gatk4/selectvariants: Update documentation and module improvements #7907

modules/nf-core/gatk4/selectvariants/environment.yml

@@ -4,6 +4,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  # renovate: datasource=conda depName=bioconda/gatk4
-  - bioconda::gatk4=4.6.1.0
-  - bioconda::gcnvkernel=0.9
+  - "bioconda::gatk4=4.6.1.0"

modules/nf-core/gatk4/selectvariants/main.nf

@@ -2,57 +2,62 @@ process GATK4_SELECTVARIANTS {
     tag "$meta.id"
     label 'process_single'
 
+
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/b2/b28daf5d9bb2f0d129dcad1b7410e0dd8a9b087aaf3ec7ced929b1f57624ad98/data':
-        'community.wave.seqera.io/library/gatk4_gcnvkernel:e48d414933d188cd' }"
+        'https://depot.galaxyproject.org/singularity/gatk4:4.6.1.0--py310hdfd78af_0':
+        'biocontainers/gatk4:4.6.1.0--py310hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(vcf), path(vcf_idx), path (intervals)
+    tuple val(meta), path(vcf), path(vcf_index)
+    path fasta
+    path fasta_fai
+    path dict
+    val intervals
 
     output:
     tuple val(meta), path("*.vcf.gz")       , emit: vcf
     tuple val(meta), path("*.vcf.gz.tbi")   , emit: tbi
-    path "versions.yml"		                , emit: versions
+    path "versions.yml", emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def interval = intervals ? "--intervals ${intervals}" : ""
-
-    def avail_mem = 3072
-    if (!task.memory) {
-        log.info '[GATK SelectVariants] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
-    } else {
-        avail_mem = (task.memory.mega*0.8).intValue()
+    def interval_command = intervals ? "--intervals ${intervals}" : ""
+    def avail_mem = 3
+    if (task.memory) {
+        avail_mem = task.memory.toGiga()
     }
+
     """
-    gatk --java-options "-Xmx${avail_mem}M -XX:-UsePerfData" \\
+    gatk --java-options "-Xmx${avail_mem}g" \\
         SelectVariants \\
-        --variant $vcf \\
+        --variant ${vcf} \\
+        --reference ${fasta} \\
         --output ${prefix}.vcf.gz \\
-        $interval \\
-        --tmp-dir . \\
-        $args
+        ${interval_command} \\
+        ${args}
+
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+        gatk4: "\$(gatk --version 2>&1 | sed -n 's/^.*(GATK) v\\([^ ]*\\).*/\\1/p')"
     END_VERSIONS
     """
 
     stub:
     def prefix = task.ext.prefix ?: "${meta.id}"
+
     """
     touch ${prefix}.vcf.gz
     touch ${prefix}.vcf.gz.tbi
 
     cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
-    END_VERSIONS
+  "${task.process}":
+      gatk4: "\$(gatk --version 2>&1 | sed -n 's/^.*(GATK) v\\([^ ]*\\).*/\\1/p')"
+  END_VERSIONS
     """
 }

modules/nf-core/gatk4/selectvariants/meta.yml

@@ -1,41 +1,53 @@
-name: gatk4_selectvariants
-description: Select a subset of variants from a VCF file
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "gatk4_selectvariants"
+description: It is used to select a subset of variants from a VCF file
 keywords:
   - gatk4
   - selectvariants
   - vcf
 tools:
-  - gatk4:
-      description: |
-        Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
-        with a primary focus on variant discovery and genotyping. Its powerful processing engine
-        and high-performance computing features make it capable of taking on projects of any size.
-      homepage: https://gatk.broadinstitute.org/hc/en-us
-      documentation: https://gatk.broadinstitute.org/hc/en-us/articles/360036362532-SelectVariants
-      tool_dev_url: https://github.com/broadinstitute/gatk
-      doi: 10.1158/1538-7445.AM2017-3590
-      licence: ["Apache-2.0"]
+  - "gatk4":
+      description: "It was developed in the Data Sciences Platform at the Broad Institute,
+        the toolkit offers a wide array of tools with a primary focus on variant discovery
+        and genotyping. Its powerful processing engine and high-performance computing
+        features make it capable of taking on projects of any size."
+      homepage: "https://gatk.broadinstitute.org/hc/en-us"
+      documentation: "https://gatk.broadinstitute.org/hc/en-us/articles/360037055952-SelectVariants"
+      tool_dev_url: "https://github.com/broadinstitute/gatk"
+      doi: "10.1158/1538-7445.AM2017-3590"
+      licence: ["BSD-3-clause"]
       identifier: ""
+
 input:
+  # Only when we have meta
   - - meta:
         type: map
         description: |
           Groovy Map containing sample information
-          e.g. [ id:'test']
+          e.g. `[ id:'sample1', single_end:false ]`
     - vcf:
-        type: list
-        description: VCF(.gz) file
+        type: file
+        description: Input VCF file
         pattern: "*.{vcf,vcf.gz}"
-    - vcf_idx:
-        type: list
-        description: VCF file index
-        pattern: "*.{idx,tbi}"
-    - intervals:
+    - vcf_index:
+        type: file
+        description: Index file of the input VCF
+        pattern: "*.{tbi,idx}"
+  - - fasta:
+        type: file
+        description: The reference fasta file
+  - - fasta_fai:
+        type: file
+        description: The index of the reference fasta file
+  - - dict:
         type: file
+        description: The sequence dictionary file
+  - - intervals:
+        type: string
         description: One or more genomic intervals over which to operate
-        pattern: ".intervals"
 output:
   - vcf:
+      #Only when we have meta
       - meta:
           type: map
           description: |
@@ -55,14 +67,14 @@ output:
           type: file
           description: Tabix index file
           pattern: "*.vcf.gz.tbi"
+
   - versions:
-      - versions.yml:
+      - "versions.yml":
           type: file
           description: File containing software versions
           pattern: "versions.yml"
+
 authors:
-  - "@mjcipriano"
-  - "@ramprasadn"
+  - "@Alveen-o"
 maintainers:
-  - "@mjcipriano"
-  - "@ramprasadn"
+  - "@Alveen-o"

modules/nf-core/gatk4/selectvariants/tests/download_test_data.nf

@@ -0,0 +1,16 @@
+process DOWNLOAD_TEST_DATA {
+    output:
+    path "*"
+
+    script:
+    """
+    wget -q https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz
+    wget -q https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz.tbi
+    wget -q https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta
+    wget -q https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta.fai
+    """
+}
+
+workflow {
+    DOWNLOAD_TEST_DATA()
+}

modules/nf-core/gatk4/selectvariants/tests/main.nf.test

@@ -1,64 +1,69 @@
 nextflow_process {
 
     name "Test Process GATK4_SELECTVARIANTS"
-    script "modules/nf-core/gatk4/selectvariants/main.nf"
+    script "../main.nf"
     process "GATK4_SELECTVARIANTS"
-    tag "modules"
-    tag "modules_nfcore"
-    tag "gatk4"
-    tag "gatk4/selectvariants"
-
-    test("selectvariants - vcf input") {
 
+    test("gatk4 selectvariants - vcf") {
+        tag "gatk4"
+        tag "modules_nfcore"
+        tag "modules"
+        tag "gatk4/selectvariants"
         when {
-            params {
-                // define parameters here. Example:
-                // outdir = "tests/results"
-            }
             process {
                 """
-                input[0] = [
+                input[0] = Channel.of([
                     [ id:'test' ], // meta map
-                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/gvcf/test.genome.vcf', checkIfExists: true),
-                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.idx', checkIfExists: true),
-                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.interval_list', checkIfExists: true)
-                ]
+                    file("${baseDir}/test-data/test.vcf.gz"),
+                    file("${baseDir}/test-data/test.vcf.gz.tbi")
+                ])
+                input[1] = Channel.of([
+                    [ id:'test' ],
+                    file("${baseDir}/test-data/genome.fasta"),
+                    file("${baseDir}/test-data/genome.fasta.fai")
+                ])
                 """
             }
         }
 
         then {
             assertAll(
-            {assert process.success},
-            {assert path(process.out.vcf.get(0).get(1)).linesGzip.contains("##fileformat=VCFv4.2")}
+                { assert process.success },
+                { assert snapshot(
+                    file(process.out.vcf.get(0).get(1)).name,
+                    file(process.out.vcf.get(0).get(2)).name,
+                    file(process.out.versions).text
+                ).match() }
             )
         }
-
-
     }
 
-    test("selectvariants - gz input") {
+    test("gatk4 selectvariants - vcf - stub") {
+
+        options "-stub"
 
         when {
             process {
                 """
-                input[0] = [
-                    [ id:'test' ], // meta map
-                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz', checkIfExists: true),
-                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz.tbi', checkIfExists: true),
-                    []
-                ]
+                input[0] = Channel.of([
+                    [ id:'test' ],
+                    file("${baseDir}/test-data/test.vcf.gz"),
+                    file("${baseDir}/test-data/test.vcf.gz.tbi")
+                ])
+                input[1] = Channel.of([
+                    [ id:'test' ],
+                    file("${baseDir}/test-data/genome.fasta"),
+                    file("${baseDir}/test-data/genome.fasta.fai")
+                ])
                 """
             }
         }
 
         then {
             assertAll(
-            {assert process.success},
-            {assert path(process.out.vcf.get(0).get(1)).linesGzip.contains("##fileformat=VCFv4.2")}
+                { assert process.success },
+                { assert snapshot(process.out).match() }
             )
         }
-
     }
-
 }

modules/nf-core/gatk4/selectvariants/tests/main.nf.test.snap

@@ -0,0 +1,67 @@
+{
+    "versions": {
+        "content": [
+            [
+
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.5"
+        },
+        "timestamp": "2025-03-25T16:59:21.50748"
+    },
+    "vcf": {
+        "content": [
+            [
+
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.5"
+        },
+        "timestamp": "2025-03-25T16:59:21.48226"
+    },
+    "tbi": {
+        "content": [
+            [
+
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.5"
+        },
+        "timestamp": "2025-03-25T16:59:21.498775"
+    },
+    "gatk4 selectvariants - vcf - stub": {
+        "content": [
+            {
+                "0": [
+
+                ],
+                "1": [
+
+                ],
+                "2": [
+
+                ],
+                "tbi": [
+
+                ],
+                "vcf": [
+
+                ],
+                "versions": [
+
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.5"
+        },
+        "timestamp": "2025-03-25T17:00:34.591574"
+    }
+}

modules/nf-core/gatk4/selectvariants/tests/modules.json

@@ -0,0 +1,12 @@
+{
+    "name": "nf-core/gatk4/selectvariants",
+    "homePage": "https://gatk.broadinstitute.org/hc/en-us/articles/360037055952-SelectVariants",
+    "tags": {
+        "gatk4-selectvariants": {
+            "test_data": {
+                "test_vcf": "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/vcf/test.vcf.gz",
+                "test_vcf_tbi": "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/vcf/test.vcf.gz.tbi"
+            }
+        }
+    }
+}