feat added vcflib/vcfbreakmulti module (#2134)

* feat added vcflib/vcfbreakmulti module

* fix comments review

* Update modules/vcflib/vcfbreakmulti/main.nf

Co-authored-by: Anders Jemt <jemten@users.noreply.github.com>

* Update modules/vcflib/vcfbreakmulti/main.nf

Co-authored-by: Anders Jemt <jemten@users.noreply.github.com>

* fix change required by reviewer

* fix commiting pytest_modules.yml

* fix version

* fix version_

* Update tests/modules/vcflib/vcfbreakmulti/test.yml

Co-authored-by: nvnieuwk <101190534+nvnieuwk@users.noreply.github.com>

* fix undid previous commit

* fix test

* Update tests/modules/vcflib/vcfbreakmulti/test.yml

Co-authored-by: nvnieuwk <101190534+nvnieuwk@users.noreply.github.com>

* Update tests/modules/vcflib/vcfbreakmulti/test.yml

Co-authored-by: nvnieuwk <101190534+nvnieuwk@users.noreply.github.com>

Co-authored-by: Anders Jemt <jemten@users.noreply.github.com>
Co-authored-by: nvnieuwk <101190534+nvnieuwk@users.noreply.github.com>

modules/vcflib/vcfbreakmulti/main.nf

@@ -0,0 +1,49 @@
+process VCFLIB_VCFBREAKMULTI {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::vcflib=1.0.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/vcflib:1.0.3--hecb563c_1':
+        'quay.io/biocontainers/vcflib:1.0.3--ha025227_0' }"
+
+    input:
+    tuple val(meta), path(vcf), path(tbi)
+
+    output:
+    tuple val(meta), path("*.vcf.gz"), emit: vcf
+    path "versions.yml"              , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def args2 = task.ext.args2 ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def VERSION = '1.0.3' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+
+    """
+    vcfbreakmulti \\
+        $vcf \\
+        $args \\
+        | bgzip -c $args2 > ${prefix}.breakmulti.vcf.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        vcflib: $VERSION
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def VERSION = '1.0.3' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+    """
+    touch ${prefix}.breakmulti.vcf.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        vcflib: $VERSION
+    END_VERSIONS
+    """
+}

modules/vcflib/vcfbreakmulti/meta.yml

@@ -0,0 +1,45 @@
+name: "vcflib_vcfbreakmulti"
+description: If multiple alleles are specified in a single record, break the record into several lines preserving allele-specific INFO fields
+keywords:
+  - vcflib
+  - vcflib/vcfbreakmulti
+tools:
+  - "vcflib":
+      description: "Command-line tools for manipulating VCF files"
+      homepage: https://github.com/vcflib/vcflib
+      documentation: https://github.com/vcflib/vcflib#USAGE
+      doi: "https://doi.org/10.1101/2021.05.21.445151"
+      licence: "['MIT']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: Compressed VCF file
+      pattern: "*.{.vcf.gz,vcf}"
+  - tbi:
+      type: file
+      description: Index of VCF file
+      pattern: "*.vcf.gz.tbi"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - vcf:
+      type: file
+      description: Compressed VCF file
+      pattern: "*.vcf.gz"
+
+authors:
+  - "@lucpen"

tests/config/pytest_modules.yml

@@ -2500,6 +2500,10 @@ vcfanno:
   - modules/vcfanno/**
   - tests/modules/vcfanno/**
 
+vcflib/vcfbreakmulti:
+  - modules/vcflib/vcfbreakmulti/**
+  - tests/modules/vcflib/vcfbreakmulti/**
+
 vcflib/vcfuniq:
   - modules/vcflib/vcfuniq/**
   - tests/modules/vcflib/vcfuniq/**

tests/modules/vcflib/vcfbreakmulti/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { VCFLIB_VCFBREAKMULTI } from '../../../../modules/vcflib/vcfbreakmulti/main.nf'
+
+workflow test_vcflib_vcfbreakmulti {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
+        file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)
+    ]
+
+    VCFLIB_VCFBREAKMULTI ( input )
+}

tests/modules/vcflib/vcfbreakmulti/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}

tests/modules/vcflib/vcfbreakmulti/test.yml

@@ -0,0 +1,16 @@
+- name: vcflib vcfbreakmulti
+  command: nextflow run ./tests/modules/vcflib/vcfbreakmulti -entry test_vcflib_vcfbreakmulti -c tests/config/nextflow.config
+  tags:
+    - vcflib/vcfbreakmulti
+    - vcflib
+  files:
+    - path: output/vcflib/test.breakmulti.vcf.gz
+      md5sum: 666d2d970399cf219dc1dc1eadff9170
+
+- name: vcflib vcfbreakmulti stub
+  command: nextflow run ./tests/modules/vcflib/vcfbreakmulti -entry test_vcflib_vcfbreakmulti -c tests/config/nextflow.config -stub
+  tags:
+    - vcflib/vcfbreakmulti
+    - vcflib
+  files:
+    - path: output/vcflib/test.breakmulti.vcf.gz