Merge remote-tracking branch 'origin/master' into gatk_spark

modules/bcftools/roh/main.nf

@@ -9,7 +9,7 @@ process BCFTOOLS_ROH {
 
     input:
     tuple val(meta), path(vcf), path(tbi)
-    path af_file
+    tuple path(af_file), path(af_file_tbi)
     path genetic_map
     path regions_file
     path samples_file

modules/bcftools/roh/meta.yml

@@ -23,6 +23,9 @@ input:
   - af_file:
       type: file
       description: "Read allele frequencies from a tab-delimited file containing the columns: CHROM\tPOS\tREF,ALT\tAF."
+  - af_file_tbi:
+      type: file
+      description: "tbi index of af_file."
   - genetic_map:
       type: file
       description: "Genetic map in the format required also by IMPUTE2."

modules/gatk/indelrealigner/main.nf

@@ -0,0 +1,54 @@
+process GATK_INDELREALIGNER {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::gatk=3.5" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gatk:3.5--hdfd78af_11':
+        'quay.io/biocontainers/gatk:3.5--hdfd78af_11' }"
+
+    input:
+    tuple val(meta), path(bam), path(bai), path(intervals)
+    path(fasta)
+    path(fai)
+    path(dict)
+    path(known_vcf)
+
+    output:
+    tuple val(meta), path("*.bam"), path("*.bai"), emit: bam
+    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 known = known_vcf ? "-known ${known_vcf}" : ""
+
+    if ("$bam" == "${prefix}.bam") error "Input and output names are the same, set prefix in module configuration to disambiguate!"
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK IndelRealigner] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+
+    """
+    gatk3 \\
+        -Xmx${avail_mem}g \\
+        -T IndelRealigner \\
+        -R ${fasta} \\
+        -I ${bam} \\
+        --targetIntervals ${intervals} \\
+        ${known} \\
+        -o ${prefix}.bam \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk: \$(echo \$(gatk3 --version))
+    END_VERSIONS
+    """
+}

modules/gatk/indelrealigner/meta.yml

@@ -0,0 +1,71 @@
+name: "gatk_indelrealigner"
+description: Performs local realignment around indels to correct for mapping errors
+keywords:
+  - bam
+  - vcf
+  - variant calling
+  - indel
+  - realignment
+tools:
+  - "gatk":
+      description: "The full Genome Analysis Toolkit (GATK) framework, license restricted."
+      homepage: "https://gatk.broadinstitute.org/hc/en-us"
+      documentation: "https://github.com/broadinstitute/gatk-docs"
+      licence: "['https://software.broadinstitute.org/gatk/download/licensing', 'BSD', 'https://www.broadinstitute.org/gatk/about/#licensing']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: Sorted and indexed BAM file
+      pattern: "*.bam"
+  - bai:
+      type: file
+      description: BAM index file
+      pattern: "*.bai"
+  - intervals:
+      type: file
+      description: Intervals file created by gatk3 RealignerTargetCreator
+      pattern: "*.{intervals,list}"
+  - fasta:
+      type: file
+      description: Reference file used to generate BAM file
+      pattern: ".{fasta,fa,fna}"
+  - fai:
+      type: file
+      description: Index of reference file used to generate BAM file
+      pattern: ".fai"
+  - dict:
+      type: file
+      description: GATK dict file for reference
+      pattern: ".dict"
+  - known_vcf:
+      type: file
+      description: Optional input VCF file(s) with known indels
+      pattern: ".vcf"
+
+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"
+  - bam:
+      type: file
+      description: Sorted and indexed BAM file with local realignment around variants
+      pattern: "*.bam"
+  - bai:
+      type: file
+      description: Output BAM Index file
+      pattern: "*.bai"
+
+authors:
+  - "@jfy133"

modules/gatk/realignertargetcreator/main.nf

@@ -0,0 +1,53 @@
+process GATK_REALIGNERTARGETCREATOR {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::gatk=3.5" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gatk:3.5--hdfd78af_11':
+        'quay.io/biocontainers/gatk:3.5--hdfd78af_11' }"
+
+    input:
+    tuple val(meta), path(input), path(index)
+    path fasta
+    path fai
+    path dict
+    path known_vcf
+
+    output:
+    tuple val(meta), path("*.intervals"), emit: intervals
+    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 known = known_vcf ? "-known ${known_vcf}" : ""
+    if ("$input" == "${prefix}.bam") error "Input and output names are the same, set prefix in module configuration to disambiguate!"
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK RealignerTargetCreator] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+
+    """
+    gatk3 \\
+        -Xmx${avail_mem}g \\
+        -T RealignerTargetCreator \\
+        -nt ${task.cpus} \\
+        -I ${input} \\
+        -R ${fasta} \\
+        -o ${prefix}.intervals \\
+        ${known} \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk: \$(echo \$(gatk3 --version))
+    END_VERSIONS
+    """
+}

modules/gatk/realignertargetcreator/meta.yml

@@ -0,0 +1,64 @@
+name: "gatk_realignertargetcreator"
+description: Generates a list of locations that should be considered for local realignment prior genotyping.
+keywords:
+  - bam
+  - vcf
+  - variant calling
+  - indel
+  - realignment
+  - targets
+tools:
+  - "gatk":
+      description: "The full Genome Analysis Toolkit (GATK) framework, license restricted."
+      homepage: "https://gatk.broadinstitute.org/hc/en-us"
+      documentation: "https://github.com/broadinstitute/gatk-docs"
+      licence: "['https://software.broadinstitute.org/gatk/download/licensing', 'BSD', 'https://www.broadinstitute.org/gatk/about/#licensing']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: Sorted and indexed BAM/CRAM/SAM file
+      pattern: "*.bam"
+  - index:
+      type: file
+      description: BAM index file
+      pattern: "*.bai"
+  - fasta:
+      type: file
+      description: Reference file used to generate BAM file
+      pattern: ".{fasta,fa,fna}"
+  - fai:
+      type: file
+      description: Index of reference file used to generate BAM file
+      pattern: ".fai"
+  - dict:
+      type: file
+      description: GATK dict file for reference
+      pattern: ".dict"
+  - known_vcf:
+      type: file
+      description: Optional input VCF file(s) with known indels
+      pattern: ".vcf"
+
+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"
+  - intervals:
+      type: file
+      description: File containg intervals that represent sites of extant and potential indels.
+      pattern: "*.intervals"
+
+authors:
+  - "@jfy133"

modules/multiqc/main.nf

@@ -7,7 +7,8 @@ process MULTIQC {
         'quay.io/biocontainers/multiqc:1.12--pyhdfd78af_0' }"
 
     input:
-    path multiqc_files
+    path  multiqc_files, stageAs: "?/*"
+    tuple path(multiqc_config), path(multiqc_logo)
 
     output:
     path "*multiqc_report.html", emit: report
@@ -20,8 +21,13 @@ process MULTIQC {
 
     script:
     def args = task.ext.args ?: ''
+    def config = multiqc_config ? "--config $multiqc_config" : ''
     """
-    multiqc -f $args .
+    multiqc \\
+        --force \\
+        $config \\
+        $args \\
+        .
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/multiqc/meta.yml

@@ -17,6 +17,14 @@ input:
       type: file
       description: |
         List of reports / files recognised by MultiQC, for example the html and zip output of FastQC
+  - multiqc_config:
+      type: file
+      description: Config yml for MultiQC
+      pattern: "*.{yml,yaml}"
+  - multiqc_logo:
+      type: file
+      description: Logo file for MultiQC
+      pattern: "*.{png}"
 output:
   - report:
       type: file

modules/rhocall/annotate/main.nf

@@ -0,0 +1,51 @@
+process RHOCALL_ANNOTATE {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::rhocall=0.5.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/rhocall:0.5.1--py39hbf8eff0_0':
+        'quay.io/biocontainers/rhocall:0.5.1--py39hbf8eff0_0' }"
+
+    input:
+    tuple val(meta), path(vcf), path(tbi)
+    tuple val(meta), path(roh)
+    path bed
+
+    output:
+    tuple val(meta), path("*_rhocall.vcf"), emit: vcf
+    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 az_bed = bed ? "-b ${bed}" : ''
+    """
+    rhocall \\
+        annotate \\
+        $args \\
+        $az_bed \\
+        -r $roh \\
+        -o ${prefix}_rhocall.vcf \\
+        $vcf
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        rhocall: \$(echo \$(rhocall --version 2>&1) | sed 's/rhocall, version //' )
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_rhocall.vcf
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        rhocall: \$(echo \$(rhocall --version 2>&1) | sed 's/rhocall, version //' )
+    END_VERSIONS
+    """
+}

modules/rhocall/annotate/meta.yml

@@ -0,0 +1,54 @@
+name: "rhocall_annotate"
+description: "Markup VCF file using rho-calls."
+keywords:
+  - roh
+  - rhocall
+tools:
+  - "rhocall":
+      description: "Call regions of homozygosity and make tentative UPD calls."
+      homepage: "https://github.com/dnil/rhocall"
+      documentation: "https://github.com/dnil/rhocall"
+      tool_dev_url: "https://github.com/dnil"
+      doi: ""
+      licence: "['GPL v3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: vcf file
+      pattern: "*.{vcf,vcf.gz}"
+  - tbi:
+      type: file
+      description: vcf index file
+      pattern: "*.{tbi}"
+  - roh:
+      type: file
+      description: Bcftools roh style TSV file with CHR,POS,AZ,QUAL
+      pattern: "*.{roh}"
+  - bed:
+      type: file
+      description: BED file with AZ windows.
+      pattern: "*.{bed}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: vcf file
+      pattern: "*.{vcf,vcf.gz}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@ramprasadn"

modules/tiddit/cov/main.nf

@@ -2,17 +2,17 @@ process TIDDIT_COV {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::tiddit=2.12.1" : null)
+    conda (params.enable_conda ? "bioconda::tiddit=3.0.0" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/tiddit:2.12.1--py38h1773678_0' :
+        'https://depot.galaxyproject.org/singularity/tiddit:3.0.0--py39h59fae87_1' :
-        'quay.io/biocontainers/tiddit:2.12.1--py38h1773678_0' }"
+        'quay.io/biocontainers/tiddit:3.0.0--py39h59fae87_1' }"
 
     input:
-    tuple val(meta), path(bam)
+    tuple val(meta), path(input)
     path  fasta
 
     output:
-    tuple val(meta), path("*.tab"), optional: true, emit: cov
+    tuple val(meta), path("*.bed"), optional: true, emit: cov
     tuple val(meta), path("*.wig"), optional: true, emit: wig
     path  "versions.yml"          , emit: versions
 
@@ -28,12 +28,12 @@ process TIDDIT_COV {
         --cov \\
         -o $prefix \\
         $args \\
-        --bam $bam \\
+        --bam $input \\
         $reference
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        tiddit: \$(echo \$(tiddit 2>&1) | sed 's/^.*TIDDIT-//; s/ .*\$//')
+        tiddit: \$(echo \$(tiddit 2>&1) | sed 's/^.*tiddit-//; s/ .*\$//')
     END_VERSIONS
     """
 
@@ -45,7 +45,7 @@ process TIDDIT_COV {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        tiddit: \$(echo \$(tiddit 2>&1) | sed 's/^.*TIDDIT-//; s/ .*\$//')
+        tiddit: \$(echo \$(tiddit 2>&1) | sed 's/^.*tiddit-//; s/ .*\$//')
     END_VERSIONS
     """
 }

modules/tiddit/cov/meta.yml

@@ -19,7 +19,7 @@ input:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
-  - bam:
+  - input:
       type: file
       description: BAM/CRAM file
       pattern: "*.{bam,cram}"

modules/tiddit/sv/main.nf

@@ -2,20 +2,19 @@ process TIDDIT_SV {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::tiddit=2.12.1" : null)
+    conda (params.enable_conda ? "bioconda::tiddit=3.0.0" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/tiddit:2.12.1--py38h1773678_0' :
+        'https://depot.galaxyproject.org/singularity/tiddit:3.0.0--py39h59fae87_1' :
-        'quay.io/biocontainers/tiddit:2.12.1--py38h1773678_0' }"
+        'quay.io/biocontainers/tiddit:3.0.0--py39h59fae87_1' }"
 
     input:
-    tuple val(meta), path(bam)
+    tuple val(meta), path(input), path(input_index)
     path  fasta
-    path  fai
+    path  bwa_index
 
     output:
     tuple val(meta), path("*.vcf")         , emit: vcf
-    tuple val(meta), path("*.ploidy.tab") , emit: ploidy
+    tuple val(meta), path("*.ploidies.tab"), emit: ploidy
-    tuple val(meta), path("*.signals.tab"), emit: signals
     path  "versions.yml"                   , emit: versions
 
     when:
@@ -24,18 +23,19 @@ process TIDDIT_SV {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def reference = fasta ? "--ref $fasta" : ""
     """
+    [[ -d $bwa_index ]] && for i in $bwa_index/*; do [[ -f $fasta && ! "\$i" =~ .*"$fasta".* ]] && ln -s \$i ${fasta}.\${i##*.} || ln -s \$i .; done
+
     tiddit \\
         --sv \\
         $args \\
-        --bam $bam \\
+        --bam $input \\
-        $reference \\
+        --ref $fasta \\
         -o $prefix
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        tiddit: \$(echo \$(tiddit 2>&1) | sed 's/^.*TIDDIT-//; s/ .*\$//')
+        tiddit: \$(echo \$(tiddit 2>&1) | sed 's/^.*tiddit-//; s/ .*\$//')
     END_VERSIONS
     """
 
@@ -43,12 +43,11 @@ process TIDDIT_SV {
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
     touch ${prefix}.vcf
-    touch ${prefix}.ploidy.tab
+    touch ${prefix}.ploidies.tab
-    touch ${prefix}.signals.tab
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        tiddit: \$(echo \$(tiddit 2>&1) | sed 's/^.*TIDDIT-//; s/ .*\$//')
+        tiddit: \$(echo \$(tiddit 2>&1) | sed 's/^.*tiddit-//; s/ .*\$//')
     END_VERSIONS
     """
 }

modules/tiddit/sv/meta.yml

@@ -17,14 +17,22 @@ input:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: BAM/CRAM file
+      pattern: "*.{bam,cram}"
+  - index:
+      type: file
+      description: BAM/CRAM index file
+      pattern: "*.{bai,crai}"
   - fasta:
       type: file
       description: Input FASTA file
       pattern: "*.{fasta,fa}"
-  - fai:
+  - bwa_index:
       type: file
-      description: FASTA index file
+      description: BWA genome index files
-      pattern: "*.{fai}"
+      pattern: "Directory containing BWA index *.{amb,ann,bwt,pac,sa}"
 output:
   - meta:
       type: map
@@ -38,11 +46,7 @@ output:
   - ploidy:
       type: file
       description: tab
-      pattern: "*.{ploidy.tab}"
+      pattern: "*.{ploidies.tab}"
-  - signals:
-      type: file
-      description: tab
-      pattern: "*.{signals.tab}"
   - versions:
       type: file
       description: File containing software versions

tests/config/pytest_modules.yml

@@ -715,6 +715,14 @@ gamma/gamma:
   - modules/gamma/gamma/**
   - tests/modules/gamma/gamma/**
 
+gatk/indelrealigner:
+  - modules/gatk/indelrealigner/**
+  - tests/modules/gatk/indelrealigner/**
+
+gatk/realignertargetcreator:
+  - modules/gatk/realignertargetcreator/**
+  - tests/modules/gatk/realignertargetcreator/**
+
 gatk/unifiedgenotyper:
   - modules/gatk/unifiedgenotyper/**
   - tests/modules/gatk/unifiedgenotyper/**
@@ -1647,6 +1655,10 @@ rgi/main:
   - modules/rgi/main/**
   - tests/modules/rgi/main/**
 
+rhocall/annotate:
+  - modules/rhocall/annotate/**
+  - tests/modules/rhocall/annotate/**
+
 rmarkdownnotebook:
   - modules/rmarkdownnotebook/**
   - tests/modules/rmarkdownnotebook/**

tests/modules/bcftools/roh/main.nf

@@ -10,7 +10,7 @@ workflow test_bcftools_roh {
              file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
              file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)]
 
-    af_file = []
+    af_file = [[],[]]
     gen_map = []
     regions = []
     targets = []
@@ -25,7 +25,7 @@ workflow test_bcftools_roh_stub {
              file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
              file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)]
 
-    af_file = []
+    af_file = [[],[]]
     gen_map = []
     regions = []
     targets = []

tests/modules/gatk/indelrealigner/main.nf

@@ -0,0 +1,33 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK_REALIGNERTARGETCREATOR } from '../../../../modules/gatk/realignertargetcreator/main.nf'
+include { GATK_INDELREALIGNER } from '../../../../modules/gatk/indelrealigner/main.nf'
+
+
+workflow test_gatk_indelrealigner {
+
+
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    fai   = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
+    dict  = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
+
+    input_realignertargetcreator     = [ [ id:'test' ], // meta map
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+                ]
+
+    GATK_REALIGNERTARGETCREATOR ( input_realignertargetcreator, fasta, fai, dict, [] )
+
+    ch_intervals = GATK_REALIGNERTARGETCREATOR.out.intervals
+
+    ch_bams_indelrealigner = Channel.of([ [ id:'test' ], // meta map
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)
+                ])
+
+    ch_input_indelrealigner = ch_bams_indelrealigner.mix(ch_intervals).groupTuple(by: 0).map{ [it[0], it[1][0], it[2], it[1][1] ] }.dump(tag: "input")
+
+    GATK_INDELREALIGNER ( ch_input_indelrealigner, fasta, fai, dict, [] )
+}

tests/modules/gatk/indelrealigner/nextflow.config

@@ -0,0 +1,6 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    ext.prefix = { "${meta.id}.realigned" }
+
+}

tests/modules/gatk/indelrealigner/test.yml

@@ -0,0 +1,12 @@
+- name: gatk indelrealigner test_gatk_indelrealigner
+  command: nextflow run ./tests/modules/gatk/indelrealigner -entry test_gatk_indelrealigner -c ./tests/config/nextflow.config  -c ./tests/modules/gatk/indelrealigner/nextflow.config
+  tags:
+    - gatk/indelrealigner
+    - gatk
+  files:
+    - path: output/gatk/test.realigned.bai
+      md5sum: 85a67df8827fe426e7f3a458134c0551
+    - path: output/gatk/test.realigned.bam
+      md5sum: ea1df6f7fcafc408fae4dc1574813d8a
+    - path: output/gatk/test.realigned.intervals
+      md5sum: 7aa7a1b235a510e6591e262382086bf8

tests/modules/gatk/realignertargetcreator/main.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK_REALIGNERTARGETCREATOR } from '../../../../modules/gatk/realignertargetcreator/main.nf'
+
+workflow test_gatk_realignertargetcreator {
+
+    input     = [ [ id:'test' ], // meta map
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                  file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+                ]
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    fai   = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
+    dict  = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
+
+    GATK_REALIGNERTARGETCREATOR ( input, fasta, fai, dict, [] )
+}

tests/modules/gatk/realignertargetcreator/nextflow.config

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

tests/modules/gatk/realignertargetcreator/test.yml

@@ -0,0 +1,8 @@
+- name: gatk realignertargetcreator test_gatk_realignertargetcreator
+  command: nextflow run ./tests/modules/gatk/realignertargetcreator -entry test_gatk_realignertargetcreator -c ./tests/config/nextflow.config  -c ./tests/modules/gatk/realignertargetcreator/nextflow.config
+  tags:
+    - gatk
+    - gatk/realignertargetcreator
+  files:
+    - path: output/gatk/test.intervals
+      md5sum: 7aa7a1b235a510e6591e262382086bf8

tests/modules/multiqc/main.nf

@@ -3,14 +3,31 @@
 nextflow.enable.dsl = 2
 
 include { FASTQC            } from '../../../modules/fastqc/main.nf'
+include { FASTQC as FASTQC2 } from '../../../modules/fastqc/main.nf'
 include { MULTIQC           } from '../../../modules/multiqc/main.nf'
 
 workflow test_multiqc {
-    input = [ [ id: 'test', single_end: false ],
+    input = [
-              [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+        [ id: 'test', single_end: false ],
-                file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
+        [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)]
     ]
 
     FASTQC  ( input )
-    MULTIQC ( FASTQC.out.zip.collect { it[1] } )
+    MULTIQC ( FASTQC.out.zip.collect { it[1] }, [[],[]] )
+}
+
+workflow test_multiqc_fn_collision {
+    fqc_input = [
+        [ id: 'test', single_end: false ],
+        [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)]
+    ]
+    mqc_input = Channel.empty()
+
+    FASTQC  ( fqc_input  )
+    mqc_input = mqc_input.mix(FASTQC.out.zip.collect { it[1] })
+
+    FASTQC2  ( fqc_input )
+    mqc_input = mqc_input.mix(FASTQC2.out.zip.collect { it[1] })
+
+    MULTIQC ( mqc_input, [[],[]] )
 }

tests/modules/multiqc/nextflow.config

@@ -1,5 +1,7 @@
 process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
-
+    withName: "FASTQC*" {
+         publishDir = [ enabled: false ]
+     }
 }

tests/modules/multiqc/test.yml

@@ -1,6 +1,13 @@
-- name: multiqc
+- name: multiqc test_multiqc
   command: nextflow run ./tests/modules/multiqc -entry test_multiqc -c ./tests/config/nextflow.config  -c ./tests/modules/multiqc/nextflow.config
   tags:
     - multiqc
   files:
     - path: output/multiqc/multiqc_report.html
+
+- name: multiqc test_multiqc_fn_collision
+  command: nextflow run ./tests/modules/multiqc -entry test_multiqc_fn_collision -c ./tests/config/nextflow.config  -c ./tests/modules/multiqc/nextflow.config
+  tags:
+    - multiqc
+  files:
+    - path: output/multiqc/multiqc_report.html

tests/modules/rhocall/annotate/main.nf

@@ -0,0 +1,40 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { RHOCALL_ANNOTATE } from '../../../../modules/rhocall/annotate/main.nf'
+include { BCFTOOLS_ROH } from '../../../../modules/bcftools/roh/main.nf'
+
+workflow test_rhocall_annotate {
+
+    input = [ [ id:'test' ], // 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)]
+
+    af_file = [[],[]]
+    gen_map = []
+    regions = []
+    targets = []
+    samples = []
+
+    BCFTOOLS_ROH ( input, af_file, gen_map, regions, samples, targets )
+    RHOCALL_ANNOTATE ( input, BCFTOOLS_ROH.out.roh, [])
+
+}
+
+workflow test_rhocall_annotate_stub {
+
+    input = [ [ id:'test' ], // 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)]
+
+    af_file = [[],[]]
+    gen_map = []
+    regions = []
+    targets = []
+    samples = []
+
+    BCFTOOLS_ROH ( input, af_file, gen_map, regions, samples, targets )
+    RHOCALL_ANNOTATE ( input, BCFTOOLS_ROH.out.roh, [])
+
+}

tests/modules/rhocall/annotate/nextflow.config

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

tests/modules/rhocall/annotate/test.yml

@@ -0,0 +1,17 @@
+- name: "rhocall annotate"
+  command: nextflow run ./tests/modules/rhocall/annotate -entry test_rhocall_annotate -c ./tests/config/nextflow.config -c ./tests/modules/rhocall/annotate/nextflow.config
+  tags:
+    - "rhocall"
+    - "rhocall/annotate"
+  files:
+    - path: "output/rhocall/test_rhocall.vcf"
+    - path: "output/rhocall/versions.yml"
+
+- name: "rhocall annotate stub"
+  command: nextflow run ./tests/modules/rhocall/annotate -entry test_rhocall_annotate_stub -c ./tests/config/nextflow.config -c ./tests/modules/rhocall/annotate/nextflow.config -stub-run
+  tags:
+    - "rhocall"
+    - "rhocall/annotate"
+  files:
+    - path: "output/rhocall/test_rhocall.vcf"
+    - path: "output/rhocall/versions.yml"

tests/modules/tiddit/cov/main.nf

@@ -2,22 +2,41 @@
 
 nextflow.enable.dsl = 2
 
-include { TIDDIT_COV } from '../../../../modules/tiddit/cov/main.nf'
+include { TIDDIT_COV as TIDDIT_COV_BED } from '../../../../modules/tiddit/cov/main.nf'
+include { TIDDIT_COV as TIDDIT_COV_WIG } from '../../../../modules/tiddit/cov/main.nf'
 
-workflow test_tiddit_cov {
+workflow test_tiddit_cov_cram_bed {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+            file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true) ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+
+    TIDDIT_COV_BED ( input, fasta )
+}
+
+workflow test_tiddit_cov_bam_bed {
 
     input = [ [ id:'test', single_end:false ], // meta map
             file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) ]
 
-    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    TIDDIT_COV_BED ( input, [] )
-
-    TIDDIT_COV ( input, fasta )
 }
 
-workflow test_tiddit_cov_no_ref {
+workflow test_tiddit_cov_cram_wig {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+            file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true) ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+
+    TIDDIT_COV_WIG ( input, fasta )
+}
+
+workflow test_tiddit_cov_bam_wig {
 
     input = [ [ id:'test', single_end:false ], // meta map
             file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) ]
 
-    TIDDIT_COV ( input, [] )
+    TIDDIT_COV_WIG ( input, [] )
 }

tests/modules/tiddit/cov/nextflow.config

@@ -2,4 +2,8 @@ process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
+    withName: TIDDIT_COV_WIG {
+        ext.args = '-w'
+    }
+
 }

tests/modules/tiddit/cov/test.yml

@@ -1,17 +1,35 @@
-- name: tiddit cov test_tiddit_cov
+- name: tiddit cov test_tiddit_cov_cram_bed
-  command: nextflow run ./tests/modules/tiddit/cov -entry test_tiddit_cov -c ./tests/config/nextflow.config -c ./tests/modules/tiddit/cov/nextflow.config
+  command: nextflow run ./tests/modules/tiddit/cov -entry test_tiddit_cov_cram_bed -c ./tests/config/nextflow.config -c ./tests/modules/tiddit/cov/nextflow.config
   tags:
     - tiddit
     - tiddit/cov
   files:
-    - path: output/tiddit/test.tab
+    - path: output/tiddit/test.bed
-      md5sum: f7974948f809f94879d8a60b726194f5
+      md5sum: 3b1a28c62a5f25bbba77c1042e9abdf7
 
-- name: tiddit cov test_tiddit_cov_no_ref
+- name: tiddit cov test_tiddit_cov_bam_bed
-  command: nextflow run ./tests/modules/tiddit/cov -entry test_tiddit_cov_no_ref -c ./tests/config/nextflow.config -c ./tests/modules/tiddit/cov/nextflow.config
+  command: nextflow run ./tests/modules/tiddit/cov -entry test_tiddit_cov_bam_bed -c ./tests/config/nextflow.config -c ./tests/modules/tiddit/cov/nextflow.config
   tags:
     - tiddit
     - tiddit/cov
   files:
-    - path: output/tiddit/test.tab
+    - path: output/tiddit/test.bed
-      md5sum: f7974948f809f94879d8a60b726194f5
+      md5sum: 9d1474f1c7c6516205254077087bb026
+
+- name: tiddit cov test_tiddit_cov_cram_wig
+  command: nextflow run ./tests/modules/tiddit/cov -entry test_tiddit_cov_cram_wig -c ./tests/config/nextflow.config -c ./tests/modules/tiddit/cov/nextflow.config
+  tags:
+    - tiddit
+    - tiddit/cov
+  files:
+    - path: output/tiddit/test.wig
+      md5sum: ca3645fd0c3491c86c075c91d16d57c4
+
+- name: tiddit cov test_tiddit_cov_bam_wig
+  command: nextflow run ./tests/modules/tiddit/cov -entry test_tiddit_cov_bam_wig -c ./tests/config/nextflow.config -c ./tests/modules/tiddit/cov/nextflow.config
+  tags:
+    - tiddit
+    - tiddit/cov
+  files:
+    - path: output/tiddit/test.wig
+      md5sum: 44bea2ac6a56774738e65773065da670

tests/modules/tiddit/sv/main.nf

@@ -2,25 +2,33 @@
 
 nextflow.enable.dsl = 2
 
+include { BWA_INDEX } from '../../../../modules/bwa/index/main.nf'
 include { TIDDIT_SV } from '../../../../modules/tiddit/sv/main.nf'
 
-workflow test_tiddit_sv {
+workflow test_tiddit_sv_bam {
     input = [
         [ id:'test' ], // meta map
-        [ file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) ] 
+        [ file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) ],
+        [ file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true) ]
     ]
 
     fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
-    fai   = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
 
-    TIDDIT_SV ( input, fasta, fai )
+    BWA_INDEX( fasta )
+
+    TIDDIT_SV ( input, fasta, BWA_INDEX.out.index)
 }
 
-workflow test_tiddit_sv_no_ref {
+workflow test_tiddit_sv_cram {
     input = [
         [ id:'test' ], // meta map
-        [ file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) ] 
+        [ 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) ]
     ]
 
-    TIDDIT_SV ( input, [], [] )
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+
+    BWA_INDEX( fasta )
+
+    TIDDIT_SV ( input, fasta, BWA_INDEX.out.index)
 }

tests/modules/tiddit/sv/test.yml

@@ -1,25 +1,21 @@
-- name: tiddit sv
+- name: tiddit sv test_tiddit_sv_bam
-  command: nextflow run ./tests/modules/tiddit/sv -entry test_tiddit_sv -c ./tests/config/nextflow.config -c ./tests/modules/tiddit/sv/nextflow.config
+  command: nextflow run ./tests/modules/tiddit/sv -entry test_tiddit_sv_bam -c ./tests/config/nextflow.config -c ./tests/modules/tiddit/sv/nextflow.config
   tags:
     - tiddit
     - tiddit/sv
   files:
-    - path: output/tiddit/test.ploidy.tab
+    - path: output/tiddit/test.ploidies.tab
-      md5sum: 45e050b0e204f0a5a3a99627cc440eaa
+      md5sum: 6319d3611f7b6b94425a184d274b3dfc
-    - path: output/tiddit/test.signals.tab
-      md5sum: dab4b2fec4ddf8eb1c23005b0770150e
     - path: output/tiddit/test.vcf
-      md5sum: bdce14ae8292bf3deb81f6f255baf859
+      md5sum: 41d3f8746f0420f894104321b7e64f67
 
-- name: tiddit sv no ref
+- name: tiddit sv test_tiddit_sv_cram
-  command: nextflow run ./tests/modules/tiddit/sv -entry test_tiddit_sv_no_ref -c ./tests/config/nextflow.config -c ./tests/modules/tiddit/sv/nextflow.config
+  command: nextflow run ./tests/modules/tiddit/sv -entry test_tiddit_sv_cram -c ./tests/config/nextflow.config -c ./tests/modules/tiddit/sv/nextflow.config
   tags:
     - tiddit
     - tiddit/sv
   files:
-    - path: output/tiddit/test.ploidy.tab
+    - path: output/tiddit/test.ploidies.tab
-      md5sum: 45e050b0e204f0a5a3a99627cc440eaa
+      md5sum: f1162a940ddc8b963f6e0e506bb5c136
-    - path: output/tiddit/test.signals.tab
-      md5sum: dab4b2fec4ddf8eb1c23005b0770150e
     - path: output/tiddit/test.vcf
-      md5sum: 3d0e83a8199b2bdb81cfe3e6b12bf64b
+      md5sum: 34db59578991285d6b62dc1500272fca