Merge branch 'nf-core:master' into antismashlite

modules/arriba/main.nf

@@ -2,15 +2,20 @@ process ARRIBA {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::arriba=2.1.0" : null)
+    conda (params.enable_conda ? "bioconda::arriba=2.2.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/arriba:2.1.0--h3198e80_1' :
+        'https://depot.galaxyproject.org/singularity/arriba:2.2.1--hecb563c_2' :
-        'quay.io/biocontainers/arriba:2.1.0--h3198e80_1' }"
+        'quay.io/biocontainers/arriba:2.2.1--hecb563c_2' }"
 
     input:
     tuple val(meta), path(bam)
     path fasta
     path gtf
+    path blacklist
+    path known_fusions
+    path structural_variants
+    path tags
+    path protein_domains
 
     output:
     tuple val(meta), path("*.fusions.tsv")          , emit: fusions
@@ -23,7 +28,12 @@ process ARRIBA {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def blacklist = (args.contains('-b')) ? '' : '-f blacklist'
+    def blacklist = blacklist ? "-b $blacklist" : "-f blacklist"
+    def known_fusions = known_fusions ? "-k $known_fusions" : ""
+    def structural_variants = structural_variants ? "-d $structual_variants" : ""
+    def tags = tags ? "-t $tags" : ""
+    def protein_domains = protein_domains ? "-p $protein_domains" : ""
+
     """
     arriba \\
         -x $bam \\
@@ -32,6 +42,10 @@ process ARRIBA {
         -o ${prefix}.fusions.tsv \\
         -O ${prefix}.fusions.discarded.tsv \\
         $blacklist \\
+        $known_fusions \\
+        $structural_variants \\
+        $tags \\
+        $protein_domains \\
         $args
 
     cat <<-END_VERSIONS > versions.yml
@@ -39,4 +53,14 @@ process ARRIBA {
         arriba: \$(arriba -h | grep 'Version:' 2>&1 |  sed 's/Version:\s//')
     END_VERSIONS
     """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    echo stub > ${prefix}.fusions.tsv
+    echo stub > ${prefix}.fusions.discarded.tsv
+
+    echo "${task.process}:" > versions.yml
+    echo ' arriba: 2.2.1' >> versions.yml
+    """
 }

modules/arriba/meta.yml

@@ -30,6 +30,26 @@ input:
       type: file
       description: Annotation GTF file
       pattern: "*.{gtf}"
+  - blacklist:
+      type: file
+      description: Blacklist file
+      pattern: "*.{tsv}"
+  - known_fusions:
+      type: file
+      description: Known fusions file
+      pattern: "*.{tsv}"
+  - structural_variants:
+      type: file
+      description: Structural variants file
+      pattern: "*.{tsv}"
+  - tags:
+      type: file
+      description: Tags file
+      pattern: "*.{tsv}"
+  - protein_domains:
+      type: file
+      description: Protein domains file
+      pattern: "*.{gff3}"
 
 output:
   - meta:
@@ -51,4 +71,4 @@ output:
       pattern: "*.{fusions.discarded.tsv}"
 
 authors:
-  - "@praveenraj2018"
+  - "@praveenraj2018,@rannick"

modules/bowtie2/align/main.nf

@@ -29,6 +29,8 @@ process BOWTIE2_ALIGN {
         def unaligned = save_unaligned ? "--un-gz ${prefix}.unmapped.fastq.gz" : ''
         """
         INDEX=`find -L ./ -name "*.rev.1.bt2" | sed 's/.rev.1.bt2//'`
+        [ -z "\$INDEX" ] && INDEX=`find -L ./ -name "*.rev.1.bt2l" | sed 's/.rev.1.bt2l//'`
+        [ -z "\$INDEX" ] && echo "BT2 index files not found" 1>&2 && exit 1
         bowtie2 \\
             -x \$INDEX \\
             -U $reads \\
@@ -49,6 +51,8 @@ process BOWTIE2_ALIGN {
         def unaligned = save_unaligned ? "--un-conc-gz ${prefix}.unmapped.fastq.gz" : ''
         """
         INDEX=`find -L ./ -name "*.rev.1.bt2" | sed 's/.rev.1.bt2//'`
+        [ -z "\$INDEX" ] && INDEX=`find -L ./ -name "*.rev.1.bt2l" | sed 's/.rev.1.bt2l//'`
+        [ -z "\$INDEX" ] && echo "BT2 index files not found" 1>&2 && exit 1
         bowtie2 \\
             -x \$INDEX \\
             -1 ${reads[0]} \\

modules/busco/main.nf

@@ -0,0 +1,84 @@
+process BUSCO {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::busco=5.3.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/busco:5.3.2--pyhdfd78af_0':
+        'quay.io/biocontainers/busco:5.3.2--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path('tmp_input/*')
+    each lineage                          // Required:    lineage to check against, "auto" enables --auto-lineage instead
+    path busco_lineages_path              // Recommended: path to busco lineages - downloads if not set
+    path config_file                      // Optional:    busco configuration file
+
+    output:
+    tuple val(meta), path("*-busco.batch_summary.txt"), emit: batch_summary
+    tuple val(meta), path("short_summary.*.txt")      , emit: short_summaries_txt, optional: true
+    tuple val(meta), path("short_summary.*.json")     , emit: short_summaries_json, optional: true
+    tuple val(meta), path("*-busco")                  , emit: busco_dir
+    path "versions.yml"                               , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}-${lineage}"
+    def busco_config = config_file ? "--config $config_file" : ''
+    def busco_lineage = lineage.equals('auto') ? '--auto-lineage' : "--lineage_dataset ${lineage}"
+    def busco_lineage_dir = busco_lineages_path ? "--offline --download_path ${busco_lineages_path}" : ''
+    """
+    # Nextflow changes the container --entrypoint to /bin/bash (container default entrypoint: /usr/local/env-execute)
+    # Check for container variable initialisation script and source it.
+    if [ -f "/usr/local/env-activate.sh" ]; then
+        set +u  # Otherwise, errors out because of various unbound variables
+        . "/usr/local/env-activate.sh"
+        set -u
+    fi
+
+    # If the augustus config directory is not writable, then copy to writeable area
+    if [ ! -w "\${AUGUSTUS_CONFIG_PATH}" ]; then
+        # Create writable tmp directory for augustus
+        AUG_CONF_DIR=\$( mktemp -d -p \$PWD )
+        cp -r \$AUGUSTUS_CONFIG_PATH/* \$AUG_CONF_DIR
+        export AUGUSTUS_CONFIG_PATH=\$AUG_CONF_DIR
+        echo "New AUGUSTUS_CONFIG_PATH=\${AUGUSTUS_CONFIG_PATH}"
+    fi
+
+    # Ensure the input is uncompressed
+    INPUT_SEQS=input_seqs
+    mkdir "\$INPUT_SEQS"
+    cd "\$INPUT_SEQS"
+    for FASTA in ../tmp_input/*; do
+        if [ "\${FASTA##*.}" == 'gz' ]; then
+            gzip -cdf "\$FASTA" > \$( basename "\$FASTA" .gz )
+        else
+            ln -s "\$FASTA" .
+        fi
+    done
+    cd ..
+
+    busco \\
+        --cpu $task.cpus \\
+        --in "\$INPUT_SEQS" \\
+        --out ${prefix}-busco \\
+        $busco_lineage \\
+        $busco_lineage_dir \\
+        $busco_config \\
+        $args
+
+    # clean up
+    rm -rf "\$INPUT_SEQS"
+
+    # Move files to avoid staging/publishing issues
+    mv ${prefix}-busco/batch_summary.txt ${prefix}-busco.batch_summary.txt
+    mv ${prefix}-busco/*/short_summary.*.{json,txt} . || echo "Short summaries were not available: No genes were found."
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        busco: \$( busco --version 2>&1 | sed 's/^BUSCO //' )
+    END_VERSIONS
+    """
+}

modules/busco/meta.yml

@@ -0,0 +1,69 @@
+name: busco
+description: Benchmarking Universal Single Copy Orthologs
+keywords:
+  - quality control
+  - genome
+  - transcriptome
+  - proteome
+tools:
+  - busco:
+      description: BUSCO provides measures for quantitative assessment of genome assembly, gene set, and transcriptome completeness based on evolutionarily informed expectations of gene content from near-universal single-copy orthologs selected from OrthoDB.
+      homepage: https://busco.ezlab.org/
+      documentation: https://busco.ezlab.org/busco_userguide.html
+      tool_dev_url: https://gitlab.com/ezlab/busco
+      doi: "10.1007/978-1-4939-9173-0_14"
+      licence: ["MIT"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: Nucleic or amino acid sequence file in FASTA format.
+      pattern: "*.{fasta,fna,fa,fasta.gz,fna.gz,fa.gz}"
+  - lineage:
+      type: value
+      description: The BUSCO lineage to use, or "auto" to automatically select lineage
+  - busco_lineages_path:
+      type: directory
+      description: Path to local BUSCO lineages directory.
+  - config_file:
+      type: file
+      description: Path to BUSCO config file.
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - batch_summary:
+      type: file
+      description: Summary of all sequence files analyzed
+      pattern: "*-busco.batch_summary.txt"
+  - short_summaries_txt:
+      type: file
+      description: Short Busco summary in plain text format
+      pattern: "short_summary.*.txt"
+  - short_summaries_json:
+      type: file
+      description: Short Busco summary in JSON format
+      pattern: "short_summary.*.json"
+  - busco_dir:
+      type: directory
+      description: BUSCO lineage specific output
+      pattern: "*-busco"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@priyanka-surana"
+  - "@charles-plessy"
+  - "@mahesh-panchal"
+  - "@muffato"
+  - "@jvhagey"

modules/cnvpytor/callcnvs/main.nf

@@ -2,43 +2,42 @@ process CNVPYTOR_CALLCNVS {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::cnvpytor=1.0" : null)
+    conda (params.enable_conda ? "bioconda::cnvpytor=1.2.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/cnvpytor:1.0--py39h6a678da_2':
+        'https://depot.galaxyproject.org/singularity/cnvpytor:1.2.1--pyhdfd78af_0':
-        'quay.io/biocontainers/cnvpytor:1.0--py39h6a678da_2' }"
+        'quay.io/biocontainers/cnvpytor:1.2.1--pyhdfd78af_0' }"
 
     input:
     tuple val(meta), path(pytor)
+    val bin_sizes
 
     output:
-    tuple val(meta), path("*.tsv"), emit: cnvs
+    tuple val(meta), path("${pytor.baseName}.pytor")	, emit: pytor
-    path "versions.yml"           , emit: versions
+    path "versions.yml"                                 , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
-    def args = task.ext.args ?: '1000'
+    def bins = bin_sizes ?: '1000'
-    def prefix = task.ext.prefix ?: "${meta.id}"
     """
     cnvpytor \\
         -root $pytor \\
-        -call $args > ${prefix}.tsv
+        -call $bin_sizes
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
+        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
     END_VERSIONS
     """
 
     stub:
-    def prefix = task.ext.prefix ?: "${meta.id}"
     """
-    touch ${prefix}.tsv
+    touch ${pytor.baseName}.pytor
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
+        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
     END_VERSIONS
     """
 }

modules/cnvpytor/callcnvs/meta.yml

@@ -17,8 +17,11 @@ input:
         e.g. [ id:'test']
   - pytor:
       type: file
-      description: cnvpytor root file
+      description: pytor file containing partitions of read depth histograms using mean-shift method
       pattern: "*.{pytor}"
+  - bin_sizes:
+      type: string
+      description: list of binsizes separated by space e.g. "1000 10000" and "1000"
 
 output:
   - meta:
@@ -26,10 +29,10 @@ output:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test' ]
-  - cnvs:
+  - pytor:
       type: file
-      description: file containing identified copy numer variations
+      description: pytor files containing cnv calls
-      pattern: "*.{tsv}"
+      pattern: "*.{pytor}"
   - versions:
       type: file
       description: File containing software versions

modules/cnvpytor/histogram/main.nf

@@ -2,13 +2,15 @@ process CNVPYTOR_HISTOGRAM {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::cnvpytor=1.0" : null)
+    conda (params.enable_conda ? "bioconda::cnvpytor=1.2.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/cnvpytor:1.0--py39h6a678da_2':
+        'https://depot.galaxyproject.org/singularity/cnvpytor:1.2.1--pyhdfd78af_0':
-        'quay.io/biocontainers/cnvpytor:1.0--py39h6a678da_2' }"
+        'quay.io/biocontainers/cnvpytor:1.2.1--pyhdfd78af_0' }"
 
     input:
     tuple val(meta), path(pytor)
+    val bin_sizes
+
 
     output:
     tuple val(meta), path("${pytor.baseName}.pytor")	, emit: pytor
@@ -18,15 +20,15 @@ process CNVPYTOR_HISTOGRAM {
     task.ext.when == null || task.ext.when
 
     script:
-    def args = task.ext.args ?: '1000'
+    def bins = bin_sizes ?: '1000'
     """
     cnvpytor \\
         -root $pytor \\
-        -his $args
+        -his $bins
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
+        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
     END_VERSIONS
     """
 
@@ -36,7 +38,7 @@ process CNVPYTOR_HISTOGRAM {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
+        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
     END_VERSIONS
     """
 }

modules/cnvpytor/histogram/meta.yml

@@ -22,6 +22,9 @@ input:
       type: file
       description: pytor file containing read depth data
       pattern: "*.{pytor}"
+  - bin_sizes:
+      type: string
+      description: list of binsizes separated by space e.g. "1000 10000" and "1000"
 
 output:
   - meta:
@@ -40,3 +43,4 @@ output:
 
 authors:
   - "@sima-r"
+  - "@ramprasadn"

modules/cnvpytor/importreaddepth/main.nf

@@ -2,10 +2,10 @@ process CNVPYTOR_IMPORTREADDEPTH {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::cnvpytor=1.0" : null)
+    conda (params.enable_conda ? "bioconda::cnvpytor=1.2.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/cnvpytor:1.0--py39h6a678da_2':
+        'https://depot.galaxyproject.org/singularity/cnvpytor:1.2.1--pyhdfd78af_0':
-        'quay.io/biocontainers/cnvpytor:1.0--py39h6a678da_2' }"
+        'quay.io/biocontainers/cnvpytor:1.2.1--pyhdfd78af_0' }"
 
     input:
     tuple val(meta), path(input_file), path(index)
@@ -32,7 +32,7 @@ process CNVPYTOR_IMPORTREADDEPTH {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
+        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
     END_VERSIONS
     """
 
@@ -43,7 +43,7 @@ process CNVPYTOR_IMPORTREADDEPTH {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
+        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
     END_VERSIONS
     """
 }

modules/cnvpytor/importreaddepth/meta.yml

@@ -52,3 +52,4 @@ output:
 
 authors:
   - "@sima-r"
+  - "@ramprasadn"

modules/cnvpytor/partition/main.nf

@@ -2,13 +2,14 @@ process CNVPYTOR_PARTITION {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::cnvpytor=1.0" : null)
+    conda (params.enable_conda ? "bioconda::cnvpytor=1.2.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/cnvpytor:1.0--py39h6a678da_2':
+        'https://depot.galaxyproject.org/singularity/cnvpytor:1.2.1--pyhdfd78af_0':
-        'quay.io/biocontainers/cnvpytor:1.0--py39h6a678da_2' }"
+        'quay.io/biocontainers/cnvpytor:1.2.1--pyhdfd78af_0' }"
 
     input:
     tuple val(meta), path(pytor)
+    val bin_sizes
 
     output:
     tuple val(meta), path("${pytor.baseName}.pytor"), emit: pytor
@@ -18,15 +19,15 @@ process CNVPYTOR_PARTITION {
     task.ext.when == null || task.ext.when
 
     script:
-    def args = task.ext.args ?: ''
+    def bins = bin_sizes ?: '1000'
     """
     cnvpytor \\
         -root $pytor \\
-        -partition $args
+        -partition $bins
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
+        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
     END_VERSIONS
     """
 
@@ -36,7 +37,7 @@ process CNVPYTOR_PARTITION {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
+        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
     END_VERSIONS
     """
 }

modules/cnvpytor/partition/meta.yml

@@ -22,6 +22,9 @@ input:
       type: file
       description: pytor file containing read depth data
       pattern: "*.{pytor}"
+  - bin_sizes:
+      type: string
+      description: list of binsizes separated by space e.g. "1000 10000" and "1000"
 
 output:
   - meta:
@@ -40,3 +43,4 @@ output:
 
 authors:
   - "@sima-r"
+  - "@ramprasadn"

modules/cnvpytor/view/main.nf

@@ -0,0 +1,60 @@
+process CNVPYTOR_VIEW {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::cnvpytor=1.2.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/cnvpytor:1.2.1--pyhdfd78af_0':
+        'quay.io/biocontainers/cnvpytor:1.2.1--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(pytor_files)
+    val bin_sizes
+    val output_format
+
+    output:
+    tuple val(meta), path("*.vcf"), emit: vcf      , optional: true
+    tuple val(meta), path("*.tsv"), emit: tsv      , optional: true
+    tuple val(meta), path("*.xls"), emit: xls      , optional: true
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def output_suffix = output_format ?: 'vcf'
+    def bins   = bin_sizes ?: '1000'
+    def input  = pytor_files.join(" ")
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+
+    python3 <<CODE
+    import cnvpytor,os
+    binsizes = "${bins}".split(" ")
+    for binsize in binsizes:
+        file_list = "${input}".split(" ")
+        app = cnvpytor.Viewer(file_list, params={} )
+        outputfile = "{}_{}.{}".format("${prefix}",binsize.strip(),"${output_suffix}")
+        app.print_filename = outputfile
+        app.bin_size = int(binsize)
+        app.print_calls_file()
+    CODE
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
+    END_VERSIONS
+    """
+
+    stub:
+    def output_suffix = output_format ?: 'vcf'
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.${output_suffix}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
+    END_VERSIONS
+    """
+}

modules/cnvpytor/view/meta.yml

@@ -0,0 +1,56 @@
+name: cnvpytor_view
+description: view function to generate vcfs
+keywords:
+  - cnv calling
+tools:
+  - cnvpytor:
+      description: calling CNVs using read depth
+      homepage: https://github.com/abyzovlab/CNVpytor
+      documentation: https://github.com/abyzovlab/CNVpytor
+      tool_dev_url: https://github.com/abyzovlab/CNVpytor
+      doi: "10.1101/2021.01.27.428472v1"
+      licence: ["MIT"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - pytor_files:
+      type: file
+      description: pytor file containing cnv calls. To merge calls from multiple samples use a list of files.
+      pattern: "*.{pytor}"
+  - bin_sizes:
+      type: string
+      description: list of binsizes separated by space e.g. "1000 10000" and "1000"
+  - output_format:
+      type: string
+      description: output format of the cnv calls. Valid entries are "tsv", "vcf", and "xls"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - tsv:
+      type: file
+      description: tsv file containing cnv calls
+      pattern: "*.{tsv}"
+  - vcf:
+      type: file
+      description: vcf file containing cnv calls
+      pattern: "*.{vcf}"
+  - xls:
+      type: file
+      description: xls file containing cnv calls
+      pattern: "*.{xls}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@sima-r"
+  - "@ramprasadn"

modules/ensemblvep/Dockerfile

@@ -8,13 +8,14 @@ LABEL \
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
 
-# Add conda installation dir to PATH (instead of doing 'conda activate')
-ENV PATH /opt/conda/envs/nf-core-vep-104.3/bin:$PATH
-
 # Setup default ARG variables
 ARG GENOME=GRCh38
 ARG SPECIES=homo_sapiens
-ARG VEP_VERSION=99
+ARG VEP_VERSION=104
+ARG VEP_TAG=104.3
+
+# Add conda installation dir to PATH (instead of doing 'conda activate')
+ENV PATH /opt/conda/envs/nf-core-vep-${VEP_TAG}/bin:$PATH
 
 # Download Genome
 RUN vep_install \
@@ -27,4 +28,4 @@ RUN vep_install \
     --NO_BIOPERL --NO_HTSLIB --NO_TEST --NO_UPDATE
 
 # Dump the details of the installed packages to a file for posterity
-RUN conda env export --name nf-core-vep-104.3 > nf-core-vep-104.3.yml
+RUN conda env export --name nf-core-vep-${VEP_TAG} > nf-core-vep-${VEP_TAG}.yml

modules/ensemblvep/build.sh

@@ -10,11 +10,12 @@ build_push() {
     VEP_TAG=$4
 
     docker build \
+        . \
         -t nfcore/vep:${VEP_TAG}.${GENOME} \
-        software/vep/. \
         --build-arg GENOME=${GENOME} \
         --build-arg SPECIES=${SPECIES} \
-        --build-arg VEP_VERSION=${VEP_VERSION}
+        --build-arg VEP_VERSION=${VEP_VERSION} \
+        --build-arg VEP_TAG=${VEP_TAG}
 
     docker push nfcore/vep:${VEP_TAG}.${GENOME}
 }

modules/ensemblvep/main.nf

@@ -13,6 +13,7 @@ process ENSEMBLVEP {
     val   species
     val   cache_version
     path  cache
+    path  extra_files
 
     output:
     tuple val(meta), path("*.ann.vcf"), emit: vcf

modules/ensemblvep/meta.yml

@@ -10,17 +10,6 @@ tools:
       homepage: https://www.ensembl.org/info/docs/tools/vep/index.html
       documentation: https://www.ensembl.org/info/docs/tools/vep/script/index.html
       licence: ["Apache-2.0"]
-params:
-  - use_cache:
-      type: boolean
-      description: |
-        Enable the usage of containers with cache
-        Does not work with conda
-  - vep_tag:
-      type: value
-      description: |
-        Specify the tag for the container
-        https://hub.docker.com/r/nfcore/vep/tags
 input:
   - meta:
       type: map
@@ -47,6 +36,10 @@ input:
       type: file
       description: |
         path to VEP cache (optional)
+  - extra_files:
+      type: tuple
+      description: |
+        path to file(s) needed for plugins  (optional)
 output:
   - vcf:
       type: file

modules/gatk4/mergebamalignment/main.nf

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

modules/gatk4/mutect2/main.nf

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

modules/gatk4/revertsam/main.nf

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

modules/gatk4/samtofastq/main.nf

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

modules/happy/happy/main.nf

@@ -0,0 +1,42 @@
+def VERSION = '0.3.14'
+
+process HAPPY_HAPPY {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::hap.py=0.3.14" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/hap.py:0.3.14--py27h5c5a3ab_0':
+        'quay.io/biocontainers/hap.py:0.3.14--py27h5c5a3ab_0' }"
+
+    input:
+    tuple val(meta), path(truth_vcf), path(query_vcf), path(bed)
+    tuple path(fasta), path(fasta_fai)
+
+    output:
+    tuple val(meta), path('*.csv'), path('*.json')  , emit: metrics
+    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}"
+
+    """
+    hap.py \\
+        $truth_vcf \\
+        $query_vcf \\
+        $args \\
+        --reference $fasta \\
+        --threads $task.cpus \\
+        -R $bed \\
+        -o $prefix
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        hap.py: $VERSION
+    END_VERSIONS
+    """
+}

modules/happy/happy/meta.yml

@@ -0,0 +1,67 @@
+name: "happy_happy"
+description: Hap.py is a tool to compare diploid genotypes at haplotype level. Rather than comparing VCF records row by row, hap.py will generate and match alternate sequences in a superlocus. A superlocus is a small region of the genome (sized between 1 and around 1000 bp) that contains one or more variants.
+keywords:
+  - happy
+  - benchmark
+  - haplotype
+tools:
+  - "happy":
+      description: "Haplotype VCF comparison tools"
+      homepage: "https://www.illumina.com/products/by-type/informatics-products/basespace-sequence-hub/apps/hap-py-benchmarking.html"
+      documentation: "https://github.com/Illumina/hap.py"
+      tool_dev_url: "https://github.com/Illumina/hap.py"
+      doi: ""
+      licence: "['BSD-2-clause']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - truth_vcf:
+      type: file
+      description: gold standard VCF file
+      pattern: "*.{vcf,vcf.gz}"
+  - query_vcf:
+      type: file
+      description: VCF/GVCF file to query
+      pattern: "*.{vcf,vcf.gz}"
+  - bed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+  - fasta:
+      type: file
+      description: FASTA file of the reference genome
+      pattern: "*.{fa,fasta}"
+  - fasta_fai:
+      type: file
+      description: The index of the reference FASTA
+      pattern: "*.fai"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - summary:
+      type: file
+      description: A CSV file containing the summary of the benchmarking
+      pattern: "*.summary.csv"
+  - extended:
+      type: file
+      description: A CSV file containing extended info of the benchmarking
+      pattern: "*.extended.csv"
+  - runinfo:
+      type: file
+      description: A JSON file containing the run info
+      pattern: "*.runinfo.json"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@nvnieuwk"

modules/happy/prepy/main.nf

@@ -0,0 +1,41 @@
+def VERSION = '0.3.14'
+
+process HAPPY_PREPY {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::hap.py=0.3.14" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/hap.py:0.3.14--py27h5c5a3ab_0':
+        'quay.io/biocontainers/hap.py:0.3.14--py27h5c5a3ab_0' }"
+
+    input:
+    tuple val(meta), path(vcf), path(bed)
+    tuple path(fasta), path(fasta_fai)
+
+    output:
+    tuple val(meta), path('*.vcf.gz')  , emit: preprocessed_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}"
+
+    """
+    pre.py \\
+        $args \\
+        -R $bed \\
+        --reference $fasta \\
+        --threads $task.cpus \\
+        $vcf \\
+        ${prefix}.vcf.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        pre.py: $VERSION
+    END_VERSIONS
+    """
+}

modules/happy/prepy/meta.yml

@@ -0,0 +1,55 @@
+name: "happy_prepy"
+description: Pre.py is a preprocessing tool made to preprocess VCF files for Hap.py
+keywords:
+  - happy
+  - benchmark
+  - haplotype
+tools:
+  - "happy":
+      description: "Haplotype VCF comparison tools"
+      homepage: "https://www.illumina.com/products/by-type/informatics-products/basespace-sequence-hub/apps/hap-py-benchmarking.html"
+      documentation: "https://github.com/Illumina/hap.py"
+      tool_dev_url: "https://github.com/Illumina/hap.py"
+      doi: ""
+      licence: "['BSD-2-clause']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: VCF file to preprocess
+      pattern: "*.{vcf,vcf.gz}"
+  - bed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+  - fasta:
+      type: file
+      description: FASTA file of the reference genome
+      pattern: "*.{fa,fasta}"
+  - fasta_fai:
+      type: file
+      description: The index of the reference FASTA
+      pattern: "*.fai"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: A preprocessed VCF file
+      pattern: "*.vcf.gz"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@nvnieuwk"

modules/krona/kronadb/main.nf

@@ -18,7 +18,9 @@ process KRONA_KRONADB {
     script:
     def args = task.ext.args ?: ''
     """
-    ktUpdateTaxonomy.sh taxonomy
+    ktUpdateTaxonomy.sh \\
+        $args \\
+        taxonomy/
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/krona/ktimporttaxonomy/main.nf

@@ -23,7 +23,10 @@ process KRONA_KTIMPORTTAXONOMY {
     script:
     def args = task.ext.args ?: ''
     """
-    ktImportTaxonomy "$report" -tax taxonomy
+    ktImportTaxonomy \\
+        $args \\
+        -tax taxonomy/ \\
+        "$report"
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/krona/ktimporttaxonomy/meta.yml

@@ -23,8 +23,11 @@ input:
         Groovy Map containing sample information
         e.g. [ id:'test']
   - database:
-      type: path
+      type: file
-      description: "Path to the taxonomy database downloaded by krona/kronadb"
+      description: |
+        Path to the taxonomy database .tab file downloaded by krona/ktUpdateTaxonomy
+        The file will be saved under a folder named "taxonomy" as "taxonomy/taxonomy.tab".
+        The parent folder will be passed as argument to ktImportTaxonomy.
   - report:
       type: file
       description: "A tab-delimited file with taxonomy IDs and (optionally) query IDs, magnitudes, and scores.  Query IDs are taken from column 1, taxonomy IDs from column 2, and scores from column 3.  Lines beginning with # will be ignored."

modules/krona/ktupdatetaxonomy/main.nf

@@ -0,0 +1,30 @@
+def VERSION='2.7.1' // Version information not provided by tool on CLI
+
+process KRONA_KTUPDATETAXONOMY {
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::krona=2.7.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/krona:2.7.1--pl526_5' :
+        'quay.io/biocontainers/krona:2.7.1--pl526_5' }"
+
+    output:
+    path 'taxonomy/taxonomy.tab', emit: db
+    path "versions.yml"         , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    ktUpdateTaxonomy.sh \\
+        $args \\
+        taxonomy/
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        krona: $VERSION
+    END_VERSIONS
+    """
+}

modules/krona/ktupdatetaxonomy/meta.yml

@@ -0,0 +1,31 @@
+name: krona_ktupdatetaxonomy
+description: KronaTools Update Taxonomy downloads a taxonomy database
+keywords:
+  - database
+  - taxonomy
+  - krona
+  - visualisation
+tools:
+  - krona:
+      description: Krona Tools is a set of scripts to create Krona charts from several Bioinformatics tools as well as from text and XML files.
+      homepage: https://github.com/marbl/Krona/wiki/KronaTools
+      documentation: https://github.com/marbl/Krona/wiki/Installing
+      tool_dev_url:
+      doi: https://doi.org/10.1186/1471-2105-12-385
+      licence:
+
+input:
+  - none: There is no input. This module downloads a pre-built taxonomy database for use with Krona Tools.
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - db:
+      type: file
+      description: A TAB separated file that contains a taxonomy database.
+      pattern: "*.{tab}"
+
+authors:
+  - "@mjakobs"

modules/md5sum/main.nf

@@ -0,0 +1,35 @@
+process MD5SUM {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "conda-forge::coreutils=9.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
+        'ubuntu:20.04' }"
+
+    input:
+    tuple val(meta), path(file)
+
+    output:
+    tuple val(meta), path("*.md5"), emit: checksum
+    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}"
+
+    """
+    md5sum \\
+        $args \\
+        ${file} \\
+        > ${file}.md5
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        md5sum: \$(echo \$(md5sum --version 2>&1 | head -n 1| sed 's/^.*) //;' ))
+    END_VERSIONS
+    """
+}

modules/md5sum/meta.yml

@@ -0,0 +1,39 @@
+name: "md5sum"
+description: Create an MD5 (128-bit) checksum
+keywords:
+  - checksum
+tools:
+  - "md5sum":
+      description: Create an MD5 (128-bit) checksum
+      homepage: "https://www.gnu.org"
+      documentation: "https://man7.org/linux/man-pages/man1/md5sum.1.html"
+      licence: GPLv3+
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - file:
+      type: file
+      description: Any file
+      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"
+  - checksum:
+      type: file
+      description: File containing checksum
+      pattern: "*.md5"
+
+authors:
+  - "@matthdsm"

modules/meryl/count/main.nf

@@ -0,0 +1,37 @@
+process MERYL_COUNT {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::meryl=1.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/meryl:1.3--h87f3376_1':
+        'quay.io/biocontainers/meryl:1.3--h87f3376_1' }"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*.meryldb"), emit: meryl_db
+    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}"
+    """
+    for READ in $reads; do
+        meryl count \\
+            threads=$task.cpus \\
+            $args \\
+            $reads \\
+            output read.\${READ%.f*}.meryldb
+    done
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        meryl: \$( meryl --version |& sed 's/meryl //' )
+    END_VERSIONS
+    """
+}

modules/meryl/count/meta.yml

@@ -0,0 +1,43 @@
+name: "meryl_count"
+description: A genomic k-mer counter (and sequence utility) with nice features.
+keywords:
+  - k-mer
+  - count
+tools:
+  - "meryl":
+      description: "A genomic k-mer counter (and sequence utility) with nice features. "
+      homepage: "https://github.com/marbl/meryl"
+      documentation: "https://meryl.readthedocs.io/en/latest/quick-start.html"
+      tool_dev_url: "https://github.com/marbl/meryl"
+      doi: ""
+      licence: "['GPL']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - meryl_db:
+      type: directory
+      description: A Meryl k-mer database
+      pattern: "*.meryldb"
+
+authors:
+  - "@mahesh-panchal"

modules/meryl/histogram/main.nf

@@ -0,0 +1,34 @@
+process MERYL_HISTOGRAM {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::meryl=1.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/meryl:1.3--h87f3376_1':
+        'quay.io/biocontainers/meryl:1.3--h87f3376_1' }"
+
+    input:
+    tuple val(meta), path(meryl_db)
+
+    output:
+    tuple val(meta), path("*.hist"), emit: hist
+    path "versions.yml"            , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    meryl histogram \\
+        threads=$task.cpus \\
+        $args \\
+        $meryl_db > ${prefix}.hist
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        meryl: \$( meryl --version |& sed 's/meryl //' )
+    END_VERSIONS
+    """
+}

modules/meryl/histogram/meta.yml

@@ -0,0 +1,41 @@
+name: "meryl_histogram"
+description: A genomic k-mer counter (and sequence utility) with nice features.
+keywords:
+  - k-mer
+  - histogram
+tools:
+  - "meryl":
+      description: "A genomic k-mer counter (and sequence utility) with nice features. "
+      homepage: "https://github.com/marbl/meryl"
+      documentation: "https://meryl.readthedocs.io/en/latest/quick-start.html"
+      tool_dev_url: "https://github.com/marbl/meryl"
+      doi: ""
+      licence: "['GPL']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - meryl_dbs:
+      type: directory
+      description: Meryl k-mer database
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - hist:
+      type: file
+      description: Histogram of k-mers
+      pattern: "*.hist"
+
+authors:
+  - "@mahesh-panchal"

modules/meryl/unionsum/main.nf

@@ -0,0 +1,35 @@
+process MERYL_UNIONSUM {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::meryl=1.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/meryl:1.3--h87f3376_1':
+        'quay.io/biocontainers/meryl:1.3--h87f3376_1' }"
+
+    input:
+    tuple val(meta), path(meryl_dbs)
+
+    output:
+    tuple val(meta), path("*.unionsum.meryldb"), emit: meryl_db
+    path "versions.yml"                        , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    meryl union-sum \\
+        threads=$task.cpus \\
+        $args \\
+        output ${prefix}.unionsum.meryldb \\
+        $meryl_dbs
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        meryl: \$( meryl --version |& sed 's/meryl //' )
+    END_VERSIONS
+    """
+}

modules/meryl/unionsum/meta.yml

@@ -0,0 +1,41 @@
+name: "meryl_unionsum"
+description: A genomic k-mer counter (and sequence utility) with nice features.
+keywords:
+  - k-mer
+  - unionsum
+tools:
+  - "meryl":
+      description: "A genomic k-mer counter (and sequence utility) with nice features. "
+      homepage: "https://github.com/marbl/meryl"
+      documentation: "https://meryl.readthedocs.io/en/latest/quick-start.html"
+      tool_dev_url: "https://github.com/marbl/meryl"
+      doi: ""
+      licence: "['GPL']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - meryl_dbs:
+      type: directory
+      description: Meryl k-mer databases
+
+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"
+  - meryl_db:
+      type: directory
+      description: A Meryl k-mer database that is the union sum of the input databases
+      pattern: "*.unionsum.meryldb"
+
+authors:
+  - "@mahesh-panchal"

modules/metaphlan3/main.nf

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

modules/motus/downloaddb/main.nf

@@ -0,0 +1,39 @@
+process MOTUS_DOWNLOADDB {
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::motus=3.0.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/motus:3.0.1--pyhdfd78af_0':
+        'quay.io/biocontainers/motus:3.0.1--pyhdfd78af_0' }"
+
+    input:
+    path motus_downloaddb_script
+
+    output:
+    path "db_mOTU/"                , emit: db
+    path "versions.yml"            , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args     = task.ext.args ?: ''
+    def software = "${motus_downloaddb_script.simpleName}_copy.py"
+    """
+    ## must copy script file to working directory,
+    ## otherwise the reference_db will be download to bin folder
+    ## other than current directory
+    cp $motus_downloaddb_script ${software}
+    python ${software} \\
+        $args \\
+        -t $task.cpus
+
+    ## mOTUs version number is not available from command line.
+    ## mOTUs save the version number in index database folder.
+    ## mOTUs will check the database version is same version as exec version.
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        mOTUs: \$(grep motus db_mOTU/db_mOTU_versions | sed 's/motus\\t//g')
+    END_VERSIONS
+    """
+}

modules/motus/downloaddb/meta.yml

@@ -0,0 +1,39 @@
+name: "motus_downloaddb"
+description: Download the mOTUs database
+keywords:
+  - classify
+  - metagenomics
+  - fastq
+  - taxonomic profiling
+  - database
+  - download
+tools:
+  - "motus":
+      description: "The mOTU profiler is a computational tool that estimates relative taxonomic abundance of known and currently unknown microbial community members using metagenomic shotgun sequencing data."
+      homepage: "None"
+      documentation: "https://github.com/motu-tool/mOTUs/wiki"
+      tool_dev_url: "https://github.com/motu-tool/mOTUs"
+      doi: "10.1038/s41467-019-08844-4"
+      licence: "['GPL v3']"
+
+input:
+  - motus_downloaddb:
+      type: directory
+      description: |
+        The mOTUs downloadDB script source file.
+        It is the source file installed or
+        remote source in github such as https://raw.githubusercontent.com/motu-tool/mOTUs/master/motus/downloadDB.py
+      pattern: "downloadDB.py"
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - db:
+      type: directory
+      description: The mOTUs database directory
+      pattern: "db_mOTU"
+
+authors:
+  - "@jianhong"

modules/rtgtools/vcfeval/main.nf

@@ -0,0 +1,59 @@
+process RTGTOOLS_VCFEVAL {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::rtg-tools=3.12.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/rtg-tools:3.12.1--hdfd78af_0':
+        'quay.io/biocontainers/rtg-tools:3.12.1--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(query_vcf), path(query_vcf_tbi)
+    tuple path(truth_vcf), path(truth_vcf_tbi)
+    path(truth_regions)
+    path(evaluation_regions)
+    path(sdf)
+
+    output:
+    tuple val(meta), path("**results/{done,progress,*.log}") , emit: logs
+    tuple val(meta), path("**tp.vcf.gz"), path("**tp.vcf.gz.tbi") , emit: tp
+    tuple val(meta), path("**fn.vcf.gz"), path("**fn.vcf.gz.tbi") , emit: fn
+    tuple val(meta), path("**fp.vcf.gz"), path("**fp.vcf.gz.tbi") , emit: fp
+    tuple val(meta), path("**baseline.vcf.gz"), path("**baseline.vcf.gz.tbi") , emit: baseline
+    tuple val(meta), path("**.tsv.gz")                    , emit: roc
+    tuple val(meta), path("**results/summary.txt")        , emit: summary
+    tuple val(meta), path("**results/phasing.txt")        , emit: phasing
+    path "versions.yml"                                   , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ""
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def bed_regions = truth_regions ? "--bed-regions=$truth_regions" : ""
+    def eval_regions = evaluation_regions ? "--evaluation-regions=$evaluation_regions" : ""
+    def truth_index = truth_vcf_tbi ? "" : "rtg index $truth_vcf"
+    def query_index = query_vcf_tbi ? "" : "rtg index $query_vcf"
+
+    """
+    $truth_index
+    $query_index
+
+    rtg vcfeval \\
+        $args \\
+        --baseline=$truth_vcf \\
+        $bed_regions \\
+        $eval_regions \\
+        --calls=$query_vcf \\
+        --output=${prefix}_results \\
+        --template=$sdf \\
+        --threads=$task.cpus \\
+
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        rtg-tools: \$(echo \$(rtg version | head -n 1 | awk '{print \$4}'))
+    END_VERSIONS
+    """
+}

modules/rtgtools/vcfeval/meta.yml

@@ -0,0 +1,95 @@
+name: "rtgtools_vcfeval"
+description: The VCFeval tool of RTG tools. It is used to evaluate called variants for agreement with a baseline variant set
+keywords:
+  - benchmarking
+  - vcf
+  - rtg-tools
+tools:
+  - "rtgtools":
+      description: "RealTimeGenomics Tools -- Utilities for accurate VCF comparison and manipulation"
+      homepage: "https://www.realtimegenomics.com/products/rtg-tools"
+      documentation: "https://github.com/RealTimeGenomics/rtg-tools"
+      tool_dev_url: "https://github.com/RealTimeGenomics/rtg-tools"
+      doi: ""
+      licence: "['BSD']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - truth_vcf:
+      type: file
+      description: A standard VCF to compare against
+      pattern: "*.{vcf,vcf.gz}"
+  - truth_vcf_index:
+      type: file
+      description: The index of the standard VCF (optional)
+      pattern: "*.tbi"
+  - query_vcf:
+      type: file
+      description: A VCF with called variants to benchmark against the standard
+      pattern: "*.{vcf,vcf.gz}"
+  - query_vcf_index:
+      type: file
+      description: The index of the called VCF (optional)
+      pattern: "*.tbi"
+  - truth_regions:
+      type: file
+      description: A BED file containining the strict regions where VCFeval should only evaluate the fully overlapping variants (optional)
+      pattern: "*.bed"
+  - evaluation_regions:
+      type: file
+      description: A BED file containing the regions where VCFeval will evaluate every fully and partially overlapping variant (optional)
+      pattern: "*.bed"
+  - sdf:
+      type: file
+      description: The SDF (RTG Sequence Data File) folder of the reference genome
+      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"
+  - logging:
+      type: file
+      description: Files containing logging from vcfeval
+      pattern: "*{done,progress,.log}"
+  - tp:
+      type: file
+      description: A tuple containing the VCF and TBI file for the true positive variants
+      pattern: "tp.vcf{.gz,.gz.tbi}"
+  - baseline:
+      type: file
+      description: A tuple containing the VCF and TBI file for the baseline true positive variants
+      pattern: "tp-baseline.vcf{.gz,.gz.tbi}"
+  - fp:
+      type: file
+      description: A tuple containing the VCF and TBI file for the false positive variants
+      pattern: "fp.vcf{.gz,.gz.tbi}"
+  - fn:
+      type: file
+      description: A tuple containing the VCF and TBI file for the false negative variants
+      pattern: "fn.vcf{.gz,.gz.tbi}"
+  - roc:
+      type: file
+      description: TSV files containing ROC data for the evaluated variants
+      pattern: "*.tsv.gz"
+  - summary:
+      type: file
+      description: A TXT file containing the summary of the evaluation
+      pattern: "summary.txt"
+  - phasing:
+      type: file
+      description: A TXT file containing the data on the phasing
+      pattern: "phasing.txt"
+
+authors:
+  - "@nvnieuwk"

modules/samtools/bam2fq/main.nf

@@ -45,7 +45,7 @@ process SAMTOOLS_BAM2FQ {
             bam2fq \\
             $args \\
             -@ $task.cpus \\
-            $inputbam >${prefix}_interleaved.fq.gz
+            $inputbam | gzip --no-name > ${prefix}_interleaved.fq.gz
 
         cat <<-END_VERSIONS > versions.yml
         "${task.process}":

modules/samtools/convert/main.nf

@@ -1,5 +1,4 @@
-//There is a -L option to only output alignments in interval, might be an option for exons/panel data?
+process SAMTOOLS_CONVERT {
-process SAMTOOLS_BAMTOCRAM {
     tag "$meta.id"
     label 'process_medium'
 
@@ -14,8 +13,8 @@ process SAMTOOLS_BAMTOCRAM {
     path  fai
 
     output:
-    tuple val(meta), path("*.cram"), path("*.crai"), emit: cram_crai
+    tuple val(meta), path("*.{cram,bam}"), path("*.{crai,bai}") , emit: alignment_index
-    path  "versions.yml"                           , emit: versions
+    path  "versions.yml"                                        , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -23,9 +22,17 @@ process SAMTOOLS_BAMTOCRAM {
     script:
     def args = task.ext.args  ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def output_extension = input.getExtension() == "bam" ? "cram" : "bam"
+
     """
-    samtools view --threads ${task.cpus} --reference ${fasta} -C $args $input > ${prefix}.cram
+    samtools view \\
-    samtools index -@${task.cpus} ${prefix}.cram
+        --threads ${task.cpus} \\
+        --reference ${fasta} \\
+        $args \\
+        $input \\
+        -o ${prefix}.${output_extension}
+
+    samtools index -@${task.cpus} ${prefix}.${output_extension}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/samtools/convert/meta.yml

@@ -1,5 +1,5 @@
-name: samtools_bamtocram
+name: samtools_convert
-description: filter/convert and then index CRAM file
+description: convert and then index CRAM -> BAM or BAM -> CRAM file
 keywords:
   - view
   - index
@@ -23,12 +23,12 @@ input:
         e.g. [ id:'test', single_end:false ]
   - input:
       type: file
-      description: BAM/SAM file
+      description: BAM/CRAM file
-      pattern: "*.{bam,sam}"
+      pattern: "*.{bam,cram}"
   - index:
       type: file
-      description: BAM/SAM index file
+      description: BAM/CRAM index file
-      pattern: "*.{bai,sai}"
+      pattern: "*.{bai,crai}"
   - fasta:
       type: file
       description: Reference file to create the CRAM file
@@ -39,10 +39,10 @@ output:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
-  - cram_crai:
+  - alignment_index:
       type: file
-      description: filtered/converted CRAM file + index
+      description: filtered/converted BAM/CRAM file + index
-      pattern: "*{.cram,.crai}"
+      pattern: "*{.bam/cram,.bai/crai}"
   - version:
       type: file
       description: File containing software version

modules/samtools/view/main.nf

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

modules/shasum/main.nf

@@ -0,0 +1,35 @@
+process SHASUM {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "conda-forge::coreutils=9.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
+        'ubuntu:20.04' }"
+
+    input:
+    tuple val(meta), path(file)
+
+    output:
+    tuple val(meta), path("*.sha256"), emit: checksum
+    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}"
+
+    """
+    sha256sum \\
+        $args \\
+        ${file} \\
+        > ${file}.sha256
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        sha256sum: \$(echo \$(sha256sum --version 2>&1 | head -n 1| sed 's/^.*) //;' ))
+    END_VERSIONS
+    """
+}

modules/shasum/meta.yml

@@ -0,0 +1,40 @@
+name: "shasum"
+description: Print SHA256 (256-bit) checksums.
+keywords:
+  - checksum
+  - sha256
+tools:
+  - "md5sum":
+      description: Create an SHA256 (256-bit) checksum.
+      homepage: "https://www.gnu.org"
+      documentation: "https://linux.die.net/man/1/shasum"
+      licence: GPLv3+
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - file:
+      type: file
+      description: Any file
+      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"
+  - checksum:
+      type: file
+      description: File containing checksum
+      pattern: "*.sha256"
+
+authors:
+  - "@matthdsm"

modules/shigatyper/main.nf

@@ -0,0 +1,64 @@
+process SHIGATYPER {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::shigatyper=2.0.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/shigatyper%3A2.0.1--pyhdfd78af_0':
+        'quay.io/biocontainers/shigatyper:2.0.1--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("${prefix}.tsv")     , emit: tsv
+    tuple val(meta), path("${prefix}-hits.tsv"), optional: true, emit: hits
+    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}"
+
+    if (meta.is_ont) {
+        """
+        shigatyper \\
+            $args \\
+            --SE $reads \\
+            --ont \\
+            --name $prefix
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            shigatyper: \$(echo \$(shigatyper --version 2>&1) | sed 's/^.*ShigaTyper //' )
+        END_VERSIONS
+        """
+    } else if (meta.single_end) {
+        """
+        shigatyper \\
+            $args \\
+            --SE $reads \\
+            --name $prefix
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            shigatyper: \$(echo \$(shigatyper --version 2>&1) | sed 's/^.*ShigaTyper //' )
+        END_VERSIONS
+        """
+    } else {
+        """
+        shigatyper \\
+            $args \\
+            --R1 ${reads[0]} \\
+            --R2 ${reads[1]} \\
+            --name $prefix
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            shigatyper: \$(echo \$(shigatyper --version 2>&1) | sed 's/^.*ShigaTyper //' )
+        END_VERSIONS
+        """
+    }
+}

modules/shigatyper/meta.yml

@@ -0,0 +1,47 @@
+name: "shigatyper"
+description: Determine Shigella serotype from Illumina or Oxford Nanopore reads
+keywords:
+  - fastq
+  - shigella
+  - serotype
+tools:
+  - "shigatyper":
+      description: "Typing tool for Shigella spp. from WGS Illumina sequencing"
+      homepage: "https://github.com/CFSAN-Biostatistics/shigatyper"
+      documentation: "https://github.com/CFSAN-Biostatistics/shigatyper"
+      tool_dev_url: "https://github.com/CFSAN-Biostatistics/shigatyper"
+      doi: "10.1128/AEM.00165-19"
+      licence: "['Public Domain']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false, is_ont:false ]
+  - reads:
+      type: file
+      description: Illumina or Nanopore FASTQ file
+      pattern: "*.fastq.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"
+  - tsv:
+      type: file
+      description: A TSV formatted file with ShigaTyper results
+      pattern: "*.tsv"
+  - hits:
+      type: file
+      description: A TSV formatted file with individual gene hits
+      pattern: "*-hits.tsv"
+
+authors:
+  - "@rpetit3"

modules/slimfastq/main.nf

@@ -0,0 +1,52 @@
+def VERSION = '2.04'
+
+process SLIMFASTQ {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::slimfastq=2.04" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/slimfastq:2.04--h87f3376_2':
+        'quay.io/biocontainers/slimfastq:2.04--h87f3376_2' }"
+
+    input:
+    tuple val(meta), path(fastq)
+
+    output:
+    tuple val(meta), path("*.sfq"), emit: sfq
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    if (meta.single_end) {
+        """
+        gzip -d -c '${fastq}' | slimfastq \\
+            $args \\
+            -f '${prefix}.sfq'
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            slimfastq: ${VERSION}
+        END_VERSIONS
+        """
+    } else {
+        """
+        gzip -d -c '${fastq[0]}' | slimfastq \\
+            $args \\
+            -f '${prefix}_1.sfq'
+
+        gzip -d -c '${fastq[1]}' | slimfastq \\
+            $args \\
+            -f '${prefix}_2.sfq'
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            slimfastq: ${VERSION}
+        END_VERSIONS
+        """
+    }
+}

modules/slimfastq/meta.yml

@@ -0,0 +1,41 @@
+name: "slimfastq"
+description: Fast, efficient, lossless compression of FASTQ files.
+keywords:
+  - FASTQ
+  - compression
+  - lossless
+tools:
+  - "slimfastq":
+      description: "slimfastq efficiently compresses/decompresses FASTQ files"
+      homepage: "https://github.com/Infinidat/slimfastq"
+      tool_dev_url: "https://github.com/Infinidat/slimfastq"
+      licence: "['BSD-3-clause']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fastq:
+      type: file
+      description: Either a single-end FASTQ file or paired-end files.
+      pattern: "*.{fq.gz,fastq.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"
+  - sfq:
+      type: file
+      description: Either one or two sequence files in slimfastq compressed format.
+      pattern: "*.{sfq}"
+
+authors:
+  - "@Midnighter"

modules/snapaligner/align/main.nf

@@ -1,4 +1,4 @@
-process SNAPALIGNER_SINGLE {
+process SNAPALIGNER_ALIGN {
     tag '$meta.id'
     label 'process_high'
 
@@ -21,15 +21,16 @@ process SNAPALIGNER_SINGLE {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def subcmd = meta.single_end ? "single" : "paired"
 
     """
     mkdir -p index
     mv $index index/
 
-    snap-aligner single \\
+    snap-aligner ${subcmd} \\
         index \\
         ${reads.join(" ")} \\
-        -o -bam ${prefix}.bam \\
+        -o ${prefix}.bam \\
         -t ${task.cpus} \\
         $args
 

modules/snapaligner/align/meta.yml

@@ -1,5 +1,5 @@
-name: "snapaligner_single"
+name: "snapaligner_align"
-description: Performs single end fastq alignment to a fasta reference using SNAP
+description: Performs fastq alignment to a fasta reference using SNAP
 keywords:
   - alignment
   - map
@@ -22,7 +22,7 @@ input:
         e.g. [ id:'test', single_end:false ]
   - reads:
       type: file
-      description: List of single end input files
+      description: List of input fastq files of size 2 for paired fastq or 1 for bam or single fastq
       pattern: "*.{fastq.gz,fq.gz,fastq,fq,bam}"
   - index:
       type: file

modules/snapaligner/paired/main.nf

@@ -1,41 +0,0 @@
-process SNAPALIGNER_PAIRED {
-    tag '$meta.id'
-    label 'process_high'
-
-    conda (params.enable_conda ? "bioconda::snap-aligner=2.0.1" : null)
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/snap-aligner:2.0.1--hd03093a_1':
-        'quay.io/biocontainers/snap-aligner:2.0.1--hd03093a_1' }"
-
-    input:
-    tuple val(meta), path(reads)
-    path index
-
-    output:
-    tuple val(meta), path("*.bam"), emit: bam
-    path "versions.yml"           , emit: versions
-
-    when:
-    task.ext.when == null || task.ext.when
-
-    script:
-    def args = task.ext.args ?: ''
-    def prefix = task.ext.prefix ?: "${meta.id}"
-
-    """
-    mkdir -p index
-    mv $index index/
-
-    snap-aligner paired \\
-        index \\
-        ${reads.join(" ")} \\
-        -o -bam ${prefix}.bam \\
-        -t ${task.cpus} \\
-        $args
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        snapaligner: \$(snap-aligner 2>&1| head -n 1 | sed 's/^.*version //;s/.\$//')
-    END_VERSIONS
-    """
-}

modules/snapaligner/paired/meta.yml

@@ -1,48 +0,0 @@
-name: "snapaligner_paired"
-description: Performs paired end fastq alignment to a fasta reference using SNAP
-keywords:
-  - alignment
-  - map
-  - fastq
-  - bam
-  - sam
-tools:
-  - "snapaligner":
-      description: "Scalable Nucleotide Alignment Program -- a fast and accurate read aligner for high-throughput sequencing data"
-      homepage: "http://snap.cs.berkeley.edu"
-      documentation: "https://1drv.ms/b/s!AhuEg_0yZD86hcpblUt-muHKYsG8fA?e=R8ogug"
-      tool_dev_url: "https://github.com/amplab/snap"
-      doi: "10.1101/2021.11.23.469039"
-      licence: "['Apache 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 2 for fastq or 1 for bam
-      pattern: "*.{fastq.gz,fq.gz,fastq,fq,bam}"
-  - index:
-      type: file
-      description: List of SNAP genome index files
-      pattern: "{Genome,GenomeIndex,GenomeIndexHash,OverflowTable}"
-
-output:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
-  - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
-  - bam:
-      type: file
-      description: Aligned BAM file
-      pattern: "*.{bam}"
-
-authors:
-  - "@matthdsm"

modules/snpeff/Dockerfile

@@ -8,15 +8,16 @@ LABEL \
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
 
-# Add conda installation dir to PATH (instead of doing 'conda activate')
-ENV PATH /opt/conda/envs/nf-core-snpeff-5.0/bin:$PATH
-
 # Setup default ARG variables
 ARG GENOME=GRCh38
 ARG SNPEFF_CACHE_VERSION=99
+ARG SNPEFF_TAG=99
+
+# Add conda installation dir to PATH (instead of doing 'conda activate')
+ENV PATH /opt/conda/envs/nf-core-snpeff-${SNPEFF_TAG}/bin:$PATH
 
 # Download Genome
 RUN snpEff download -v ${GENOME}.${SNPEFF_CACHE_VERSION}
 
 # Dump the details of the installed packages to a file for posterity
-RUN conda env export --name nf-core-snpeff-5.0 > nf-core-snpeff-5.0.yml
+RUN conda env export --name nf-core-snpeff-${SNPEFF_TAG} > nf-core-snpeff-${SNPEFF_TAG}.yml

modules/snpeff/build.sh

@@ -9,10 +9,11 @@ build_push() {
     SNPEFF_TAG=$3
 
     docker build \
+        . \
         -t nfcore/snpeff:${SNPEFF_TAG}.${GENOME} \
-        software/snpeff/. \
         --build-arg GENOME=${GENOME} \
-        --build-arg SNPEFF_CACHE_VERSION=${SNPEFF_CACHE_VERSION}
+        --build-arg SNPEFF_CACHE_VERSION=${SNPEFF_CACHE_VERSION} \
+        --build-arg SNPEFF_TAG=${SNPEFF_TAG}
 
     docker push nfcore/snpeff:${SNPEFF_TAG}.${GENOME}
 }

modules/snpeff/meta.yml

@@ -10,18 +10,6 @@ tools:
       homepage: https://pcingola.github.io/SnpEff/
       documentation: https://pcingola.github.io/SnpEff/se_introduction/
       licence: ["MIT"]
-params:
-  - use_cache:
-      type: boolean
-      description: |
-        boolean to enable the usage of containers with cache
-        Enable the usage of containers with cache
-        Does not work with conda
-  - snpeff_tag:
-      type: value
-      description: |
-        Specify the tag for the container
-        https://hub.docker.com/r/nfcore/snpeff/tags
 input:
   - meta:
       type: map

modules/sratools/prefetch/main.nf

@@ -1,43 +1,26 @@
 process SRATOOLS_PREFETCH {
     tag "$id"
     label 'process_low'
-    label 'error_retry'
 
     conda (params.enable_conda ? 'bioconda::sra-tools=2.11.0' : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/sra-tools:2.11.0--pl5262h314213e_0' :
+        'https://depot.galaxyproject.org/singularity/sra-tools:2.11.0--pl5321ha49a11a_3' :
-        'quay.io/biocontainers/sra-tools:2.11.0--pl5262h314213e_0' }"
+        'quay.io/biocontainers/sra-tools:2.11.0--pl5321ha49a11a_3' }"
 
     input:
     tuple val(meta), val(id)
 
     output:
-    tuple val(meta), path("$id"), emit: sra
+    tuple val(meta), path(id), emit: sra
     path "versions.yml"         , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
-    script:
+    shell:
-    def args = task.ext.args ?: ''
+    args = task.ext.args ?: ''
-    def config = "/LIBS/GUID = \"${UUID.randomUUID().toString()}\"\\n/libs/cloud/report_instance_identity = \"true\"\\n"
+    args2 = task.ext.args2 ?: '5 1 100'  // <num retries> <base delay in seconds> <max delay in seconds>
-    """
+    config = "/LIBS/GUID = \"${UUID.randomUUID().toString()}\"\\n/libs/cloud/report_instance_identity = \"true\"\\n"
-    eval "\$(vdb-config -o n NCBI_SETTINGS | sed 's/[" ]//g')"
-    if [[ ! -f "\${NCBI_SETTINGS}" ]]; then
-        mkdir -p "\$(dirname "\${NCBI_SETTINGS}")"
-        printf '${config}' > "\${NCBI_SETTINGS}"
-    fi
 
-    prefetch \\
+    template 'retry_with_backoff.sh'
-        $args \\
-        --progress \\
-        $id
-
-    vdb-validate $id
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        sratools: \$(prefetch --version 2>&1 | grep -Eo '[0-9.]+')
-    END_VERSIONS
-    """
 }

modules/sratools/prefetch/templates/retry_with_backoff.sh

@@ -0,0 +1,59 @@
+#!/usr/bin/env bash
+
+set -u
+
+retry_with_backoff() {
+    local max_attempts=${1}
+    local delay=${2}
+    local max_time=${3}
+    local attempt=1
+    local output=
+    local status=
+
+    # Remove the first three arguments to this function in order to access
+    # the 'real' command with `${@}`.
+    shift 3
+
+    while [ ${attempt} -le ${max_attempts} ]; do
+        output=$("${@}")
+        status=${?}
+
+        if [ ${status} -eq 0 ]; then
+            break
+        fi
+
+        if [ ${attempt} -lt ${max_attempts} ]; then
+            echo "Failed attempt ${attempt} of ${max_attempts}. Retrying in ${delay} s." >&2
+            sleep ${delay}
+        elif [ ${attempt} -eq ${max_attempts} ]; then
+            echo "Failed after ${attempt} attempts." >&2
+            return ${status}
+        fi
+
+        attempt=$(( ${attempt} + 1 ))
+        delay=$(( ${delay} * 2 ))
+        if [ ${delay} -ge ${max_time} ]; then
+            delay=${max_time}
+        fi
+    done
+
+    echo "${output}"
+}
+
+eval "$(vdb-config -o n NCBI_SETTINGS | sed 's/[" ]//g')"
+if [[ ! -f "${NCBI_SETTINGS}" ]]; then
+    mkdir -p "$(dirname "${NCBI_SETTINGS}")"
+    printf '!{config}' > "${NCBI_SETTINGS}"
+fi
+
+retry_with_backoff !{args2} \
+    prefetch \
+    !{args} \
+    !{id}
+
+vdb-validate !{id}
+
+cat <<-END_VERSIONS > versions.yml
+"!{task.process}":
+    sratools: $(prefetch --version 2>&1 | grep -Eo '[0-9.]+')
+END_VERSIONS

modules/srst2/srst2/main.nf

@@ -0,0 +1,47 @@
+process SRST2_SRST2 {
+    tag "${meta.id}"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::srst2=0.2.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/srst2%3A0.2.0--py27_2':
+        'quay.io/biocontainers/srst2:0.2.0--py27_2'}"
+
+    input:
+    tuple val(meta), path(fastq_s), path(db)
+
+    output:
+    tuple val(meta), path("*_genes_*_results.txt")               , optional:true, emit: gene_results
+    tuple val(meta), path("*_fullgenes_*_results.txt")           , optional:true, emit: fullgene_results
+    tuple val(meta), path("*_mlst_*_results.txt")                , optional:true, emit: mlst_results
+    tuple val(meta), path("*.pileup")                            ,                emit: pileup
+    tuple val(meta), path("*.sorted.bam")                        ,                emit: sorted_bam
+    path "versions.yml"                                          ,                emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ""
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def read_s = meta.single_end ? "--input_se ${fastq_s}" : "--input_pe ${fastq_s[0]} ${fastq_s[1]}"
+    if (meta.db=="gene") {
+        database = "--gene_db ${db}"
+    } else if (meta.db=="mlst") {
+        database = "--mlst_db ${db}"
+    } else {
+        error "Please set meta.db to either \"gene\" or \"mlst\""
+    }
+    """
+    srst2 \\
+        ${read_s} \\
+        --threads $task.cpus \\
+        --output ${prefix} \\
+        ${database} \\
+        $args
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        srst2: \$(echo \$(srst2 --version 2>&1) | sed 's/srst2 //' ))
+    END_VERSIONS
+    """
+}

modules/srst2/srst2/meta.yml

@@ -0,0 +1,72 @@
+name: srst2_srst2
+description: |
+  Short Read Sequence Typing for Bacterial Pathogens is a program designed to take Illumina sequence data,
+  a MLST database and/or a database of gene sequences (e.g. resistance genes, virulence genes, etc)
+  and report the presence of STs and/or reference genes.
+keywords:
+  - mlst
+  - typing
+  - illumina
+tools:
+  - srst2:
+      description: "Short Read Sequence Typing for Bacterial Pathogens"
+      homepage: "http://katholt.github.io/srst2/"
+      documentation: "https://github.com/katholt/srst2/blob/master/README.md"
+      tool_dev_url: "https://github.com/katholt/srst2"
+      doi: "10.1186/s13073-014-0090-6"
+      licence: ["BSD"]
+
+input:
+  - meta:
+      type: map0.2.0-4
+      description: |
+        Groovy Map containing sample information
+        id: should be the identification number or sample name
+        single_end: should be true for single end data and false for paired in data
+        db: should be either 'gene' to use the --gene_db option or "mlst" to use the --mlst_db option
+        e.g. [ id:'sample', single_end:false , db:'gene']
+  - fasta:
+      type: file
+      description: |
+        gzipped fasta file. If files are NOT in
+        MiSeq format sample_S1_L001_R1_001.fastq.gz uses --forward and --reverse parameters; otherwise
+        default is _1, i.e. expect forward reads as sample_1.fastq.gz).
+      pattern: "*.fastq.gz"
+  - db:
+      type: file
+      description: Database in FASTA format
+      pattern: "*.fasta"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'sample', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - txt:
+      type: file
+      description: A detailed report, with one row per gene per sample described here github.com/katholt/srst2#gene-typing
+      pattern: "*_fullgenes_*_results.txt"
+  - txt:
+      type: file
+      description: A tabulated summary report of samples x genes.
+      pattern: "*_genes_*_results.txt"
+  - txt:
+      type: file
+      description: A tabulated summary report of mlst subtyping.
+      pattern: "*_mlst_*_results.txt"
+  - bam:
+      type: file
+      description: Sorted BAM file
+      pattern: "*.sorted.bam"
+  - pileup:
+      type: file
+      description: SAMtools pileup file
+      pattern: "*.pileup"
+
+authors:
+  - "@jvhagey"

modules/svdb/merge/main.nf

@@ -2,10 +2,10 @@ process SVDB_MERGE {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::svdb=2.6.0" : null)
+    conda (params.enable_conda ? "bioconda::svdb=2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/svdb:2.6.0--py39h5371cbf_0':
+        'https://depot.galaxyproject.org/singularity/svdb:2.6.1--py39h5371cbf_0':
-        'quay.io/biocontainers/svdb:2.6.0--py39h5371cbf_0' }"
+        'quay.io/biocontainers/svdb:2.6.1--py39h5371cbf_0' }"
 
     input:
     tuple val(meta), path(vcfs)

modules/svdb/query/main.nf

@@ -2,10 +2,10 @@ process SVDB_QUERY {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::svdb=2.6.0" : null)
+    conda (params.enable_conda ? "bioconda::svdb=2.6.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/svdb:2.6.0--py39h5371cbf_0':
+        'https://depot.galaxyproject.org/singularity/svdb:2.6.1--py39h5371cbf_0':
-        'quay.io/biocontainers/svdb:2.6.0--py39h5371cbf_0' }"
+        'quay.io/biocontainers/svdb:2.6.1--py39h5371cbf_0' }"
 
     input:
     tuple val(meta), path(vcf)

modules/vardictjava/main.nf

@@ -0,0 +1,49 @@
+def VERSION = '1.8.3'
+
+process VARDICTJAVA {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::vardict-java=1.8.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/vardict-java:1.8.3--hdfd78af_0':
+        'quay.io/biocontainers/vardict-java:1.8.3--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(bam), path(bai), path(bed)
+    tuple path(fasta), path(fasta_fai)
+
+    output:
+    tuple val(meta), path("*.vcf.gz"), emit: vcf
+    path "versions.yml"              , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def args2 = task.ext.args2 ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    vardict-java \\
+        $args \\
+        -c 1 -S 2 -E 3 \\
+        -b $bam \\
+        -th $task.cpus \\
+        -N $prefix \\
+        -G $fasta \\
+        $bed \\
+        | teststrandbias.R \\
+        | var2vcf_valid.pl \\
+            $args2 \\
+            -N $prefix \\
+        | gzip -c > ${prefix}.vcf.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        vardict-java: $VERSION
+        var2vcf_valid.pl: \$(echo \$(var2vcf_valid.pl -h | sed -n 2p | awk '{ print \$2 }'))
+    END_VERSIONS
+    """
+}

modules/vardictjava/meta.yml

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

subworkflows/nf-core/annotation/ensemblvep/main.nf

@@ -0,0 +1,31 @@
+//
+// Run VEP to annotate VCF files
+//
+
+include { ENSEMBLVEP       } from '../../../../modules/ensemblvep/main'
+include { TABIX_BGZIPTABIX } from '../../../../modules/tabix/bgziptabix/main'
+
+workflow ANNOTATION_ENSEMBLVEP {
+    take:
+    vcf               // channel: [ val(meta), vcf ]
+    vep_genome        //   value: genome to use
+    vep_species       //   value: species to use
+    vep_cache_version //   value: cache version to use
+    vep_cache         //    path: /path/to/vep/cache (optionnal)
+    vep_extra_files   // channel: [ file1, file2...] (optionnal)
+
+    main:
+    ch_versions = Channel.empty()
+
+    ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
+    TABIX_BGZIPTABIX(ENSEMBLVEP.out.vcf)
+
+    // Gather versions of all tools used
+    ch_versions = ch_versions.mix(ENSEMBLVEP.out.versions.first())
+    ch_versions = ch_versions.mix(TABIX_BGZIPTABIX.out.versions.first())
+
+    emit:
+    vcf_tbi  = TABIX_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
+    reports  = ENSEMBLVEP.out.report       //    path: *.html
+    versions = ch_versions                 //    path: versions.yml
+}

subworkflows/nf-core/annotation/ensemblvep/meta.yml

@@ -0,0 +1,49 @@
+name: annotation_ensemblvep
+description: |
+  Perform annotation with ensemblvep and bgzip + tabix index the resulting VCF file
+keywords:
+  - ensemblvep
+modules:
+  - ensemblvep
+  - tabix/bgziptabix
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: |
+        vcf to annotate
+  - genome:
+      type: value
+      description: |
+        which genome to annotate with
+  - species:
+      type: value
+      description: |
+        which species to annotate with
+  - cache_version:
+      type: value
+      description: |
+        which version of the cache to annotate with
+  - cache:
+      type: file
+      description: |
+        path to VEP cache (optional)
+  - extra_files:
+      type: tuple
+      description: |
+        path to file(s) needed for plugins  (optional)
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - vcf_tbi:
+      type: file
+      description: Compressed vcf file + tabix index
+      pattern: "[ *{.vcf.gz,vcf.gz.tbi} ]"
+authors:
+  - "@maxulysse"

subworkflows/nf-core/annotation/snpeff/main.nf

@@ -0,0 +1,28 @@
+//
+// Run SNPEFF to annotate VCF files
+//
+
+include { SNPEFF           } from '../../../../modules/snpeff/main'
+include { TABIX_BGZIPTABIX } from '../../../../modules/tabix/bgziptabix/main'
+
+workflow ANNOTATION_SNPEFF {
+    take:
+    vcf          // channel: [ val(meta), vcf ]
+    snpeff_db    //   value: db version to use
+    snpeff_cache //    path: /path/to/snpeff/cache (optionnal)
+
+    main:
+    ch_versions = Channel.empty()
+
+    SNPEFF(vcf, snpeff_db, snpeff_cache)
+    TABIX_BGZIPTABIX(SNPEFF.out.vcf)
+
+    // Gather versions of all tools used
+    ch_versions = ch_versions.mix(SNPEFF.out.versions.first())
+    ch_versions = ch_versions.mix(TABIX_BGZIPTABIX.out.versions.first())
+
+    emit:
+    vcf_tbi  = TABIX_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
+    reports  = SNPEFF.out.report           //    path: *.html
+    versions = ch_versions                 //    path: versions.yml
+}

subworkflows/nf-core/annotation/snpeff/meta.yml

@@ -11,11 +11,19 @@ input:
       type: map
       description: |
         Groovy Map containing sample information
-        e.g. [ id:'test' ]
+        e.g. [ id:'test', single_end:false ]
-  - input:
+  - vcf:
-      type: vcf
+      type: file
-      description: list containing one vcf file
+      description: |
-      pattern: "[ *.{vcf,vcf.gz} ]"
+        vcf to annotate
+  - db:
+      type: value
+      description: |
+        which db to annotate with
+  - cache:
+      type: file
+      description: |
+        path to snpEff cache (optional)
 output:
   - versions:
       type: file

subworkflows/nf-core/annotation_ensemblvep/main.nf

@@ -1,26 +0,0 @@
-//
-// Run VEP to annotate VCF files
-//
-
-include { ENSEMBLVEP                                } from '../../../modules/ensemblvep/main'
-include { TABIX_BGZIPTABIX as ANNOTATION_BGZIPTABIX } from '../../../modules/tabix/bgziptabix/main'
-
-workflow ANNOTATION_ENSEMBLVEP {
-    take:
-    vcf               // channel: [ val(meta), vcf ]
-    vep_genome        //   value: which genome
-    vep_species       //   value: which species
-    vep_cache_version //   value: which cache version
-    vep_cache         //    path: path_to_vep_cache (optionnal)
-
-    main:
-    ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache)
-    ANNOTATION_BGZIPTABIX(ENSEMBLVEP.out.vcf)
-
-    ch_versions = ENSEMBLVEP.out.versions.first().mix(ANNOTATION_BGZIPTABIX.out.versions.first())
-
-    emit:
-    vcf_tbi  = ANNOTATION_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
-    reports  = ENSEMBLVEP.out.report            //    path: *.html
-    versions = ch_versions                      //    path: versions.yml
-}

subworkflows/nf-core/annotation_ensemblvep/meta.yml

@@ -1,29 +0,0 @@
-name: annotation_ensemblvep
-description: |
-  Perform annotation with ensemblvep and bgzip + tabix index the resulting VCF file
-keywords:
-  - ensemblvep
-modules:
-  - ensemblvep
-  - tabix/bgziptabix
-input:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test' ]
-  - input:
-      type: vcf
-      description: list containing one vcf file
-      pattern: "[ *.{vcf,vcf.gz} ]"
-output:
-  - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
-  - vcf_tbi:
-      type: file
-      description: Compressed vcf file + tabix index
-      pattern: "[ *{.vcf.gz,vcf.gz.tbi} ]"
-authors:
-  - "@maxulysse"

subworkflows/nf-core/annotation_snpeff/main.nf

@@ -1,23 +0,0 @@
-//
-// Run SNPEFF to annotate VCF files
-//
-
-include { SNPEFF                                    } from '../../../modules/snpeff/main'
-include { TABIX_BGZIPTABIX as ANNOTATION_BGZIPTABIX } from '../../../modules/tabix/bgziptabix/main'
-
-workflow ANNOTATION_SNPEFF {
-    take:
-    vcf            // channel: [ val(meta), vcf ]
-    snpeff_db      //   value: version of db to use
-    snpeff_cache   //    path: path_to_snpeff_cache (optionnal)
-
-    main:
-    SNPEFF(vcf, snpeff_db, snpeff_cache)
-    ANNOTATION_BGZIPTABIX(SNPEFF.out.vcf)
-    ch_versions = SNPEFF.out.versions.first().mix(ANNOTATION_BGZIPTABIX.out.versions.first())
-
-    emit:
-    vcf_tbi  = ANNOTATION_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
-    reports  = SNPEFF.out.report                //    path: *.html
-    versions = ch_versions                      //    path: versions.yml
-}

tests/config/pytest_modules.yml

@@ -341,6 +341,10 @@ bracken/bracken:
   - modules/bracken/bracken/**
   - tests/modules/bracken/bracken/**
 
+busco:
+  - modules/busco/**
+  - tests/modules/busco/**
+
 bwa/aln:
   - modules/bwa/aln/**
   - tests/modules/bwa/aln/**
@@ -895,6 +899,14 @@ hamronization/summarize:
   - modules/hamronization/summarize/**
   - tests/modules/hamronization/summarize/**
 
+happy/happy:
+  - modules/happy/happy/**
+  - tests/modules/happy/happy/**
+
+happy/prepy:
+  - modules/happy/prepy/**
+  - tests/modules/happy/prepy/**
+
 hicap:
   - modules/hicap/**
   - tests/modules/hicap/**
@@ -1062,6 +1074,10 @@ krona/ktimporttext:
   - modules/krona/ktimporttext/**
   - tests/modules/krona/ktimporttext/**
 
+krona/ktupdatetaxonomy:
+  - modules/krona/ktupdatetaxonomy/**
+  - tests/modules/krona/ktupdatetaxonomy/**
+
 last/dotplot:
   - modules/last/dotplot/**
   - tests/modules/last/dotplot/**
@@ -1182,6 +1198,10 @@ maxbin2:
   - modules/maxbin2/**
   - tests/modules/maxbin2/**
 
+md5sum:
+  - modules/md5sum/**
+  - tests/modules/md5sum/**
+
 medaka:
   - modules/medaka/**
   - tests/modules/medaka/**
@@ -1198,6 +1218,18 @@ meningotype:
   - modules/meningotype/**
   - tests/modules/meningotype/**
 
+meryl/count:
+  - modules/meryl/count/**
+  - tests/modules/meryl/count/**
+
+meryl/histogram:
+  - modules/meryl/histogram/**
+  - tests/modules/meryl/histogram/**
+
+meryl/unionsum:
+  - modules/meryl/unionsum/**
+  - tests/modules/meryl/unionsum/**
+
 metabat2/jgisummarizebamcontigdepths:
   - modules/metabat2/jgisummarizebamcontigdepths/**
   - tests/modules/metabat2/jgisummarizebamcontigdepths/**
@@ -1246,6 +1278,10 @@ mosdepth:
   - modules/mosdepth/**
   - tests/modules/mosdepth/**
 
+motus/downloaddb:
+  - modules/motus/downloaddb/**
+  - tests/modules/motus/downloaddb/**
+
 msisensor/msi:
   - modules/msisensor/msi/**
   - tests/modules/msisensor/msi/**
@@ -1587,6 +1623,10 @@ rseqc/tin:
   - modules/rseqc/tin/**
   - tests/modules/rseqc/tin/**
 
+rtgtools/vcfeval:
+  - modules/rtgtools/vcfeval/**
+  - tests/modules/rtgtools/vcfeval/**
+
 salmon/index:
   - modules/salmon/index/**
   - tests/modules/salmon/index/**
@@ -1607,9 +1647,9 @@ samtools/bam2fq:
   - modules/samtools/bam2fq/**
   - tests/modules/samtools/bam2fq/**
 
-samtools/bamtocram:
+samtools/convert:
-  - modules/samtools/bamtocram/**
+  - modules/samtools/convert/**
-  - tests/modules/samtools/bamtocram/**
+  - tests/modules/samtools/convert/**
 
 samtools/collatefastq:
   - modules/samtools/collatefastq/**
@@ -1723,6 +1763,14 @@ seqwish/induce:
   - modules/seqwish/induce/**
   - tests/modules/seqwish/induce/**
 
+shasum:
+  - modules/shasum/**
+  - tests/modules/shasum/**
+
+shigatyper:
+  - modules/shigatyper/**
+  - tests/modules/shigatyper/**
+
 shovill:
   - modules/shovill/**
   - tests/modules/shovill/**
@@ -1731,18 +1779,18 @@ sistr:
   - modules/sistr/**
   - tests/modules/sistr/**
 
+slimfastq:
+  - modules/slimfastq/**
+  - tests/modules/slimfastq/**
+
+snapaligner/align:
+  - modules/snapaligner/align/**
+  - tests/modules/snapaligner/align/**
+
 snapaligner/index:
   - modules/snapaligner/index/**
   - tests/modules/snapaligner/index/**
 
-snapaligner/paired:
-  - modules/snapaligner/paired/**
-  - tests/modules/snapaligner/paired/**
-
-snapaligner/single:
-  - modules/snapaligner/single/**
-  - tests/modules/snapaligner/single/**
-
 snpdists:
   - modules/snpdists/**
   - tests/modules/snpdists/**
@@ -1779,6 +1827,10 @@ sratools/prefetch:
   - modules/sratools/prefetch/**
   - tests/modules/sratools/prefetch/**
 
+srst2/srst2:
+  - modules/srst2/srst2/**
+  - tests/modules/srst2/srst2/**
+
 ssuissero:
   - modules/ssuissero/**
   - tests/modules/ssuissero/**
@@ -1920,6 +1972,10 @@ unzip:
   - modules/unzip/**
   - tests/modules/unzip/**
 
+vardictjava:
+  - modules/vardictjava/**
+  - tests/modules/vardictjava/**
+
 variantbam:
   - modules/variantbam/**
   - tests/modules/variantbam/**

tests/config/test_data.config

@@ -111,7 +111,9 @@ params {
                 test_sequencing_summary                        = "${test_data_dir}/genomics/sarscov2/nanopore/sequencing_summary/test.sequencing_summary.txt"
             }
             'metagenome' {
+                classified_reads_assignment                    = "${test_data_dir}/genomics/sarscov2/metagenome/test_1.kraken2.reads.txt"
                 kraken_report                                  = "${test_data_dir}/genomics/sarscov2/metagenome/test_1.kraken2.report.txt"
+                krona_taxonomy                                 = "${test_data_dir}/genomics/sarscov2/metagenome/krona_taxonomy.tab"
             }
         }
         'homo_sapiens' {
@@ -123,6 +125,7 @@ params {
                 genome_gff3                                    = "${test_data_dir}/genomics/homo_sapiens/genome/genome.gff3"
                 genome_gtf                                     = "${test_data_dir}/genomics/homo_sapiens/genome/genome.gtf"
                 genome_interval_list                           = "${test_data_dir}/genomics/homo_sapiens/genome/genome.interval_list"
+                genome_multi_interval_bed                      = "${test_data_dir}/genomics/homo_sapiens/genome/genome.multi_intervals.bed"
                 genome_sizes                                   = "${test_data_dir}/genomics/homo_sapiens/genome/genome.sizes"
                 genome_bed                                     = "${test_data_dir}/genomics/homo_sapiens/genome/genome.bed"
                 genome_header                                  = "${test_data_dir}/genomics/homo_sapiens/genome/genome.header"
@@ -132,6 +135,7 @@ params {
                 transcriptome_fasta                            = "${test_data_dir}/genomics/homo_sapiens/genome/transcriptome.fasta"
                 genome2_fasta                                  = "${test_data_dir}/genomics/homo_sapiens/genome/genome2.fasta"
                 genome_chain_gz                                = "${test_data_dir}/genomics/homo_sapiens/genome/genome.chain.gz"
+                genome_21_sdf                                  = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome_sdf.tar.gz"
                 genome_21_fasta                                = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta"
                 genome_21_fasta_fai                            = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai"
                 genome_21_dict                                 = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.dict"
@@ -179,16 +183,16 @@ params {
                 vcfanno_toml                                   = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/vcfanno/vcfanno.toml"
             }
             'pangenome' {
-                pangenome_fa                                  = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.fa"
+                pangenome_fa                                   = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.fa"
-                pangenome_fa_gz                               = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.fa.gz"
+                pangenome_fa_gz                                = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.fa.gz"
-                pangenome_paf                                 = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.paf"
+                pangenome_paf                                  = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.paf"
-                pangenome_paf_gz                              = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.paf.gz"
+                pangenome_paf_gz                               = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.paf.gz"
-                pangenome_seqwish_gfa                         = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.seqwish.gfa"
+                pangenome_seqwish_gfa                          = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.seqwish.gfa"
-                pangenome_smoothxg_gfa                        = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.smoothxg.gfa"
+                pangenome_smoothxg_gfa                         = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.smoothxg.gfa"
-                pangenome_gfaffix_gfa                         = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.gfaffix.gfa"
+                pangenome_gfaffix_gfa                          = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.gfaffix.gfa"
                 'odgi' {
-                    pangenome_og                                  = "${test_data_dir}/pangenomics/homo_sapiens/odgi/pangenome.og"
+                    pangenome_og                               = "${test_data_dir}/pangenomics/homo_sapiens/odgi/pangenome.og"
-                    pangenome_lay                                 = "${test_data_dir}/pangenomics/homo_sapiens/odgi/pangenome.lay"
+                    pangenome_lay                              = "${test_data_dir}/pangenomics/homo_sapiens/odgi/pangenome.lay"
                 }
             }
             'illumina' {
@@ -263,6 +267,9 @@ params {
                 test2_haplotc_ann_vcf_gz                       = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.ann.vcf.gz"
                 test2_haplotc_ann_vcf_gz_tbi                   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.ann.vcf.gz.tbi"
 
+                test2_haplotc_vcf_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.vcf.gz"
+                test2_haplotc_vcf_gz_tbi                       = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.vcf.gz.tbi"
+
                 test2_recal                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.recal"
                 test2_recal_idx                                = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.recal.idx"
                 test2_tranches                                 = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.tranches"
@@ -315,25 +322,25 @@ params {
                 test_pytor                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/pytor/test.pytor"
             }
             'pacbio' {
-                primers                                       = "${test_data_dir}/genomics/homo_sapiens/pacbio/fasta/primers.fasta"
+                primers                         = "${test_data_dir}/genomics/homo_sapiens/pacbio/fasta/primers.fasta"
-                alz                                           = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.bam"
+                alz                             = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.bam"
-                alzpbi                                        = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.bam.pbi"
+                alzpbi                          = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.bam.pbi"
-                ccs                                           = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.ccs.bam"
+                ccs                             = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.ccs.bam"
-                ccs_fa                                        = "${test_data_dir}/genomics/homo_sapiens/pacbio/fasta/alz.ccs.fasta"
+                ccs_fa                          = "${test_data_dir}/genomics/homo_sapiens/pacbio/fasta/alz.ccs.fasta"
-                ccs_fa_gz                                     = "${test_data_dir}/genomics/homo_sapiens/pacbio/fasta/alz.ccs.fasta.gz"
+                ccs_fa_gz                       = "${test_data_dir}/genomics/homo_sapiens/pacbio/fasta/alz.ccs.fasta.gz"
-                ccs_fq                                        = "${test_data_dir}/genomics/homo_sapiens/pacbio/fastq/alz.ccs.fastq"
+                ccs_fq                          = "${test_data_dir}/genomics/homo_sapiens/pacbio/fastq/alz.ccs.fastq"
-                ccs_fq_gz                                     = "${test_data_dir}/genomics/homo_sapiens/pacbio/fastq/alz.ccs.fastq.gz"
+                ccs_fq_gz                       = "${test_data_dir}/genomics/homo_sapiens/pacbio/fastq/alz.ccs.fastq.gz"
-                ccs_xml                                       = "${test_data_dir}/genomics/homo_sapiens/pacbio/xml/alz.ccs.consensusreadset.xml"
+                ccs_xml                         = "${test_data_dir}/genomics/homo_sapiens/pacbio/xml/alz.ccs.consensusreadset.xml"
-                hifi                                          = "${test_data_dir}/genomics/homo_sapiens/pacbio/fastq/test_hifi.fastq.gz"
+                hifi                            = "${test_data_dir}/genomics/homo_sapiens/pacbio/fastq/test_hifi.fastq.gz"
-                lima                                          = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.bam"
+                lima                            = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.bam"
-                refine                                        = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.bam"
+                refine                          = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.bam"
-                cluster                                       = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.clustered.bam"
+                cluster                         = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.clustered.bam"
-                singletons                                    = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.clustered.singletons.bam"
+                singletons                      = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.clustered.singletons.bam"
-                aligned                                       = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.clustered.singletons.merged.aligned.bam"
+                aligned                         = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.clustered.singletons.merged.aligned.bam"
-                alignedbai                                    = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.clustered.singletons.merged.aligned.bam.bai"
+                alignedbai                      = "${test_data_dir}/genomics/homo_sapiens/pacbio/bam/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.clustered.singletons.merged.aligned.bam.bai"
-                genemodel1                                    = "${test_data_dir}/genomics/homo_sapiens/pacbio/bed/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.clustered.singletons.merged.aligned_tc.bed"
+                genemodel1                      = "${test_data_dir}/genomics/homo_sapiens/pacbio/bed/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.clustered.singletons.merged.aligned_tc.bed"
-                genemodel2                                    = "${test_data_dir}/genomics/homo_sapiens/pacbio/bed/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.clustered.singletons.merged.aligned_tc.2.bed"
+                genemodel2                      = "${test_data_dir}/genomics/homo_sapiens/pacbio/bed/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.clustered.singletons.merged.aligned_tc.2.bed"
-                filelist                                      = "${test_data_dir}/genomics/homo_sapiens/pacbio/txt/filelist.txt"
+                filelist                        = "${test_data_dir}/genomics/homo_sapiens/pacbio/txt/filelist.txt"
             }
         }
         'bacteroides_fragilis' {
@@ -342,6 +349,7 @@ params {
                 genome_gbff_gz                  = "${test_data_dir}/genomics/prokaryotes/bacteroides_fragilis/genome/genome.gbff.gz"
                 genome_paf                      = "${test_data_dir}/genomics/prokaryotes/bacteroides_fragilis/genome/genome.paf"
                 genome_mapping_potential_arg    = "${test_data_dir}/genomics/prokaryotes/bacteroides_fragilis/genome/genome.mapping.potential.ARG"
+                genome_gff_gz                  = "${test_data_dir}/genomics/prokaryotes/bacteroides_fragilis/genome/genome.gff.gz"
 
             }
             'illumina' {
@@ -391,31 +399,31 @@ params {
         }
         'generic' {
             'csv' {
-                test_csv = "${test_data_dir}/generic/csv/test.csv"
+                test_csv                        = "${test_data_dir}/generic/csv/test.csv"
             }
             'notebooks' {
-                rmarkdown = "${test_data_dir}/generic/notebooks/rmarkdown/rmarkdown_notebook.Rmd"
+                rmarkdown                       = "${test_data_dir}/generic/notebooks/rmarkdown/rmarkdown_notebook.Rmd"
-                ipython_md = "${test_data_dir}/generic/notebooks/jupyter/ipython_notebook.md"
+                ipython_md                      = "${test_data_dir}/generic/notebooks/jupyter/ipython_notebook.md"
-                ipython_ipynb = "${test_data_dir}/generic/notebooks/jupyter/ipython_notebook.ipynb"
+                ipython_ipynb                   = "${test_data_dir}/generic/notebooks/jupyter/ipython_notebook.ipynb"
             }
             'tsv' {
-                test_tsv = "${test_data_dir}/generic/tsv/test.tsv"
+                test_tsv                        = "${test_data_dir}/generic/tsv/test.tsv"
             }
             'txt' {
-                hello = "${test_data_dir}/generic/txt/hello.txt"
+                hello                           = "${test_data_dir}/generic/txt/hello.txt"
             }
             'cnn' {
-                reference = "${test_data_dir}/generic/cnn/reference.cnn"
+                reference                       = "${test_data_dir}/generic/cnn/reference.cnn"
             }
             'cooler'{
-                test_pairix_pair_gz                           = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.GM12878-MboI.pairs.subsample.blksrt.txt.gz"
+                test_pairix_pair_gz             = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.GM12878-MboI.pairs.subsample.blksrt.txt.gz"
-                test_pairix_pair_gz_px2                       = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.GM12878-MboI.pairs.subsample.blksrt.txt.gz.px2"
+                test_pairix_pair_gz_px2         = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.GM12878-MboI.pairs.subsample.blksrt.txt.gz.px2"
-                test_pairs_pair                               = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.sample1.pairs"
+                test_pairs_pair                 = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.sample1.pairs"
-                test_tabix_pair_gz                            = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.GM12878-MboI.pairs.subsample.sorted.possrt.txt.gz"
+                test_tabix_pair_gz              = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.GM12878-MboI.pairs.subsample.sorted.possrt.txt.gz"
-                test_tabix_pair_gz_tbi                        = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.GM12878-MboI.pairs.subsample.sorted.possrt.txt.gz.tbi"
+                test_tabix_pair_gz_tbi          = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.GM12878-MboI.pairs.subsample.sorted.possrt.txt.gz.tbi"
-                hg19_chrom_sizes                              = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.chrom.sizes"
+                hg19_chrom_sizes                = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.chrom.sizes"
-                test_merge_cool                               = "${test_data_dir}/genomics/homo_sapiens/cooler/merge/toy/toy.symm.upper.2.cool"
+                test_merge_cool                 = "${test_data_dir}/genomics/homo_sapiens/cooler/merge/toy/toy.symm.upper.2.cool"
-                test_merge_cool_cp2                           = "${test_data_dir}/genomics/homo_sapiens/cooler/merge/toy/toy.symm.upper.2.cp2.cool"
+                test_merge_cool_cp2             = "${test_data_dir}/genomics/homo_sapiens/cooler/merge/toy/toy.symm.upper.2.cp2.cool"
 
             }
         }

tests/modules/arriba/main.nf

@@ -20,7 +20,7 @@ workflow test_arriba_single_end {
 
     STAR_GENOMEGENERATE ( fasta, gtf )
     STAR_ALIGN ( input, STAR_GENOMEGENERATE.out.index, gtf, star_ignore_sjdbgtf, seq_platform, seq_center )
-    ARRIBA ( STAR_ALIGN.out.bam, fasta, gtf )
+    ARRIBA ( STAR_ALIGN.out.bam, fasta, gtf , [], [], [], [], [])
 }
 
 workflow test_arriba_paired_end {
@@ -38,5 +38,5 @@ workflow test_arriba_paired_end {
 
     STAR_GENOMEGENERATE ( fasta, gtf )
     STAR_ALIGN ( input, STAR_GENOMEGENERATE.out.index, gtf, star_ignore_sjdbgtf, seq_platform, seq_center )
-    ARRIBA ( STAR_ALIGN.out.bam, fasta, gtf )
+    ARRIBA ( STAR_ALIGN.out.bam, fasta, gtf, [], [], [], [], [])
 }

tests/modules/arriba/test.yml

@@ -4,7 +4,7 @@
     - arriba
   files:
     - path: output/arriba/test.fusions.discarded.tsv
-      md5sum: cad8c215b938d1e45b747a5b7898a4c2
+      md5sum: 7602ab4ccbbb0c54fbca12a942877e6d
     - path: output/arriba/test.fusions.tsv
       md5sum: 7c3383f7eb6d79b84b0bd30a7ef02d70
     - path: output/star/star/Genome
@@ -39,6 +39,7 @@
     - path: output/star/star/transcriptInfo.tab
       md5sum: 0c3a5adb49d15e5feff81db8e29f2e36
     - path: output/star/test.Aligned.out.bam
+      md5sum: 4fa079d11f8938e51015e3e477fa7149
     - path: output/star/test.Log.final.out
     - path: output/star/test.Log.out
     - path: output/star/test.Log.progress.out
@@ -50,7 +51,7 @@
     - arriba
   files:
     - path: output/arriba/test.fusions.discarded.tsv
-      md5sum: 85e36c887464e4deaa65f45174d3b8fd
+      md5sum: cdc6cfbc75e68ce29a766f50f390274d
     - path: output/arriba/test.fusions.tsv
       md5sum: 7c3383f7eb6d79b84b0bd30a7ef02d70
     - path: output/star/star/Genome

tests/modules/bowtie2/align/main.nf

@@ -32,4 +32,4 @@ workflow test_bowtie2_align_paired_end {
 
     BOWTIE2_BUILD ( fasta )
     BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned )
-}
+}

tests/modules/bowtie2/align/nextflow.config

@@ -1,5 +1,16 @@
+params {
+    force_large_index = false
+}
+
 process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
-
+}
+
+if (params.force_large_index) {
+    process {
+        withName: BOWTIE2_BUILD {
+            ext.args = '--large-index'
+        }
+    }
 }

tests/modules/bowtie2/align/test.yml

@@ -39,3 +39,45 @@
       md5sum: 52be6950579598a990570fbcf5372184
     - path: ./output/bowtie2/bowtie2/genome.rev.2.bt2
       md5sum: e3b4ef343dea4dd571642010a7d09597
+
+- name: bowtie2 align single-end large-index
+  command: nextflow run ./tests/modules/bowtie2/align -entry test_bowtie2_align_single_end -c ./tests/config/nextflow.config -c ./tests/modules/bowtie2/align/nextflow.config --force_large_index
+  tags:
+    - bowtie2
+    - bowtie2/align
+  files:
+    - path: ./output/bowtie2/test.bam
+    - path: ./output/bowtie2/test.bowtie2.log
+    - path: ./output/bowtie2/bowtie2/genome.3.bt2l
+      md5sum: 8952b3e0b1ce9a7a5916f2e147180853
+    - path: ./output/bowtie2/bowtie2/genome.2.bt2l
+      md5sum: 22c284084784a0720989595e0c9461fd
+    - path: ./output/bowtie2/bowtie2/genome.1.bt2l
+      md5sum: 07d811cd4e350d56267183d2ac7023a5
+    - path: ./output/bowtie2/bowtie2/genome.4.bt2l
+      md5sum: c25be5f8b0378abf7a58c8a880b87626
+    - path: ./output/bowtie2/bowtie2/genome.rev.1.bt2l
+      md5sum: fda48e35925fb24d1c0785f021981e25
+    - path: ./output/bowtie2/bowtie2/genome.rev.2.bt2l
+      md5sum: 802c26d32b970e1b105032b7ce7348b4
+
+- name: bowtie2 align paired-end large-index
+  command: nextflow run ./tests/modules/bowtie2/align -entry test_bowtie2_align_paired_end -c ./tests/config/nextflow.config -c ./tests/modules/bowtie2/align/nextflow.config --force_large_index
+  tags:
+    - bowtie2
+    - bowtie2/align
+  files:
+    - path: ./output/bowtie2/test.bam
+    - path: ./output/bowtie2/test.bowtie2.log
+    - path: ./output/bowtie2/bowtie2/genome.3.bt2l
+      md5sum: 8952b3e0b1ce9a7a5916f2e147180853
+    - path: ./output/bowtie2/bowtie2/genome.2.bt2l
+      md5sum: 22c284084784a0720989595e0c9461fd
+    - path: ./output/bowtie2/bowtie2/genome.1.bt2l
+      md5sum: 07d811cd4e350d56267183d2ac7023a5
+    - path: ./output/bowtie2/bowtie2/genome.4.bt2l
+      md5sum: c25be5f8b0378abf7a58c8a880b87626
+    - path: ./output/bowtie2/bowtie2/genome.rev.1.bt2l
+      md5sum: fda48e35925fb24d1c0785f021981e25
+    - path: ./output/bowtie2/bowtie2/genome.rev.2.bt2l
+      md5sum: 802c26d32b970e1b105032b7ce7348b4

tests/modules/busco/main.nf

@@ -0,0 +1,404 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BUSCO } from '../../../modules/busco/main.nf'
+
+workflow test_busco_genome_single_fasta {
+
+    input = [
+        [ id:'test' ], // meta map
+        file( params.test_data['bacteroides_fragilis']['genome']['genome_fna_gz'], checkIfExists: true)
+    ]
+
+    BUSCO (
+        input,
+        ['bacteria_odb10', 'bacteroidetes_odb10'],  // Launch with 'auto' to use --auto-lineage, and specified lineages // 'auto' removed from test due to memory issues
+        [], // Download busco lineage
+        [], // No config
+    )
+
+    /* Output tree:
+    /tmp/tmpyz_hi62i/busco/
+    ├── short_summary.specific.bacteria_odb10.genome.fna.json -> /tmp/tmpza_0dth3/33/7d8c9b2c8931d9ad6a67aa843895e7/short_summary.specific.bacteria_odb10.genome.fna.json
+    ├── short_summary.specific.bacteria_odb10.genome.fna.txt -> /tmp/tmpza_0dth3/33/7d8c9b2c8931d9ad6a67aa843895e7/short_summary.specific.bacteria_odb10.genome.fna.txt
+    ├── short_summary.specific.bacteroidetes_odb10.genome.fna.json -> /tmp/tmpza_0dth3/6a/e95a0cd21785ce33d63b8f73a68a51/short_summary.specific.bacteroidetes_odb10.genome.fna.json
+    ├── short_summary.specific.bacteroidetes_odb10.genome.fna.txt -> /tmp/tmpza_0dth3/6a/e95a0cd21785ce33d63b8f73a68a51/short_summary.specific.bacteroidetes_odb10.genome.fna.txt
+    ├── test-bacteria_odb10-busco -> /tmp/tmpza_0dth3/33/7d8c9b2c8931d9ad6a67aa843895e7/test-bacteria_odb10-busco/
+    │   ├── genome.fna/
+    │   │   ├── logs/
+    │   │   │   ├── hmmsearch_err.log
+    │   │   │   ├── hmmsearch_out.log
+    │   │   │   ├── prodigal_err.log
+    │   │   │   └── prodigal_out.log
+    │   │   ├── prodigal_output/
+    │   │   │   └── predicted_genes/
+    │   │   └── run_bacteria_odb10/
+    │   │       ├── busco_sequences/
+    │   │       ├── full_table.tsv
+    │   │       ├── hmmer_output/
+    │   │       ├── missing_busco_list.tsv
+    │   │       ├── short_summary.json
+    │   │       └── short_summary.txt
+    │   └── logs/
+    │       └── busco.log
+    ├── test-bacteria_odb10-busco.batch_summary.txt -> /tmp/tmpza_0dth3/33/7d8c9b2c8931d9ad6a67aa843895e7/test-bacteria_odb10-busco.batch_summary.txt
+    ├── test-bacteroidetes_odb10-busco -> /tmp/tmpza_0dth3/6a/e95a0cd21785ce33d63b8f73a68a51/test-bacteroidetes_odb10-busco/
+    │   ├── genome.fna/
+    │   │   ├── logs/
+    │   │   │   ├── hmmsearch_err.log
+    │   │   │   ├── hmmsearch_out.log
+    │   │   │   ├── prodigal_err.log
+    │   │   │   └── prodigal_out.log
+    │   │   ├── prodigal_output/
+    │   │   │   └── predicted_genes/
+    │   │   └── run_bacteroidetes_odb10/
+    │   │       ├── busco_sequences/
+    │   │       ├── full_table.tsv
+    │   │       ├── hmmer_output/
+    │   │       ├── missing_busco_list.tsv
+    │   │       ├── short_summary.json
+    │   │       └── short_summary.txt
+    │   └── logs/
+    │       └── busco.log
+    ├── test-bacteroidetes_odb10-busco.batch_summary.txt -> /tmp/tmpza_0dth3/6a/e95a0cd21785ce33d63b8f73a68a51/test-bacteroidetes_odb10-busco.batch_summary.txt
+    └── versions.yml -> /tmp/tmpza_0dth3/6a/e95a0cd21785ce33d63b8f73a68a51/versions.yml
+
+    Former Output tree -w 'auto':
+    /tmp/tmp846crjv2/busco/
+    ├── short_summary.generic.bacteria_odb10.genome.fna.json -> /tmp/tmpi6af66j1/18/8be22ecd7a71471ff5082bd512972b/short_summary.generic.bacteria_odb10.genome.fna.json
+    ├── short_summary.generic.bacteria_odb10.genome.fna.txt -> /tmp/tmpi6af66j1/18/8be22ecd7a71471ff5082bd512972b/short_summary.generic.bacteria_odb10.genome.fna.txt
+    ├── short_summary.specific.bacteria_odb10.genome.fna.json -> /tmp/tmpi6af66j1/45/107812e983a8e695c380ebc215e7d9/short_summary.specific.bacteria_odb10.genome.fna.json
+    ├── short_summary.specific.bacteria_odb10.genome.fna.txt -> /tmp/tmpi6af66j1/45/107812e983a8e695c380ebc215e7d9/short_summary.specific.bacteria_odb10.genome.fna.txt
+    ├── short_summary.specific.bacteroidales_odb10.genome.fna.json -> /tmp/tmpi6af66j1/18/8be22ecd7a71471ff5082bd512972b/short_summary.specific.bacteroidales_odb10.genome.fna.json
+    ├── short_summary.specific.bacteroidales_odb10.genome.fna.txt -> /tmp/tmpi6af66j1/18/8be22ecd7a71471ff5082bd512972b/short_summary.specific.bacteroidales_odb10.genome.fna.txt
+    ├── short_summary.specific.bacteroidetes_odb10.genome.fna.json -> /tmp/tmpi6af66j1/a2/eb4a34894f3ac5554759ad6c9f652b/short_summary.specific.bacteroidetes_odb10.genome.fna.json
+    ├── short_summary.specific.bacteroidetes_odb10.genome.fna.txt -> /tmp/tmpi6af66j1/a2/eb4a34894f3ac5554759ad6c9f652b/short_summary.specific.bacteroidetes_odb10.genome.fna.txt
+    ├── test-auto-busco -> /tmp/tmpi6af66j1/18/8be22ecd7a71471ff5082bd512972b/test-auto-busco/
+    │   ├── genome.fna/
+    │   │   ├── auto_lineage/
+    │   │   │   ├── run_archaea_odb10/
+    │   │   │   ├── run_bacteria_odb10/
+    │   │   │   └── run_eukaryota_odb10/
+    │   │   ├── logs/
+    │   │   │   ├── hmmsearch_err.log
+    │   │   │   ├── hmmsearch_out.log
+    │   │   │   ├── metaeuk_err.log
+    │   │   │   ├── metaeuk_out.log
+    │   │   │   ├── prodigal_err.log
+    │   │   │   ├── prodigal_out.log
+    │   │   │   ├── sepp_err.log
+    │   │   │   └── sepp_out.log
+    │   │   ├── prodigal_output/
+    │   │   │   └── predicted_genes/
+    │   │   ├── run_bacteria_odb10 -> /tmp/tmpi6af66j1/18/8be22ecd7a71471ff5082bd512972b/test-auto-busco/genome.fna/auto_lineage/run_bacteria_odb10/  [recursive, not followed]
+    │   │   └── run_bacteroidales_odb10/
+    │   │       ├── busco_sequences/
+    │   │       ├── full_table.tsv
+    │   │       ├── hmmer_output/
+    │   │       ├── missing_busco_list.tsv
+    │   │       ├── short_summary.json
+    │   │       └── short_summary.txt
+    │   └── logs/
+    │       └── busco.log
+    ├── test-auto-busco.batch_summary.txt -> /tmp/tmpi6af66j1/18/8be22ecd7a71471ff5082bd512972b/test-auto-busco.batch_summary.txt
+    ├── test-bacteria_odb10-busco -> /tmp/tmpi6af66j1/45/107812e983a8e695c380ebc215e7d9/test-bacteria_odb10-busco/
+    │   ├── genome.fna/
+    │   │   ├── logs/
+    │   │   │   ├── hmmsearch_err.log
+    │   │   │   ├── hmmsearch_out.log
+    │   │   │   ├── prodigal_err.log
+    │   │   │   └── prodigal_out.log
+    │   │   ├── prodigal_output/
+    │   │   │   └── predicted_genes/
+    │   │   └── run_bacteria_odb10/
+    │   │       ├── busco_sequences/
+    │   │       ├── full_table.tsv
+    │   │       ├── hmmer_output/
+    │   │       ├── missing_busco_list.tsv
+    │   │       ├── short_summary.json
+    │   │       └── short_summary.txt
+    │   └── logs/
+    │       └── busco.log
+    ├── test-bacteria_odb10-busco.batch_summary.txt -> /tmp/tmpi6af66j1/45/107812e983a8e695c380ebc215e7d9/test-bacteria_odb10-busco.batch_summary.txt
+    ├── test-bacteroidetes_odb10-busco -> /tmp/tmpi6af66j1/a2/eb4a34894f3ac5554759ad6c9f652b/test-bacteroidetes_odb10-busco/
+    │   ├── genome.fna/
+    │   │   ├── logs/
+    │   │   │   ├── hmmsearch_err.log
+    │   │   │   ├── hmmsearch_out.log
+    │   │   │   ├── prodigal_err.log
+    │   │   │   └── prodigal_out.log
+    │   │   ├── prodigal_output/
+    │   │   │   └── predicted_genes/
+    │   │   └── run_bacteroidetes_odb10/
+    │   │       ├── busco_sequences/
+    │   │       ├── full_table.tsv
+    │   │       ├── hmmer_output/
+    │   │       ├── missing_busco_list.tsv
+    │   │       ├── short_summary.json
+    │   │       └── short_summary.txt
+    │   └── logs/
+    │       └── busco.log
+    ├── test-bacteroidetes_odb10-busco.batch_summary.txt -> /tmp/tmpi6af66j1/a2/eb4a34894f3ac5554759ad6c9f652b/test-bacteroidetes_odb10-busco.batch_summary.txt
+    └── versions.yml -> /tmp/tmpi6af66j1/18/8be22ecd7a71471ff5082bd512972b/versions.yml
+    */
+
+}
+
+workflow test_busco_genome_multi_fasta {
+
+    input = [
+        [ id:'test' ], // meta map
+        [
+            file( params.test_data['bacteroides_fragilis']['genome']['genome_fna_gz'], checkIfExists: true),
+            file( params.test_data['candidatus_portiera_aleyrodidarum']['genome']['genome_fasta'], checkIfExists: true)
+        ]
+    ]
+
+    BUSCO (
+        input,
+        'bacteria_odb10',
+        [], // Download busco lineage
+        [], // No config
+    )
+
+    /* Output tree:
+    /tmp/tmpk19byek7/busco/
+    ├── short_summary.specific.bacteria_odb10.genome.fasta.json -> /tmp/tmplt9fv3tl/15/ff310a16d9ce7ad24e207a05ce718e/short_summary.specific.bacteria_odb10.genome.fasta.json
+    ├── short_summary.specific.bacteria_odb10.genome.fasta.txt -> /tmp/tmplt9fv3tl/15/ff310a16d9ce7ad24e207a05ce718e/short_summary.specific.bacteria_odb10.genome.fasta.txt
+    ├── short_summary.specific.bacteria_odb10.genome.fna.json -> /tmp/tmplt9fv3tl/15/ff310a16d9ce7ad24e207a05ce718e/short_summary.specific.bacteria_odb10.genome.fna.json
+    ├── short_summary.specific.bacteria_odb10.genome.fna.txt -> /tmp/tmplt9fv3tl/15/ff310a16d9ce7ad24e207a05ce718e/short_summary.specific.bacteria_odb10.genome.fna.txt
+    ├── test-bacteria_odb10-busco -> /tmp/tmplt9fv3tl/15/ff310a16d9ce7ad24e207a05ce718e/test-bacteria_odb10-busco/
+    │   ├── genome.fasta/
+    │   │   ├── logs/
+    │   │   │   ├── hmmsearch_err.log
+    │   │   │   ├── hmmsearch_out.log
+    │   │   │   ├── prodigal_err.log
+    │   │   │   └── prodigal_out.log
+    │   │   ├── prodigal_output/
+    │   │   │   └── predicted_genes/
+    │   │   └── run_bacteria_odb10/
+    │   │       ├── busco_sequences/
+    │   │       ├── full_table.tsv
+    │   │       ├── hmmer_output/
+    │   │       ├── missing_busco_list.tsv
+    │   │       ├── short_summary.json
+    │   │       └── short_summary.txt
+    │   ├── genome.fna/
+    │   │   ├── logs/
+    │   │   │   ├── hmmsearch_err.log
+    │   │   │   ├── hmmsearch_out.log
+    │   │   │   ├── prodigal_err.log
+    │   │   │   └── prodigal_out.log
+    │   │   ├── prodigal_output/
+    │   │   │   └── predicted_genes/
+    │   │   └── run_bacteria_odb10/
+    │   │       ├── busco_sequences/
+    │   │       ├── full_table.tsv
+    │   │       ├── hmmer_output/
+    │   │       ├── missing_busco_list.tsv
+    │   │       ├── short_summary.json
+    │   │       └── short_summary.txt
+    │   └── logs/
+    │       └── busco.log
+    ├── test-bacteria_odb10-busco.batch_summary.txt -> /tmp/tmplt9fv3tl/15/ff310a16d9ce7ad24e207a05ce718e/test-bacteria_odb10-busco.batch_summary.txt
+    └── versions.yml -> /tmp/tmplt9fv3tl/15/ff310a16d9ce7ad24e207a05ce718e/versions.yml
+    */
+
+}
+
+workflow test_busco_eukaryote_metaeuk {
+
+    input = [
+        [ id:'test' ], // meta map
+        file( params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+
+    BUSCO (
+        input,
+        'eukaryota_odb10',
+        [], // Download busco lineage
+        [], // No config
+    )
+
+    /* Output tree:
+    /tmp/tmpeq4dsir5/busco/
+    ├── short_summary.specific.eukaryota_odb10.genome.fasta.json -> /tmp/tmp60hby2pk/6f/529873d91cda6bae3a4a6a21746aee/short_summary.specific.eukaryota_odb10.genome.fasta.json
+    ├── short_summary.specific.eukaryota_odb10.genome.fasta.txt -> /tmp/tmp60hby2pk/6f/529873d91cda6bae3a4a6a21746aee/short_summary.specific.eukaryota_odb10.genome.fasta.txt
+    ├── test-eukaryota_odb10-busco -> /tmp/tmp60hby2pk/6f/529873d91cda6bae3a4a6a21746aee/test-eukaryota_odb10-busco/
+    │   ├── genome.fasta/
+    │   │   ├── logs/
+    │   │   │   ├── hmmsearch_err.log
+    │   │   │   ├── hmmsearch_out.log
+    │   │   │   ├── metaeuk_err.log
+    │   │   │   └── metaeuk_out.log
+    │   │   └── run_eukaryota_odb10/
+    │   │       ├── busco_sequences/
+    │   │       ├── full_table.tsv
+    │   │       ├── hmmer_output/
+    │   │       ├── metaeuk_output/
+    │   │       ├── missing_busco_list.tsv
+    │   │       ├── short_summary.json
+    │   │       └── short_summary.txt
+    │   └── logs/
+    │       └── busco.log
+    ├── test-eukaryota_odb10-busco.batch_summary.txt -> /tmp/tmp60hby2pk/6f/529873d91cda6bae3a4a6a21746aee/test-eukaryota_odb10-busco.batch_summary.txt
+    └── versions.yml -> /tmp/tmp60hby2pk/6f/529873d91cda6bae3a4a6a21746aee/versions.yml
+    */
+
+}
+
+workflow test_busco_eukaryote_augustus {
+
+    input = [
+        [ id:'test' ], // meta map
+        file( params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+
+    BUSCO (
+        input,
+        'eukaryota_odb10',
+        [], // Download busco lineage
+        [], // No config
+    )
+
+    /* Output tree:
+    /tmp/tmp2xqaygjj/busco/
+    ├── test-eukaryota_odb10-busco -> /tmp/tmpjqs61x9o/3f/67cc14e873c0ceb45e2a27594d624c/test-eukaryota_odb10-busco/
+    │   ├── genome.fasta/
+    │   │   ├── blast_db/
+    │   │   │   ├── genome.fasta.ndb
+    │   │   │   ├── genome.fasta.nhr
+    │   │   │   ├── genome.fasta.nin
+    │   │   │   ├── genome.fasta.not
+    │   │   │   ├── genome.fasta.nsq
+    │   │   │   ├── genome.fasta.ntf
+    │   │   │   └── genome.fasta.nto
+    │   │   ├── logs/
+    │   │   │   ├── makeblastdb_err.log
+    │   │   │   ├── makeblastdb_out.log
+    │   │   │   ├── tblastn_err.log
+    │   │   │   └── tblastn_out.log
+    │   │   └── run_eukaryota_odb10/
+    │   │       ├── augustus_output/
+    │   │       ├── blast_output/
+    │   │       ├── busco_sequences/
+    │   │       └── hmmer_output/
+    │   └── logs/
+    │       └── busco.log
+    ├── test-eukaryota_odb10-busco.batch_summary.txt -> /tmp/tmpjqs61x9o/3f/67cc14e873c0ceb45e2a27594d624c/test-eukaryota_odb10-busco.batch_summary.txt
+    └── versions.yml -> /tmp/tmpjqs61x9o/3f/67cc14e873c0ceb45e2a27594d624c/versions.yml
+    */
+
+}
+
+workflow test_busco_protein {
+
+    input = [
+        [ id:'test' ], // meta map
+        file( params.test_data['candidatus_portiera_aleyrodidarum']['genome']['proteome_fasta'], checkIfExists: true)
+    ]
+
+    BUSCO (
+        input,
+        'bacteria_odb10',
+        [], // Download busco lineage
+        [], // No config
+    )
+
+    /* Output tree:
+    /tmp/tmpzwd5dn56/busco/
+    ├── short_summary.specific.bacteria_odb10.proteome.fasta.json -> /tmp/tmpk1nlgbf_/ae/0db07b5cd08fb23d0aba5f134ebbe2/short_summary.specific.bacteria_odb10.proteome.fasta.json
+    ├── short_summary.specific.bacteria_odb10.proteome.fasta.txt -> /tmp/tmpk1nlgbf_/ae/0db07b5cd08fb23d0aba5f134ebbe2/short_summary.specific.bacteria_odb10.proteome.fasta.txt
+    ├── test-bacteria_odb10-busco -> /tmp/tmpk1nlgbf_/ae/0db07b5cd08fb23d0aba5f134ebbe2/test-bacteria_odb10-busco/
+    │   ├── logs/
+    │   │   └── busco.log
+    │   └── proteome.fasta/
+    │       ├── logs/
+    │       │   ├── hmmsearch_err.log
+    │       │   └── hmmsearch_out.log
+    │       └── run_bacteria_odb10/
+    │           ├── busco_sequences/
+    │           ├── full_table.tsv
+    │           ├── hmmer_output/
+    │           ├── missing_busco_list.tsv
+    │           ├── short_summary.json
+    │           └── short_summary.txt
+    ├── test-bacteria_odb10-busco.batch_summary.txt -> /tmp/tmpk1nlgbf_/ae/0db07b5cd08fb23d0aba5f134ebbe2/test-bacteria_odb10-busco.batch_summary.txt
+    └── versions.yml -> /tmp/tmpk1nlgbf_/ae/0db07b5cd08fb23d0aba5f134ebbe2/versions.yml
+    */
+}
+workflow test_busco_transcriptome {
+
+    input = [
+        [ id:'test' ], // meta map
+        file( params.test_data['bacteroides_fragilis']['illumina']['test1_contigs_fa_gz'], checkIfExists: true)
+    ]
+
+    BUSCO (
+        input,
+        'bacteria_odb10',
+        [], // Download busco lineage
+        [], // No config
+    )
+
+    /* Output tree:
+    /tmp/tmpitjyvo9g/busco/
+    ├── short_summary.specific.bacteria_odb10.test1.contigs.fa.json -> /tmp/tmp6wqi0eyx/4f/ed0b23f0fc807bb68091298845c135/short_summary.specific.bacteria_odb10.test1.contigs.fa.json
+    ├── short_summary.specific.bacteria_odb10.test1.contigs.fa.txt -> /tmp/tmp6wqi0eyx/4f/ed0b23f0fc807bb68091298845c135/short_summary.specific.bacteria_odb10.test1.contigs.fa.txt
+    ├── test-bacteria_odb10-busco -> /tmp/tmp6wqi0eyx/4f/ed0b23f0fc807bb68091298845c135/test-bacteria_odb10-busco/
+    │   ├── logs/
+    │   │   └── busco.log
+    │   └── test1.contigs.fa/
+    │       ├── blast_db/
+    │       │   ├── test1.contigs.fa.ndb
+    │       │   ├── test1.contigs.fa.nhr
+    │       │   ├── test1.contigs.fa.nin
+    │       │   ├── test1.contigs.fa.not
+    │       │   ├── test1.contigs.fa.nsq
+    │       │   ├── test1.contigs.fa.ntf
+    │       │   └── test1.contigs.fa.nto
+    │       ├── logs/
+    │       │   ├── hmmsearch_err.log
+    │       │   ├── hmmsearch_out.log
+    │       │   ├── makeblastdb_err.log
+    │       │   ├── makeblastdb_out.log
+    │       │   ├── tblastn_err.log
+    │       │   └── tblastn_out.log
+    │       ├── run_bacteria_odb10/
+    │       │   ├── blast_output/
+    │       │   ├── busco_sequences/
+    │       │   ├── full_table.tsv
+    │       │   ├── hmmer_output/
+    │       │   ├── missing_busco_list.tsv
+    │       │   ├── short_summary.json
+    │       │   ├── short_summary.txt
+    │       │   └── single_copy_proteins.faa
+    │       └── translated_proteins/
+    │           ├── 1024388at2.faa
+    │           ├── 1054741at2.faa
+    │           ├── 1093223at2.faa
+    │           ├── 1151822at2.faa
+    │           ├── 143460at2.faa
+    │           ├── 1491686at2.faa
+    │           ├── 1504821at2.faa
+    │           ├── 1574817at2.faa
+    │           ├── 1592033at2.faa
+    │           ├── 1623045at2.faa
+    │           ├── 1661836at2.faa
+    │           ├── 1674344at2.faa
+    │           ├── 1698718at2.faa
+    │           ├── 1990650at2.faa
+    │           ├── 223233at2.faa
+    │           ├── 402899at2.faa
+    │           ├── 505485at2.faa
+    │           ├── 665824at2.faa
+    │           ├── 776861at2.faa
+    │           ├── 874197at2.faa
+    │           ├── 932854at2.faa
+    │           └── 95696at2.faa
+    ├── test-bacteria_odb10-busco.batch_summary.txt -> /tmp/tmp6wqi0eyx/4f/ed0b23f0fc807bb68091298845c135/test-bacteria_odb10-busco.batch_summary.txt
+    └── versions.yml -> /tmp/tmp6wqi0eyx/4f/ed0b23f0fc807bb68091298845c135/versions.yml
+    */
+
+}

tests/modules/busco/nextflow.config

@@ -0,0 +1,28 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: 'test_busco_genome_single_fasta:BUSCO' {
+        ext.args = '--mode genome'
+    }
+
+    withName: 'test_busco_genome_multi_fasta:BUSCO' {
+        ext.args = '--mode genome'
+    }
+
+    withName: 'test_busco_eukaryote_metaeuk:BUSCO' {
+        ext.args = '--mode genome'
+    }
+
+    withName: 'test_busco_eukaryote_augustus:BUSCO' {
+        ext.args = '--mode genome --augustus'
+    }
+
+    withName: 'test_busco_protein:BUSCO' {
+        ext.args = '--mode proteins'
+    }
+
+    withName: 'test_busco_transcriptome:BUSCO'{
+        ext.args = '--mode transcriptome'
+    }
+}

tests/modules/busco/test.yml

@@ -0,0 +1,159 @@
+- name: busco test_busco_genome_single_fasta
+  command: nextflow run tests/modules/busco -entry test_busco_genome_single_fasta -c tests/config/nextflow.config
+  tags:
+    - busco
+  files:
+    - path: output/busco/short_summary.specific.bacteria_odb10.genome.fna.json
+      contains:
+        - "one_line_summary"
+        - "input_file"
+        - "mode"
+        - "dataset"
+    - path: output/busco/short_summary.specific.bacteria_odb10.genome.fna.txt
+      contains:
+        - "BUSCO version"
+        - "The lineage dataset is"
+        - "BUSCO was run in mode"
+        - "Complete BUSCOs"
+        - "Missing BUSCOs"
+        - "Dependencies and versions"
+    - path: output/busco/short_summary.specific.bacteroidetes_odb10.genome.fna.json
+      contains:
+        - "one_line_summary"
+        - "input_file"
+        - "mode"
+        - "dataset"
+    - path: output/busco/short_summary.specific.bacteroidetes_odb10.genome.fna.txt
+      contains:
+        - "BUSCO version"
+        - "The lineage dataset is"
+        - "BUSCO was run in mode"
+        - "Complete BUSCOs"
+        - "Missing BUSCOs"
+        - "Dependencies and versions"
+    - path: output/busco/test-bacteria_odb10-busco.batch_summary.txt
+      md5sum: e50690742e9ae6abdd2bf99334ff9e12
+    - path: output/busco/test-bacteroidetes_odb10-busco.batch_summary.txt
+      md5sum: 4c1b2c4317c88398eddc30877ed740d9
+    - path: output/busco/versions.yml
+      md5sum: 8aa830f71587d859df35c6cfab59f35d
+
+- name: busco test_busco_genome_multi_fasta
+  command: nextflow run tests/modules/busco -entry test_busco_genome_multi_fasta -c tests/config/nextflow.config
+  tags:
+    - busco
+  files:
+    - path: output/busco/short_summary.specific.bacteria_odb10.genome.fasta.json
+      contains:
+        - "one_line_summary"
+        - "input_file"
+        - "mode"
+        - "dataset"
+    - path: output/busco/short_summary.specific.bacteria_odb10.genome.fasta.txt
+      contains:
+        - "BUSCO version"
+        - "The lineage dataset is"
+        - "BUSCO was run in mode"
+        - "Complete BUSCOs"
+        - "Missing BUSCOs"
+        - "Dependencies and versions"
+    - path: output/busco/short_summary.specific.bacteria_odb10.genome.fna.json
+      contains:
+        - "one_line_summary"
+        - "input_file"
+        - "mode"
+        - "dataset"
+    - path: output/busco/short_summary.specific.bacteria_odb10.genome.fna.txt
+      contains:
+        - "BUSCO version"
+        - "The lineage dataset is"
+        - "BUSCO was run in mode"
+        - "Complete BUSCOs"
+        - "Missing BUSCOs"
+        - "Dependencies and versions"
+    - path: output/busco/test-bacteria_odb10-busco.batch_summary.txt
+      md5sum: 5360dfe83bec1f5741ee115e53e6b517
+    - path: output/busco/versions.yml
+      md5sum: 9a959eb0a1f765777dff1ea2f5c139c0
+
+- name: busco test_busco_eukaryote_metaeuk
+  command: nextflow run tests/modules/busco -entry test_busco_eukaryote_metaeuk -c tests/config/nextflow.config
+  tags:
+    - busco
+  files:
+    - path: output/busco/short_summary.specific.eukaryota_odb10.genome.fasta.json
+      contains:
+        - "one_line_summary"
+        - "input_file"
+        - "mode"
+        - "dataset"
+    - path: output/busco/short_summary.specific.eukaryota_odb10.genome.fasta.txt
+      contains:
+        - "BUSCO version"
+        - "The lineage dataset is"
+        - "BUSCO was run in mode"
+        - "Complete BUSCOs"
+        - "Missing BUSCOs"
+        - "Dependencies and versions"
+    - path: output/busco/test-eukaryota_odb10-busco.batch_summary.txt
+      md5sum: a70806f99ba5706d7353d3353b3f1d2b
+    - path: output/busco/versions.yml
+      md5sum: 34a808c257e6db1b0456f3b4372bc477
+
+- name: busco test_busco_eukaryote_augustus
+  command: nextflow run tests/modules/busco -entry test_busco_eukaryote_augustus -c tests/config/nextflow.config
+  tags:
+    - busco
+  files:
+    - path: output/busco/test-eukaryota_odb10-busco.batch_summary.txt
+      md5sum: 660393dd43cd6a093b952d4b8ad41e40
+    - path: output/busco/versions.yml
+      md5sum: 2caac915461410b16a1524ac064cd0df
+
+- name: busco test_busco_protein
+  command: nextflow run tests/modules/busco -entry test_busco_protein -c tests/config/nextflow.config
+  tags:
+    - busco
+  files:
+    - path: output/busco/short_summary.specific.bacteria_odb10.proteome.fasta.json
+      contains:
+        - "one_line_summary"
+        - "input_file"
+        - "mode"
+        - "dataset"
+    - path: output/busco/short_summary.specific.bacteria_odb10.proteome.fasta.txt
+      contains:
+        - "BUSCO version"
+        - "The lineage dataset is"
+        - "BUSCO was run in mode"
+        - "Complete BUSCOs"
+        - "Missing BUSCOs"
+        - "Dependencies and versions"
+    - path: output/busco/test-bacteria_odb10-busco.batch_summary.txt
+      md5sum: fd3b4e30ce74d1fcb95d6286d6e2049f
+    - path: output/busco/versions.yml
+      md5sum: d7392261a57960a7e6aea609dce824f5
+
+- name: busco test_busco_transcriptome
+  command: nextflow run tests/modules/busco -entry test_busco_transcriptome -c tests/config/nextflow.config
+  tags:
+    - busco
+  files:
+    - path: output/busco/short_summary.specific.bacteria_odb10.test1.contigs.fa.json
+      contains:
+        - "one_line_summary"
+        - "input_file"
+        - "mode"
+        - "dataset"
+    - path: output/busco/short_summary.specific.bacteria_odb10.test1.contigs.fa.txt
+      contains:
+        - "BUSCO version"
+        - "The lineage dataset is"
+        - "BUSCO was run in mode"
+        - "Complete BUSCOs"
+        - "Missing BUSCOs"
+        - "Dependencies and versions"
+    - path: output/busco/test-bacteria_odb10-busco.batch_summary.txt
+      md5sum: 9a176cafe66ac0adca89dc34ad2be13f
+    - path: output/busco/versions.yml
+      md5sum: 30eacbc7df70f6b1e72e0a7b6d02a7e1

tests/modules/cnvpytor/callcnvs/test.yml

@@ -4,10 +4,8 @@
     - cnvpytor
     - cnvpytor/callcnvs
   files:
-    - path: output/cnvpytor/test.tsv
+    - path: output/cnvpytor/test.pytor
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/cnvpytor/versions.yml
-      md5sum: 0bea08a253fcb2ff0ff79b99df77b9fa
 
 - name: cnvpytor callcnvs test_cnvpytor_callcnvs stub
   command: nextflow run tests/modules/cnvpytor/callcnvs -entry test_cnvpytor_callcnvs -c tests/config/nextflow.config -stub-run
@@ -15,6 +13,5 @@
     - cnvpytor
     - cnvpytor/callcnvs
   files:
-    - path: output/cnvpytor/test.tsv
+    - path: output/cnvpytor/test.pytor
     - path: output/cnvpytor/versions.yml
-      md5sum: 0bea08a253fcb2ff0ff79b99df77b9fa

tests/modules/cnvpytor/histogram/test.yml

@@ -5,9 +5,7 @@
     - cnvpytor/histogram
   files:
     - path: output/cnvpytor/test.pytor
-      md5sum: aa03a8fa15b39f77816705a48e10312a
     - path: output/cnvpytor/versions.yml
-      md5sum: 0f4d75c4f3a3eb26c22616d12b0b78b2
 
 - name: cnvpytor histogram test_cnvpytor_histogram stub
   command: nextflow run tests/modules/cnvpytor/histogram -entry test_cnvpytor_histogram -c tests/config/nextflow.config -stub-run
@@ -17,4 +15,3 @@
   files:
     - path: output/cnvpytor/test.pytor
     - path: output/cnvpytor/versions.yml
-      md5sum: 0f4d75c4f3a3eb26c22616d12b0b78b2

tests/modules/cnvpytor/importreaddepth/test.yml

@@ -6,7 +6,6 @@
   files:
     - path: output/cnvpytor/test.pytor
     - path: output/cnvpytor/versions.yml
-      md5sum: 5834495324c08a37f3fd73ccdd881dc8
 
 - name: cnvpytor importreaddepth test_cnvpytor_importreaddepth stub
   command: nextflow run tests/modules/cnvpytor/importreaddepth -entry test_cnvpytor_importreaddepth -c tests/config/nextflow.config -stub-run
@@ -16,7 +15,6 @@
   files:
     - path: output/cnvpytor/test.pytor
     - path: output/cnvpytor/versions.yml
-      md5sum: 5834495324c08a37f3fd73ccdd881dc8
 
 - name: cnvpytor importreaddepth test_cnvpytor_importreaddepth_cram
   command: nextflow run tests/modules/cnvpytor/importreaddepth -entry test_cnvpytor_importreaddepth_cram -c tests/config/nextflow.config
@@ -26,7 +24,6 @@
   files:
     - path: output/cnvpytor/test.pytor
     - path: output/cnvpytor/versions.yml
-      md5sum: dfa0afb0982d985b96d1633f71ebb82a
 
 - name: cnvpytor importreaddepth test_cnvpytor_importreaddepth_cram stub
   command: nextflow run tests/modules/cnvpytor/importreaddepth -entry test_cnvpytor_importreaddepth_cram -c tests/config/nextflow.config -stub-run
@@ -36,4 +33,3 @@
   files:
     - path: output/cnvpytor/test.pytor
     - path: output/cnvpytor/versions.yml
-      md5sum: dfa0afb0982d985b96d1633f71ebb82a

tests/modules/cnvpytor/partition/test.yml

@@ -5,9 +5,7 @@
     - cnvpytor/partition
   files:
     - path: output/cnvpytor/test.pytor
-      md5sum: aa03a8fa15b39f77816705a48e10312a
     - path: output/cnvpytor/versions.yml
-      md5sum: 7fd6ec952a316463bcd324f176b46b64
 
 - name: cnvpytor partition test_cnvpytor_partition stub
   command: nextflow run tests/modules/cnvpytor/partition -entry test_cnvpytor_partition -c tests/config/nextflow.config -stub-run
@@ -17,4 +15,3 @@
   files:
     - path: output/cnvpytor/test.pytor
     - path: output/cnvpytor/versions.yml
-      md5sum: 7fd6ec952a316463bcd324f176b46b64

tests/modules/cnvpytor/view/main.nf

@@ -0,0 +1,42 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CNVPYTOR_VIEW } from '../../../../modules/cnvpytor/view/main.nf'
+
+workflow test_cnvpytor_view {
+
+    input = [
+        [ id:'test'], // meta map
+        [file(params.test_data['homo_sapiens']['illumina']['test_pytor'], checkIfExists: true)]
+    ]
+
+    bin_sizes = "10000 100000"
+
+    CNVPYTOR_VIEW ( input, bin_sizes, [] )
+}
+
+workflow test_cnvpytor_view_tsvout {
+
+    input = [
+        [ id:'test'], // meta map
+        [file(params.test_data['homo_sapiens']['illumina']['test_pytor'], checkIfExists: true)]
+    ]
+
+    output_suffix = "tsv"
+
+    CNVPYTOR_VIEW ( input, [], output_suffix )
+}
+
+workflow test_cnvpytor_view_stub {
+
+    input = [
+        [ id:'test'], // meta map
+        [file(params.test_data['homo_sapiens']['illumina']['test_pytor'], checkIfExists: true)]
+    ]
+
+    bin_sizes = []
+    output_suffix = []
+
+    CNVPYTOR_VIEW ( input, bin_sizes, output_suffix )
+}

tests/modules/cnvpytor/view/nextflow.config

@@ -0,0 +1,7 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    withName: CNVPYTOR_VIEW {
+        ext.args = '10000 100000'
+    }
+}

tests/modules/cnvpytor/view/test.yml

@@ -0,0 +1,27 @@
+- name: cnvpytor view test_cnvpytor_view
+  command: nextflow run tests/modules/cnvpytor/view -entry test_cnvpytor_view -c tests/config/nextflow.config
+  tags:
+    - cnvpytor
+    - cnvpytor/view
+  files:
+    - path: output/cnvpytor/test_10000.vcf
+    - path: output/cnvpytor/test_100000.vcf
+    - path: output/cnvpytor/versions.yml
+
+- name: cnvpytor view test_cnvpytor_view tsv
+  command: nextflow run tests/modules/cnvpytor/view -entry test_cnvpytor_view_tsvout -c tests/config/nextflow.config
+  tags:
+    - cnvpytor
+    - cnvpytor/view
+  files:
+    - path: output/cnvpytor/test_1000.tsv
+    - path: output/cnvpytor/versions.yml
+
+- name: cnvpytor view test_cnvpytor_view stub
+  command: nextflow run tests/modules/cnvpytor/view -entry test_cnvpytor_view_stub -c tests/config/nextflow.config  -stub-run
+  tags:
+    - cnvpytor
+    - cnvpytor/view
+  files:
+    - path: output/cnvpytor/test.vcf
+    - path: output/cnvpytor/versions.yml

tests/modules/ensemblvep/main.nf

@@ -10,5 +10,5 @@ workflow test_ensemblvep {
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
     ]
 
-    ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [] )
+    ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [], [] )
 }

tests/modules/gatk4/mergebamalignment/main.nf

@@ -14,3 +14,14 @@ workflow test_gatk4_mergebamalignment {
 
     GATK4_MERGEBAMALIGNMENT ( input, fasta, dict )
 }
+
+workflow test_gatk4_mergebamalignment_stubs {
+     input    = [ [ id:'test' ], // meta map
+                 file(params.test_data['sarscov2']['illumina']['test_single_end_bam'], checkIfExists: true),
+                 file(params.test_data['sarscov2']['illumina']['test_unaligned_bam'], checkIfExists: true)
+               ]
+    fasta    = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    dict     = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
+
+    GATK4_MERGEBAMALIGNMENT ( input, fasta, dict )
+}

tests/modules/gatk4/mergebamalignment/test.yml

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

tests/modules/gatk4/mutect2/main.nf

@@ -118,3 +118,25 @@ workflow test_gatk4_mutect2_mitochondria {
 
     GATK4_MUTECT2_MITO ( input, fasta, fai, dict, [], [], [], [] )
 }
+
+workflow test_gatk4_mutect2_tumor_normal_pair_f1r2_stubs {
+     input = [ [ id:'test', normal_id:'normal', tumor_id:'tumour' ], // meta map
+              [ file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam'], checkIfExists: true),
+                file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_bam'], checkIfExists: true)
+                ],
+              [ file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true),
+                file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true)
+                ],
+              []
+            ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_21_dict'], checkIfExists: true)
+    germline_resource = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz'], checkIfExists: true)
+    germline_resource_tbi = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz_tbi'], checkIfExists: true)
+    panel_of_normals = file(params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz'], checkIfExists: true)
+    panel_of_normals_tbi = file(params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz_tbi'], checkIfExists: true)
+
+    GATK4_MUTECT2_F1R2 ( input, fasta, fai, dict, germline_resource, germline_resource_tbi, panel_of_normals, panel_of_normals_tbi )
+}

tests/modules/gatk4/mutect2/test.yml

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

tests/modules/gatk4/revertsam/main.nf

@@ -11,3 +11,11 @@ workflow test_gatk4_revertsam {
 
     GATK4_REVERTSAM ( input )
 }
+
+workflow test_gatk4_revertsam_stubs {
+    input = [ [ id:'test' ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+            ]
+
+    GATK4_REVERTSAM ( input )
+}