Merge branch 'master' into sexdeterrmine

modules/bamtools/convert/meta.yml

@@ -42,7 +42,6 @@ output:
       type: file
       description: File containing software versions
       pattern: "versions.yml"
-  ## TODO nf-core: Delete / customise this example output
   - out:
       type: file
       description: The data in the asked format (bed, fasta, fastq, json, pileup, sam, yaml)

modules/bcftools/concat/main.nf

@@ -8,7 +8,7 @@ process BCFTOOLS_CONCAT {
         'quay.io/biocontainers/bcftools:1.14--h88f3f91_0' }"
 
     input:
-    tuple val(meta), path(vcfs)
+    tuple val(meta), path(vcfs), path(tbi)
 
     output:
     tuple val(meta), path("*.gz"), emit: vcf

modules/bcftools/concat/meta.yml

@@ -25,6 +25,11 @@ input:
       description: |
         List containing 2 or more vcf files
         e.g. [ 'file1.vcf', 'file2.vcf' ]
+  - tbi:
+      type: files
+      description: |
+        List containing 2 or more index files (optional)
+        e.g. [ 'file1.tbi', 'file2.tbi' ]
 output:
   - meta:
       type: map

modules/bcftools/roh/main.nf

@@ -0,0 +1,61 @@
+process BCFTOOLS_ROH {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::bcftools=1.15.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bcftools:1.15.1--h0ea216a_0':
+        'quay.io/biocontainers/bcftools:1.15.1--h0ea216a_0' }"
+
+    input:
+    tuple val(meta), path(vcf), path(tbi)
+    tuple path(af_file), path(af_file_tbi)
+    path genetic_map
+    path regions_file
+    path samples_file
+    path targets_file
+
+    output:
+    tuple val(meta), path("*.roh"), emit: roh
+    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 af_read   = af_file         ? "--AF-file ${af_file}"           : ''
+    def gen_map   = genetic_map     ? "--genetic-map ${genetic_map}"   : ''
+    def reg_file  = regions_file    ? "--regions-file ${regions_file}" : ''
+    def samp_file = samples_file    ? "--samples-file ${samples_file}" : ''
+    def targ_file = targets_file    ? "--targets-file ${targets_file}" : ''
+    """
+    bcftools \\
+        roh \\
+        $args \\
+        $af_read \\
+        $gen_map \\
+        $reg_file \\
+        $samp_file \\
+        $targ_file \\
+        -o ${prefix}.roh \\
+        $vcf
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bcftools: \$(bcftools --version 2>&1 | head -n1 | sed 's/^.*bcftools //; s/ .*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix    = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.roh
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bcftools: \$(bcftools --version 2>&1 | head -n1 | sed 's/^.*bcftools //; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/bcftools/roh/meta.yml

@@ -0,0 +1,58 @@
+name: "bcftools_roh"
+description: A program for detecting runs of homo/autozygosity. Only bi-allelic sites are considered.
+keywords:
+  - roh
+tools:
+  - "roh":
+      description: "A program for detecting runs of homo/autozygosity. Only bi-allelic sites are considered."
+      homepage: https://www.htslib.org/
+      documentation: http://www.htslib.org/doc/bcftools.html
+      doi: 10.1093/bioinformatics/btp352
+      licence: ["MIT"]
+
+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}"
+  - 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."
+  - regions_file:
+      type: file
+      description: "Regions can be specified either on command line or in a VCF, BED, or tab-delimited file (the default)."
+  - samples_file:
+      type: file
+      description: "File of sample names to include or exclude if prefixed with '^'."
+  - targets_file:
+      type: file
+      description: "Targets can be specified either on command line or in a VCF, BED, or tab-delimited file (the default)."
+
+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"
+  - roh:
+      type: file
+      description: Contains site-specific and/or per-region runs of homo/autozygosity calls.
+      pattern: "*.{roh}"
+
+authors:
+  - "@ramprasadn"

modules/cnvkit/batch/main.nf

@@ -10,6 +10,7 @@ process CNVKIT_BATCH {
     input:
     tuple val(meta), path(tumor), path(normal)
     path  fasta
+    path  fasta_fai
     path  targets
     path  reference
 
@@ -28,35 +29,69 @@ process CNVKIT_BATCH {
     script:
     def args = task.ext.args ?: ''
 
-    // execute samtools only when cram files are input, cnvkit runs natively on bam but is prohibitively slow
+    def tumor_exists = tumor ? true : false
-    // input pair is assumed to have same extension if both exist
+    def normal_exists = normal ? true : false
-    def is_cram = tumor.Extension == "cram" ? true : false
+
-    def tumor_out = is_cram ? tumor.BaseName + ".bam" : "${tumor}"
+    // execute samtools only when cram files are input, cnvkit runs natively on bam but is prohibitively slow
+    def tumor_cram = tumor_exists && tumor.Extension == "cram" ? true : false
+    def normal_cram = normal_exists && normal.Extension == "cram" ? true : false
+    def tumor_bam = tumor_exists && tumor.Extension == "bam" ? true : false
+    def normal_bam = normal_exists && normal.Extension == "bam" ? true : false
+
+    def tumor_out = tumor_cram ? tumor.BaseName + ".bam" : "${tumor}"
 
-    // do not run samtools on normal samples in tumor_only mode
-    def normal_exists = normal ? true: false
     // tumor_only mode does not need fasta & target
     // instead it requires a pre-computed reference.cnn which is built from fasta & target
     def (normal_out, normal_args, fasta_args) = ["", "", ""]
+    def fai_reference = fasta_fai ? "--fai-reference ${fasta_fai}" : ""
 
     if (normal_exists){
         def normal_prefix = normal.BaseName
-        normal_out = is_cram ? "${normal_prefix}" + ".bam" : "${normal}"
+        normal_out = normal_cram ? "${normal_prefix}" + ".bam" : "${normal}"
-        normal_args = normal_prefix ? "--normal $normal_out" : ""
         fasta_args = fasta ? "--fasta $fasta" : ""
+
+        // germline mode
+        // normal samples must be input without a flag
+        // requires flag --normal to be empty []
+        if(!tumor_exists){
+            tumor_out = "${normal_prefix}" + ".bam"
+            normal_args = "--normal "
+        }
+        // somatic mode
+        else {
+            normal_args = normal_prefix ? "--normal $normal_out" : ""
+        }
     }
 
     def target_args = targets ? "--targets $targets" : ""
     def reference_args = reference ? "--reference $reference" : ""
 
+    // somatic_mode cram_input
+    if (tumor_cram && normal_cram){
         """
-    if $is_cram; then
+        samtools view -T $fasta $fai_reference $tumor -@ $task.cpus -o $tumor_out
-        samtools view -T $fasta $tumor -@ $task.cpus -o $tumor_out
+        samtools view -T $fasta $fai_reference $normal -@ $task.cpus -o $normal_out
-        if $normal_exists; then
-            samtools view -T $fasta $normal -@ $task.cpus -o $normal_out
-        fi
-    fi
 
+        cnvkit.py \\
+            batch \\
+            $tumor_out \\
+            $normal_args \\
+            $fasta_args \\
+            $reference_args \\
+            $target_args \\
+            --processes $task.cpus \\
+            $args
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+            cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+        END_VERSIONS
+        """
+    }
+    // somatic_mode bam_input
+    else if (tumor_bam && normal_bam){
+        """
         cnvkit.py \\
             batch \\
             $tumor_out \\
@@ -72,4 +107,89 @@ process CNVKIT_BATCH {
             cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
         END_VERSIONS
         """
+    }
+    // tumor_only_mode cram_input
+    else if(tumor_cram && !normal_exists){
+        """
+        samtools view -T $fasta $fai_reference $tumor -@ $task.cpus -o $tumor_out
+
+        cnvkit.py \\
+            batch \\
+            $tumor_out \\
+            $normal_args \\
+            $fasta_args \\
+            $reference_args \\
+            $target_args \\
+            --processes $task.cpus \\
+            $args
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+            cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+        END_VERSIONS
+        """
+    }
+    // tumor_only bam_input
+    else if(tumor_bam && !normal_exists){
+        """
+        cnvkit.py \\
+            batch \\
+            $tumor_out \\
+            $normal_args \\
+            $fasta_args \\
+            $reference_args \\
+            $target_args \\
+            --processes $task.cpus \\
+            $args
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+        END_VERSIONS
+        """
+    }
+    // germline mode cram_input
+    // normal_args must be --normal []
+    else if (normal_cram && !tumor_exists){
+        """
+        samtools view -T $fasta $fai_reference $normal -@ $task.cpus -o $tumor_out
+
+        cnvkit.py \\
+            batch \\
+            $tumor_out \\
+            $normal_args \\
+            $fasta_args \\
+            $reference_args \\
+            $target_args \\
+            --processes $task.cpus \\
+            $args
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+            cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+        END_VERSIONS
+        """
+    }
+    // germline mode bam_input
+    else if (normal_bam && !tumor_exists){
+        """
+        cnvkit.py \\
+            batch \\
+            $tumor_out \\
+            $normal_args \\
+            $fasta_args \\
+            $reference_args \\
+            $target_args \\
+            --processes $task.cpus \\
+            $args
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+        END_VERSIONS
+        """
+    }
+
 }

modules/cnvkit/batch/meta.yml

@@ -29,6 +29,10 @@ input:
       type: file
       description: |
         Input reference genome fasta file (only needed for cram_input and/or when normal_samples are provided)
+  - fasta_fai:
+      type: file
+      description: |
+        Input reference genome fasta index (optional, but recommended for cram_input)
   - targetfile:
       type: file
       description: |

modules/cnvkit/reference/main.nf

@@ -1,5 +1,5 @@
 process CNVKIT_REFERENCE {
-    tag "$reference"
+    tag "$fasta"
     label 'process_low'
 
     conda (params.enable_conda ? "bioconda::cnvkit=0.9.9" : null)
@@ -13,14 +13,15 @@ process CNVKIT_REFERENCE {
     path antitargets
 
     output:
-    path("*.cnn")                 , emit: cnn
+    path "*.cnn"       , emit: cnn
-    path "versions.yml"           , emit: versions
+    path "versions.yml", emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: targets.BaseName
 
     """
     cnvkit.py \\
@@ -28,7 +29,7 @@ process CNVKIT_REFERENCE {
         --fasta $fasta \\
         --targets $targets \\
         --antitargets $antitargets \\
-        --output reference.cnn \\
+        --output ${prefix}.reference.cnn \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/deeptools/bamcoverage/main.nf

@@ -2,13 +2,15 @@ process DEEPTOOLS_BAMCOVERAGE {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::deeptools=3.5.1" : null)
+    conda (params.enable_conda ? "bioconda::deeptools=3.5.1 bioconda::samtools=1.15.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/deeptools:3.5.1--py_0':
+        'https://depot.galaxyproject.org/singularity/mulled-v2-eb9e7907c7a753917c1e4d7a64384c047429618a:2c687053c0252667cca265c9f4118f2c205a604c-0':
-        'quay.io/biocontainers/deeptools:3.5.1--py_0' }"
+        'quay.io/biocontainers/mulled-v2-eb9e7907c7a753917c1e4d7a64384c047429618a:2c687053c0252667cca265c9f4118f2c205a604c-0' }"
 
     input:
     tuple val(meta), path(input), path(input_index)
+    path(fasta)
+    path(fasta_fai)
 
     output:
     tuple val(meta), path("*.bigWig")   , emit: bigwig, optional: true
@@ -22,9 +24,35 @@ process DEEPTOOLS_BAMCOVERAGE {
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}.bigWig"
 
+    // cram_input is currently not working with deeptools
+    // therefore it's required to convert cram to bam first
+    def is_cram = input.Extension == "cram" ? true : false
+    def input_out = is_cram ? input.BaseName + ".bam" : "${input}"
+    def fai_reference = fasta_fai ? "--fai-reference ${fasta_fai}" : ""
+
+    if (is_cram){
+        """
+        samtools view -T $fasta $input $fai_reference -@ $task.cpus -o $input_out
+        samtools index -b $input_out -@ $task.cpus
+
+        bamCoverage \\
+            --bam $input_out \\
+            $args \\
+            --numberOfProcessors ${task.cpus} \\
+            --outFileName ${prefix}
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+            deeptools: \$(bamCoverage --version | sed -e "s/bamCoverage //g")
+        END_VERSIONS
+        """
+
+    }
+    else {
         """
         bamCoverage \\
-        --bam $input \\
+            --bam $input_out \\
             $args \\
             --numberOfProcessors ${task.cpus} \\
             --outFileName ${prefix}
@@ -34,4 +62,6 @@ process DEEPTOOLS_BAMCOVERAGE {
             deeptools: \$(bamCoverage --version | sed -e "s/bamCoverage //g")
         END_VERSIONS
         """
+    }
+
 }

modules/deeptools/bamcoverage/meta.yml

@@ -25,6 +25,14 @@ input:
       type: file
       description: BAM/CRAM index file
       pattern: "*.{bai,crai}"
+  - fasta:
+      type: file
+      description: Reference file the CRAM file was created with (required with CRAM input)
+      pattern: "*.{fasta,fa}"
+  - fasta_fai:
+      type: file
+      description: Index of the reference file (optional, but recommended)
+      pattern: "*.{fai}"
 
 output:
   - meta:
@@ -47,3 +55,4 @@ output:
 
 authors:
   - "@FriederikeHanssen"
+  - "@SusiJo"

modules/ensemblvep/Dockerfile

@@ -11,8 +11,8 @@ RUN conda env create -f /environment.yml && conda clean -a
 # Setup default ARG variables
 ARG GENOME=GRCh38
 ARG SPECIES=homo_sapiens
-ARG VEP_VERSION=104
+ARG VEP_VERSION=105
-ARG VEP_TAG=104.3
+ARG VEP_TAG=105.0
 
 # Add conda installation dir to PATH (instead of doing 'conda activate')
 ENV PATH /opt/conda/envs/nf-core-vep-${VEP_TAG}/bin:$PATH

modules/ensemblvep/build.sh

@@ -20,9 +20,9 @@ build_push() {
     docker push nfcore/vep:${VEP_TAG}.${GENOME}
 }
 
-build_push "GRCh37"    "homo_sapiens"           "104" "104.3"
+build_push "GRCh37"    "homo_sapiens"           "105" "105.0"
-build_push "GRCh38"    "homo_sapiens"           "104" "104.3"
+build_push "GRCh38"    "homo_sapiens"           "105" "105.0"
-build_push "GRCm38"    "mus_musculus"           "102" "104.3"
+build_push "GRCm38"    "mus_musculus"           "102" "105.0"
-build_push "GRCm39"    "mus_musculus"           "104" "104.3"
+build_push "GRCm39"    "mus_musculus"           "105" "105.0"
-build_push "CanFam3.1" "canis_lupus_familiaris" "104" "104.3"
+build_push "CanFam3.1" "canis_lupus_familiaris" "104" "105.0"
-build_push "WBcel235"  "caenorhabditis_elegans" "104" "104.3"
+build_push "WBcel235"  "caenorhabditis_elegans" "105" "105.0"

modules/ensemblvep/environment.yml

@@ -1,10 +1,10 @@
 # You can use this file to create a conda environment for this module:
 #   conda env create -f environment.yml
-name: nf-core-vep-104.3
+name: nf-core-vep-105.0
 channels:
   - conda-forge
   - bioconda
   - defaults
 
 dependencies:
-  - bioconda::ensembl-vep=104.3
+  - bioconda::ensembl-vep=105.0

modules/ensemblvep/main.nf

@@ -13,6 +13,7 @@ process ENSEMBLVEP {
     val   species
     val   cache_version
     path  cache
+    path  fasta
     path  extra_files
 
     output:
@@ -27,6 +28,8 @@ process ENSEMBLVEP {
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
     def dir_cache = cache ? "\${PWD}/${cache}" : "/.vep"
+    def reference = fasta ? "--fasta $fasta" : ""
+
     """
     mkdir $prefix
 
@@ -34,6 +37,7 @@ process ENSEMBLVEP {
         -i $vcf \\
         -o ${prefix}.ann.vcf \\
         $args \\
+        $reference \\
         --assembly $genome \\
         --species $species \\
         --cache \\

modules/ensemblvep/meta.yml

@@ -36,6 +36,11 @@ input:
       type: file
       description: |
         path to VEP cache (optional)
+  - fasta:
+      type: file
+      description: |
+        reference FASTA file (optional)
+      pattern: "*.{fasta,fa}"
   - extra_files:
       type: tuple
       description: |

modules/filtlong/main.nf

@@ -11,7 +11,7 @@ process FILTLONG {
     tuple val(meta), path(shortreads), path(longreads)
 
     output:
-    tuple val(meta), path("${meta.id}_lr_filtlong.fastq.gz"), emit: reads
+    tuple val(meta), path("*.fastq.gz"), emit: reads
     path "versions.yml"                                     , emit: versions
 
     when:
@@ -20,13 +20,14 @@ process FILTLONG {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def short_reads = meta.single_end ? "-1 $shortreads" : "-1 ${shortreads[0]} -2 ${shortreads[1]}"
+    def short_reads = !shortreads ? "" : meta.single_end ? "-1 $shortreads" : "-1 ${shortreads[0]} -2 ${shortreads[1]}"
+    if ("$longreads" == "${prefix}.fastq.gz") error "Longread FASTQ input and output names are the same, set prefix in module configuration to disambiguate!"
     """
     filtlong \\
         $short_reads \\
         $args \\
         $longreads \\
-        | gzip -n > ${prefix}_lr_filtlong.fastq.gz
+        | gzip -n > ${prefix}.fastq.gz
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/gamma/gamma/main.nf

@@ -1,6 +1,6 @@
 def VERSION = '2.1' // Version information not provided by tool on CLI
 
-process GAMMA {
+process GAMMA_GAMMA {
     tag "$meta.id"
     label 'process_low'
 
@@ -26,13 +26,24 @@ process GAMMA {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+
     """
+    if [[ ${fasta} == *.gz ]]
+    then
+        FNAME=\$(basename ${fasta} .gz)
+        gunzip -f ${fasta}
+        GAMMA.py \\
+        $args \\
+        "\${FNAME}" \\
+        $db \\
+        $prefix
+    else
         GAMMA.py \\
         $args \\
         $fasta \\
         $db \\
         $prefix
-
+    fi
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         gamma: $VERSION

modules/gamma/gamma/meta.yml

@@ -1,4 +1,4 @@
-name: "gamma"
+name: "gamma_gamma"
 description: Gene Allele Mutation Microbial Assessment
 keywords:
   - gamma
@@ -61,3 +61,4 @@ output:
 authors:
   - "@sateeshperi"
   - "@rastanton"
+  - "@jvhagey"

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/gatk/unifiedgenotyper/main.nf

@@ -0,0 +1,63 @@
+process GATK_UNIFIEDGENOTYPER {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::gatk=3.5" : null)
+    container "${ 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  intervals
+    path  contamination
+    path  dbsnp
+    path  comp
+
+    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 prefix = task.ext.prefix ?: "${meta.id}"
+    def contamination_file = contamination ? "-contaminationFile ${contamination}" : ""
+    def dbsnp_file = dbsnp ? "--dbsnp ${dbsnp}" : ""
+    def comp_file = comp ? "--comp ${comp}" : ""
+    def intervals_file = intervals ? "--intervals ${intervals}" : ""
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK RealignerTargetCreator] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+
+    """
+    gatk3 \\
+        -Xmx${avail_mem}g \\
+        -nt ${task.cpus} \\
+        -T UnifiedGenotyper \\
+        -I ${input} \\
+        -R ${fasta} \\
+        ${contamination_file} \\
+        ${dbsnp_file} \\
+        ${comp_file} \\
+        ${intervals_file} \\
+        -o ${prefix}.vcf \\
+        $args
+
+    gzip -n *.vcf
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk: \$(echo \$(gatk3 --version))
+    END_VERSIONS
+    """
+}

modules/gatk/unifiedgenotyper/meta.yml

@@ -0,0 +1,73 @@
+name: "gatk_unifiedgenotyper"
+keywords:
+  - bam
+  - vcf
+  - variant calling
+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"
+  - intervals:
+      type: file
+      description: Bed file with the genomic regions included in the library (optional)
+      pattern: "*.intervals"
+  - contamination:
+      type: file
+      description: Tab-separated file containing fraction of contamination in sequencing data (per sample) to aggressively remove
+      pattern: "*"
+  - dbsnps:
+      type: file
+      description: VCF file containing known sites (optional)
+      pattern: "*"
+  - comp:
+      type: file
+      description: Comparison VCF file (optional)
+      pattern: "*"
+
+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 containing called variants
+      pattern: "*.vcf.gz"
+
+authors:
+  - "@ilight1542"
+  - "@jfy133"

modules/gatk4/applybqsrspark/main.nf

@@ -2,10 +2,8 @@ process GATK4_APPLYBQSR_SPARK {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1 conda-forge::openjdk=8.0.312" : null)
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+    container 'broadinstitute/gatk:4.2.6.1'
-        '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(bqsr_table), path(intervals)

modules/gatk4/baserecalibratorspark/main.nf

@@ -2,10 +2,8 @@ process GATK4_BASERECALIBRATOR_SPARK {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1 conda-forge::openjdk=8.0.312" : null)
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+    container 'broadinstitute/gatk:4.2.6.1'
-        '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(intervals)

modules/gatk4/calibratedragstrmodel/main.nf

@@ -0,0 +1,51 @@
+process GATK4_CALIBRATEDRAGSTRMODEL {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
+    container "${ 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(bam), path(bam_index), path(intervals)
+    path  fasta
+    path  fasta_fai
+    path  dict
+    path  strtablefile
+
+    output:
+    tuple val(meta), path("*.txt")   , emit: dragstr_model
+    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_command = intervals ? "--intervals $intervals" : ""
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK CalibrateDragstrModel] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+    """
+    gatk --java-options "-Xmx${avail_mem}g" CalibrateDragstrModel \\
+        --input $bam \\
+        --output ${prefix}.txt \\
+        --reference $fasta \\
+        --str-table-path $strtablefile \\
+        --threads $task.cpus \\
+        $intervals_command \\
+        --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/calibratedragstrmodel/meta.yml

@@ -0,0 +1,74 @@
+name: gatk4_calibratedragstrmodel
+description: estimates the parameters for the DRAGstr model
+keywords:
+  - gatk4
+  - bam
+  - cram
+  - sam
+  - calibratedragstrmodel
+tools:
+  - gatk4:
+      description:
+        Genome Analysis Toolkit (GATK4). 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/articles/360057441571-CalibrateDragstrModel-BETA-
+      tool_dev_url: https://github.com/broadinstitute/gatk
+      doi: 10.1158/1538-7445.AM2017-3590
+      licence: ["Apache-2.0"]
+
+input:
+  # Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - bam_index:
+      type: file
+      description: index of the BAM/CRAM/SAM file
+      pattern: "*.{bai,crai,sai}"
+  - intervals:
+      type: file
+      description: BED file or interval list containing regions (optional)
+      pattern: "*.{bed,interval_list}"
+  - fasta:
+      type: file
+      description: The reference FASTA file
+      pattern: "*.{fasta,fa}"
+  - fasta_fai:
+      type: file
+      description: The index of the reference FASTA file
+      pattern: "*.fai"
+  - dict:
+      type: file
+      description: The sequence dictionary of the reference FASTA file
+      pattern: "*.dict"
+  - strtablefile:
+      type: file
+      description: The StrTableFile zip folder of the reference FASTA file
+      pattern: "*.zip"
+
+output:
+  #Only when we have meta
+  - 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"
+  - dragstr_model:
+      type: file
+      description: The DragSTR model
+      pattern: "*.txt"
+
+authors:
+  - "@nvnieuwk"

modules/gatk4/composestrtablefile/main.nf

@@ -0,0 +1,53 @@
+process GATK4_COMPOSESTRTABLEFILE {
+    tag "$fasta"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
+    container "${ 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:
+    path(fasta)
+    path(fasta_fai)
+    path(dict)
+
+    output:
+    path "*.zip"            , emit: str_table
+    path "versions.yml"     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+
+    def avail_mem = 6
+    if (!task.memory) {
+        log.info '[GATK ComposeSTRTableFile] Available memory not known - defaulting to 6GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+    """
+    gatk --java-options "-Xmx${avail_mem}g" ComposeSTRTableFile \\
+        --reference $fasta \\
+        --output ${fasta.baseName}.zip \\
+        --tmp-dir . \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    touch test.zip
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/gatk4/composestrtablefile/meta.yml

@@ -0,0 +1,43 @@
+name: "gatk4_composestrtablefile"
+description: This tool looks for low-complexity STR sequences along the reference that are later used to estimate the Dragstr model during single sample auto calibration CalibrateDragstrModel.
+keywords:
+  - gatk4
+  - composestrtablefile
+tools:
+  - gatk4:
+      description:
+        Genome Analysis Toolkit (GATK4). 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/articles/4405451249819-ComposeSTRTableFile
+      tool_dev_url: https://github.com/broadinstitute/gatk
+      doi: 10.1158/1538-7445.AM2017-3590
+      licence: ["Apache-2.0"]
+
+input:
+  - fasta:
+      type: file
+      description: FASTA reference file
+      pattern: "*.{fasta,fa}"
+  - fasta_fai:
+      type: file
+      description: index of the FASTA reference file
+      pattern: "*.fai"
+  - dict:
+      type: file
+      description: Sequence dictionary of the FASTA reference file
+      pattern: "*.dict"
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - str_table:
+      type: file
+      description: A zipped folder containing the STR table files
+      pattern: "*.zip"
+
+authors:
+  - "@nvnieuwk"

modules/gatk4/haplotypecaller/main.nf

@@ -8,7 +8,7 @@ process GATK4_HAPLOTYPECALLER {
         'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(input), path(input_index), path(intervals)
+    tuple val(meta), path(input), path(input_index), path(intervals), path(dragstr_model)
     path  fasta
     path  fai
     path  dict
@@ -28,6 +28,7 @@ process GATK4_HAPLOTYPECALLER {
     def prefix = task.ext.prefix ?: "${meta.id}"
     def dbsnp_command = dbsnp ? "--dbsnp $dbsnp" : ""
     def interval_command = intervals ? "--intervals $intervals" : ""
+    def dragstr_command = dragstr_model ? "--dragstr-params-path $dragstr_model" : ""
 
     def avail_mem = 3
     if (!task.memory) {
@@ -42,6 +43,7 @@ process GATK4_HAPLOTYPECALLER {
         --reference $fasta \\
         $dbsnp_command \\
         $interval_command \\
+        $dragstr_command \\
         --tmp-dir . \\
         $args
 

modules/gatk4/haplotypecaller/meta.yml

@@ -32,6 +32,10 @@ input:
   - intervals:
       type: file
       description: Bed file with the genomic regions included in the library (optional)
+  - dragstr_model:
+      type: file
+      description: Text file containing the DragSTR model of the used BAM/CRAM file (optional)
+      pattern: "*.txt"
   - fasta:
       type: file
       description: The reference fasta file

modules/gatk4/markduplicatesspark/main.nf

@@ -2,10 +2,8 @@ process GATK4_MARKDUPLICATES_SPARK {
     tag "$meta.id"
     label 'process_high'
 
-    conda (params.enable_conda ? "bioconda::gatk4=4.2.3.0" : null)
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1 conda-forge::openjdk=8.0.312" : null)
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+    container 'broadinstitute/gatk:4.2.6.1'
-        'https://depot.galaxyproject.org/singularity/gatk4:4.2.3.0--hdfd78af_0' :
-        'broadinstitute/gatk:4.2.3.0' }"
 
     input:
     tuple val(meta), path(bam)
@@ -15,6 +13,7 @@ process GATK4_MARKDUPLICATES_SPARK {
 
     output:
     tuple val(meta), path("${prefix}"),     emit: output
+    tuple val(meta), path("*.metrics"),     emit: metrics, optional: true
     path "versions.yml"               ,     emit: versions
 
     when:
@@ -25,6 +24,7 @@ process GATK4_MARKDUPLICATES_SPARK {
     prefix = task.ext.prefix ?: "${meta.id}"
     def input_list = bam.collect{"--input $it"}.join(' ')
 
+
     def avail_mem = 3
     if (!task.memory) {
         log.info '[GATK MarkDuplicatesSpark] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@@ -32,8 +32,6 @@ process GATK4_MARKDUPLICATES_SPARK {
         avail_mem = task.memory.giga
     }
     """
-    export SPARK_USER=spark3
-
     gatk --java-options "-Xmx${avail_mem}g" MarkDuplicatesSpark \\
         $input_list \\
         --output $prefix \\
@@ -45,6 +43,7 @@ process GATK4_MARKDUPLICATES_SPARK {
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+        openjdk: \$(echo \$(java -version 2>&1) | grep version | sed 's/\"//g' | cut -f3 -d ' ')
     END_VERSIONS
     """
 }

modules/gatk4/markduplicatesspark/meta.yml

@@ -58,3 +58,4 @@ authors:
   - "@ajodeh-juma"
   - "@FriederikeHanssen"
   - "@maxulysse"
+  - "@SusiJo"

modules/gatk4/mergevcfs/main.nf

@@ -13,6 +13,7 @@ process GATK4_MERGEVCFS {
 
     output:
     tuple val(meta), path('*.vcf.gz'), emit: vcf
+    tuple val(meta), path("*.tbi")   , emit: tbi
     path  "versions.yml"             , emit: versions
 
     when:

modules/gatk4/mergevcfs/meta.yml

@@ -35,6 +35,11 @@ output:
       type: file
       description: merged vcf file
       pattern: "*.vcf.gz"
+  - tbi:
+      type: file
+      description: index files for the merged vcf files
+      pattern: "*.tbi"
+
   - versions:
       type: file
       description: File containing software versions

modules/gatk4/reblockgvcf/main.nf

@@ -0,0 +1,52 @@
+process GATK4_REBLOCKGVCF {
+    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(gvcf), path(tbi), path(intervals)
+    path fasta
+    path fai
+    path dict
+    path dbsnp
+    path dbsnp_tbi
+
+    output:
+    tuple val(meta), path("*.rb.g.vcf.gz"), path("*.tbi")  , 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 dbsnp_command = dbsnp ? "--dbsnp $dbsnp" : ""
+    def interval_command = intervals ? "--intervals $intervals" : ""
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK ReblockGVCF] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+    """
+    gatk --java-options "-Xmx${avail_mem}g" ReblockGVCF \\
+        --variant $gvcf \\
+        --output ${prefix}.rb.g.vcf.gz \\
+        --reference $fasta \\
+        $dbsnp_command \\
+        $interval_command \\
+        --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/reblockgvcf/meta.yml

@@ -0,0 +1,74 @@
+name: "gatk4_reblockgvcf"
+description: Condenses homRef blocks in a single-sample GVCF
+keywords:
+  - gatk4
+  - reblockgvcf
+  - gvcf
+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 ]
+  - gvcf:
+      type: file
+      description: GVCF file created using HaplotypeCaller using the '-ERC GVCF' or '-ERC BP_RESOLUTION' mode
+      pattern: "*.{vcf,gvcf}.gz"
+  - tbi:
+      type: file
+      description: Index of the GVCF file
+      pattern: "*.tbi"
+  - intervals:
+      type: file
+      description: Bed file with the genomic regions included in the library (optional)
+  - fasta:
+      type: file
+      description: The reference fasta file
+      pattern: "*.fasta"
+  - fai:
+      type: file
+      description: Index of reference fasta file
+      pattern: "fasta.fai"
+  - dict:
+      type: file
+      description: GATK sequence dictionary
+      pattern: "*.dict"
+  - dbsnp:
+      type: file
+      description: VCF file containing known sites (optional)
+  - dbsnp_tbi:
+      type: file
+      description: VCF index of dbsnp (optional)
+
+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"
+  - gvcf:
+      type: file
+      description: Filtered GVCF
+      pattern: "*rb.g.vcf.gz"
+  - tbi:
+      type: file
+      description: Index of the filtered GVCF
+      pattern: "*rb.g.vcf.gz.tbi"
+
+authors:
+  - "@nvnieuwk"

modules/kat/hist/main.nf

@@ -0,0 +1,42 @@
+process KAT_HIST {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::kat=2.4.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/kat:2.4.2--py38hfc5f9d8_2':
+        'quay.io/biocontainers/kat:2.4.2--py38hfc5f9d8_2' }"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*.hist")                   , emit: hist
+    tuple val(meta), path("*.hist.dist_analysis.json"), emit: json
+    tuple val(meta), path("*.png")                    , emit: png           , optional: true
+    tuple val(meta), path("*.ps")                     , emit: ps            , optional: true
+    tuple val(meta), path("*.pdf")                    , emit: pdf           , optional: true
+    tuple val(meta), path("*-hash.jf*")               , emit: jellyfish_hash, 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}"
+    """
+    kat hist \\
+        --threads $task.cpus \\
+        --output_prefix ${prefix}.hist \\
+        $args \\
+        $reads
+
+    ls -l
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kat: \$( kat hist --version | sed 's/kat //' )
+    END_VERSIONS
+    """
+}

modules/kat/hist/meta.yml

@@ -0,0 +1,64 @@
+name: "kat_hist"
+description: Creates a histogram of the number of distinct k-mers having a given frequency.
+keywords:
+  - k-mer
+  - histogram
+  - count
+tools:
+  - "kat":
+      description: "KAT is a suite of tools that analyse jellyfish hashes or sequence files (fasta or fastq) using kmer counts"
+      homepage: https://www.earlham.ac.uk/kat-tools
+      documentation: https://kat.readthedocs.io/en/latest/index.html
+      tool_dev_url: https://github.com/TGAC/KAT
+      doi: http://bioinformatics.oxfordjournals.org/content/early/2016/10/20/bioinformatics.btw663.abstract
+      licence: "['GPL v3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+
+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"
+  - hist:
+      type: file
+      description: KAT histogram of k-mer counts
+      pattern: "*.hist"
+  - json:
+      type: file
+      description: KAT histogram summary of distance analysis
+      pattern: "*.hist.dist_analysis.json"
+  - png:
+      type: file
+      description: KAT plot of k-mer histogram in PNG format
+      pattern: "*.png"
+  - ps:
+      type: file
+      description: KAT plot of k-mer histogram in PS format
+      pattern: "*.ps"
+  - pdf:
+      type: file
+      description: KAT plot of k-mer histogram in PDF format
+      pattern: "*.pdf"
+  - jellyfish_hash:
+      type: file
+      description: Jellyfish hash file
+      pattern: "*-hist.jf*"
+
+authors:
+  - "@mahesh-panchal"

modules/mash/screen/main.nf

@@ -8,8 +8,8 @@ process MASH_SCREEN {
         'quay.io/biocontainers/mash:2.3--he348c14_1' }"
 
     input:
-    tuple val(meta), path(query_sketch)
+    tuple val(meta), path(query)
-    path fastx_db
+    path sequences_sketch
 
     output:
     tuple val(meta), path("*.screen"), emit: screen
@@ -26,8 +26,8 @@ process MASH_SCREEN {
         screen \\
         $args \\
         -p $task.cpus \\
-        $query_sketch \\
+        $sequences_sketch \\
-        $fastx_db \\
+        $query \\
         > ${prefix}.screen
 
     cat <<-END_VERSIONS > versions.yml

modules/mash/screen/meta.yml

@@ -20,13 +20,14 @@ input:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
-  - query_sketch:
+  - query:
       type: file
-      description: MinHash sketch of query sequences
+      description: Query sequences
-      pattern: "*.msh"
+      pattern: "*.fastq.gz"
-  - fastx_db:
+  - sequence_sketch:
       type: file
       description: Sequence files to match against
+      pattern: "*.msh"
 
 output:
   - meta:

modules/mosdepth/main.nf

@@ -10,17 +10,21 @@ process MOSDEPTH {
     input:
     tuple val(meta), path(bam), path(bai)
     path  bed
-    val   window_size
+    path  fasta
 
     output:
     tuple val(meta), path('*.global.dist.txt')      , emit: global_txt
-    tuple val(meta), path('*.region.dist.txt')    , emit: regions_txt , optional:true
     tuple val(meta), path('*.summary.txt')          , emit: summary_txt
-    tuple val(meta), path('*.per-base.d4')        , emit: d4          , optional:true
+    tuple val(meta), path('*.region.dist.txt')      , optional:true, emit: regions_txt
-    tuple val(meta), path('*.per-base.bed.gz')    , emit: per_base_bed, optional:true
+    tuple val(meta), path('*.per-base.d4')          , optional:true, emit: per_base_d4
-    tuple val(meta), path('*.per-base.bed.gz.csi'), emit: per_base_csi, optional:true
+    tuple val(meta), path('*.per-base.bed.gz')      , optional:true, emit: per_base_bed
-    tuple val(meta), path('*.regions.bed.gz')     , emit: regions_bed , optional:true
+    tuple val(meta), path('*.per-base.bed.gz.csi')  , optional:true, emit: per_base_csi
-    tuple val(meta), path('*.regions.bed.gz.csi') , emit: regions_csi , optional:true
+    tuple val(meta), path('*.regions.bed.gz')       , optional:true, emit: regions_bed
+    tuple val(meta), path('*.regions.bed.gz.csi')   , optional:true, emit: regions_csi
+    tuple val(meta), path('*.quantized.bed.gz')     , optional:true, emit: quantized_bed
+    tuple val(meta), path('*.quantized.bed.gz.csi') , optional:true, emit: quantized_csi
+    tuple val(meta), path('*.thresholds.bed.gz')    , optional:true, emit: thresholds_bed
+    tuple val(meta), path('*.thresholds.bed.gz.csi'), optional:true, emit: thresholds_csi
     path  "versions.yml"                            , emit: versions
 
     when:
@@ -29,19 +33,24 @@ process MOSDEPTH {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    if (window_size) {
+    def reference = fasta ? "--fasta ${fasta}" : ""
-        interval = "--by ${window_size}"
+    def interval = bed ? "--by ${bed}" : ""
-    } else if ( bed ) {
+    if (bed && args.contains("--by")) {
-        interval = "--by ${bed}"
+        exit 1, "'--by' can only be specified once when running mosdepth! Either remove input BED file definition or remove '--by' from 'ext.args' definition"
-    } else {
-        interval = ""
     }
+    if (!bed && args.contains("--thresholds")) {
+        exit 1, "'--thresholds' can only be specified in conjunction with '--by'"
+    }
+
     """
     mosdepth \\
+        --threads $task.cpus \\
         $interval \\
+        $reference \\
         $args \\
         $prefix \\
         $bam
+
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         mosdepth: \$(mosdepth --version 2>&1 | sed 's/^.*mosdepth //; s/ .*\$//')
@@ -59,6 +68,10 @@ process MOSDEPTH {
     touch ${prefix}.per-base.bed.gz.csi
     touch ${prefix}.regions.bed.gz
     touch ${prefix}.regions.bed.gz.csi
+    touch ${prefix}.quantized.bed.gz
+    touch ${prefix}.quantized.bed.gz.csi
+    touch ${prefix}.thresholds.bed.gz
+    touch ${prefix}.thresholds.bed.gz.csi
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/mosdepth/meta.yml

@@ -30,10 +30,10 @@ input:
       type: file
       description: BED file with intersected intervals
       pattern: "*.{bed}"
-  - window_size:
+  - fasta:
-      type: integer
+      type: file
-      description: Window size
+      description: Reference genome FASTA file
-      pattern: "[0-9]+"
+      pattern: "*.{fa,fasta}"
 output:
   - meta:
       type: map
@@ -60,6 +60,10 @@ output:
       type: file
       description: Index file for BED file with per-base coverage
       pattern: "*.{per-base.bed.gz.csi}"
+  - per_base_d4:
+      type: file
+      description: D4 file with per-base coverage
+      pattern: "*.{per-base.d4}"
   - regions_bed:
       type: file
       description: BED file with per-region coverage
@@ -68,6 +72,22 @@ output:
       type: file
       description: Index file for BED file with per-region coverage
       pattern: "*.{regions.bed.gz.csi}"
+  - quantized_bed:
+      type: file
+      description: BED file with binned coverage
+      pattern: "*.{quantized.bed.gz}"
+  - quantized_csi:
+      type: file
+      description: Index file for BED file with binned coverage
+      pattern: "*.{quantized.bed.gz.csi}"
+  - thresholds_bed:
+      type: file
+      description: BED file with the number of bases in each region that are covered at or above each threshold
+      pattern: "*.{thresholds.bed.gz}"
+  - thresholds_csi:
+      type: file
+      description: Index file for BED file with threshold coverage
+      pattern: "*.{thresholds.bed.gz.csi}"
   - versions:
       type: file
       description: File containing software versions
@@ -76,3 +96,4 @@ authors:
   - "@joseespinosa"
   - "@drpatelh"
   - "@ramprasadn"
+  - "@matthdsm"

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/picard/addorreplacereadgroups/main.nf

@@ -2,10 +2,10 @@ process PICARD_ADDORREPLACEREADGROUPS {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::picard=2.27.1" : null)
+    conda (params.enable_conda ? "bioconda::picard=2.27.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/picard:2.27.2--hdfd78af_0' :
-        'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }"
+        'quay.io/biocontainers/picard:2.27.2--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam)

modules/picard/cleansam/main.nf

@@ -2,10 +2,10 @@ process PICARD_CLEANSAM {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::picard=2.27.1" : null)
+    conda (params.enable_conda ? "bioconda::picard=2.27.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/picard:2.27.2--hdfd78af_0' :
-        'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }"
+        'quay.io/biocontainers/picard:2.27.2--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam)

modules/picard/collecthsmetrics/main.nf

@@ -2,10 +2,10 @@ process PICARD_COLLECTHSMETRICS {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::picard=2.27.1" : null)
+    conda (params.enable_conda ? "bioconda::picard=2.27.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/picard:2.27.2--hdfd78af_0' :
-        'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }"
+        'quay.io/biocontainers/picard:2.27.2--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam)

modules/picard/collectmultiplemetrics/main.nf

@@ -2,10 +2,10 @@ process PICARD_COLLECTMULTIPLEMETRICS {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::picard=2.27.1" : null)
+    conda (params.enable_conda ? "bioconda::picard=2.27.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/picard:2.27.2--hdfd78af_0' :
-        'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }"
+        'quay.io/biocontainers/picard:2.27.2--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam)

modules/picard/collectwgsmetrics/main.nf

@@ -2,10 +2,10 @@ process PICARD_COLLECTWGSMETRICS {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::picard=2.27.1" : null)
+    conda (params.enable_conda ? "bioconda::picard=2.27.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/picard:2.27.2--hdfd78af_0' :
-        'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }"
+        'quay.io/biocontainers/picard:2.27.2--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam)

modules/picard/createsequencedictionary/main.nf

@@ -2,10 +2,10 @@ process PICARD_CREATESEQUENCEDICTIONARY {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::picard=2.27.1" : null)
+    conda (params.enable_conda ? "bioconda::picard=2.27.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/picard:2.27.2--hdfd78af_0' :
-        'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }"
+        'quay.io/biocontainers/picard:2.27.2--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(fasta)

modules/picard/crosscheckfingerprints/main.nf

@@ -2,10 +2,10 @@ process PICARD_CROSSCHECKFINGERPRINTS {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::picard=2.27.1" : null)
+    conda (params.enable_conda ? "bioconda::picard=2.27.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/picard:2.27.2--hdfd78af_0' :
-        'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }"
+        'quay.io/biocontainers/picard:2.27.2--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(input1)

modules/picard/filtersamreads/main.nf

@@ -2,10 +2,10 @@ process PICARD_FILTERSAMREADS {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::picard=2.27.1" : null)
+    conda (params.enable_conda ? "bioconda::picard=2.27.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/picard:2.27.2--hdfd78af_0' :
-        'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }"
+        'quay.io/biocontainers/picard:2.27.2--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam), path(readlist)

modules/picard/fixmateinformation/main.nf

@@ -2,10 +2,10 @@ process PICARD_FIXMATEINFORMATION {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::picard=2.27.1" : null)
+    conda (params.enable_conda ? "bioconda::picard=2.27.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/picard:2.27.2--hdfd78af_0' :
-        'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }"
+        'quay.io/biocontainers/picard:2.27.2--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam)

modules/picard/liftovervcf/main.nf

@@ -2,10 +2,10 @@ process PICARD_LIFTOVERVCF {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::picard=2.27.1" : null)
+    conda (params.enable_conda ? "bioconda::picard=2.27.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/picard:2.27.2--hdfd78af_0' :
-        'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }"
+        'quay.io/biocontainers/picard:2.27.2--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(input_vcf)

modules/picard/markduplicates/main.nf

@@ -2,10 +2,10 @@ process PICARD_MARKDUPLICATES {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::picard=2.27.1" : null)
+    conda (params.enable_conda ? "bioconda::picard=2.27.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/picard:2.27.2--hdfd78af_0' :
-        'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }"
+        'quay.io/biocontainers/picard:2.27.2--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam)

modules/picard/mergesamfiles/main.nf

@@ -2,10 +2,10 @@ process PICARD_MERGESAMFILES {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::picard=2.27.1" : null)
+    conda (params.enable_conda ? "bioconda::picard=2.27.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/picard:2.27.2--hdfd78af_0' :
-        'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }"
+        'quay.io/biocontainers/picard:2.27.2--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bams)

modules/picard/sortsam/main.nf

@@ -2,10 +2,10 @@ process PICARD_SORTSAM {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::picard=2.27.1" : null)
+    conda (params.enable_conda ? "bioconda::picard=2.27.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/picard:2.27.2--hdfd78af_0' :
-        'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }"
+        'quay.io/biocontainers/picard:2.27.2--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam)

modules/picard/sortvcf/main.nf

@@ -2,10 +2,10 @@ process PICARD_SORTVCF {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::picard=2.27.1" : null)
+    conda (params.enable_conda ? "bioconda::picard=2.27.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/picard:2.27.2--hdfd78af_0' :
-        'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }"
+        'quay.io/biocontainers/picard:2.27.2--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(vcf)

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/snippy/run/main.nf

@@ -0,0 +1,55 @@
+process SNIPPY_RUN {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::snippy=4.6.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/snippy:4.6.0--hdfd78af_2' :
+        'quay.io/biocontainers/snippy:4.6.0--hdfd78af_2' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path reference
+
+    output:
+    tuple val(meta), path("${prefix}/${prefix}.tab")              , emit: tab
+    tuple val(meta), path("${prefix}/${prefix}.csv")              , emit: csv
+    tuple val(meta), path("${prefix}/${prefix}.html")             , emit: html
+    tuple val(meta), path("${prefix}/${prefix}.vcf")              , emit: vcf
+    tuple val(meta), path("${prefix}/${prefix}.bed")              , emit: bed
+    tuple val(meta), path("${prefix}/${prefix}.gff")              , emit: gff
+    tuple val(meta), path("${prefix}/${prefix}.bam")              , emit: bam
+    tuple val(meta), path("${prefix}/${prefix}.bam.bai")          , emit: bai
+    tuple val(meta), path("${prefix}/${prefix}.log")              , emit: log
+    tuple val(meta), path("${prefix}/${prefix}.aligned.fa")       , emit: aligned_fa
+    tuple val(meta), path("${prefix}/${prefix}.consensus.fa")     , emit: consensus_fa
+    tuple val(meta), path("${prefix}/${prefix}.consensus.subs.fa"), emit: consensus_subs_fa
+    tuple val(meta), path("${prefix}/${prefix}.raw.vcf")          , emit: raw_vcf
+    tuple val(meta), path("${prefix}/${prefix}.filt.vcf")         , emit: filt_vcf
+    tuple val(meta), path("${prefix}/${prefix}.vcf.gz")           , emit: vcf_gz
+    tuple val(meta), path("${prefix}/${prefix}.vcf.gz.csi")       , emit: vcf_csi
+    tuple val(meta), path("${prefix}/${prefix}.txt")              , emit: txt
+    path "versions.yml"                                           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    def read_inputs = meta.single_end ? "--se ${reads[0]}" : "--R1 ${reads[0]} --R2 ${reads[1]}"
+    """
+    snippy \\
+        $args \\
+        --cpus $task.cpus \\
+        --outdir $prefix \\
+        --reference $reference \\
+        --prefix $prefix \\
+        $read_inputs
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        snippy: \$(echo \$(snippy --version 2>&1) | sed 's/snippy //')
+    END_VERSIONS
+    """
+}

modules/snippy/run/meta.yml

@@ -0,0 +1,110 @@
+name: snippy_run
+description: Rapid haploid variant calling
+keywords:
+  - variant
+  - fastq
+  - bacteria
+tools:
+  - snippy:
+      description: "Rapid bacterial SNP calling and core genome alignments"
+      homepage: "https://github.com/tseemann/snippy"
+      documentation: "https://github.com/tseemann/snippy"
+      tool_dev_url: "https://github.com/tseemann/snippy"
+      doi: ""
+      licence: "['GPL v2']"
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+      pattern: "*.{fq,fastq,fq.gz,fastq.gz}"
+  - index:
+      type: file
+      description: Reference genome in GenBank (preferred) or FASTA format
+      pattern: "*.{gbk,gbk.gz,fa,fa.gz}"
+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"
+  - tab:
+      type: file
+      description: A simple tab-separated summary of all the variants
+      pattern: "*.tab"
+  - csv:
+      type: file
+      description: A comma-separated version of the .tab file
+      pattern: "*.csv"
+  - html:
+      type: file
+      description: A HTML version of the .tab file
+      pattern: "*.html"
+  - vcf:
+      type: file
+      description: The final annotated variants in VCF format
+      pattern: "*.vcf"
+  - bed:
+      type: file
+      description: The variants in BED format
+      pattern: "*.bed"
+  - gff:
+      type: file
+      description: The variants in GFF3 format
+      pattern: "*.gff"
+  - bam:
+      type: file
+      description: The alignments in BAM format. Includes unmapped, multimapping reads. Excludes duplicates.
+      pattern: "*.bam"
+  - bai:
+      type: file
+      description: Index for the .bam file
+      pattern: "*.bam.bai"
+  - log:
+      type: file
+      description: A log file with the commands run and their outputs
+      pattern: "*.log"
+  - aligned_fa:
+      type: file
+      description: A version of the reference but with - at position with depth=0 and N for 0 < depth < --mincov (does not have variants)
+      pattern: "*.aligned.fa"
+  - consensus_fa:
+      type: file
+      description: A version of the reference genome with all variants instantiated
+      pattern: "*.consensus.fa"
+  - consensus_subs_fa:
+      type: file
+      description: A version of the reference genome with only substitution variants instantiated
+      pattern: "*.consensus.subs.fa"
+  - raw_vcf:
+      type: file
+      description: The unfiltered variant calls from Freebayes
+      pattern: "*.raw.vcf"
+  - filt_vcf:
+      type: file
+      description: The filtered variant calls from Freebayes
+      pattern: "*.filt.vcf"
+  - vcf_gz:
+      type: file
+      description: Compressed .vcf file via BGZIP
+      pattern: "*.vcf.gz"
+  - vcf_csi:
+      type: file
+      description: Index for the .vcf.gz via bcftools index
+      pattern: "*.vcf.gz.csi"
+  - txt:
+      type: file
+      description: Tab-separated columnar list of statistics
+      pattern: "*.txt"
+authors:
+  - "@rpetit3"

modules/star/align/main.nf

@@ -2,11 +2,10 @@ process STAR_ALIGN {
     tag "$meta.id"
     label 'process_high'
 
-    // Note: 2.7X indices incompatible with AWS iGenomes.
+    conda (params.enable_conda ? "bioconda::star=2.7.10a bioconda::samtools=1.15.1 conda-forge::gawk=5.1.0" : null)
-    conda (params.enable_conda ? 'bioconda::star=2.7.9a' : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/star:2.7.9a--h9ee0642_0' :
+        'https://depot.galaxyproject.org/singularity/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:afaaa4c6f5b308b4b6aa2dd8e99e1466b2a6b0cd-0' :
-        'quay.io/biocontainers/star:2.7.9a--h9ee0642_0' }"
+        'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:afaaa4c6f5b308b4b6aa2dd8e99e1466b2a6b0cd-0' }"
 
     input:
     tuple val(meta), path(reads)
@@ -67,6 +66,8 @@ process STAR_ALIGN {
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         star: \$(STAR --version | sed -e "s/STAR_//g")
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+        gawk: \$(echo \$(gawk --version 2>&1) | sed 's/^.*GNU Awk //; s/, .*\$//')
     END_VERSIONS
     """
 }

modules/star/genomegenerate/main.nf

@@ -2,11 +2,10 @@ process STAR_GENOMEGENERATE {
     tag "$fasta"
     label 'process_high'
 
-    // Note: 2.7X indices incompatible with AWS iGenomes.
+    conda (params.enable_conda ? "bioconda::star=2.7.10a bioconda::samtools=1.15.1 conda-forge::gawk=5.1.0" : null)
-    conda (params.enable_conda ? "bioconda::star=2.7.9a bioconda::samtools=1.15.1 conda-forge::gawk=5.1.0" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1c4c32d87798d425c970ececfbadd155e7560277-0' :
+        'https://depot.galaxyproject.org/singularity/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:afaaa4c6f5b308b4b6aa2dd8e99e1466b2a6b0cd-0' :
-        'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1c4c32d87798d425c970ececfbadd155e7560277-0' }"
+        'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:afaaa4c6f5b308b4b6aa2dd8e99e1466b2a6b0cd-0' }"
 
     input:
     path fasta
@@ -14,7 +13,7 @@ process STAR_GENOMEGENERATE {
 
     output:
     path "star"        , emit: index
-    path "versions.yml" , emit: versions
+    path "versions.yml", emit: versions
 
     when:
     task.ext.when == null || task.ext.when

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

modules/untar/main.nf

@@ -21,12 +21,18 @@ process UNTAR {
     def args  = task.ext.args ?: ''
     def args2 = task.ext.args2 ?: ''
     untar     = archive.toString() - '.tar.gz'
+
     """
+    mkdir output
+
     tar \\
+        -C output --strip-components 1 \\
         -xzvf \\
         $args \\
         $archive \\
-        $args2 \\
+        $args2
+
+    mv output ${untar}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/vsearch/usearchglobal/main.nf

@@ -0,0 +1,67 @@
+process VSEARCH_USEARCHGLOBAL {
+    tag "${meta.id}"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::vsearch=2.21.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/vsearch:2.21.1--h95f258a_0':
+        'quay.io/biocontainers/vsearch:2.21.1--h95f258a_0' }"
+
+    input:
+    tuple val(meta), path(queryfasta)
+    path db
+    val idcutoff
+    val outoption
+    val user_columns
+
+    output:
+    tuple val(meta), path('*.aln')    , optional: true, emit: aln
+    tuple val(meta), path('*.biom')   , optional: true, emit: biom
+    tuple val(meta), path('*.lca')    , optional: true, emit: lca
+    tuple val(meta), path('*.mothur') , optional: true, emit: mothur
+    tuple val(meta), path('*.otu')    , optional: true, emit: otu
+    tuple val(meta), path('*.sam')    , optional: true, emit: sam
+    tuple val(meta), path('*.tsv')    , optional: true, emit: tsv
+    tuple val(meta), path('*.txt')    , optional: true, emit: txt
+    tuple val(meta), path('*.uc')     , optional: true, emit: uc
+    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 columns = user_columns ? "--userfields ${user_columns}" : ''
+    switch ( outoption ) {
+        case "alnout": outfmt = "--alnout"; out_ext = 'aln'; break
+        case "biomout": outfmt = "--biomout"; out_ext = 'biom'; break
+        case "blast6out": outfmt = "--blast6out"; out_ext = 'txt'; break
+        case "mothur_shared_out": outfmt = "--mothur_shared_out"; out_ext = 'mothur'; break
+        case "otutabout": outfmt = "--otutabout"; out_ext = 'otu'; break
+        case "samout": outfmt = "--samout"; out_ext = 'sam'; break
+        case "uc": outfmt = "--uc"; out_ext = 'uc'; break
+        case "userout": outfmt = "--userout"; out_ext = 'tsv'; break
+        case "lcaout": outfmt = "--lcaout"; out_ext = 'lca'; break
+        default:
+            outfmt = "--alnout";
+            out_ext = 'aln';
+            log.warn("Unknown output file format provided (${outoption}): selecting pairwise alignments (alnout)");
+            break
+    }
+    """
+    vsearch \\
+        --usearch_global $queryfasta \\
+        --db $db \\
+        --id $idcutoff \\
+        --threads $task.cpus \\
+        $args \\
+        ${columns} \\
+        ${outfmt} ${prefix}.${out_ext}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        vsearch: \$(vsearch --version 2>&1 | head -n 1 | sed 's/vsearch //g' | sed 's/,.*//g' | sed 's/^v//' | sed 's/_.*//')
+    END_VERSIONS
+    """
+}

modules/vsearch/usearchglobal/meta.yml

@@ -0,0 +1,83 @@
+name: "vsearch_usearchglobal"
+description: Compare target sequences to fasta-formatted query sequences using global pairwise alignment.
+keywords:
+  - vsearch
+  - usearch
+  - alignment
+  - fasta
+tools:
+  - "vsearch":
+      description: "VSEARCH is a versatile open-source tool for microbiome analysis, including chimera detection, clustering, dereplication and rereplication, extraction, FASTA/FASTQ/SFF file processing, masking, orienting, pair-wise alignment, restriction site cutting, searching, shuffling, sorting, subsampling, and taxonomic classification of amplicon sequences for metagenomics, genomics, and population genetics. (USEARCH alternative)"
+      homepage: "https://github.com/torognes/vsearch"
+      documentation: "None"
+      tool_dev_url: "https://github.com/torognes/vsearch"
+      doi: "doi: 10.7717/peerj.2584"
+      licence: "['GPL v3-or-later OR BSD-2-clause']"
+
+input:
+  - meta:
+      type: map
+      description: Groovy Map containing sample information e.g. [ id:'test' ]
+  - queryfasta:
+      type: file
+      description: Query sequences in FASTA format
+      pattern: "*.{fasta,fa,fna,faa}"
+  - db:
+      type: file
+      description: Reference database file in FASTA or UDB format
+      pattern: "*"
+  - idcutoff:
+      type: real
+      description: Reject the sequence match if the pairwise identity is lower than the given id cutoff value (value ranging from 0.0 to 1.0 included)
+  - outoption:
+      type: string
+      description: Specify the type of output file to be generated by selecting one of the vsearch output file options
+      pattern: "alnout|biomout|blast6out|mothur_shared_out|otutabout|samout|uc|userout|lcaout"
+  - user_columns:
+      type: string
+      description: If using the `userout` option, specify which columns to include in output, with fields separated with `+` (e.g. query+target+id). See USEARCH manual for valid options. For other output options, use an empty string.
+
+output:
+  - aln:
+      type: file
+      description: Results in pairwise alignment format
+      pattern: "*.{aln}"
+  - biom:
+      type: file
+      description: Results in an OTU table in the biom version 1.0 file format
+      pattern: "*.{biom}"
+  - lca:
+      type: file
+      description: Last common ancestor (LCA) information about the hits of each query in tab-separated format
+      pattern: "*.{lca}"
+  - mothur:
+      type: file
+      description: Results in an OTU table in the mothur ’shared’ tab-separated plain text file format
+      pattern: "*.{mothur}"
+  - otu:
+      type: file
+      description: Results in an OTU table in the classic tab-separated plain text format
+      pattern: "*.{otu}"
+  - sam:
+      type: file
+      description: Results written in sam format
+      pattern: "*.{sam}"
+  - tsv:
+      type: file
+      description: Results in tab-separated output, columns defined by user
+      pattern: "*.{tsv}"
+  - txt:
+      type: file
+      description: Tab delimited results in blast-like tabular format
+      pattern: "*.{txt}"
+  - uc:
+      type: file
+      description: Tab delimited results in a uclust-like format with 10 columns
+      pattern: "*.{uc}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@jtangrot"

tests/config/pytest_modules.yml

@@ -166,6 +166,10 @@ bcftools/reheader:
   - modules/bcftools/reheader/**
   - tests/modules/bcftools/reheader/**
 
+bcftools/roh:
+  - modules/bcftools/roh/**
+  - tests/modules/bcftools/roh/**
+
 bcftools/sort:
   - modules/bcftools/sort/**
   - tests/modules/bcftools/sort/**
@@ -707,9 +711,21 @@ freebayes:
   - modules/freebayes/**
   - tests/modules/freebayes/**
 
-gamma:
+gamma/gamma:
-  - modules/gamma/**
+  - modules/gamma/gamma/**
-  - tests/modules/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/**
 
 gatk4/applybqsr:
   - modules/gatk4/applybqsr/**
@@ -739,6 +755,10 @@ gatk4/calculatecontamination:
   - modules/gatk4/calculatecontamination/**
   - tests/modules/gatk4/calculatecontamination/**
 
+gatk4/calibratedragstrmodel:
+  - modules/gatk4/calibratedragstrmodel/**
+  - tests/modules/gatk4/calibratedragstrmodel/**
+
 gatk4/cnnscorevariants:
   - modules/gatk4/cnnscorevariants/**
   - tests/modules/gatk4/cnnscorevariants/**
@@ -747,6 +767,10 @@ gatk4/combinegvcfs:
   - modules/gatk4/combinegvcfs/**
   - tests/modules/gatk4/combinegvcfs/**
 
+gatk4/composestrtablefile:
+  - modules/gatk4/composestrtablefile/**
+  - tests/modules/gatk4/composestrtablefile/**
+
 gatk4/createsequencedictionary:
   - modules/gatk4/createsequencedictionary/**
   - tests/modules/gatk4/createsequencedictionary/**
@@ -835,6 +859,10 @@ gatk4/mutect2:
   - modules/gatk4/mutect2/**
   - tests/modules/gatk4/mutect2/**
 
+gatk4/reblockgvcf:
+  - modules/gatk4/reblockgvcf/**
+  - tests/modules/gatk4/reblockgvcf/**
+
 gatk4/revertsam:
   - modules/gatk4/revertsam/**
   - tests/modules/gatk4/revertsam/**
@@ -1089,6 +1117,10 @@ kallistobustools/ref:
   - modules/kallistobustools/ref/**
   - tests/modules/kallistobustools/ref/**
 
+kat/hist:
+  - modules/kat/hist/**
+  - tests/modules/kat/hist/**
+
 khmer/normalizebymedian:
   - modules/khmer/normalizebymedian/**
   - tests/modules/khmer/normalizebymedian/**
@@ -1627,6 +1659,10 @@ rgi/main:
   - modules/rgi/main/**
   - tests/modules/rgi/main/**
 
+rhocall/annotate:
+  - modules/rhocall/annotate/**
+  - tests/modules/rhocall/annotate/**
+
 rmarkdownnotebook:
   - modules/rmarkdownnotebook/**
   - tests/modules/rmarkdownnotebook/**
@@ -1847,6 +1883,10 @@ snapaligner/index:
   - modules/snapaligner/index/**
   - tests/modules/snapaligner/index/**
 
+snippy/run:
+  - modules/snippy/run/**
+  - tests/modules/snippy/run/**
+
 snpdists:
   - modules/snpdists/**
   - tests/modules/snpdists/**
@@ -2048,6 +2088,10 @@ vcftools:
   - modules/vcftools/**
   - tests/modules/vcftools/**
 
+vsearch/usearchglobal:
+  - modules/vsearch/usearchglobal/**
+  - tests/modules/vsearch/usearchglobal/**
+
 yara/index:
   - modules/yara/index/**
   - tests/modules/yara/index/**

tests/config/test_data.config

@@ -23,6 +23,8 @@ params {
                 test_bed12                                     = "${test_data_dir}/genomics/sarscov2/genome/bed/test.bed12"
                 baits_bed                                      = "${test_data_dir}/genomics/sarscov2/genome/bed/baits.bed"
 
+                reference_cnn                                  = "${test_data_dir}/genomics/sarscov2/genome/cnn/reference.cnn"
+
                 kraken2                                        = "${test_data_dir}/genomics/sarscov2/genome/db/kraken2"
                 kraken2_tar_gz                                 = "${test_data_dir}/genomics/sarscov2/genome/db/kraken2.tar.gz"
 
@@ -121,6 +123,7 @@ params {
                 genome_elfasta                                 = "${test_data_dir}/genomics/homo_sapiens/genome/genome.elfasta"
                 genome_fasta                                   = "${test_data_dir}/genomics/homo_sapiens/genome/genome.fasta"
                 genome_fasta_fai                               = "${test_data_dir}/genomics/homo_sapiens/genome/genome.fasta.fai"
+                genome_strtablefile                            = "${test_data_dir}/genomics/homo_sapiens/genome/genome_strtablefile.zip"
                 genome_dict                                    = "${test_data_dir}/genomics/homo_sapiens/genome/genome.dict"
                 genome_gff3                                    = "${test_data_dir}/genomics/homo_sapiens/genome/genome.gff3"
                 genome_gtf                                     = "${test_data_dir}/genomics/homo_sapiens/genome/genome.gtf"
@@ -146,6 +149,7 @@ params {
                 genome_21_multi_interval_bed_gz                = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed.gz"
                 genome_21_multi_interval_bed_gz_tbi            = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed.gz.tbi"
                 genome_21_chromosomes_dir                      = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/chromosomes.tar.gz"
+                genome_21_reference_cnn                        = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/reference_chr21.cnn"
 
                 dbsnp_146_hg38_elsites                         = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.elsites"
                 dbsnp_146_hg38_vcf_gz                          = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
@@ -263,6 +267,8 @@ params {
                 test_pileups_table                             = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.pileups.table"
                 test2_pileups_table                            = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.pileups.table"
 
+                test_paired_end_sorted_dragstrmodel            = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_paired_end_sorted_dragstrmodel.txt"
+
                 test_genomicsdb_tar_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_genomicsdb.tar.gz"
                 test_pon_genomicsdb_tar_gz                     = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_pon_genomicsdb.tar.gz"
 
@@ -324,6 +330,8 @@ params {
                 test_sv_vcf                                   =  "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/sv_query.vcf.gz"
 
                 test_pytor                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/pytor/test.pytor"
+
+                test_flowcell                                 = "${test_data_dir}/genomics/homo_sapiens/illumina/bcl/flowcell.tar.gz"
             }
             'pacbio' {
                 primers                         = "${test_data_dir}/genomics/homo_sapiens/pacbio/fasta/primers.fasta"
@@ -416,9 +424,6 @@ params {
             'txt' {
                 hello                           = "${test_data_dir}/generic/txt/hello.txt"
             }
-            'cnn' {
-                reference                       = "${test_data_dir}/generic/cnn/reference.cnn"
-            }
             'cooler'{
                 test_pairix_pair_gz             = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.GM12878-MboI.pairs.subsample.blksrt.txt.gz"
                 test_pairix_pair_gz_px2         = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.GM12878-MboI.pairs.subsample.blksrt.txt.gz.px2"

tests/modules/bcftools/concat/main.nf

@@ -4,13 +4,25 @@ nextflow.enable.dsl = 2
 
 include { BCFTOOLS_CONCAT } from '../../../../modules/bcftools/concat/main.nf'
 
-workflow test_bcftools_concat {
+workflow test_bcftools_concat_tbi {
     
     input = [ [ id:'test3' ], // meta map
               [ file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
-                file(params.test_data['sarscov2']['illumina']['test2_vcf_gz'], checkIfExists: true) ]
+                file(params.test_data['sarscov2']['illumina']['test2_vcf_gz'], checkIfExists: true) ],
+              [ file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test2_vcf_gz_tbi'], checkIfExists: true) ]
+            ]
+
+    BCFTOOLS_CONCAT ( input )
+}
+
+workflow test_bcftools_concat_no_tbi {
+    
+    input = [ [ id:'test3' ], // meta map
+              [ file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test2_vcf_gz'], checkIfExists: true) ],
+              []
             ]
 
-
     BCFTOOLS_CONCAT ( input )
 }

tests/modules/bcftools/concat/test.yml

@@ -1,8 +1,17 @@
-- name: bcftools concat test_bcftools_concat
+- name: bcftools concat test_bcftools_concat_tbi
-  command: nextflow run ./tests/modules/bcftools/concat -entry test_bcftools_concat -c ./tests/config/nextflow.config -c ./tests/modules/bcftools/concat/nextflow.config
+  command: nextflow run ./tests/modules/bcftools/concat -entry test_bcftools_concat_tbi -c ./tests/config/nextflow.config  -c ./tests/modules/bcftools/concat/nextflow.config
   tags:
-    - bcftools/concat
     - bcftools
+    - bcftools/concat
+  files:
+    - path: output/bcftools/test3.vcf.gz
+      md5sum: 35c88bfaad20101062e98beb217d7137
+
+- name: bcftools concat test_bcftools_concat_no_tbi
+  command: nextflow run ./tests/modules/bcftools/concat -entry test_bcftools_concat_no_tbi -c ./tests/config/nextflow.config  -c ./tests/modules/bcftools/concat/nextflow.config
+  tags:
+    - bcftools
+    - bcftools/concat
   files:
     - path: output/bcftools/test3.vcf.gz
       md5sum: 35c88bfaad20101062e98beb217d7137

tests/modules/bcftools/roh/main.nf

@@ -0,0 +1,35 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BCFTOOLS_ROH } from '../../../../modules/bcftools/roh/main.nf'
+
+workflow test_bcftools_roh {
+
+    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 )
+}
+
+workflow test_bcftools_roh_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 )
+}

tests/modules/bcftools/roh/nextflow.config

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

tests/modules/bcftools/roh/test.yml

@@ -0,0 +1,17 @@
+- name: "bcftools roh"
+  command: nextflow run ./tests/modules/bcftools/roh -entry test_bcftools_roh -c ./tests/config/nextflow.config -c ./tests/modules/bcftools/roh/nextflow.config
+  tags:
+    - "bcftools"
+    - "bcftools/roh"
+  files:
+    - path: "output/bcftools/test.roh"
+    - path: "output/bcftools/versions.yml"
+
+- name: "bcftools roh stub"
+  command: nextflow run ./tests/modules/bcftools/roh -entry test_bcftools_roh_stub -c ./tests/config/nextflow.config -c ./tests/modules/bcftools/roh/nextflow.config
+  tags:
+    - "bcftools"
+    - "bcftools/roh"
+  files:
+    - path: "output/bcftools/test.roh"
+    - path: "output/bcftools/versions.yml"

tests/modules/cnvkit/batch/main.nf

@@ -5,8 +5,9 @@ nextflow.enable.dsl = 2
 include { CNVKIT_BATCH as CNVKIT_HYBRID    } from '../../../../modules/cnvkit/batch/main.nf'
 include { CNVKIT_BATCH as CNVKIT_WGS       } from '../../../../modules/cnvkit/batch/main.nf'
 include { CNVKIT_BATCH as CNVKIT_TUMORONLY } from '../../../../modules/cnvkit/batch/main.nf'
+include { CNVKIT_BATCH as CNVKIT_GERMLINE } from '../../../../modules/cnvkit/batch/main.nf'
 
-workflow test_cnvkit_hybrid {
+workflow test_cnvkit_hybrid_somatic {
 
     input = [
         [ id:'test' ], // meta map
@@ -16,10 +17,10 @@ workflow test_cnvkit_hybrid {
     fasta   = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
     targets = file(params.test_data['sarscov2']['genome']['baits_bed'], checkIfExists: true)
 
-    CNVKIT_HYBRID ( input, fasta, targets, [] )
+    CNVKIT_HYBRID ( input, fasta, [], targets, [] )
 }
 
-workflow test_cnvkit_wgs {
+workflow test_cnvkit_wgs_somatic {
 
     input = [
         [ id:'test'], // meta map
@@ -28,10 +29,10 @@ workflow test_cnvkit_wgs {
     ]
     fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
 
-    CNVKIT_WGS ( input, fasta, [], [] )
+    CNVKIT_WGS ( input, fasta, [], [], [] )
 }
 
-workflow test_cnvkit_cram {
+workflow test_cnvkit_cram_wgs_somatic {
 
     input = [
         [ id:'test'], // meta map
@@ -39,31 +40,60 @@ workflow test_cnvkit_cram {
         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)
+    fasta_fai     = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
 
-    CNVKIT_WGS ( input, fasta, [], [] )
+    CNVKIT_WGS ( input, fasta, fasta_fai, [], [] )
 }
 
-workflow test_cnvkit_tumoronly {
+
+workflow test_cnvkit_tumoronly_hybrid_bam {
 
     input = [
         [ id:'test'], // 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_recalibrated_sorted_bam'], checkIfExists: true),
         []
     ]
-    reference = file(params.test_data['generic']['cnn']['reference'], checkIfExists: true)
+    reference = file(params.test_data['homo_sapiens']['genome']['genome_21_reference_cnn'], checkIfExists: true)
 
-    CNVKIT_TUMORONLY ( input, [], [], reference )
+    CNVKIT_TUMORONLY ( input, [], [],  [], reference )
 }
 
-workflow test_cnvkit_tumoronly_cram {
+workflow test_cnvkit_tumoronly_hybrid_cram {
 
     input = [
         [ id:'test'], // meta map
-        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_cram'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_cram'], checkIfExists: true),
         []
     ]
     fasta     = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
-    reference = file(params.test_data['generic']['cnn']['reference'], checkIfExists: true)
+    reference = file(params.test_data['homo_sapiens']['genome']['genome_21_reference_cnn'], checkIfExists: true)
 
-    CNVKIT_TUMORONLY ( input, fasta, [], reference )
+    CNVKIT_TUMORONLY ( input, fasta, [], [], reference )
+}
+
+workflow test_cnvkit_germline_hybrid_cram {
+
+    input = [
+        [ id:'test'], // meta map
+        [],
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_cram'], checkIfExists: true)
+    ]
+    fasta     = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
+    fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
+    targets   = file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
+
+    CNVKIT_GERMLINE ( input, fasta, fasta_fai, targets,  [])
+}
+
+workflow test_cnvkit_germline_hybrid_bam {
+
+    input = [
+        [ id:'test'], // meta map
+        [],
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_bam'], checkIfExists: true)
+    ]
+    fasta     = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
+    targets   = file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
+
+    CNVKIT_GERMLINE ( input, fasta, [], targets,  [])
 }

tests/modules/cnvkit/batch/test.yml

@@ -1,5 +1,5 @@
-- name: cnvkit batch test_cnvkit_hybrid
+- name: cnvkit batch test_cnvkit_hybrid_somatic
-  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_hybrid -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
+  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_hybrid_somatic -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
   tags:
     - cnvkit
     - cnvkit/batch
@@ -26,8 +26,8 @@
     - path: output/cnvkit/test.single_end.sorted.targetcoverage.cnn
       md5sum: aa8a018b1d4d1e688c9f9f6ae01bf4d7
 
-- name: cnvkit batch test_cnvkit_wgs
+- name: cnvkit batch test_cnvkit_wgs_somatic
-  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_wgs -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
+  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_wgs_somatic -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
   tags:
     - cnvkit
     - cnvkit/batch
@@ -56,8 +56,8 @@
     - path: output/cnvkit/test2.paired_end.sorted.targetcoverage.cnn
       md5sum: 6ae6b3fce7299eedca6133d911c38fe1
 
-- name: cnvkit batch test_cnvkit_cram
+- name: cnvkit batch test_cnvkit_cram_wgs_somatic
-  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_cram -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
+  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_cram_wgs_somatic -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
   tags:
     - cnvkit
     - cnvkit/batch
@@ -86,22 +86,98 @@
     - path: output/cnvkit/test2.paired_end.sorted.targetcoverage.cnn
       md5sum: 6ae6b3fce7299eedca6133d911c38fe1
 
-- name: cnvkit batch test_cnvkit_tumoronly
+- name: cnvkit batch test_cnvkit_tumoronly_hybrid_bam
-  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_tumoronly -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
+  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_tumoronly_hybrid_bam -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
   tags:
     - cnvkit
     - cnvkit/batch
   files:
-    - path: output/cnvkit/reference.antitarget-tmp.bed
+    - path: output/cnvkit/reference_chr21.antitarget-tmp.bed
-    - path: output/cnvkit/reference.target-tmp.bed
+      md5sum: 3d4d20f9f23b39970865d29ef239d20b
-      md5sum: 26d25ff2d6c45b6d92169b3559c6acdb
+    - path: output/cnvkit/reference_chr21.target-tmp.bed
+      md5sum: 657b25dbda8516624efa8cb2cf3716ca
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.antitargetcoverage.cnn
+      md5sum: 067115082c4af4b64d58c0dc3a3642e4
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.bintest.cns
+      md5sum: f6adc75a0a86b7a921eca1b79a394cb0
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.call.cns
+      md5sum: f7caeca04aba28b125ce26b511f42afb
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.cnr
+      md5sum: d9bdb71ce807051369577ee7f807a40c
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.cns
+      md5sum: 2b56aac606ba6183d018b30ca58afcec
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.targetcoverage.cnn
+      md5sum: e6d0190c1c37ce6e41f76ca5b24ccca3
 
-- name: cnvkit batch test_cnvkit_tumoronly_cram
+- name: cnvkit batch test_cnvkit_tumoronly_hybrid_cram
-  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_tumoronly_cram -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
+  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_tumoronly_hybrid_cram -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
   tags:
     - cnvkit
     - cnvkit/batch
   files:
-    - path: output/cnvkit/reference.antitarget-tmp.bed
+    - path: output/cnvkit/reference_chr21.antitarget-tmp.bed
-    - path: output/cnvkit/reference.target-tmp.bed
+      md5sum: 3d4d20f9f23b39970865d29ef239d20b
-      md5sum: 26d25ff2d6c45b6d92169b3559c6acdb
+    - path: output/cnvkit/reference_chr21.target-tmp.bed
+      md5sum: 657b25dbda8516624efa8cb2cf3716ca
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.antitargetcoverage.cnn
+      md5sum: 067115082c4af4b64d58c0dc3a3642e4
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.bintest.cns
+      md5sum: f6adc75a0a86b7a921eca1b79a394cb0
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.call.cns
+      md5sum: f7caeca04aba28b125ce26b511f42afb
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.cnr
+      md5sum: d9bdb71ce807051369577ee7f807a40c
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.cns
+      md5sum: 2b56aac606ba6183d018b30ca58afcec
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.targetcoverage.cnn
+      md5sum: e6d0190c1c37ce6e41f76ca5b24ccca3
+
+- name: cnvkit batch test_cnvkit_germline_hybrid_cram
+  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_germline_hybrid_cram -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
+  tags:
+    - cnvkit
+    - cnvkit/batch
+  files:
+    - path: output/cnvkit/multi_intervals.antitarget.bed
+      md5sum: 3d4d20f9f23b39970865d29ef239d20b
+    - path: output/cnvkit/multi_intervals.target.bed
+      md5sum: 86d30493bb2e619a93f4ebc2923d29f3
+    - path: output/cnvkit/reference.cnn
+      md5sum: a09ee4be5dda1cf0f68073bdb3aad8ec
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.antitargetcoverage.cnn
+      md5sum: 067115082c4af4b64d58c0dc3a3642e4
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.bintest.cns
+      md5sum: 68b62b75cd91b2ffe5633686fb943490
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.call.cns
+      md5sum: df196edd72613c59186f4d87df3dc4a4
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.cnr
+      md5sum: 3b4fc0cc73be78f978cfe2422470753e
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.cns
+      md5sum: 4e67451dbcb6601fc3fa5dd7e570f1d4
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.targetcoverage.cnn
+      md5sum: b4a49faf170e436ec32dcc21ccc3ce8f
+
+- name: cnvkit batch test_cnvkit_germline_hybrid_bam
+  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_germline_hybrid_bam -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
+  tags:
+    - cnvkit
+    - cnvkit/batch
+  files:
+    - path: output/cnvkit/multi_intervals.antitarget.bed
+      md5sum: 3d4d20f9f23b39970865d29ef239d20b
+    - path: output/cnvkit/multi_intervals.target.bed
+      md5sum: 86d30493bb2e619a93f4ebc2923d29f3
+    - path: output/cnvkit/reference.cnn
+      md5sum: a09ee4be5dda1cf0f68073bdb3aad8ec
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.antitargetcoverage.cnn
+      md5sum: 067115082c4af4b64d58c0dc3a3642e4
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.bintest.cns
+      md5sum: 68b62b75cd91b2ffe5633686fb943490
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.call.cns
+      md5sum: df196edd72613c59186f4d87df3dc4a4
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.cnr
+      md5sum: 3b4fc0cc73be78f978cfe2422470753e
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.cns
+      md5sum: 4e67451dbcb6601fc3fa5dd7e570f1d4
+    - path: output/cnvkit/test2.paired_end.recalibrated.sorted.targetcoverage.cnn
+      md5sum: b4a49faf170e436ec32dcc21ccc3ce8f

tests/modules/cnvkit/reference/test.yml

@@ -4,5 +4,5 @@
     - cnvkit/reference
     - cnvkit
   files:
-    - path: output/cnvkit/reference.cnn
+    - path: output/cnvkit/multi_intervals.reference.cnn
       md5sum: 7c4a7902f5ab101b1f9d6038d331b3d9

tests/modules/deeptools/bamcoverage/main.nf

@@ -12,7 +12,7 @@ workflow test_deeptools_bamcoverage_bam {
           file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)
         ]
 
-    DEEPTOOLS_BAMCOVERAGE ( input )
+    DEEPTOOLS_BAMCOVERAGE ( input, [], [] )
 }
 
 workflow test_deeptools_bamcoverage_cram {
@@ -22,6 +22,20 @@ workflow test_deeptools_bamcoverage_cram {
           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)
 
-    DEEPTOOLS_BAMCOVERAGE ( input )
+    DEEPTOOLS_BAMCOVERAGE ( input, fasta, fasta_fai)
+}
+
+workflow test_deeptools_bamcoverage_cram_no_fasta_fai {
+
+    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)
+
+    DEEPTOOLS_BAMCOVERAGE ( input, fasta, [])
 }

tests/modules/deeptools/bamcoverage/test.yml

@@ -1,21 +1,26 @@
 - name: deeptools bamcoverage test_deeptools_bamcoverage_bam
-  command: nextflow run tests/modules/deeptools/bamcoverage -entry test_deeptools_bamcoverage_bam -c tests/config/nextflow.config
+  command: nextflow run ./tests/modules/deeptools/bamcoverage -entry test_deeptools_bamcoverage_bam -c ./tests/config/nextflow.config  -c ./tests/modules/deeptools/bamcoverage/nextflow.config
   tags:
-    - deeptools
     - deeptools/bamcoverage
+    - deeptools
   files:
     - path: output/deeptools/test.bigWig
       md5sum: 95fe9383a9e6c02aea6b785cf074274f
-    - path: output/deeptools/versions.yml
-      md5sum: 68c94e73b7a8c0935578bad61fea54c1
 
 - name: deeptools bamcoverage test_deeptools_bamcoverage_cram
-  command: nextflow run tests/modules/deeptools/bamcoverage -entry test_deeptools_bamcoverage_cram -c tests/config/nextflow.config
+  command: nextflow run ./tests/modules/deeptools/bamcoverage -entry test_deeptools_bamcoverage_cram -c ./tests/config/nextflow.config  -c ./tests/modules/deeptools/bamcoverage/nextflow.config
   tags:
-    - deeptools
     - deeptools/bamcoverage
+    - deeptools
+  files:
+    - path: output/deeptools/test.bigWig
+      md5sum: 95fe9383a9e6c02aea6b785cf074274f
+
+- name: deeptools bamcoverage test_deeptools_bamcoverage_cram_no_fasta_fai
+  command: nextflow run ./tests/modules/deeptools/bamcoverage -entry test_deeptools_bamcoverage_cram_no_fasta_fai -c ./tests/config/nextflow.config  -c ./tests/modules/deeptools/bamcoverage/nextflow.config
+  tags:
+    - deeptools/bamcoverage
+    - deeptools
   files:
     - path: output/deeptools/test.bigWig
       md5sum: 95fe9383a9e6c02aea6b785cf074274f
-    - path: output/deeptools/versions.yml
-      md5sum: 665bbd2979c49bf3974a24bd44a88e94

tests/modules/ensemblvep/main.nf

@@ -4,11 +4,22 @@ nextflow.enable.dsl = 2
 
 include { ENSEMBLVEP } from '../../../modules/ensemblvep/main.nf'
 
-workflow test_ensemblvep {
+workflow test_ensemblvep_fasta {
     input = [
         [ id:'test' ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
     ]
 
-    ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [], [] )
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+
+    ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [], fasta, [] )
+}
+
+workflow test_ensemblvep_no_fasta {
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
+    ]
+
+    ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [], [], [] )
 }

tests/modules/ensemblvep/test.yml

@@ -1,5 +1,13 @@
-- name: ensemblvep test_ensemblvep
+- name: ensemblvep test_ensemblvep_fasta
-  command: nextflow run ./tests/modules/ensemblvep -entry test_ensemblvep -c ./tests/config/nextflow.config -c ./tests/modules/ensemblvep/nextflow.config
+  command: nextflow run ./tests/modules/ensemblvep -entry test_ensemblvep_fasta -c ./tests/config/nextflow.config -c ./tests/modules/ensemblvep/nextflow.config
+  tags:
+    - ensemblvep
+  files:
+    - path: output/ensemblvep/test.ann.vcf
+    - path: output/ensemblvep/test.summary.html
+
+- name: ensemblvep test_ensemblvep_no_fasta
+  command: nextflow run ./tests/modules/ensemblvep -entry test_ensemblvep_no_fasta -c ./tests/config/nextflow.config -c ./tests/modules/ensemblvep/nextflow.config
   tags:
     - ensemblvep
   files:

tests/modules/filtlong/nextflow.config

@@ -2,4 +2,7 @@ process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
+    ext.args = "--min_length 10"
+    ext.prefix = "test_lr"
+
 }

tests/modules/filtlong/test.yml

@@ -3,21 +3,24 @@
   tags:
     - filtlong
   files:
-    - path: output/filtlong/test_lr_filtlong.fastq.gz
+    - path: output/filtlong/test_lr.fastq.gz
-      md5sum: 7029066c27ac6f5ef18d660d5741979a
+      contains:
+        - "@00068f7a-51b3-4933-8fc6-7d6e29181ff9"
 
 - name: filtlong test_filtlong_illumina_se
   command: nextflow run ./tests/modules/filtlong -entry test_filtlong_illumina_se -c ./tests/config/nextflow.config  -c ./tests/modules/filtlong/nextflow.config
   tags:
     - filtlong
   files:
-    - path: output/filtlong/test_lr_filtlong.fastq.gz
+    - path: output/filtlong/test_lr.fastq.gz
-      md5sum: 7029066c27ac6f5ef18d660d5741979a
+      contains:
+        - "@00068f7a-51b3-4933-8fc6-7d6e29181ff9"
 
 - name: filtlong test_filtlong_illumina_pe
   command: nextflow run ./tests/modules/filtlong -entry test_filtlong_illumina_pe -c ./tests/config/nextflow.config  -c ./tests/modules/filtlong/nextflow.config
   tags:
     - filtlong
   files:
-    - path: output/filtlong/test_lr_filtlong.fastq.gz
+    - path: output/filtlong/test_lr.fastq.gz
-      md5sum: 7029066c27ac6f5ef18d660d5741979a
+      contains:
+        - "@00068f7a-51b3-4933-8fc6-7d6e29181ff9"

tests/modules/gamma/gamma/main.nf

@@ -0,0 +1,29 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GAMMA_GAMMA } from '../../../../modules/gamma/gamma/main.nf'
+
+workflow test_unzip {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['bacteroides_fragilis']['illumina']['test1_contigs_fa_gz'], checkIfExists: true),
+    ]
+
+    db = [ file("https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/srst2/ResGANNCBI_20210507_srst2.fasta", checkIfExists: true), ]
+
+    GAMMA_GAMMA ( input, db )
+}
+
+workflow test_gamma {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+
+    db = [ file(params.test_data['sarscov2']['genome']['transcriptome_fasta'], checkIfExists: true) ]
+
+    GAMMA_GAMMA ( input, db )
+}

tests/modules/gamma/gamma/test.yml

@@ -0,0 +1,29 @@
+- name: gamma gamma test_unzip
+  command: nextflow run tests/modules/gamma/gamma -entry test_unzip -c tests/config/nextflow.config
+  tags:
+    - gamma/gamma
+    - gamma
+  files:
+    - path: output/gamma/test.fasta
+      md5sum: 5b3b831d863fffaa3410a9ee7bfa12ce
+    - path: output/gamma/test.gamma
+      md5sum: 46165a89e10b7315d3a9b0aa6c561626
+    - path: output/gamma/test.psl
+      md5sum: f489ce4602ddbcb692d5781ee3fbf449
+    - path: output/gamma/versions.yml
+      md5sum: 8baafec7b3b87f788f69e30d317c9722
+
+- name: gamma gamma test_gamma
+  command: nextflow run tests/modules/gamma/gamma -entry test_gamma -c tests/config/nextflow.config
+  tags:
+    - gamma/gamma
+    - gamma
+  files:
+    - path: output/gamma/test.fasta
+      md5sum: df37b48466181311e0a679f3c5878484
+    - path: output/gamma/test.gamma
+      md5sum: 3256708fa517a65ed01d99e0e3c762ae
+    - path: output/gamma/test.psl
+      md5sum: 162a2757ed3b167ae1e0cdb24213f940
+    - path: output/gamma/versions.yml
+      md5sum: b75c2871d8cac2f8ac67c0fbd22babd6

tests/modules/gamma/main.nf

@@ -1,17 +0,0 @@
-#!/usr/bin/env nextflow
-
-nextflow.enable.dsl = 2
-
-include { GAMMA } from '../../../modules/gamma/main.nf'
-
-workflow test_gamma {
-    
-    input = [
-        [ id:'test', single_end:false ], // meta map
-        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
-    ]
-
-    db = [ file(params.test_data['sarscov2']['genome']['transcriptome_fasta'], checkIfExists: true) ]
-
-    GAMMA ( input, db )
-}

tests/modules/gamma/test.yml

@@ -1,13 +0,0 @@
-- name: gamma test_gamma
-  command: nextflow run tests/modules/gamma -entry test_gamma -c tests/config/nextflow.config
-  tags:
-    - gamma
-  files:
-    - path: output/gamma/test.fasta
-      md5sum: df37b48466181311e0a679f3c5878484
-    - path: output/gamma/test.gamma
-      md5sum: 3256708fa517a65ed01d99e0e3c762ae
-    - path: output/gamma/test.psl
-      md5sum: 162a2757ed3b167ae1e0cdb24213f940
-    - path: output/gamma/versions.yml
-      md5sum: 3fefb5b46c94993362243c5f9a472057

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