Merge pull request #2 from jfy133/upstream-for-indel

Upstream

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

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

modules/bcftools/roh/meta.yml

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

modules/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
 
@@ -28,48 +29,167 @@ 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 $is_cram; then
+    if (tumor_cram && normal_cram){
-        samtools view -T $fasta $tumor -@ $task.cpus -o $tumor_out
+        """
-        if $normal_exists; then
+        samtools view -T $fasta $fai_reference $tumor -@ $task.cpus -o $tumor_out
-            samtools view -T $fasta $normal -@ $task.cpus -o $normal_out
+        samtools view -T $fasta $fai_reference $normal -@ $task.cpus -o $normal_out
-        fi
-    fi
 
-    cnvkit.py \\
+        cnvkit.py \\
-        batch \\
+            batch \\
-        $tumor_out \\
+            $tumor_out \\
-        $normal_args \\
+            $normal_args \\
-        $fasta_args \\
+            $fasta_args \\
-        $reference_args \\
+            $reference_args \\
-        $target_args \\
+            $target_args \\
-        --processes $task.cpus \\
+            --processes $task.cpus \\
-        $args
+            $args
+
+        cat <<-END_VERSIONS > versions.yml
+        "${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 \\
+            $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
+        """
+    }
+    // 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
+        """
+    }
 
-    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/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
@@ -22,16 +24,44 @@ process DEEPTOOLS_BAMCOVERAGE {
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}.bigWig"
 
-    """
+    // cram_input is currently not working with deeptools
-    bamCoverage \\
+    // therefore it's required to convert cram to bam first
-        --bam $input \\
+    def is_cram = input.Extension == "cram" ? true : false
-        $args \\
+    def input_out = is_cram ? input.BaseName + ".bam" : "${input}"
-        --numberOfProcessors ${task.cpus} \\
+    def fai_reference = fasta_fai ? "--fai-reference ${fasta_fai}" : ""
-        --outFileName ${prefix}
+
+    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_out \\
+            $args \\
+            --numberOfProcessors ${task.cpus} \\
+            --outFileName ${prefix}
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            deeptools: \$(bamCoverage --version | sed -e "s/bamCoverage //g")
+        END_VERSIONS
+        """
+    }
 
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        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/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/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/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/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/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/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

@@ -2,21 +2,20 @@ 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("*.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
-    path  "versions.yml"                  , emit: versions
 
     when:
     task.ext.when == null || task.ext.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}":

tests/config/pytest_modules.yml

@@ -719,6 +719,14 @@ 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/**
   - tests/modules/gatk4/applybqsr/**
@@ -747,6 +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/**
@@ -755,6 +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/**
@@ -1639,6 +1655,10 @@ rgi/main:
   - modules/rgi/main/**
   - tests/modules/rgi/main/**
 
+rhocall/annotate:
+  - modules/rhocall/annotate/**
+  - tests/modules/rhocall/annotate/**
+
 rmarkdownnotebook:
   - modules/rmarkdownnotebook/**
   - tests/modules/rmarkdownnotebook/**
@@ -1855,6 +1875,10 @@ snapaligner/index:
   - modules/snapaligner/index/**
   - tests/modules/snapaligner/index/**
 
+snippy/run:
+  - modules/snippy/run/**
+  - tests/modules/snippy/run/**
+
 snpdists:
   - modules/snpdists/**
   - tests/modules/snpdists/**

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"
@@ -262,6 +266,8 @@ 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"
 
@@ -323,6 +329,8 @@ 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                         = "${test_data_dir}/genomics/homo_sapiens/pacbio/fasta/primers.fasta"
@@ -415,9 +423,6 @@ params {
             'txt' {
                 hello                           = "${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

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

tests/modules/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
@@ -28,42 +29,71 @@ 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
         file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_cram'], checkIfExists: true),
         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     = 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/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/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

@@ -1,23 +1,26 @@
 - name: filtlong test_filtlong
-  command: nextflow run ./tests/modules/filtlong -entry test_filtlong -c ./tests/config/nextflow.config -c ./tests/modules/filtlong/nextflow.config
+  command: nextflow run ./tests/modules/filtlong -entry test_filtlong -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_se
-  command: nextflow run ./tests/modules/filtlong -entry test_filtlong_illumina_se -c ./tests/config/nextflow.config -c ./tests/modules/filtlong/nextflow.config
+  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
+  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/gatk/realignertargetcreator/main.nf

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

tests/modules/gatk/realignertargetcreator/nextflow.config

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

tests/modules/gatk/realignertargetcreator/test.yml

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

tests/modules/gatk/unifiedgenotyper/main.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK_UNIFIEDGENOTYPER } from '../../../../modules/gatk/unifiedgenotyper/main.nf'
+
+workflow test_gatk_unifiedgenotyper {
+
+    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_UNIFIEDGENOTYPER ( input, fasta, fai, dict, [], [], [], [])
+}

tests/modules/gatk/unifiedgenotyper/nextflow.config

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

tests/modules/gatk/unifiedgenotyper/test.yml

@@ -0,0 +1,9 @@
+- name: gatk unifiedgenotyper test_gatk_unifiedgenotyper
+  command: nextflow run ./tests/modules/gatk/unifiedgenotyper -entry test_gatk_unifiedgenotyper -c ./tests/config/nextflow.config  -c ./tests/modules/gatk/unifiedgenotyper/nextflow.config
+  tags:
+    - gatk
+    - gatk/unifiedgenotyper
+  files:
+    - path: output/gatk/test.vcf.gz
+      contains:
+        - "#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	test"

tests/modules/gatk4/calibratedragstrmodel/main.nf

@@ -0,0 +1,66 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_CALIBRATEDRAGSTRMODEL } from '../../../../modules/gatk4/calibratedragstrmodel/main.nf'
+
+workflow test_gatk4_calibratedragstrmodel_bam {
+    
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+        []
+    ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+
+    fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+
+    strtablefile = file(params.test_data['homo_sapiens']['genome']['genome_strtablefile'], checkIfExists: true)
+
+    GATK4_CALIBRATEDRAGSTRMODEL ( input, fasta, fasta_fai, dict, strtablefile )
+}
+
+workflow test_gatk4_calibratedragstrmodel_cram {
+    
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram_crai'], checkIfExists: true),
+        []
+    ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+
+    fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+
+    strtablefile = file(params.test_data['homo_sapiens']['genome']['genome_strtablefile'], checkIfExists: true)
+
+    GATK4_CALIBRATEDRAGSTRMODEL ( input, fasta, fasta_fai, dict, strtablefile )
+}
+
+workflow test_gatk4_calibratedragstrmodel_beds {
+    
+    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),
+        file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)
+    ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+
+    fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+
+    strtablefile = file(params.test_data['homo_sapiens']['genome']['genome_strtablefile'], checkIfExists: true)
+
+    GATK4_CALIBRATEDRAGSTRMODEL ( input, fasta, fasta_fai, dict, strtablefile )
+}
+

tests/modules/gatk4/calibratedragstrmodel/nextflow.config

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

tests/modules/gatk4/calibratedragstrmodel/test.yml

@@ -0,0 +1,26 @@
+- name: gatk4 calibratedragstrmodel test_gatk4_calibratedragstrmodel_bam
+  command: nextflow run ./tests/modules/gatk4/calibratedragstrmodel -entry test_gatk4_calibratedragstrmodel_bam -c ./tests/config/nextflow.config  -c ./tests/modules/gatk4/calibratedragstrmodel/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/calibratedragstrmodel
+  files:
+    - path: output/gatk4/test.txt
+      md5sum: e16fa32906c74bb18b93e98a86718ff1
+
+- name: gatk4 calibratedragstrmodel test_gatk4_calibratedragstrmodel_cram
+  command: nextflow run ./tests/modules/gatk4/calibratedragstrmodel -entry test_gatk4_calibratedragstrmodel_cram -c ./tests/config/nextflow.config  -c ./tests/modules/gatk4/calibratedragstrmodel/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/calibratedragstrmodel
+  files:
+    - path: output/gatk4/test.txt
+      md5sum: 81c7bf338886cb4d5c2cc07fc56afe44
+
+- name: gatk4 calibratedragstrmodel test_gatk4_calibratedragstrmodel_beds
+  command: nextflow run ./tests/modules/gatk4/calibratedragstrmodel -entry test_gatk4_calibratedragstrmodel_beds -c ./tests/config/nextflow.config  -c ./tests/modules/gatk4/calibratedragstrmodel/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/calibratedragstrmodel
+  files:
+    - path: output/gatk4/test.txt
+      md5sum: cb6a9acdee042302b54fd1f59b5f54ee

tests/modules/gatk4/composestrtablefile/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_COMPOSESTRTABLEFILE } from '../../../../modules/gatk4/composestrtablefile/main.nf'
+
+workflow test_gatk4_composestrtablefile {
+    
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+
+    fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+
+    GATK4_COMPOSESTRTABLEFILE ( fasta, fasta_fai, dict )
+}

tests/modules/gatk4/composestrtablefile/nextflow.config

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

tests/modules/gatk4/composestrtablefile/test.yml

@@ -0,0 +1,7 @@
+- name: gatk4 composestrtablefile test_gatk4_composestrtablefile
+  command: nextflow run ./tests/modules/gatk4/composestrtablefile -entry test_gatk4_composestrtablefile -c ./tests/config/nextflow.config  -c ./tests/modules/gatk4/composestrtablefile/nextflow.config
+  tags:
+    - gatk4/composestrtablefile
+    - gatk4
+  files:
+    - path: output/gatk4/genome.zip

tests/modules/gatk4/haplotypecaller/main.nf

@@ -8,6 +8,7 @@ workflow test_gatk4_haplotypecaller {
     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)
@@ -21,6 +22,7 @@ workflow test_gatk4_haplotypecaller_cram {
     input = [ [ id:'test' ], // 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)
@@ -34,7 +36,8 @@ workflow test_gatk4_haplotypecaller_intervals_dbsnp {
    input = [ [ id:'test' ], // 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),
-                file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)
+                file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true),
+                []
             ]
 
     fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
@@ -45,3 +48,20 @@ workflow test_gatk4_haplotypecaller_intervals_dbsnp {
 
     GATK4_HAPLOTYPECALLER ( input, fasta, fai, dict, sites, sites_tbi )
 }
+
+workflow test_gatk4_haplotypecaller_dragstr_model {
+   input = [ [ id:'test' ], // 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),
+                [],
+                file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_dragstrmodel'], checkIfExists: true)
+            ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+    sites = []
+    sites_tbi = []
+
+    GATK4_HAPLOTYPECALLER ( input, fasta, fai, dict, sites, sites_tbi )
+}

tests/modules/gatk4/haplotypecaller/test.yml

@@ -6,7 +6,6 @@
   files:
     - path: output/gatk4/test.vcf.gz
     - path: output/gatk4/test.vcf.gz.tbi
-    - path: output/gatk4/versions.yml
 
 - name: gatk4 haplotypecaller test_gatk4_haplotypecaller_cram
   command: nextflow run ./tests/modules/gatk4/haplotypecaller -entry test_gatk4_haplotypecaller_cram -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/haplotypecaller/nextflow.config
@@ -16,7 +15,6 @@
   files:
     - path: output/gatk4/test.vcf.gz
     - path: output/gatk4/test.vcf.gz.tbi
-    - path: output/gatk4/versions.yml
 
 - name: gatk4 haplotypecaller test_gatk4_haplotypecaller_intervals_dbsnp
   command: nextflow run ./tests/modules/gatk4/haplotypecaller -entry test_gatk4_haplotypecaller_intervals_dbsnp -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/haplotypecaller/nextflow.config
@@ -26,4 +24,12 @@
   files:
     - path: output/gatk4/test.vcf.gz
     - path: output/gatk4/test.vcf.gz.tbi
-    - path: output/gatk4/versions.yml
+
+- name: gatk4 haplotypecaller test_gatk4_haplotypecaller_dragstr_model
+  command: nextflow run ./tests/modules/gatk4/haplotypecaller -entry test_gatk4_haplotypecaller_dragstr_model -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/haplotypecaller/nextflow.config
+  tags:
+    - gatk4/haplotypecaller
+    - gatk4
+  files:
+    - path: output/gatk4/test.vcf.gz
+    - path: output/gatk4/test.vcf.gz.tbi

tests/modules/gatk4/mergevcfs/test.yml

@@ -6,6 +6,8 @@
   files:
     - path: output/gatk4/test.vcf.gz
       md5sum: 5b289bda88d3a3504f2e19ee8cff177c
+    - path: output/gatk4/test.vcf.gz.tbi
+      md5sum: a81673763b13086cfce9a23e72a35a16
     - path: output/gatk4/versions.yml
 
 - name: gatk4 mergevcfs test_gatk4_mergevcfs_no_dict

tests/modules/multiqc/main.nf

@@ -2,15 +2,32 @@
 
 nextflow.enable.dsl = 2
 
-include { FASTQC  } from '../../../modules/fastqc/main.nf'
+include { FASTQC            } from '../../../modules/fastqc/main.nf'
-include { MULTIQC } from '../../../modules/multiqc/main.nf'
+include { FASTQC as FASTQC2 } from '../../../modules/fastqc/main.nf'
+include { MULTIQC           } from '../../../modules/multiqc/main.nf'
 
 workflow test_multiqc {
-    input = [ [ id: 'test', single_end: false ],
+    input = [
-              [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+        [ id: 'test', single_end: false ],
-                file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
+        [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)]
-            ]
+    ]
 
     FASTQC  ( input )
-    MULTIQC ( FASTQC.out.zip.collect { it[1] } )
+    MULTIQC ( FASTQC.out.zip.collect { it[1] }, [[],[]] )
+}
+
+workflow test_multiqc_fn_collision {
+    fqc_input = [
+        [ id: 'test', single_end: false ],
+        [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)]
+    ]
+    mqc_input = Channel.empty()
+
+    FASTQC  ( fqc_input  )
+    mqc_input = mqc_input.mix(FASTQC.out.zip.collect { it[1] })
+
+    FASTQC2  ( fqc_input )
+    mqc_input = mqc_input.mix(FASTQC2.out.zip.collect { it[1] })
+
+    MULTIQC ( mqc_input, [[],[]] )
 }

tests/modules/multiqc/nextflow.config

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

tests/modules/multiqc/test.yml

@@ -1,5 +1,12 @@
-- name: multiqc
+- name: multiqc test_multiqc
-  command: nextflow run ./tests/modules/multiqc -entry test_multiqc -c ./tests/config/nextflow.config -c ./tests/modules/multiqc/nextflow.config
+  command: nextflow run ./tests/modules/multiqc -entry test_multiqc -c ./tests/config/nextflow.config  -c ./tests/modules/multiqc/nextflow.config
+  tags:
+    - multiqc
+  files:
+    - path: output/multiqc/multiqc_report.html
+
+- name: multiqc test_multiqc_fn_collision
+  command: nextflow run ./tests/modules/multiqc -entry test_multiqc_fn_collision -c ./tests/config/nextflow.config  -c ./tests/modules/multiqc/nextflow.config
   tags:
     - multiqc
   files:

tests/modules/rhocall/annotate/main.nf

@@ -0,0 +1,40 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { RHOCALL_ANNOTATE } from '../../../../modules/rhocall/annotate/main.nf'
+include { BCFTOOLS_ROH } from '../../../../modules/bcftools/roh/main.nf'
+
+workflow test_rhocall_annotate {
+
+    input = [ [ id:'test' ], // meta map
+             file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
+             file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)]
+
+    af_file = [[],[]]
+    gen_map = []
+    regions = []
+    targets = []
+    samples = []
+
+    BCFTOOLS_ROH ( input, af_file, gen_map, regions, samples, targets )
+    RHOCALL_ANNOTATE ( input, BCFTOOLS_ROH.out.roh, [])
+
+}
+
+workflow test_rhocall_annotate_stub {
+
+    input = [ [ id:'test' ], // meta map
+             file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
+             file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)]
+
+    af_file = [[],[]]
+    gen_map = []
+    regions = []
+    targets = []
+    samples = []
+
+    BCFTOOLS_ROH ( input, af_file, gen_map, regions, samples, targets )
+    RHOCALL_ANNOTATE ( input, BCFTOOLS_ROH.out.roh, [])
+
+}

tests/modules/rhocall/annotate/nextflow.config

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

tests/modules/rhocall/annotate/test.yml

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

tests/modules/snippy/run/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SNIPPY_RUN } from '../../../../modules/snippy/run/main.nf'
+
+workflow test_snippy_run {
+    
+    input = [ [ id:'test', single_end:false ], // meta map
+              [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
+            ]
+    reference = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+
+    SNIPPY_RUN ( input, reference )
+}

tests/modules/snippy/run/nextflow.config

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

tests/modules/snippy/run/test.yml

@@ -0,0 +1,39 @@
+- name: snippy run test_snippy_run
+  command: |
+    nextflow run tests/modules/snippy/run -entry test_snippy_run -c tests/config/nextflow.config -c tests/modules/snippy/run/nextflow.config
+  tags:
+    - snippy/run
+    - snippy
+  files:
+    - path: output/snippy/test/test.aligned.fa
+      md5sum: 47e3390d4167edf1955d162d37aca5e3
+    - path: output/snippy/test/test.bam
+    - path: output/snippy/test/test.bam.bai
+    - path: output/snippy/test/test.bed
+    - path: output/snippy/test/test.consensus.fa
+      md5sum: 483f4a5dfe60171c86ee9b7e6dff908b
+    - path: output/snippy/test/test.consensus.subs.fa
+      md5sum: 483f4a5dfe60171c86ee9b7e6dff908b
+    - path: output/snippy/test/test.csv
+      md5sum: 322f942115e5945c2041a88246166703
+    - path: output/snippy/test/test.filt.vcf
+      contains: ["fileformat", "freebayes", "CHROM"]
+    - path: output/snippy/test/test.gff
+      md5sum: df19e1b84ba6f691d20c72b397c88abf
+    - path: output/snippy/test/test.html
+      md5sum: 1ccbf0ffcadae1a6b2e11681d24c9938
+    - path: output/snippy/test/test.log
+      contains: ["snippy", "consensus", "subs"]
+    - path: output/snippy/test/test.raw.vcf
+      contains: ["fileformat", "freebayes", "CHROM"]
+    - path: output/snippy/test/test.tab
+      md5sum: beb9bde3bce985e53e8feba9ec5b136e
+    - path: output/snippy/test/test.txt
+      contains: ["DateTime", "ReadFiles", "VariantTotal"]
+    - path: output/snippy/test/test.vcf
+      contains: ["fileformat", "freebayes", "CHROM"]
+    - path: output/snippy/test/test.vcf.gz
+    - path: output/snippy/test/test.vcf.gz.csi
+      md5sum: bed9fa291c220a1ba04eb2d448932ffc
+    - path: output/snippy/versions.yml
+      md5sum: 518aad56c4dbefb6cbcde5ab38cf7b5d

tests/modules/tiddit/cov/main.nf

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

tests/modules/tiddit/cov/nextflow.config

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

tests/modules/tiddit/cov/test.yml

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

tests/modules/tiddit/sv/main.nf

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

tests/modules/tiddit/sv/test.yml

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

tests/modules/untar/main.nf

@@ -12,3 +12,13 @@ workflow test_untar {
 
     UNTAR ( input )
 }
+
+
+workflow test_untar_different_output_path {
+    input = [
+        [],
+        file(params.test_data['homo_sapiens']['illumina']['test_flowcell'], checkIfExists: true)
+    ]
+
+    UNTAR ( input )
+}

tests/modules/untar/test.yml

@@ -1,5 +1,5 @@
-- name: untar
+- name: untar test_untar
-  command: nextflow run ./tests/modules/untar -entry test_untar -c ./tests/config/nextflow.config -c ./tests/modules/untar/nextflow.config
+  command: nextflow run ./tests/modules/untar -entry test_untar -c ./tests/config/nextflow.config  -c ./tests/modules/untar/nextflow.config
   tags:
     - untar
   files:
@@ -9,3 +9,11 @@
       md5sum: a033d00cf6759407010b21700938f543
     - path: output/untar/kraken2/taxo.k2d
       md5sum: 094d5891cdccf2f1468088855c214b2c
+
+- name: untar test_untar_different_output_path
+  command: nextflow run ./tests/modules/untar -entry test_untar_different_output_path -c ./tests/config/nextflow.config  -c ./tests/modules/untar/nextflow.config
+  tags:
+    - untar
+  files:
+    - path: output/untar/flowcell/RunInfo.xml
+      md5sum: 03038959f4dd181c86bc97ae71fe270a