new module gatk4/printsvevidence (#2103)

* new module gatk4/printsvevidence

* linting

Co-authored-by: Simon Pearce <24893913+SPPearce@users.noreply.github.com>

modules/gatk4/printsvevidence/main.nf

@@ -0,0 +1,66 @@
+process GATK4_PRINTSVEVIDENCE {
+    tag "${meta.id}"
+    label 'process_single'
+
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
+    container "${ 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(evidence), path(evidence_index)
+    path bed
+    path fasta
+    path fasta_fai
+    path dict
+
+
+    output:
+    tuple val(meta), path("*.txt.gz")       , emit: printed_evidence
+    tuple val(meta), path("*.txt.gz.tbi")   , emit: printed_evidence_index
+    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 intervals = bed ? "--intervals ${bed}" : ""
+    def reference = fasta ? "--reference ${fasta}" : ""
+
+    def file_name = evidence.getFileName()
+
+    def file_type = file_name =~ ".sr.txt" ? "sr" :
+                    file_name =~ ".pe.txt" ? "pe" :
+                    file_name =~ ".baf.txt" ? "baf" :
+                    file_name =~ ".rd.txt" ? "rd" :
+                    false
+
+    if(!file_type){
+        error("The input file name should contain one of the following: '.sr.txt', '.pe.txt', '.baf.txt', '.rd.txt'")
+    }
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK PRINTSVEVIDENCE] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+
+    """
+    gatk --java-options "-Xmx${avail_mem}g" PrintSVEvidence \\
+        --evidence-file ${evidence} \\
+        --sequence-dictionary ${dict} \\
+        ${intervals} \\
+        ${reference} \\
+        --output ${prefix}.${file_type}.txt.gz \\
+        --tmp-dir . \\
+        ${args}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/gatk4/printsvevidence/meta.yml

@@ -0,0 +1,68 @@
+name: "gatk4_printsvevidence"
+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:
+  - structural variants
+  - gatk4
+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/categories/360002369672s
+    doi: 10.1158/1538-7445.AM2017-3590
+    licence: ["Apache-2.0"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - evidence:
+      type: file
+      description: The evidence file created by CollectSVEvidence
+      pattern: "*.{pe,sr,baf,rd}.txt(.gz)"
+  - evidence_index:
+      type: file
+      description: The index of the evidence file created by CollectSVEvidence
+      pattern: "*.{pe,sr,baf,rd}.txt(.gz).tbi"
+  - bed:
+      type: file
+      description: An optional BED file
+      pattern: "*.bed"
+  - fasta:
+      type: file
+      description: An optional reference FASTA file
+      pattern: "*.{fa,fasta}"
+  - fasta_fai:
+      type: file
+      description: An optional reference FASTA file index
+      pattern: "*.fai"
+  - dict:
+      type: file
+      description: The mandatory sequence dictionary 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"
+  - printed_evidence:
+      type: file
+      description: The output file containing the discordant read pairs or the soft clipped reads
+      pattern: "*.{pe,sr,baf,rd}.txt.gz"
+  - printed_evidence:
+      type: file
+      description: The index of the output file containing the discordant read pairs or the soft clipped reads
+      pattern: "*.{pe,sr,baf,rd}.txt.gz.tbi"
+
+authors:
+  - "@nvnieuwk"

tests/config/pytest_modules.yml

@@ -1003,6 +1003,10 @@ gatk4/mutect2:
   - modules/gatk4/mutect2/**
   - tests/modules/gatk4/mutect2/**
 
+gatk4/printsvevidence:
+  - modules/gatk4/printsvevidence/**
+  - tests/modules/gatk4/printsvevidence/**
+
 gatk4/reblockgvcf:
   - modules/gatk4/reblockgvcf/**
   - tests/modules/gatk4/reblockgvcf/**

tests/modules/gatk4/printsvevidence/main.nf

@@ -0,0 +1,116 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_PRINTSVEVIDENCE as GATK4_PRINTSVEVIDENCE_PE } from '../../../../modules/gatk4/printsvevidence/main.nf'
+include { GATK4_PRINTSVEVIDENCE as GATK4_PRINTSVEVIDENCE_SR } from '../../../../modules/gatk4/printsvevidence/main.nf'
+include { GATK4_COLLECTSVEVIDENCE                           } from '../../../../modules/gatk4/collectsvevidence/main.nf'
+
+workflow test_gatk4_printsvevidence {
+    
+    input = Channel.of(
+        [
+            [ id:'normal', 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),
+            [],
+            []
+        ],
+        [
+            [ id:'tumour', single_end:false ], // meta map
+            file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam'], checkIfExists: true),
+            file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam_bai'], 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
+    )
+
+    pe_files = GATK4_COLLECTSVEVIDENCE.out.paired_end_evidence
+                    .combine(GATK4_COLLECTSVEVIDENCE.out.paired_end_evidence_index, by:0)
+    sr_files = GATK4_COLLECTSVEVIDENCE.out.split_read_evidence
+                    .combine(GATK4_COLLECTSVEVIDENCE.out.split_read_evidence_index, by:0)
+
+    GATK4_PRINTSVEVIDENCE_PE( 
+        pe_files,
+        [],
+        fasta,
+        fasta_fai,
+        dict
+    )
+
+    GATK4_PRINTSVEVIDENCE_SR( 
+        sr_files,
+        [],
+        fasta,
+        fasta_fai,
+        dict
+    )
+
+}
+
+workflow test_gatk4_printsvevidence_bed_no_fasta {
+    
+    input = Channel.of(
+        [
+            [ id:'normal', 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),
+            [],
+            []
+        ],
+        [
+            [ id:'tumour', single_end:false ], // meta map
+            file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam'], checkIfExists: true),
+            file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam_bai'], checkIfExists: true),
+            [],
+            []
+        ]
+    )
+
+    fasta = []
+    fasta_fai = []
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+
+    bed = file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)
+
+    GATK4_COLLECTSVEVIDENCE(
+        input, 
+        fasta, 
+        fasta_fai, 
+        dict
+    )
+
+    pe_files = GATK4_COLLECTSVEVIDENCE.out.paired_end_evidence
+                    .combine(GATK4_COLLECTSVEVIDENCE.out.paired_end_evidence_index, by:0)
+    sr_files = GATK4_COLLECTSVEVIDENCE.out.split_read_evidence
+                    .combine(GATK4_COLLECTSVEVIDENCE.out.split_read_evidence_index, by:0)
+
+    GATK4_PRINTSVEVIDENCE_PE( 
+        pe_files,
+        bed,
+        fasta,
+        fasta_fai,
+        dict
+    )
+
+    GATK4_PRINTSVEVIDENCE_SR( 
+        sr_files,
+        bed,
+        fasta,
+        fasta_fai,
+        dict
+    )
+
+}

tests/modules/gatk4/printsvevidence/nextflow.config

@@ -0,0 +1,14 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: GATK4_COLLECTSVEVIDENCE {
+        ext.args = {"--sample-name ${meta.id}"}
+    }
+
+
+    withName: "GATK4_PRINTSVEVIDENCE*" {
+        ext.prefix = {"${meta.id}_print"}
+    }
+
+}

tests/modules/gatk4/printsvevidence/test.yml

@@ -0,0 +1,77 @@
+- name: gatk4 printsvevidence test_gatk4_printsvevidence
+  command: nextflow run ./tests/modules/gatk4/printsvevidence -entry test_gatk4_printsvevidence -c ./tests/config/nextflow.config  -c ./tests/modules/gatk4/printsvevidence/nextflow.config
+  tags:
+    - gatk4/printsvevidence
+    - gatk4
+  files:
+    - path: output/gatk4/normal.pe.txt.gz
+      md5sum: 19f13dd0408204590b40239d14acbdde
+    - path: output/gatk4/normal.pe.txt.gz.tbi
+      md5sum: 876170d2727a467263cbacecbd9979ee
+    - path: output/gatk4/normal.sr.txt.gz
+      md5sum: fb9ce52193a0db3a084890bd6bbf6a64
+    - path: output/gatk4/normal.sr.txt.gz.tbi
+      md5sum: 3e7b04492c53765e3c84d76b59e1f2c5
+    - path: output/gatk4/normal_print.pe.txt.gz
+      md5sum: 19f13dd0408204590b40239d14acbdde
+    - path: output/gatk4/normal_print.pe.txt.gz.tbi
+      md5sum: 876170d2727a467263cbacecbd9979ee
+    - path: output/gatk4/normal_print.sr.txt.gz
+      md5sum: fb9ce52193a0db3a084890bd6bbf6a64
+    - path: output/gatk4/normal_print.sr.txt.gz.tbi
+      md5sum: 3e7b04492c53765e3c84d76b59e1f2c5
+    - path: output/gatk4/tumour.pe.txt.gz
+      md5sum: 11fb8aeeea29370d9d1b49448456da81
+    - path: output/gatk4/tumour.pe.txt.gz.tbi
+      md5sum: 876170d2727a467263cbacecbd9979ee
+    - path: output/gatk4/tumour.sr.txt.gz
+      md5sum: 3ce47a0e0abac1c2b291e73a2b57cba0
+    - path: output/gatk4/tumour.sr.txt.gz.tbi
+      md5sum: f2105270ba79ed645bac9842be79f411
+    - path: output/gatk4/tumour_print.pe.txt.gz
+      md5sum: 11fb8aeeea29370d9d1b49448456da81
+    - path: output/gatk4/tumour_print.pe.txt.gz.tbi
+      md5sum: 876170d2727a467263cbacecbd9979ee
+    - path: output/gatk4/tumour_print.sr.txt.gz
+      md5sum: 3ce47a0e0abac1c2b291e73a2b57cba0
+    - path: output/gatk4/tumour_print.sr.txt.gz.tbi
+      md5sum: f2105270ba79ed645bac9842be79f411
+
+- name: gatk4 printsvevidence test_gatk4_printsvevidence_bed_no_fasta
+  command: nextflow run ./tests/modules/gatk4/printsvevidence -entry test_gatk4_printsvevidence_bed_no_fasta -c ./tests/config/nextflow.config  -c ./tests/modules/gatk4/printsvevidence/nextflow.config
+  tags:
+    - gatk4/printsvevidence
+    - gatk4
+  files:
+    - path: output/gatk4/normal.pe.txt.gz
+      md5sum: 19f13dd0408204590b40239d14acbdde
+    - path: output/gatk4/normal.pe.txt.gz.tbi
+      md5sum: 876170d2727a467263cbacecbd9979ee
+    - path: output/gatk4/normal.sr.txt.gz
+      md5sum: fb9ce52193a0db3a084890bd6bbf6a64
+    - path: output/gatk4/normal.sr.txt.gz.tbi
+      md5sum: 3e7b04492c53765e3c84d76b59e1f2c5
+    - path: output/gatk4/normal_print.pe.txt.gz
+      md5sum: 19f13dd0408204590b40239d14acbdde
+    - path: output/gatk4/normal_print.pe.txt.gz.tbi
+      md5sum: 876170d2727a467263cbacecbd9979ee
+    - path: output/gatk4/normal_print.sr.txt.gz
+      md5sum: fb9ce52193a0db3a084890bd6bbf6a64
+    - path: output/gatk4/normal_print.sr.txt.gz.tbi
+      md5sum: 3e7b04492c53765e3c84d76b59e1f2c5
+    - path: output/gatk4/tumour.pe.txt.gz
+      md5sum: 11fb8aeeea29370d9d1b49448456da81
+    - path: output/gatk4/tumour.pe.txt.gz.tbi
+      md5sum: 876170d2727a467263cbacecbd9979ee
+    - path: output/gatk4/tumour.sr.txt.gz
+      md5sum: 3ce47a0e0abac1c2b291e73a2b57cba0
+    - path: output/gatk4/tumour.sr.txt.gz.tbi
+      md5sum: f2105270ba79ed645bac9842be79f411
+    - path: output/gatk4/tumour_print.pe.txt.gz
+      md5sum: 11fb8aeeea29370d9d1b49448456da81
+    - path: output/gatk4/tumour_print.pe.txt.gz.tbi
+      md5sum: 876170d2727a467263cbacecbd9979ee
+    - path: output/gatk4/tumour_print.sr.txt.gz
+      md5sum: 3ce47a0e0abac1c2b291e73a2b57cba0
+    - path: output/gatk4/tumour_print.sr.txt.gz.tbi
+      md5sum: f2105270ba79ed645bac9842be79f411