new module: jvarkit vcf2table (#6631)

* 1st

* vcf2table

* fix tests.snap

* rm name

* Apply suggestions from code review

Co-authored-by: Simon Pearce <[email protected]>

* test content

* fix meta

* update tools 3.0.0

* update env.yml

---------

Co-authored-by: Simon Pearce <[email protected]>

modules/nf-core/jvarkit/vcf2table/environment.yml

@@ -0,0 +1,8 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - "bioconda:bcftools=1.20"
+  - "bioconda::jvarkit=2024.08.25"

modules/nf-core/jvarkit/vcf2table/main.nf

@@ -0,0 +1,63 @@
+process JVARKIT_VCF2TABLE {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/jvarkit:2024.08.25--hdfd78af_1':
+        'biocontainers/jvarkit:2024.08.25--hdfd78af_1' }"
+
+    input:
+    tuple val(meta), path(vcf), path(tbi), path(regions_file)
+    tuple val(meta2), path(pedigree)
+    output:
+    tuple val(meta), path("*.${extension}"), emit: output
+    path "versions.yml"                    , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args1        = task.ext.args1 ?: ''
+    def args2        = task.ext.args2 ?: ''
+    def prefix       = task.ext.prefix ?: "${meta.id}"
+    def ped          = pedigree?"--pedigree \"${pedigree}\"":""
+    def regions_file = regions_file? (tbi ? " --regions-file" : " --targets-file")+" \"${regions_file}\" ":""
+    extension =     getFileExtension(args2); /* custom function, see below */
+
+    if ("$vcf" == "${prefix}.${extension}") error "Input and output names are the same, set prefix in module configuration to disambiguate!"
+    """
+    mkdir -p TMP
+
+    bcftools view ${regions_file} -O v ${args1} "${vcf}" |\\
+        jvarkit -Xmx${task.memory.giga}g  -XX:-UsePerfData -Djava.io.tmpdir=TMP vcf2table ${ped}  ${args2} > "${prefix}.${extension}"
+
+    rm -rf TMP
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bcftools: \$(bcftools --version 2>&1 | head -n1 | sed 's/^.*bcftools //; s/ .*\$//')
+        jvarkit: \$(jvarkit -v)
+    END_VERSIONS
+    """
+
+    stub:
+    def args2        = task.ext.args2 ?: ''
+    extension  = getFileExtension(args2); /* custom function, see below */
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch "${prefix}.${extension}"
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bcftools: \$(bcftools --version 2>&1 | head -n1 | sed 's/^.*bcftools //; s/ .*\$//')
+        jvarkit: \$(jvarkit -v)
+    END_VERSIONS
+    """
+}
+
+
+// Custom Function to get VCF extension
+String getFileExtension(String args) {
+    return args.contains("--format html") ? "html" : "txt"
+}

modules/nf-core/jvarkit/vcf2table/meta.yml

@@ -0,0 +1,75 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "jvarkit_vcf2table"
+description: Convert VCF to a user friendly table
+keywords:
+  - vcf
+  - bcf
+  - text
+  - html
+  - visualization
+tools:
+  - "jvarkit":
+      description: "Java utilities for Bioinformatics."
+      homepage: "https://github.com/lindenb/jvarkit"
+      documentation: "https://jvarkit.readthedocs.io/"
+      tool_dev_url: "https://github.com/lindenb/jvarkit"
+      doi: "10.6084/m9.figshare.1425030"
+      licence: ["MIT"]
+      args_id: "$args2"
+      identifier: ""
+  - "bcftools":
+      description: |
+        View, subset and filter VCF or BCF files by position and filtering expression. Convert between VCF and BCF
+      homepage: "http://samtools.github.io/bcftools/bcftools.html"
+      documentation: "http://www.htslib.org/doc/bcftools.html"
+      doi: "10.1093/bioinformatics/btp352"
+      licence: ["MIT"]
+      args_id: "$args1"
+      identifier: "biotools:samtools"
+input:
+  - - "meta":
+        type: map
+        description: |
+          Groovy Map containing VCF information
+          e.g. [ id:'genome' ]
+    - vcf:
+        type: file
+        description: Input vcf/bcf file
+        pattern: "*.{vcf,bcf,vcf.gz,bcf.gz}"
+    - tbi:
+        type: file
+        description: Optional index file for the VCF
+        pattern: "*.{tbi,csi}"
+    - regions_file:
+        type: file
+        description: Optional. Restrict to regions listed in a file
+        pattern: "*.{bed,bed.gz,txt,tsv}"
+  - - meta2:
+        type: map
+        description: |
+          Groovy Map containing pedigree information
+    - pedigree:
+        type: file
+        description: Optional pedigree for jvarkit
+        pattern: "*.{ped,pedigree}"
+output:
+  - output:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing VCF information
+            e.g. [ id:'test', single_end:false ]
+      - "*.${extension}":
+          type: file
+          description: Output file
+          pattern: "*.{txt,html}"
+  - versions:
+      - "versions.yml":
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@lindenb"
+maintainers:
+  - "@lindenb"

modules/nf-core/jvarkit/vcf2table/tests/main.nf.test

@@ -0,0 +1,76 @@
+nextflow_process {
+
+    name "Test Process JVARKIT_VCF2TABLE"
+    script "../main.nf"
+    process "JVARKIT_VCF2TABLE"
+    config "./nextflow.config"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "jvarkit"
+    tag "jvarkit/vcf2table"
+
+    test("sarscov2 - vcf") {
+
+        when {
+            process {
+                """
+                input[0] =[
+                    [id:"vcf_test"],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/vcf/test.vcf', checkIfExists: true),
+                    [],
+                    []
+                ]
+                input[1] = [ [] , [] ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert path(process.out.output[0][1]).text.startsWith(">>MT192765.1:197/G (n. 1)")},
+                { assert snapshot(
+					path(process.out.output[0][1]),
+					process.out.versions
+					).match()
+			    }
+            )
+        }
+
+    }
+
+
+
+    test("sarscov2 - vcf - stub") {
+
+        options  "-stub"
+
+        when {
+            process {
+                """
+                input[0] =[
+                    [id:"vcf_test"],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/vcf/test.vcf', checkIfExists: true),
+                    [],
+                    []
+                ]
+                input[1] = [ [] , [] ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+					path(process.out.output[0][1]),
+					process.out.versions
+					).match()
+			    }
+            )
+        }
+
+    }
+
+}

modules/nf-core/jvarkit/vcf2table/tests/main.nf.test.snap

@@ -0,0 +1,30 @@
+{
+    "sarscov2 - vcf": {
+        "content": [
+            "vcf_test.txt:md5,91513583ed7c0d0e63bb046c03419460",
+           [
+           "versions.yml:md5,0c4f207f3c21b881974f056ea9f863c7"
+           ] 
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-09-03T14:00:13.118369362"
+    },
+
+    "sarscov2 - vcf - stub": {
+        "content": [
+           "vcf_test.txt:md5,d41d8cd98f00b204e9800998ecf8427e",
+           [
+           "versions.yml:md5,0c4f207f3c21b881974f056ea9f863c7"
+           ] 
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-09-03T14:00:13.118369362"
+    }
+
+}

modules/nf-core/jvarkit/vcf2table/tests/nextflow.config

@@ -0,0 +1,7 @@
+process {
+
+    withName: JVARKIT_VCF2TABLE {
+        ext.args2=" --hide NO_CALL "
+    }
+
+}

modules/nf-core/jvarkit/vcf2table/tests/tags.yml

@@ -0,0 +1,2 @@
+jvarkit/vcf2table:
+  - "modules/nf-core/jvarkit/vcf2table/**"