Merge branch 'master' into add-slimfastq

modules/gatk4/mergebamalignment/main.nf

@@ -43,4 +43,15 @@ process GATK4_MERGEBAMALIGNMENT {
         gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
     END_VERSIONS
     """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.bam
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
 }

modules/gatk4/mutect2/main.nf

@@ -57,4 +57,18 @@ process GATK4_MUTECT2 {
         gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
     END_VERSIONS
     """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.vcf.gz
+    touch ${prefix}.vcf.gz.tbi
+    touch ${prefix}.vcf.gz.stats
+    touch ${prefix}.f1r2.tar.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
 }

modules/gatk4/revertsam/main.nf

@@ -39,4 +39,15 @@ process GATK4_REVERTSAM {
         gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
     END_VERSIONS
     """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.reverted.bam
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
 }

modules/gatk4/samtofastq/main.nf

@@ -40,4 +40,17 @@ process GATK4_SAMTOFASTQ {
         gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
     END_VERSIONS
     """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.fastq.gz
+    touch ${prefix}_1.fastq.gz
+    touch ${prefix}_2.fastq.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
 }

modules/metaphlan3/main.nf

@@ -23,7 +23,7 @@ process METAPHLAN3 {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def input_type  = ("$input".endsWith(".fastq.gz")) ? "--input_type fastq" :  ("$input".contains(".fasta")) ? "--input_type fasta" : ("$input".endsWith(".bowtie2out.txt")) ? "--input_type bowtie2out" : "--input_type sam"
+    def input_type  = ("$input".endsWith(".fastq.gz") || "$input".endsWith(".fq.gz")) ? "--input_type fastq" :  ("$input".contains(".fasta")) ? "--input_type fasta" : ("$input".endsWith(".bowtie2out.txt")) ? "--input_type bowtie2out" : "--input_type sam"
     def input_data  = ("$input_type".contains("fastq")) && !meta.single_end ? "${input[0]},${input[1]}" : "$input"
     def bowtie2_out = "$input_type" == "--input_type bowtie2out" || "$input_type" == "--input_type sam" ? '' : "--bowtie2out ${prefix}.bowtie2out.txt"
 

modules/samtools/view/main.nf

@@ -41,4 +41,16 @@ process SAMTOOLS_VIEW {
         samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
     END_VERSIONS
     """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.bam
+    touch ${prefix}.cram
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
 }

modules/vardictjava/main.nf

@@ -0,0 +1,50 @@
+def VERSION = '1.8.3'
+
+process VARDICTJAVA {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::vardict-java=1.8.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/vardict-java:1.8.3--hdfd78af_0':
+        'quay.io/biocontainers/vardict-java:1.8.3--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(bam), path(bai)
+    path(bed)
+    tuple path(fasta), path(fasta_fai)
+
+    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}"
+
+    """
+    vardict-java \\
+        $args \\
+        -c 1 -S 2 -E 3 \\
+        -b $bam \\
+        -th $task.cpus \\
+        -N $prefix \\
+        -G $fasta \\
+        $bed \\
+        | teststrandbias.R \\
+        | var2vcf_valid.pl \\
+            $args2 \\
+            -N $prefix \\
+        | gzip -c > ${prefix}.vcf.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        vardict-java: $VERSION
+        var2vcf_valid.pl: \$(echo \$(var2vcf_valid.pl -h | sed -n 2p | awk '{ print \$2 }'))
+    END_VERSIONS
+    """
+}

modules/vardictjava/meta.yml

@@ -0,0 +1,60 @@
+name: "vardictjava"
+
+description: The Java port of the VarDict variant caller
+keywords:
+  - variant calling
+  - VarDict
+  - AstraZeneca
+tools:
+  - "vardictjava":
+      description: "Java port of the VarDict variant discovery program"
+      homepage: "https://github.com/AstraZeneca-NGS/VarDictJava"
+      documentation: "https://github.com/AstraZeneca-NGS/VarDictJava"
+      tool_dev_url: "https://github.com/AstraZeneca-NGS/VarDictJava"
+      doi: "10.1093/nar/gkw227 "
+      licence: "['MIT']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: BAM/SAM file
+      pattern: "*.{bam,sam}"
+  - bai:
+      type: file
+      description: Index of the BAM file
+      pattern: "*.bai"
+  - fasta:
+      type: file
+      description: FASTA of the reference genome
+      pattern: "*.{fa,fasta}"
+  - fasta_fai:
+      type: file
+      description: The index of the FASTA of the reference genome
+      pattern: "*.fai"
+  - bed:
+      type: file
+      description: BED with the regions of interest
+      pattern: "*.bed"
+
+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: VCF file output
+      pattern: "*.vcf.gz"
+
+authors:
+  - "@nvnieuwk"

tests/config/pytest_modules.yml

@@ -1924,6 +1924,10 @@ unzip:
   - modules/unzip/**
   - tests/modules/unzip/**
 
+vardictjava:
+  - modules/vardictjava/**
+  - tests/modules/vardictjava/**
+
 variantbam:
   - modules/variantbam/**
   - tests/modules/variantbam/**

tests/modules/gatk4/mergebamalignment/main.nf

@@ -14,3 +14,14 @@ workflow test_gatk4_mergebamalignment {
 
     GATK4_MERGEBAMALIGNMENT ( input, fasta, dict )
 }
+
+workflow test_gatk4_mergebamalignment_stubs {
+     input    = [ [ id:'test' ], // meta map
+                 "test_foo.bam",
+                 "test_bar.bam"
+               ]
+    fasta    = "genome.fasta"
+    dict     = "genome.fasta.dict"
+
+    GATK4_MERGEBAMALIGNMENT ( input, fasta, dict )
+}

tests/modules/gatk4/mergebamalignment/test.yml

@@ -7,3 +7,12 @@
     - path: output/gatk4/test.bam
       md5sum: e6f1b343700b7ccb94e81ae127433988
     - path: output/gatk4/versions.yml
+
+- name: gatk4 mergebamalignment test_gatk4_mergebamalignment_stubs
+  command: nextflow run ./tests/modules/gatk4/mergebamalignment -entry test_gatk4_mergebamalignment -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/mergebamalignment/nextflow.config -stub-run
+  tags:
+    - gatk4
+    - gatk4/mergebamalignment
+  files:
+    - path: output/gatk4/test.bam
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/mutect2/main.nf

@@ -118,3 +118,25 @@ workflow test_gatk4_mutect2_mitochondria {
 
     GATK4_MUTECT2_MITO ( input, fasta, fai, dict, [], [], [], [] )
 }
+
+workflow test_gatk4_mutect2_tumor_normal_pair_f1r2_stubs {
+    input = [ [ id:'test', normal_id:'normal', tumor_id:'tumour' ], // meta map
+              [ "foo_paired.bam",
+                "foo_paired2.bam"
+                ],
+              [ "foo_paired.bam.bai",
+                "foo_paired2.bam.bai"
+                ],
+              []
+            ]
+
+    fasta = "genome.fasta"
+    fai = "genome.fasta.fai"
+    dict = "genome.fasta.dict"
+    germline_resource = "genome_gnomAD.r2.1.1.vcf.gz"
+    germline_resource_tbi = "genome_gnomAD.r2.1.1.vcf.gz.tbi"
+    panel_of_normals = "genome_mills_and_1000G.indels.hg38.vcf.gz"
+    panel_of_normals_tbi = "genome_mills_and_1000G.indels.hg38.vcf.gz.tbi"
+
+    GATK4_MUTECT2_F1R2 ( input, fasta, fai, dict, germline_resource, germline_resource_tbi, panel_of_normals, panel_of_normals_tbi )
+}

tests/modules/gatk4/mutect2/test.yml

@@ -69,3 +69,15 @@
       md5sum: fc6ea14ca2da346babe78161beea28c9
     - path: output/gatk4/test.vcf.gz.tbi
     - path: output/gatk4/versions.yml
+
+- name: gatk4 mutect2 test_gatk4_mutect2_tumor_normal_pair_f1r2_stubs
+  command: nextflow run ./tests/modules/gatk4/mutect2 -entry test_gatk4_mutect2_tumor_normal_pair_f1r2 -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/mutect2/nextflow.config -stub-run
+  tags:
+    - gatk4
+    - gatk4/mutect2
+  files:
+    - path: output/gatk4/test.f1r2.tar.gz
+    - path: output/gatk4/test.vcf.gz
+    - path: output/gatk4/test.vcf.gz.stats
+    - path: output/gatk4/test.vcf.gz.tbi
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/revertsam/main.nf

@@ -11,3 +11,11 @@ workflow test_gatk4_revertsam {
 
     GATK4_REVERTSAM ( input )
 }
+
+workflow test_gatk4_revertsam_stubs {
+    input = [ [ id:'test' ], // meta map
+              "foo_paired_end.bam"
+            ]
+
+    GATK4_REVERTSAM ( input )
+}

tests/modules/gatk4/revertsam/test.yml

@@ -7,3 +7,12 @@
     - path: output/gatk4/test.reverted.bam
       md5sum: f783a88deb45c3a2c20ca12cbe1c5652
     - path: output/gatk4/versions.yml
+
+- name: gatk4 revertsam test_gatk4_revertsam_stubs
+  command: nextflow run ./tests/modules/gatk4/revertsam -entry test_gatk4_revertsam -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/revertsam/nextflow.config -stub-run
+  tags:
+    - gatk4
+    - gatk4/revertsam
+  files:
+    - path: output/gatk4/test.reverted.bam
+    - path: output/gatk4/versions.yml

tests/modules/gatk4/samtofastq/main.nf

@@ -19,3 +19,11 @@ workflow test_gatk4_samtofastq_paired_end {
 
     GATK4_SAMTOFASTQ ( input )
 }
+
+workflow test_gatk4_samtofastq_paired_end_stubs {
+    input = [ [ id:'test', single_end: false ], // meta map
+              [ "foo_paired_end.bam" ]
+            ]
+
+    GATK4_SAMTOFASTQ ( input )
+}

tests/modules/gatk4/samtofastq/test.yml

@@ -19,3 +19,13 @@
     - path: output/gatk4/test_2.fastq.gz
       md5sum: 613bf64c023609e1c62ad6ce9e4be8d7
     - path: output/gatk4/versions.yml
+
+- name: gatk4 samtofastq test_gatk4_samtofastq_paired_end_stubs
+  command: nextflow run ./tests/modules/gatk4/samtofastq -entry test_gatk4_samtofastq_paired_end -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/samtofastq/nextflow.config -stub-run
+  tags:
+    - gatk4
+    - gatk4/samtofastq
+  files:
+    - path: output/gatk4/test_1.fastq.gz
+    - path: output/gatk4/test_2.fastq.gz
+    - path: output/gatk4/versions.yml

tests/modules/samtools/view/main.nf

@@ -22,3 +22,12 @@ workflow test_samtools_view_cram {
 
     SAMTOOLS_VIEW ( input, fasta )
 }
+
+workflow test_samtools_view_stubs {
+    input = [ [ id:'test', single_end:false ], // meta map
+                "foo_paired_end.bam",
+                []
+            ]
+
+    SAMTOOLS_VIEW ( input, [] )
+}

tests/modules/samtools/view/test.yml

@@ -14,3 +14,11 @@
     - samtools
   files:
     - path: output/samtools/test.cram
+
+- name: samtools view test_samtools_view_stubs
+  command: nextflow run ./tests/modules/samtools/view -entry test_samtools_view -c ./tests/config/nextflow.config -c ./tests/modules/samtools/view/nextflow.config -stub-run
+  tags:
+    - samtools/view
+    - samtools
+  files:
+    - path: output/samtools/test.bam

tests/modules/vardictjava/main.nf

@@ -0,0 +1,23 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { VARDICTJAVA } from '../../../modules/vardictjava/main.nf'
+
+workflow test_vardictjava {
+    
+    bam_input_ch = Channel.value([
+        [ id:'test' ], // 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)
+    ])
+
+    bed = Channel.value(file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true))
+
+    reference = Channel.value([
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    ])
+
+    VARDICTJAVA ( bam_input_ch, bed, reference )
+}

tests/modules/vardictjava/nextflow.config

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

tests/modules/vardictjava/test.yml

@@ -0,0 +1,9 @@
+- name: vardictjava test_vardictjava
+  command: nextflow run tests/modules/vardictjava -entry test_vardictjava -c tests/config/nextflow.config
+  tags:
+    - vardictjava
+  files:
+    - path: output/vardictjava/test.vcf.gz
+      md5sum: 3f1f227afc532bddeb58f16fd3013fc8
+    - path: output/vardictjava/versions.yml
+      md5sum: 9b62c431a4f2680412b61c7071bdb1cd