new module gatk4/collectsvevidence (#2039)

modules/gatk4/collectsvevidence/main.nf

@@ -0,0 +1,56 @@
+process GATK4_COLLECTSVEVIDENCE {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(input), path(input_index), path(allele_count_vcf), path(allele_count_vcf_tbi)
+    path fasta
+    path fasta_fai
+    path dict
+
+    output:
+    tuple val(meta), path("*.sr.txt.gz")    , emit: split_read_evidence
+    tuple val(meta), path("*.sr.txt.gz.tbi"), emit: split_read_evidence_index
+    tuple val(meta), path("*.pe.txt.gz")    , emit: paired_end_evidence
+    tuple val(meta), path("*.pe.txt.gz.tbi"), emit: paired_end_evidence_index
+    tuple val(meta), path("*.ld.txt.gz")    , emit: allele_counts, optional:true
+    tuple val(meta), path("*.ld.txt.gz.tbi"), emit: allele_counts_index, optional:true
+    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 allele_vcf = allele_count_vcf ? "--allele-count-file ${prefix}.ld.txt.gz --allele-count-vcf ${allele_count_vcf}" : ""
+    def reference  = fasta ? "--reference ${fasta}" : ""
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK COLLECTSVEVIDENCE] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+    """
+    gatk --java-options "-Xmx${avail_mem}g" CollectSVEvidence \\
+        ${args} \\
+        --input ${input} \\
+        --sr-file ${prefix}.sr.txt.gz \\
+        --pe-file ${prefix}.pe.txt.gz \\
+        ${allele_vcf} \\
+        ${reference} \\
+        --tmp-dir . \\
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/gatk4/collectsvevidence/meta.yml

@@ -0,0 +1,88 @@
+name: "gatk4_collectsvevidence"
+description: Gathers paired-end and split read evidence files for use in the GATK-SV pipeline. Output files are a file containing the location of and orientation of read pairs marked as discordant, and a file containing the clipping location of all soft clipped reads and the orientation of the clipping.
+keywords:
+  - gatk4
+  - collectsvevidence
+  - structural variants
+  - metrics
+tools:
+  - "gatk4":
+      description: "Genome Analysis Toolkit (GATK4)"
+      homepage: "https://gatk.broadinstitute.org/hc/en-us"
+      documentation: "None"
+      tool_dev_url: "https://github.com/broadinstitute/gatk"
+      doi: "10.1158/1538-7445.AM2017-3590"
+      licence: "['BSD-3-clause']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - input_index:
+      type: file
+      description: Index of the BAM/CRAM/SAM file
+      pattern: "*.{bai,crai,sai}"
+  - allele_count_vcf:
+      type: file
+      description: Optional - input VCF of SNPs marking loci for allele counts, needed for the allele counts output
+      pattern: "*.vcf.gz"
+  - allele_count_vcf_index:
+      type: file
+      description: Optional - index of the VCF file, needed for the allele counts output
+      pattern: "*.tbi"
+  - fasta:
+      type: file
+      description: Optional - reference FASTA file needed when the input is a CRAM file
+      pattern: "*.{fasta,fa}"
+  - fasta_fai:
+      type: file
+      description: Optional - index of the reference FASTA file needed when the input is a CRAM file
+      pattern: "*.fai"
+  - dict:
+      type: file
+      description: Optional - sequence dictionary of the reference FASTA file needed when the input is a CRAM file
+      pattern: "*.dict"
+
+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"
+  - split_read_evidence:
+      type: file
+      description: Output file for split read evidence
+      pattern: "*.sr.txt.gz"
+  - split_read_evidence_index:
+      type: file
+      description: Index of the output file for split read evidence
+      pattern: "*.sr.txt.gz.tbi"
+  - paired_end_evidence:
+      type: file
+      description: Output file for paired end evidence
+      pattern: "*.pe.txt.gz"
+  - paired_end_evidence_index:
+      type: file
+      description: Index of the output file for paired end evidence
+      pattern: "*.pe.txt.gz.tbi"
+  - allele_counts:
+      type: file
+      description: Output file for allele counts
+      pattern: "*.ld.txt.gz"
+  - allele_counts_index:
+      type: file
+      description: Index of the output file for allele counts
+      pattern: "*.ld.txt.gz.tbi"
+
+authors:
+  - "@nvnieuwk"

tests/config/pytest_modules.yml

@@ -871,6 +871,10 @@ gatk4/collectreadcounts:
   - modules/gatk4/collectreadcounts/**
   - tests/modules/gatk4/collectreadcounts/**
 
+gatk4/collectsvevidence:
+  - modules/gatk4/collectsvevidence/**
+  - tests/modules/gatk4/collectsvevidence/**
+
 gatk4/combinegvcfs:
   - modules/gatk4/combinegvcfs/**
   - tests/modules/gatk4/combinegvcfs/**

tests/modules/gatk4/collectsvevidence/main.nf

@@ -0,0 +1,56 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_COLLECTSVEVIDENCE } from '../../../../modules/gatk4/collectsvevidence/main.nf'
+
+workflow test_gatk4_collectsvevidence_cram {
+    
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram_crai'], checkIfExists: true),
+        [],
+        []
+    ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+
+    GATK4_COLLECTSVEVIDENCE ( input, fasta, fasta_fai, dict )
+}
+
+workflow test_gatk4_collectsvevidence_bam {
+    
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+        [],
+        []
+    ]
+
+    fasta = []
+    fasta_fai = []
+    dict = []
+
+    GATK4_COLLECTSVEVIDENCE ( input, fasta, fasta_fai, dict )
+}
+
+workflow test_gatk4_collectsvevidence_allele_count {
+    
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_haplotc_cnn_vcf_gz'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_haplotc_cnn_vcf_gz_tbi'], checkIfExists: true)
+    ]
+
+    fasta = []
+    fasta_fai = []
+    dict = []
+
+    GATK4_COLLECTSVEVIDENCE ( input, fasta, fasta_fai, dict )
+}

tests/modules/gatk4/collectsvevidence/nextflow.config

@@ -0,0 +1,9 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+    withName: GATK4_COLLECTSVEVIDENCE {
+        ext.args = "--sample-name normal"
+    }
+
+}

tests/modules/gatk4/collectsvevidence/test.yml

@@ -0,0 +1,48 @@
+- name: gatk4 collectsvevidence test_gatk4_collectsvevidence_cram
+  command: nextflow run ./tests/modules/gatk4/collectsvevidence -entry test_gatk4_collectsvevidence_cram -c ./tests/config/nextflow.config  -c ./tests/modules/gatk4/collectsvevidence/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/collectsvevidence
+  files:
+    - path: output/gatk4/test.pe.txt.gz
+      md5sum: 19f13dd0408204590b40239d14acbdde
+    - path: output/gatk4/test.pe.txt.gz.tbi
+      md5sum: 876170d2727a467263cbacecbd9979ee
+    - path: output/gatk4/test.sr.txt.gz
+      md5sum: fb9ce52193a0db3a084890bd6bbf6a64
+    - path: output/gatk4/test.sr.txt.gz.tbi
+      md5sum: 3e7b04492c53765e3c84d76b59e1f2c5
+
+- name: gatk4 collectsvevidence test_gatk4_collectsvevidence_bam
+  command: nextflow run ./tests/modules/gatk4/collectsvevidence -entry test_gatk4_collectsvevidence_bam -c ./tests/config/nextflow.config  -c ./tests/modules/gatk4/collectsvevidence/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/collectsvevidence
+  files:
+    - path: output/gatk4/test.pe.txt.gz
+      md5sum: 19f13dd0408204590b40239d14acbdde
+    - path: output/gatk4/test.pe.txt.gz.tbi
+      md5sum: 876170d2727a467263cbacecbd9979ee
+    - path: output/gatk4/test.sr.txt.gz
+      md5sum: fb9ce52193a0db3a084890bd6bbf6a64
+    - path: output/gatk4/test.sr.txt.gz.tbi
+      md5sum: 3e7b04492c53765e3c84d76b59e1f2c5
+
+- name: gatk4 collectsvevidence test_gatk4_collectsvevidence_allele_count
+  command: nextflow run ./tests/modules/gatk4/collectsvevidence -entry test_gatk4_collectsvevidence_allele_count -c ./tests/config/nextflow.config  -c ./tests/modules/gatk4/collectsvevidence/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/collectsvevidence
+  files:
+    - path: output/gatk4/test.ld.txt.gz
+      md5sum: c07747510deb2c2c886ee4e34d0a9c97
+    - path: output/gatk4/test.ld.txt.gz.tbi
+      md5sum: d1479eeb2217c2b8b4a84cf7237aca45
+    - path: output/gatk4/test.pe.txt.gz
+      md5sum: 19f13dd0408204590b40239d14acbdde
+    - path: output/gatk4/test.pe.txt.gz.tbi
+      md5sum: 876170d2727a467263cbacecbd9979ee
+    - path: output/gatk4/test.sr.txt.gz
+      md5sum: fb9ce52193a0db3a084890bd6bbf6a64
+    - path: output/gatk4/test.sr.txt.gz.tbi
+      md5sum: 3e7b04492c53765e3c84d76b59e1f2c5