                "unclassified_name": "unclassified",
+                "unclassified_ncbi_taxonomy_id": "0",
+                "unclassified_num_assigned_reads": "1",
+                "unclassified_fraction_total_reads": "2e-05"
+            }
+        }
+    }
+}

tests/data/samplename_samplesheet.csv

@@ -0,0 +1,5 @@
+sample,sample_name,fastq_1,fastq_2
+SAMPLE1,A1@ sample1,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R1.fastq.gz,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R2.fastq.gz
+SAMPLE2,B2@,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_sample2_R1.fastq.gz,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_sample2_R2.fastq.gz
+SAMPLE3,B2#,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R1.fastq.gz,
+SAMPLE4,,https://github.com/nf-core/test-datasets/raw/mag/test_data/test_minigut_R1.fastq.gz,