Merge branch 'master' into motus_profile

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' :
-        'quay.io/biocontainers/arriba:2.1.0--h3198e80_1' }"
+        'https://depot.galaxyproject.org/singularity/arriba:2.2.1--hecb563c_2' :
+        '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

@@ -1,11 +1,11 @@
 process BOWTIE2_ALIGN {
     tag "$meta.id"
-    label 'process_high'
+    label "process_high"
 
-    conda (params.enable_conda ? 'bioconda::bowtie2=2.4.4 bioconda::samtools=1.15.1 conda-forge::pigz=2.6' : null)
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/mulled-v2-ac74a7f02cebcfcc07d8e8d1d750af9c83b4d45a:1744f68fe955578c63054b55309e05b41c37a80d-0' :
-        'quay.io/biocontainers/mulled-v2-ac74a7f02cebcfcc07d8e8d1d750af9c83b4d45a:1744f68fe955578c63054b55309e05b41c37a80d-0' }"
+    conda (params.enable_conda ? "bioconda::bowtie2=2.4.4 bioconda::samtools=1.15.1 conda-forge::pigz=2.6" : null)
+    container "${ workflow.containerEngine == "singularity" && !task.ext.singularity_pull_docker_container ?
+        "https://depot.galaxyproject.org/singularity/mulled-v2-ac74a7f02cebcfcc07d8e8d1d750af9c83b4d45a:1744f68fe955578c63054b55309e05b41c37a80d-0" :
+        "quay.io/biocontainers/mulled-v2-ac74a7f02cebcfcc07d8e8d1d750af9c83b4d45a:1744f68fe955578c63054b55309e05b41c37a80d-0" }"
 
     input:
     tuple val(meta), path(reads)
@@ -13,69 +13,59 @@ process BOWTIE2_ALIGN {
     val   save_unaligned
 
     output:
-    tuple val(meta), path('*.bam')    , emit: bam
-    tuple val(meta), path('*.log')    , emit: log
-    tuple val(meta), path('*fastq.gz'), emit: fastq, optional:true
+    tuple val(meta), path("*.bam")    , emit: bam
+    tuple val(meta), path("*.log")    , emit: log
+    tuple val(meta), path("*fastq.gz"), emit: fastq, optional:true
     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 args = task.ext.args ?: ""
+    def args2 = task.ext.args2 ?: ""
     def prefix = task.ext.prefix ?: "${meta.id}"
+
+    def unaligned = ""
+    def reads_args = ""
     if (meta.single_end) {
-        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 \\
-            --threads $task.cpus \\
-            $unaligned \\
-            $args \\
-            2> ${prefix}.bowtie2.log \\
-            | samtools view -@ $task.cpus $args2 -bhS -o ${prefix}.bam -
-
-        cat <<-END_VERSIONS > versions.yml
-        "${task.process}":
-            bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
-            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
-            pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
-        END_VERSIONS
-        """
+        unaligned = save_unaligned ? "--un-gz ${prefix}.unmapped.fastq.gz" : ""
+        reads_args = "-U ${reads}"
     } else {
-        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]} \\
-            -2 ${reads[1]} \\
-            --threads $task.cpus \\
-            $unaligned \\
-            $args \\
-            2> ${prefix}.bowtie2.log \\
-            | samtools view -@ $task.cpus $args2 -bhS -o ${prefix}.bam -
-
-        if [ -f ${prefix}.unmapped.fastq.1.gz ]; then
-            mv ${prefix}.unmapped.fastq.1.gz ${prefix}.unmapped_1.fastq.gz
-        fi
-        if [ -f ${prefix}.unmapped.fastq.2.gz ]; then
-            mv ${prefix}.unmapped.fastq.2.gz ${prefix}.unmapped_2.fastq.gz
-        fi
-
-        cat <<-END_VERSIONS > versions.yml
-        "${task.process}":
-            bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
-            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
-            pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
-        END_VERSIONS
-        """
+        unaligned = save_unaligned ? "--un-conc-gz ${prefix}.unmapped.fastq.gz" : ""
+        reads_args = "-1 ${reads[0]} -2 ${reads[1]}"
     }
+
+    def samtools_command = "samtools view -@ $task.cpus --bam --with-header ${args2} > ${prefix}.bam"
+
+
+    """
+    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 "Bowtie2 index files not found" 1>&2 && exit 1
+
+    bowtie2 \\
+        -x \$INDEX \\
+        $reads_args \\
+        --threads $task.cpus \\
+        $unaligned \\
+        $args \\
+        2> ${prefix}.bowtie2.log \\
+        | $samtools_command
+
+    if [ -f ${prefix}.unmapped.fastq.1.gz ]; then
+        mv ${prefix}.unmapped.fastq.1.gz ${prefix}.unmapped_1.fastq.gz
+    fi
+
+    if [ -f ${prefix}.unmapped.fastq.2.gz ]; then
+        mv ${prefix}.unmapped.fastq.2.gz ${prefix}.unmapped_2.fastq.gz
+    fi
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+        pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
+    END_VERSIONS
+    """
 }

modules/custom/sratoolsncbisettings/main.nf

@@ -0,0 +1,20 @@
+process CUSTOM_SRATOOLSNCBISETTINGS {
+    tag 'ncbi-settings'
+    label 'process_low'
+
+    conda (params.enable_conda ? 'bioconda::sra-tools=2.11.0' : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/sra-tools:2.11.0--pl5321ha49a11a_3' :
+        'quay.io/biocontainers/sra-tools:2.11.0--pl5321ha49a11a_3' }"
+
+    output:
+    path('*.mkfg')     , emit: ncbi_settings
+    path 'versions.yml', emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    shell:
+    config = "/LIBS/GUID = \"${UUID.randomUUID().toString()}\"\\n/libs/cloud/report_instance_identity = \"true\"\\n"
+    template 'detect_ncbi_settings.sh'
+}

modules/custom/sratoolsncbisettings/meta.yml

@@ -0,0 +1,28 @@
+name: "sratoolsncbisettings"
+description: Test for the presence of suitable NCBI settings or create them on the fly.
+keywords:
+  - NCBI
+  - settings
+  - sra-tools
+  - prefetch
+  - fasterq-dump
+tools:
+  - "sratools":
+      description: "SRA Toolkit and SDK from NCBI"
+      homepage: https://github.com/ncbi/sra-tools
+      documentation: https://github.com/ncbi/sra-tools/wiki
+      tool_dev_url: https://github.com/ncbi/sra-tools
+      licence: "['Public Domain']"
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - ncbi_settings:
+      type: file
+      description: An NCBI user settings file.
+      pattern: "*.mkfg"
+
+authors:
+  - "@Midnighter"

modules/custom/sratoolsncbisettings/templates/detect_ncbi_settings.sh

@@ -0,0 +1,45 @@
+#!/usr/bin/env bash
+
+set -u
+
+
+# Get the expected NCBI settings path and define the environment variable
+# `NCBI_SETTINGS`.
+eval "$(vdb-config -o n NCBI_SETTINGS | sed 's/[" ]//g')"
+
+# If the user settings do not exist yet, create a file suitable for `prefetch`
+# and `fasterq-dump`. If an existing settings file does not contain the required
+# values, error out with a helpful message.
+if [[ ! -f "${NCBI_SETTINGS}" ]]; then
+    printf '!{config}' > 'user-settings.mkfg'
+else
+    prefetch --help &> /dev/null
+    if [[ $? = 78 ]]; then
+        echo "You have an existing vdb-config at '${NCBI_SETTINGS}' but it is"\
+        "missing the required entries for /LIBS/GUID and"\
+        "/libs/cloud/report_instance_identity."\
+        "Feel free to add the following to your settings file:" >&2
+        echo "$(printf '!{config}')" >&2
+        exit 1
+    fi
+    fasterq-dump --help &> /dev/null
+    if [[ $? = 78 ]]; then
+        echo "You have an existing vdb-config at '${NCBI_SETTINGS}' but it is"\
+        "missing the required entries for /LIBS/GUID and"\
+        "/libs/cloud/report_instance_identity."\
+        "Feel free to add the following to your settings file:" >&2
+        echo "$(printf '!{config}')" >&2
+        exit 1
+    fi
+    if [[ "${NCBI_SETTINGS}" != *.mkfg ]]; then
+        echo "The detected settings '${NCBI_SETTINGS}' do not have the required"\
+        "file extension '.mkfg'." >&2
+        exit 1
+    fi
+    cp "${NCBI_SETTINGS}" ./
+fi
+
+cat <<-END_VERSIONS > versions.yml
+"!{task.process}":
+    sratools: $(vdb-config --version 2>&1 | grep -Eo '[0-9.]+')
+END_VERSIONS

modules/gatk4/splitintervals/main.nf

@@ -0,0 +1,48 @@
+process GATK4_SPLITINTERVALS {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
+        'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(intervals)
+    path(fasta)
+    path(fasta_fai)
+    path(dict)
+
+    output:
+    tuple val(meta), path("**.interval_list"), emit: split_intervals
+    path "versions.yml"                      , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def reference = fasta ? "--reference $fasta" : ""
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK SplitIntervals] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+
+    """
+    gatk --java-options "-Xmx${avail_mem}g" SplitIntervals \\
+        --output ${prefix} \\
+        --intervals $intervals \\
+        $reference \\
+        --tmp-dir . \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/gatk4/splitintervals/meta.yml

@@ -0,0 +1,53 @@
+name: gatk4_splitintervals
+keywords:
+  - interval
+  - bed
+tools:
+  - gatk4:
+      description: Genome Analysis Toolkit (GATK4)
+      homepage: https://gatk.broadinstitute.org/hc/en-us
+      documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s
+      tool_dev_url: https://github.com/broadinstitute/gatk
+      doi: "10.1158/1538-7445.AM2017-3590"
+      licence: ["BSD-3-clause"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - interval:
+      type: file
+      description: Interval list or BED
+      pattern: "*.{interval,interval_list,bed}"
+  - fasta:
+      type: file
+      description: Reference FASTA
+      pattern: "*.{fa,fasta}"
+  - fasta_fai:
+      type: file
+      description: Reference FASTA index
+      pattern: "*.fai"
+  - dict:
+      type: file
+      description: Reference sequence dictionary
+      pattern: "*.dict"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - bed:
+      type: file
+      description: A list of scattered interval lists
+      pattern: "*.interval_list"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@nvnieuwk"

modules/genomescope2/main.nf

@@ -0,0 +1,40 @@
+process GENOMESCOPE2 {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::genomescope2=2.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/genomescope2:2.0--py310r41hdfd78af_5':
+        'quay.io/biocontainers/genomescope2:2.0--py310r41hdfd78af_5' }"
+
+    input:
+    tuple val(meta), path(histogram)
+
+    output:
+    tuple val(meta), path("*_linear_plot.png")            , emit: linear_plot_png
+    tuple val(meta), path("*_transformed_linear_plot.png"), emit: transformed_linear_plot_png
+    tuple val(meta), path("*_log_plot.png")               , emit: log_plot_png
+    tuple val(meta), path("*_transformed_log_plot.png")   , emit: transformed_log_plot_png
+    tuple val(meta), path("*_model.txt")                  , emit: model
+    tuple val(meta), path("*_summary.txt")                , emit: summary
+    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}"
+    """
+    genomescope2 \\
+        --input $histogram \\
+        $args \\
+        --output . \\
+        --name_prefix $prefix
+
+    cat <<-END_VERSIONS > versions.yml
+    '${task.process}':
+        genomescope2: \$( genomescope2 -v | sed 's/GenomeScope //' )
+    END_VERSIONS
+    """
+}

modules/genomescope2/meta.yml

@@ -0,0 +1,67 @@
+name: "genomescope2"
+description: Estimate genome heterozygosity, repeat content, and size from sequencing reads using a kmer-based statistical approach
+keywords:
+  - "genome size"
+  - "genome heterozygosity"
+  - "repeat content"
+tools:
+  - "genomescope2":
+      description: "Reference-free profiling of polyploid genomes"
+      homepage: "http://qb.cshl.edu/genomescope/genomescope2.0/"
+      documentation: "https://github.com/tbenavi1/genomescope2.0/blob/master/README.md"
+      tool_dev_url: "https://github.com/tbenavi1/genomescope2.0"
+      doi: "https://doi.org/10.1038/s41467-020-14998-3"
+      licence: "['Apache License, Version 2.0 (Apache-2.0)']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - histogram:
+      type: file
+      description: A K-mer histogram file
+      pattern: "*.hist"
+
+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"
+  - linear_plot_png:
+      type: file
+      description: A genomescope2 linear plot in PNG format
+      pattern: "*_linear_plot.png"
+  - linear_plot_png:
+      type: file
+      description: A genomescope2 linear plot in PNG format
+      pattern: "*_linear_plot.png"
+  - transformed_linear_plot_png:
+      type: file
+      description: A genomescope2 transformed linear plot in PNG format
+      pattern: "*_transformed_linear_plot.png"
+  - log_plot_png:
+      type: file
+      description: A genomescope2 log plot in PNG format
+      pattern: "*_log_plot.png"
+  - transformed_log_plot_png:
+      type: file
+      description: A genomescope2 transformed log plot in PNG format
+      pattern: "*_transformed_log_plot.png"
+  - model:
+      type: file
+      description: Genomescope2 model fit summary
+      pattern: "*_model.txt"
+  - summary:
+      type: file
+      description: Genomescope2 histogram summary
+      pattern: "*_summary.txt"
+
+authors:
+  - "@mahesh-panchal"

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/rtgtools/vcfeval/main.nf

@@ -0,0 +1,60 @@
+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"
+    def avail_mem = task.memory.toGiga() + "G"
+
+    """
+    $truth_index
+    $query_index
+
+    rtg RTG_MEM=$avail_mem 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/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_BAMTOCRAM {
+process SAMTOOLS_CONVERT {
     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
-    path  "versions.yml"                           , emit: versions
+    tuple val(meta), path("*.{cram,bam}"), path("*.{crai,bai}") , emit: alignment_index
+    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 > ${prefix}.cram
-    samtools index -@${task.cpus} ${prefix}.cram
+    samtools view \\
+        --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
-description: filter/convert and then index CRAM file
+name: samtools_convert
+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
-      pattern: "*.{bam,sam}"
+      description: BAM/CRAM file
+      pattern: "*.{bam,cram}"
   - index:
       type: file
-      description: BAM/SAM index file
-      pattern: "*.{bai,sai}"
+      description: BAM/CRAM index file
+      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
-      pattern: "*{.cram,.crai}"
+      description: filtered/converted BAM/CRAM file + index
+      pattern: "*{.bam/cram,.bai/crai}"
   - version:
       type: file
       description: File containing software version

modules/sratools/fasterqdump/main.nf

@@ -9,6 +9,7 @@ process SRATOOLS_FASTERQDUMP {
 
     input:
     tuple val(meta), path(sra)
+    path ncbi_settings
 
     output:
     tuple val(meta), path(output), emit: reads
@@ -20,17 +21,12 @@ process SRATOOLS_FASTERQDUMP {
     script:
     def args = task.ext.args ?: ''
     def args2 = task.ext.args2 ?: ''
-    def config = "/LIBS/GUID = \"${UUID.randomUUID().toString()}\"\\n/libs/cloud/report_instance_identity = \"true\"\\n"
     // Paired-end data extracted by fasterq-dump (--split-3 the default) always creates
     // *_1.fastq *_2.fastq files but sometimes also an additional *.fastq file
     // for unpaired reads which we ignore here.
     output = meta.single_end ? '*.fastq.gz' : '*_{1,2}.fastq.gz'
     """
-    eval "\$(vdb-config -o n NCBI_SETTINGS | sed 's/[" ]//g')"
-    if [[ ! -f "\${NCBI_SETTINGS}" ]]; then
-        mkdir -p "\$(dirname "\${NCBI_SETTINGS}")"
-        printf '${config}' > "\${NCBI_SETTINGS}"
-    fi
+    export NCBI_SETTINGS="\$PWD/${ncbi_settings}"
 
     fasterq-dump \\
         $args \\

modules/sratools/fasterqdump/meta.yml

@@ -10,7 +10,7 @@ tools:
       homepage: https://github.com/ncbi/sra-tools
       documentation: https://github.com/ncbi/sra-tools/wiki
       tool_dev_url: https://github.com/ncbi/sra-tools
-      licence: ["US-Government-Work"]
+      licence: ["Public Domain"]
 
 input:
   - meta:
@@ -22,6 +22,11 @@ input:
       type: directory
       description: Directory containing ETL data for the given SRA.
       pattern: "*/*.sra"
+  - ncbi_settings:
+      type: file
+      description: >
+        An NCBI user settings file.
+      pattern: "*.mkfg"
 
 output:
   - meta:

modules/sratools/prefetch/main.nf

@@ -9,10 +9,11 @@ process SRATOOLS_PREFETCH {
 
     input:
     tuple val(meta), val(id)
+    path ncbi_settings
 
     output:
     tuple val(meta), path(id), emit: sra
-    path "versions.yml"         , emit: versions
+    path 'versions.yml'      , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -20,7 +21,5 @@ process SRATOOLS_PREFETCH {
     shell:
     args = task.ext.args ?: ''
     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"
-
     template 'retry_with_backoff.sh'
 }

modules/sratools/prefetch/meta.yml

@@ -10,7 +10,7 @@ tools:
       homepage: https://github.com/ncbi/sra-tools
       documentation: https://github.com/ncbi/sra-tools/wiki
       tool_dev_url: https://github.com/ncbi/sra-tools
-      licence: ["US-Government-Work"]
+      licence: ["Public Domain"]
 
 input:
   - meta:
@@ -22,6 +22,11 @@ input:
       type: val
       description: >
         A string denoting an SRA id.
+  - ncbi_settings:
+      type: file
+      description: >
+        An NCBI user settings file.
+      pattern: "*.mkfg"
 
 output:
   - meta:

modules/sratools/prefetch/templates/retry_with_backoff.sh

@@ -40,11 +40,7 @@ retry_with_backoff() {
     echo "${output}"
 }
 
-eval "$(vdb-config -o n NCBI_SETTINGS | sed 's/[" ]//g')"
-if [[ ! -f "${NCBI_SETTINGS}" ]]; then
-    mkdir -p "$(dirname "${NCBI_SETTINGS}")"
-    printf '!{config}' > "${NCBI_SETTINGS}"
-fi
+export NCBI_SETTINGS="$PWD/!{ncbi_settings}"
 
 retry_with_backoff !{args2} \
     prefetch \

subworkflows/nf-core/sra_fastq/main.nf

@@ -1,34 +0,0 @@
-//
-// Download FASTQ sequencing reads from the NCBI's Sequence Read Archive (SRA).
-//
-
-params.prefetch_options    = [:]
-params.fasterqdump_options = [:]
-
-include { SRATOOLS_PREFETCH    } from '../../../modules/sratools/prefetch/main'    addParams( options: params.prefetch_options    )
-include { SRATOOLS_FASTERQDUMP } from '../../../modules/sratools/fasterqdump/main' addParams( options: params.fasterqdump_options )
-
-workflow SRA_FASTQ {
-    take:
-    sra_ids  // channel: [ val(meta), val(id) ]
-
-    main:
-
-    ch_versions = Channel.empty()
-
-    //
-    // Prefetch sequencing reads in SRA format.
-    //
-    SRATOOLS_PREFETCH ( sra_ids )
-    ch_versions = ch_versions.mix( SRATOOLS_PREFETCH.out.versions.first() )
-
-    //
-    // Convert the SRA format into one or more compressed FASTQ files.
-    //
-    SRATOOLS_FASTERQDUMP ( SRATOOLS_PREFETCH.out.sra )
-    ch_versions = ch_versions.mix( SRATOOLS_FASTERQDUMP.out.versions.first() )
-
-    emit:
-    reads    = SRATOOLS_FASTERQDUMP.out.reads  // channel: [ val(meta), [ reads ] ]
-    versions = ch_versions                     // channel: [ versions.yml ]
-}

subworkflows/nf-core/srafastq/main.nf

@@ -0,0 +1,38 @@
+include { CUSTOM_SRATOOLSNCBISETTINGS } from '../../../modules/custom/sratoolsncbisettings/main'
+include { SRATOOLS_PREFETCH           } from '../../../modules/sratools/prefetch/main'
+include { SRATOOLS_FASTERQDUMP        } from '../../../modules/sratools/fasterqdump/main'
+
+/**
+ * Download FASTQ sequencing reads from the NCBI's Sequence Read Archive (SRA).
+ */
+workflow SRAFASTQ {
+    take:
+    sra_ids  // channel: [ val(meta), val(id) ]
+
+    main:
+
+    ch_versions = Channel.empty()
+
+    //
+    // Detect existing NCBI user settings or create new ones.
+    //
+    CUSTOM_SRATOOLSNCBISETTINGS()
+    def settings = CUSTOM_SRATOOLSNCBISETTINGS.out.ncbi_settings
+    ch_versions = ch_versions.mix( CUSTOM_SRATOOLSNCBISETTINGS.out.versions )
+
+    //
+    // Prefetch sequencing reads in SRA format.
+    //
+    SRATOOLS_PREFETCH ( sra_ids, settings )
+    ch_versions = ch_versions.mix( SRATOOLS_PREFETCH.out.versions.first() )
+
+    //
+    // Convert the SRA format into one or more compressed FASTQ files.
+    //
+    SRATOOLS_FASTERQDUMP ( SRATOOLS_PREFETCH.out.sra, settings )
+    ch_versions = ch_versions.mix( SRATOOLS_FASTERQDUMP.out.versions.first() )
+
+    emit:
+    reads    = SRATOOLS_FASTERQDUMP.out.reads  // channel: [ val(meta), [ reads ] ]
+    versions = ch_versions                     // channel: [ versions.yml ]
+}

subworkflows/nf-core/srafastq/meta.yml

@@ -1,11 +1,14 @@
 name: sra_fastq
 description: Download FASTQ sequencing reads from the NCBI's Sequence Read Archive (SRA).
 keywords:
+  - SRA
+  - NCBI
   - sequencing
   - FASTQ
   - prefetch
-  - dump
+  - fasterq-dump
 modules:
+  - custom/sratoolsncbisettings
   - sratools/prefetch
   - sratools/fasterqdump
 input:
@@ -17,7 +20,7 @@ input:
   - id:
       type: string
       description: >
-        SRA identifier.
+        SRA run identifier.
 # TODO Update when we decide on a standard for subworkflow docs
 output:
   - meta:

tests/config/pytest_modules.yml

@@ -495,6 +495,10 @@ custom/getchromsizes:
   - modules/custom/getchromsizes/**
   - tests/modules/custom/getchromsizes/**
 
+custom/sratoolsncbisettings:
+  - modules/custom/sratoolsncbisettings/**
+  - tests/modules/custom/sratoolsncbisettings/**
+
 cutadapt:
   - modules/cutadapt/**
   - tests/modules/cutadapt/**
@@ -815,6 +819,10 @@ gatk4/selectvariants:
   - modules/gatk4/selectvariants/**
   - tests/modules/gatk4/selectvariants/**
 
+gatk4/splitintervals:
+  - modules/gatk4/splitintervals/**
+  - tests/modules/gatk4/splitintervals/**
+
 gatk4/splitncigarreads:
   - modules/gatk4/splitncigarreads/**
   - tests/modules/gatk4/splitncigarreads/**
@@ -835,6 +843,10 @@ genmap/mappability:
   - modules/genmap/mappability/**
   - tests/modules/genmap/mappability/**
 
+genomescope2:
+  - modules/genomescope2/**
+  - tests/modules/genomescope2/**
+
 genrich:
   - modules/genrich/**
   - tests/modules/genrich/**
@@ -1214,6 +1226,18 @@ 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/**
@@ -1611,6 +1635,10 @@ 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/**
@@ -1631,14 +1659,14 @@ samtools/bam2fq:
   - modules/samtools/bam2fq/**
   - tests/modules/samtools/bam2fq/**
 
-samtools/bamtocram:
-  - modules/samtools/bamtocram/**
-  - tests/modules/samtools/bamtocram/**
-
 samtools/collatefastq:
   - modules/samtools/collatefastq/**
   - tests/modules/samtools/collatefastq/**
 
+samtools/convert:
+  - modules/samtools/convert/**
+  - tests/modules/samtools/convert/**
+
 samtools/depth:
   - modules/samtools/depth/**
   - tests/modules/samtools/depth/**
@@ -1767,14 +1795,14 @@ slimfastq:
   - modules/slimfastq/**
   - tests/modules/slimfastq/**
 
-snapaligner/index:
-  - modules/snapaligner/index/**
-  - tests/modules/snapaligner/index/**
-
 snapaligner/align:
   - modules/snapaligner/align/**
   - tests/modules/snapaligner/align/**
 
+snapaligner/index:
+  - modules/snapaligner/index/**
+  - tests/modules/snapaligner/index/**
+
 snpdists:
   - modules/snpdists/**
   - tests/modules/snpdists/**

tests/config/test_data.config

@@ -135,6 +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                                 = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.dict"
@@ -212,110 +213,113 @@ params {
                 test_paired_end_hla                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/example_hla_pe.bam"
                 test_paired_end_hla_sorted_bam                          = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/example_hla_pe.sorted.bam"
                 test_paired_end_hla_sorted_bam_bai                      = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/example_hla_pe.sorted.bam.bai"
+                test2_paired_end_sorted_bam                    = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam"
+                test2_paired_end_sorted_bam_bai                = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam.bai"
+                test2_paired_end_name_sorted_bam               = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.name.sorted.bam"
+                test2_paired_end_markduplicates_sorted_bam     = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.markduplicates.sorted.bam"
+                test2_paired_end_markduplicates_sorted_bam_bai = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.markduplicates.sorted.bam.bai"
+                test2_paired_end_recalibrated_sorted_bam       = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.recalibrated.sorted.bam"
+                test2_paired_end_recalibrated_sorted_bam_bai   = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.recalibrated.sorted.bam.bai"
+                test2_paired_end_umi_consensus_bam             = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_consensus.bam"
+                test2_paired_end_umi_converted_bam             = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_converted.bam"
+                test2_paired_end_umi_grouped_bam               = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_grouped.bam"
+                test2_paired_end_umi_histogram_txt             = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_histogram.txt"
+                test2_paired_end_umi_unsorted_bam              = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_unsorted.bam"
+                test2_paired_end_umi_unsorted_tagged_bam       = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.unsorted_tagged.bam"
 
-                test2_paired_end_sorted_bam                             = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam"
-                test2_paired_end_sorted_bam_bai                         = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam.bai"
-                test2_paired_end_name_sorted_bam                        = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.name.sorted.bam"
-                test2_paired_end_markduplicates_sorted_bam              = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.markduplicates.sorted.bam"
-                test2_paired_end_markduplicates_sorted_bam_bai          = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.markduplicates.sorted.bam.bai"
-                test2_paired_end_recalibrated_sorted_bam                = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.recalibrated.sorted.bam"
-                test2_paired_end_recalibrated_sorted_bam_bai            = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.recalibrated.sorted.bam.bai"
-                test2_paired_end_umi_consensus_bam                      = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_consensus.bam"
-                test2_paired_end_umi_converted_bam                      = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_converted.bam"
-                test2_paired_end_umi_grouped_bam                        = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_grouped.bam"
-                test2_paired_end_umi_histogram_txt                      = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_histogram.txt"
-                test2_paired_end_umi_unsorted_bam                       = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_unsorted.bam"
-                test2_paired_end_umi_unsorted_tagged_bam                = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.unsorted_tagged.bam"
 
-                mitochon_standin_recalibrated_sorted_bam                = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/mitochon_standin.recalibrated.sorted.bam"
-                mitochon_standin_recalibrated_sorted_bam_bai            = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/mitochon_standin.recalibrated.sorted.bam.bai"
+                mitochon_standin_recalibrated_sorted_bam       = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/mitochon_standin.recalibrated.sorted.bam"
+                mitochon_standin_recalibrated_sorted_bam_bai   = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/mitochon_standin.recalibrated.sorted.bam.bai"
 
-                test_paired_end_sorted_cram                             = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram"
-                test_paired_end_sorted_cram_crai                        = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram.crai"
-                test_paired_end_markduplicates_sorted_cram              = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.markduplicates.sorted.cram"
-                test_paired_end_markduplicates_sorted_cram_crai         = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.markduplicates.sorted.cram.crai"
-                test_paired_end_recalibrated_sorted_cram                = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram"
-                test_paired_end_recalibrated_sorted_cram_crai           = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram.crai"
+                test_paired_end_sorted_cram                      = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram"
+                test_paired_end_sorted_cram_crai                 = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram.crai"
+                test_paired_end_markduplicates_sorted_cram       = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.markduplicates.sorted.cram"
+                test_paired_end_markduplicates_sorted_cram_crai  = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.markduplicates.sorted.cram.crai"
+                test_paired_end_recalibrated_sorted_cram         = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram"
+                test_paired_end_recalibrated_sorted_cram_crai    = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram.crai"
 
-                test2_paired_end_sorted_cram                            = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.sorted.cram"
-                test2_paired_end_sorted_cram_crai                       = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.sorted.cram.crai"
-                test2_paired_end_markduplicates_sorted_cram             = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.markduplicates.sorted.cram"
-                test2_paired_end_markduplicates_sorted_cram_crai        = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.markduplicates.sorted.cram.crai"
-                test2_paired_end_recalibrated_sorted_cram               = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.recalibrated.sorted.cram"
-                test2_paired_end_recalibrated_sorted_cram_crai          = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.recalibrated.sorted.cram.crai"
+                test2_paired_end_sorted_cram                     = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.sorted.cram"
+                test2_paired_end_sorted_cram_crai                = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.sorted.cram.crai"
+                test2_paired_end_markduplicates_sorted_cram      = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.markduplicates.sorted.cram"
+                test2_paired_end_markduplicates_sorted_cram_crai = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.markduplicates.sorted.cram.crai"
+                test2_paired_end_recalibrated_sorted_cram        = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.recalibrated.sorted.cram"
+                test2_paired_end_recalibrated_sorted_cram_crai   = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test2.paired_end.recalibrated.sorted.cram.crai"
 
-                test_1_fastq_gz                                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_1.fastq.gz"
-                test_2_fastq_gz                                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_2.fastq.gz"
-                test_umi_1_fastq_gz                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.umi_1.fastq.gz"
-                test_umi_2_fastq_gz                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.umi_2.fastq.gz"
-                test2_1_fastq_gz                                        = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2_1.fastq.gz"
-                test2_2_fastq_gz                                        = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2_2.fastq.gz"
-                test2_umi_1_fastq_gz                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_1.fastq.gz"
-                test2_umi_2_fastq_gz                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_2.fastq.gz"
-                test_rnaseq_1_fastq_gz                                  = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_rnaseq_1.fastq.gz"
-                test_rnaseq_2_fastq_gz                                  = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_rnaseq_2.fastq.gz"
+                test_1_fastq_gz                                = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_1.fastq.gz"
+                test_2_fastq_gz                                = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_2.fastq.gz"
+                test_umi_1_fastq_gz                            = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.umi_1.fastq.gz"
+                test_umi_2_fastq_gz                            = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.umi_2.fastq.gz"
+                test2_1_fastq_gz                               = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2_1.fastq.gz"
+                test2_2_fastq_gz                               = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2_2.fastq.gz"
+                test2_umi_1_fastq_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_1.fastq.gz"
+                test2_umi_2_fastq_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_2.fastq.gz"
+                test_rnaseq_1_fastq_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_rnaseq_1.fastq.gz"
+                test_rnaseq_2_fastq_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_rnaseq_2.fastq.gz"
 
-                test_baserecalibrator_table                             = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.baserecalibrator.table"
-                test2_baserecalibrator_table                            = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.baserecalibrator.table"
-                test_pileups_table                                      = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.pileups.table"
-                test2_pileups_table                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.pileups.table"
+                test_baserecalibrator_table                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.baserecalibrator.table"
+                test2_baserecalibrator_table                   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.baserecalibrator.table"
+                test_pileups_table                             = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.pileups.table"
+                test2_pileups_table                            = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.pileups.table"
 
-                test_genomicsdb_tar_gz                                  = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_genomicsdb.tar.gz"
-                test_pon_genomicsdb_tar_gz                              = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_pon_genomicsdb.tar.gz"
+                test_genomicsdb_tar_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_genomicsdb.tar.gz"
+                test_pon_genomicsdb_tar_gz                     = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_pon_genomicsdb.tar.gz"
 
-                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_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_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                                          = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.tranches"
-                test2_allele_specific_recal                             = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2_allele_specific.recal"
-                test2_allele_specific_recal_idx                         = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2_allele_specific.recal.idx"
-                test2_allele_specific_tranches                          = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2_allele_specific.tranches"
+                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"
 
-                test_test2_paired_mutect2_calls_vcf_gz                  = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz"
-                test_test2_paired_mutect2_calls_vcf_gz_tbi              = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz.tbi"
-                test_test2_paired_mutect2_calls_vcf_gz_stats            = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz.stats"
-                test_test2_paired_mutect2_calls_f1r2_tar_gz             = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.f1r2.tar.gz"
-                test_test2_paired_mutect2_calls_artifact_prior_tar_gz   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired_mutect2_calls.artifact-prior.tar.gz"
-                test_test2_paired_segmentation_table                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired.segmentation.table"
-                test_test2_paired_contamination_table                   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired.contamination.table"
+                test2_recal                                    = "${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"
+                test2_allele_specific_recal                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2_allele_specific.recal"
+                test2_allele_specific_recal_idx                = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2_allele_specific.recal.idx"
+                test2_allele_specific_tranches                 = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2_allele_specific.tranches"
 
-                test_genome_vcf                                         = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf"
-                test_genome_vcf_gz                                      = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz"
-                test_genome_vcf_gz_tbi                                  = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz.tbi"
-                test_genome_vcf_idx                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.idx"
+                test_test2_paired_mutect2_calls_vcf_gz         = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz"
+                test_test2_paired_mutect2_calls_vcf_gz_tbi     = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz.tbi"
+                test_test2_paired_mutect2_calls_vcf_gz_stats   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz.stats"
+                test_test2_paired_mutect2_calls_f1r2_tar_gz    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.f1r2.tar.gz"
+                test_test2_paired_mutect2_calls_artifact_prior_tar_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired_mutect2_calls.artifact-prior.tar.gz"
+                test_test2_paired_segmentation_table           = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired.segmentation.table"
+                test_test2_paired_contamination_table          = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired.contamination.table"
 
-                test2_genome_vcf                                        = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf"
-                test2_genome_vcf_gz                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.gz"
-                test2_genome_vcf_gz_tbi                                 = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.gz.tbi"
-                test2_genome_vcf_idx                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.idx"
+                test_genome_vcf                                = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf"
+                test_genome_vcf_gz                             = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz"
+                test_genome_vcf_gz_tbi                         = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz.tbi"
+                test_genome_vcf_idx                            = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.idx"
 
-                test_genome21_indels_vcf_gz                             = "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.genome_21.somatic_sv.vcf.gz"
-                test_genome21_indels_vcf_gz_tbi                         = "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.genome_21.somatic_sv.vcf.gz.tbi"
+                test2_genome_vcf                               = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf"
+                test2_genome_vcf_gz                            = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.gz"
+                test2_genome_vcf_gz_tbi                        = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.gz.tbi"
+                test2_genome_vcf_idx                           = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.idx"
 
-                test_mpileup                                            = "${test_data_dir}/genomics/homo_sapiens/illumina/mpileup/test.mpileup.gz"
-                test2_mpileup                                           = "${test_data_dir}/genomics/homo_sapiens/illumina/mpileup/test2.mpileup.gz"
+                test_genome21_indels_vcf_gz                    = "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.genome_21.somatic_sv.vcf.gz"
+                test_genome21_indels_vcf_gz_tbi                = "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.genome_21.somatic_sv.vcf.gz.tbi"
 
-                test_broadpeak                                          = "${test_data_dir}/genomics/homo_sapiens/illumina/broadpeak/test.broadPeak"
-                test2_broadpeak                                         = "${test_data_dir}/genomics/homo_sapiens/illumina/broadpeak/test2.broadPeak"
+                test_mpileup                                   = "${test_data_dir}/genomics/homo_sapiens/illumina/mpileup/test.mpileup.gz"
+                test2_mpileup                                  = "${test_data_dir}/genomics/homo_sapiens/illumina/mpileup/test2.mpileup.gz"
 
-                test_narrowpeak                                         = "${test_data_dir}/genomics/homo_sapiens/illumina/narrowpeak/test.narrowPeak"
-                test2_narrowpeak                                        = "${test_data_dir}/genomics/homo_sapiens/illumina/narrowpeak/test2.narrowPeak"
+                test_broadpeak                                 = "${test_data_dir}/genomics/homo_sapiens/illumina/broadpeak/test.broadPeak"
+                test2_broadpeak                                = "${test_data_dir}/genomics/homo_sapiens/illumina/broadpeak/test2.broadPeak"
 
-                test_10x_1_fastq_gz                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/10xgenomics/test_10x_S1_L001_R1_001.fastq.gz"
-                test_10x_2_fastq_gz                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/10xgenomics/test_10x_S1_L001_R2_001.fastq.gz"
+                test_narrowpeak                                = "${test_data_dir}/genomics/homo_sapiens/illumina/narrowpeak/test.narrowPeak"
+                test2_narrowpeak                               = "${test_data_dir}/genomics/homo_sapiens/illumina/narrowpeak/test2.narrowPeak"
 
-                test_yak                                                = "${test_data_dir}/genomics/homo_sapiens/illumina/yak/test.yak"
-                test2_yak                                               = "${test_data_dir}/genomics/homo_sapiens/illumina/yak/test2.yak"
+                test_10x_1_fastq_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/10xgenomics/test_10x_S1_L001_R1_001.fastq.gz"
+                test_10x_2_fastq_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/10xgenomics/test_10x_S1_L001_R2_001.fastq.gz"
 
-                cutandrun_bedgraph_test_1                               = "${test_data_dir}/genomics/homo_sapiens/illumina/bedgraph/cutandtag_h3k27me3_test_1.bedGraph"
-                cutandrun_bedgraph_test_2                               = "${test_data_dir}/genomics/homo_sapiens/illumina/bedgraph/cutandtag_igg_test_1.bedGraph"
+                test_yak                                      = "${test_data_dir}/genomics/homo_sapiens/illumina/yak/test.yak"
+                test2_yak                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/yak/test2.yak"
 
-                test_rnaseq_vcf                                         =  "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.rnaseq.vcf"
-                test_sv_vcf                                             =  "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/sv_query.vcf.gz"
+                cutandrun_bedgraph_test_1                     = "${test_data_dir}/genomics/homo_sapiens/illumina/bedgraph/cutandtag_h3k27me3_test_1.bedGraph"
+                cutandrun_bedgraph_test_2                     = "${test_data_dir}/genomics/homo_sapiens/illumina/bedgraph/cutandtag_igg_test_1.bedGraph"
 
-                test_pytor                                              = "${test_data_dir}/genomics/homo_sapiens/illumina/pytor/test.pytor"
+                test_rnaseq_vcf                               =  "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.rnaseq.vcf"
+                test_sv_vcf                                   =  "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/sv_query.vcf.gz"
+
+                test_pytor                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/pytor/test.pytor"
             }
             'pacbio' {
                 primers                         = "${test_data_dir}/genomics/homo_sapiens/pacbio/fasta/primers.fasta"
@@ -345,6 +349,7 @@ params {
                 genome_gbff_gz                  = "${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' {
@@ -377,7 +382,7 @@ params {
                 test3_gff                       = "${test_data_dir}/genomics/prokaryotes/candidatus_portiera_aleyrodidarum/genome/gff/test3.gff"
             }
             'illumina' {
-                test_1_fastq_gz                 = "${test_data_dir}/genomics/prokaryotes/candidatus_portiera_aleyrodidarum/illumina/fasta/test_1.fastq.gz"
+                test_1_fastq_gz                 = "${test_data_dir}/genomics/prokaryotes/candidatus_portiera_aleyrodidarum/illumina/fastq/test_1.fastq.gz"
                 test_2_fastq_gz                 = "${test_data_dir}/genomics/prokaryotes/candidatus_portiera_aleyrodidarum/illumina/fastq/test_2.fastq.gz"
                 test_se_fastq_gz                = "${test_data_dir}/genomics/prokaryotes/candidatus_portiera_aleyrodidarum/illumina/fastq/test_se.fastq.gz"
             }
@@ -421,6 +426,9 @@ params {
                 test_merge_cool_cp2             = "${test_data_dir}/genomics/homo_sapiens/cooler/merge/toy/toy.symm.upper.2.cp2.cool"
 
             }
+            'config' {
+                ncbi_user_settings              = "${test_data_dir}/generic/config/ncbi_user_settings.mkfg"
+            }
         }
     }
 }

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

@@ -30,6 +30,35 @@ workflow test_bowtie2_align_paired_end {
     fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
     save_unaligned = false
 
+    BOWTIE2_BUILD ( fasta )
+    BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned )
+}
+
+workflow test_bowtie2_align_single_end_large_index {
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    save_unaligned = false
+
+    BOWTIE2_BUILD ( fasta )
+    BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned )
+}
+
+workflow test_bowtie2_align_paired_end_large_index {
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+            file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    save_unaligned = false
+
     BOWTIE2_BUILD ( fasta )
     BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned )
 }

tests/modules/bowtie2/align/nextflow.config

@@ -5,6 +5,7 @@ params {
 process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
 }
 
 if (params.force_large_index) {

tests/modules/bowtie2/align/test.yml

@@ -1,4 +1,4 @@
-- name: bowtie2 align single-end
+- name: bowtie2 align test_bowtie2_align_single_end
   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
   tags:
     - bowtie2
@@ -6,78 +6,34 @@
   files:
     - path: ./output/bowtie2/test.bam
     - path: ./output/bowtie2/test.bowtie2.log
-    - path: ./output/bowtie2/bowtie2/genome.3.bt2
-      md5sum: 4ed93abba181d8dfab2e303e33114777
-    - path: ./output/bowtie2/bowtie2/genome.2.bt2
-      md5sum: 47b153cd1319abc88dda532462651fcf
-    - path: ./output/bowtie2/bowtie2/genome.1.bt2
-      md5sum: cbe3d0bbea55bc57c99b4bfa25b5fbdf
-    - path: ./output/bowtie2/bowtie2/genome.4.bt2
-      md5sum: c25be5f8b0378abf7a58c8a880b87626
-    - path: ./output/bowtie2/bowtie2/genome.rev.1.bt2
-      md5sum: 52be6950579598a990570fbcf5372184
-    - path: ./output/bowtie2/bowtie2/genome.rev.2.bt2
-      md5sum: e3b4ef343dea4dd571642010a7d09597
+    - path: ./output/bowtie2/versions.yml
 
-- name: bowtie2 align paired-end
-  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
+- name: bowtie2 align test_bowtie2_align_paired_end
+  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
   tags:
     - bowtie2
     - bowtie2/align
   files:
     - path: ./output/bowtie2/test.bam
     - path: ./output/bowtie2/test.bowtie2.log
-    - path: ./output/bowtie2/bowtie2/genome.3.bt2
-      md5sum: 4ed93abba181d8dfab2e303e33114777
-    - path: ./output/bowtie2/bowtie2/genome.2.bt2
-      md5sum: 47b153cd1319abc88dda532462651fcf
-    - path: ./output/bowtie2/bowtie2/genome.1.bt2
-      md5sum: cbe3d0bbea55bc57c99b4bfa25b5fbdf
-    - path: ./output/bowtie2/bowtie2/genome.4.bt2
-      md5sum: c25be5f8b0378abf7a58c8a880b87626
-    - path: ./output/bowtie2/bowtie2/genome.rev.1.bt2
-      md5sum: 52be6950579598a990570fbcf5372184
-    - path: ./output/bowtie2/bowtie2/genome.rev.2.bt2
-      md5sum: e3b4ef343dea4dd571642010a7d09597
+    - path: ./output/bowtie2/versions.yml
 
-- 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
+- name: bowtie2 align test_bowtie2_align_single_end_large_index
+  command: nextflow run tests/modules/bowtie2/align -entry test_bowtie2_align_single_end_large_index -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
+    - path: ./output/bowtie2/versions.yml
 
-- 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
+- name: bowtie2 align test_bowtie2_align_paired_end_large_index
+  command: nextflow run tests/modules/bowtie2/align -entry test_bowtie2_align_paired_end_large_index -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
+    - path: ./output/bowtie2/versions.yml

tests/modules/custom/sratoolsncbisettings/main.nf

@@ -0,0 +1,44 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CUSTOM_SRATOOLSNCBISETTINGS } from '../../../../modules/custom/sratoolsncbisettings/main.nf'
+
+workflow test_sratoolsncbisettings_with_good_existing {
+
+    file(params.settings_path).mkdirs()
+    def settings = file(params.test_data['generic']['config']['ncbi_user_settings'], checkIfExists: true)
+    settings.copyTo(params.settings_file)
+
+    CUSTOM_SRATOOLSNCBISETTINGS()
+}
+
+workflow test_sratoolsncbisettings_with_bad_existing {
+
+    file(params.settings_path).mkdirs()
+    def settings = file(params.settings_file)
+    settings.text = '''
+    ## auto-generated configuration file - DO NOT EDIT ##
+
+    config/default = "false"
+    /repository/remote/main/CGI/resolver-cgi = "https://trace.ncbi.nlm.nih.gov/Traces/names/names.fcgi"
+    /repository/remote/protected/CGI/resolver-cgi = "https://trace.ncbi.nlm.nih.gov/Traces/names/names.fcgi"
+    /repository/user/ad/public/apps/file/volumes/flatAd = "."
+    /repository/user/ad/public/apps/refseq/volumes/refseqAd = "."
+    /repository/user/ad/public/apps/sra/volumes/sraAd = "."
+    /repository/user/ad/public/apps/sraPileup/volumes/ad = "."
+    /repository/user/ad/public/apps/sraRealign/volumes/ad = "."
+    /repository/user/ad/public/apps/wgs/volumes/wgsAd = "."
+    /repository/user/ad/public/root = "."
+    /repository/user/default-path = "/root/ncbi"
+    '''.stripIndent()
+
+    CUSTOM_SRATOOLSNCBISETTINGS()
+}
+
+workflow test_sratoolsncbisettings_with_nonexisting {
+    def settings = file(params.settings_file)
+    settings.delete()
+
+    CUSTOM_SRATOOLSNCBISETTINGS()
+}

tests/modules/custom/sratoolsncbisettings/nextflow.config

@@ -0,0 +1,8 @@
+params.settings_path = '/tmp/.ncbi'
+params.settings_file = "${params.settings_path}/user-settings.mkfg"
+
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}

tests/modules/custom/sratoolsncbisettings/nextflow_mount.config

@@ -0,0 +1,17 @@
+params.settings_path = '/tmp/.ncbi'
+params.settings_file = "${params.settings_path}/user-settings.mkfg"
+
+env.NCBI_SETTINGS = params.settings_file
+
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: CUSTOM_SRATOOLSNCBISETTINGS {
+        containerOptions = {
+            (workflow.containerEngine == 'singularity') ?
+            "-B ${params.settings_path}:${params.settings_path}" :
+            "-v ${params.settings_path}:${params.settings_path}"
+        }
+    }
+}

tests/modules/custom/sratoolsncbisettings/test.yml

@@ -0,0 +1,44 @@
+- name: "custom sratoolsncbisettings test_sratoolsncbisettings_with_good_existing"
+  command: nextflow run ./tests/modules/custom/sratoolsncbisettings -entry test_sratoolsncbisettings_with_good_existing -c ./tests/config/nextflow.config -c ./tests/modules/custom/sratoolsncbisettings/nextflow_mount.config
+  tags:
+    - "custom"
+    - "custom/sratoolsncbisettings"
+  files:
+    - path: "output/custom/user-settings.mkfg"
+      md5sum: 955e27aff2c277c2f1f0943a098888c1
+    - path: output/custom/versions.yml
+      contains:
+        - "sratools: 2.11.0"
+
+- name: "custom sratoolsncbisettings test_sratoolsncbisettings_with_bad_existing"
+  command: nextflow run ./tests/modules/custom/sratoolsncbisettings -entry test_sratoolsncbisettings_with_bad_existing -c ./tests/config/nextflow.config -c ./tests/modules/custom/sratoolsncbisettings/nextflow_mount.config
+  tags:
+    - "custom"
+    - "custom/sratoolsncbisettings"
+  exit_code: 1
+  stdout:
+    contains:
+      - "Command error:"
+      - "missing the required entries"
+      - "/LIBS/GUID"
+      - "/libs/cloud/report_instance_identity"
+      - "Feel free to add the following"
+  files:
+    - path: "output/custom/user-settings.mkfg"
+      should_exist: false
+    - path: output/custom/versions.yml
+      should_exist: false
+
+- name: "custom sratoolsncbisettings test_sratoolsncbisettings_with_nonexisting"
+  command: nextflow run ./tests/modules/custom/sratoolsncbisettings -entry test_sratoolsncbisettings_with_nonexisting -c ./tests/config/nextflow.config -c ./tests/modules/custom/sratoolsncbisettings/nextflow.config
+  tags:
+    - "custom"
+    - "custom/sratoolsncbisettings"
+  files:
+    - path: "output/custom/user-settings.mkfg"
+      contains:
+        - "/LIBS/GUID"
+        - "/libs/cloud/report_instance_identity"
+    - path: output/custom/versions.yml
+      contains:
+        - "sratools: 2.11.0"

tests/modules/gatk4/mergebamalignment/main.nf

@@ -17,11 +17,11 @@ workflow test_gatk4_mergebamalignment {
 
 workflow test_gatk4_mergebamalignment_stubs {
      input    = [ [ id:'test' ], // meta map
-                 "test_foo.bam",
-                 "test_bar.bam"
+                 file(params.test_data['sarscov2']['illumina']['test_single_end_bam'], checkIfExists: true),
+                 file(params.test_data['sarscov2']['illumina']['test_unaligned_bam'], checkIfExists: true)
                ]
-    fasta    = "genome.fasta"
-    dict     = "genome.fasta.dict"
+    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

@@ -9,7 +9,7 @@
     - path: output/gatk4/versions.yml
 
 - name: gatk4 mergebamalignment test_gatk4_mergebamalignment_stubs
-  command: nextflow run ./tests/modules/gatk4/mergebamalignment -entry test_gatk4_mergebamalignment -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/mergebamalignment/nextflow.config -stub-run
+  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

tests/modules/gatk4/mutect2/main.nf

@@ -120,23 +120,23 @@ workflow test_gatk4_mutect2_mitochondria {
 }
 
 workflow test_gatk4_mutect2_tumor_normal_pair_f1r2_stubs {
-    input = [ [ id:'test', normal_id:'normal', tumor_id:'tumour' ], // meta map
-              [ "foo_paired.bam",
-                "foo_paired2.bam"
+     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)
                 ],
-              [ "foo_paired.bam.bai",
-                "foo_paired2.bam.bai"
+              [ 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 = "genome.fasta"
-    fai = "genome.fasta.fai"
-    dict = "genome.fasta.dict"
-    germline_resource = "genome_gnomAD.r2.1.1.vcf.gz"
-    germline_resource_tbi = "genome_gnomAD.r2.1.1.vcf.gz.tbi"
-    panel_of_normals = "genome_mills_and_1000G.indels.hg38.vcf.gz"
-    panel_of_normals_tbi = "genome_mills_and_1000G.indels.hg38.vcf.gz.tbi"
+    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

@@ -71,7 +71,7 @@
     - path: output/gatk4/versions.yml
 
 - name: gatk4 mutect2 test_gatk4_mutect2_tumor_normal_pair_f1r2_stubs
-  command: nextflow run ./tests/modules/gatk4/mutect2 -entry test_gatk4_mutect2_tumor_normal_pair_f1r2 -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/mutect2/nextflow.config -stub-run
+  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

tests/modules/gatk4/revertsam/main.nf

@@ -14,7 +14,7 @@ workflow test_gatk4_revertsam {
 
 workflow test_gatk4_revertsam_stubs {
     input = [ [ id:'test' ], // meta map
-              "foo_paired_end.bam"
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
             ]
 
     GATK4_REVERTSAM ( input )

tests/modules/gatk4/revertsam/test.yml

@@ -9,7 +9,7 @@
     - path: output/gatk4/versions.yml
 
 - name: gatk4 revertsam test_gatk4_revertsam_stubs
-  command: nextflow run ./tests/modules/gatk4/revertsam -entry test_gatk4_revertsam -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/revertsam/nextflow.config -stub-run
+  command: nextflow run ./tests/modules/gatk4/revertsam -entry test_gatk4_revertsam_stubs -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/revertsam/nextflow.config -stub-run
   tags:
     - gatk4
     - gatk4/revertsam

tests/modules/gatk4/samtofastq/main.nf

@@ -21,8 +21,8 @@ workflow test_gatk4_samtofastq_paired_end {
 }
 
 workflow test_gatk4_samtofastq_paired_end_stubs {
-    input = [ [ id:'test', single_end: false ], // meta map
-              [ "foo_paired_end.bam" ]
+    input = [ [ id:'test', single_end: true ], // meta map
+              [ file(params.test_data['sarscov2']['illumina']['test_single_end_bam'], checkIfExists: true) ]
             ]
 
     GATK4_SAMTOFASTQ ( input )

tests/modules/gatk4/samtofastq/test.yml

@@ -21,7 +21,7 @@
     - path: output/gatk4/versions.yml
 
 - name: gatk4 samtofastq test_gatk4_samtofastq_paired_end_stubs
-  command: nextflow run ./tests/modules/gatk4/samtofastq -entry test_gatk4_samtofastq_paired_end -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/samtofastq/nextflow.config -stub-run
+  command: nextflow run ./tests/modules/gatk4/samtofastq -entry test_gatk4_samtofastq_paired_end_stubs -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/samtofastq/nextflow.config -stub-run
   tags:
     - gatk4
     - gatk4/samtofastq

tests/modules/gatk4/splitintervals/main.nf

@@ -0,0 +1,33 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_SPLITINTERVALS } from '../../../../modules/gatk4/splitintervals/main.nf'
+
+workflow test_gatk4_splitintervals_bed {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['genome']['genome_multi_interval_bed'], checkIfExists: true)
+    ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    fasta_dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+
+    GATK4_SPLITINTERVALS ( input, fasta, fasta_fai, fasta_dict)
+}
+
+workflow test_gatk4_splitintervals_intervals {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['genome']['genome_interval_list'], checkIfExists: true)
+    ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    fasta_dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+
+    GATK4_SPLITINTERVALS ( input, fasta, fasta_fai, fasta_dict)
+}

tests/modules/gatk4/splitintervals/nextflow.config

@@ -0,0 +1,9 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+
+    withName: GATK4_SPLITINTERVALS {
+        ext.args = "--scatter-count 2"
+    }
+}

tests/modules/gatk4/splitintervals/test.yml

@@ -0,0 +1,23 @@
+- name: gatk4 splitintervals test_gatk4_splitintervals_bed
+  command: nextflow run tests/modules/gatk4/splitintervals -entry test_gatk4_splitintervals_bed -c tests/config/nextflow.config
+  tags:
+    - gatk4/splitintervals
+    - gatk4
+  files:
+    - path: output/gatk4/test/0000-scattered.interval_list
+      md5sum: c8d6b19e7a92535b6ce9608eae558faa
+    - path: output/gatk4/test/0001-scattered.interval_list
+      md5sum: b1877ad96aec308906594c50ebbe3ded
+    - path: output/gatk4/versions.yml
+
+- name: gatk4 splitintervals test_gatk4_splitintervals_intervals
+  command: nextflow run tests/modules/gatk4/splitintervals -entry test_gatk4_splitintervals_intervals -c tests/config/nextflow.config
+  tags:
+    - gatk4/splitintervals
+    - gatk4
+  files:
+    - path: output/gatk4/test/0000-scattered.interval_list
+      md5sum: ebd6b34a335efc6732ff541936c6d2d5
+    - path: output/gatk4/test/0001-scattered.interval_list
+      md5sum: 9459b0e124fa84ec1e64ac4615bc9af7
+    - path: output/gatk4/versions.yml

tests/modules/genomescope2/main.nf

@@ -0,0 +1,19 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MERYL_COUNT     } from '../../../modules/meryl/count/main.nf'
+include { MERYL_HISTOGRAM } from '../../../modules/meryl/histogram/main.nf'
+include { GENOMESCOPE2    } from '../../../modules/genomescope2/main.nf'
+
+workflow test_genomescope2 {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['bacteroides_fragilis']['illumina']['test1_1_fastq_gz'], checkIfExists: true)
+    ]
+
+    MERYL_COUNT ( input )
+    MERYL_HISTOGRAM ( MERYL_COUNT.out.meryl_db )
+    GENOMESCOPE2 ( MERYL_HISTOGRAM.out.hist )
+}

tests/modules/genomescope2/nextflow.config

@@ -0,0 +1,13 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: 'MERYL.*' {
+        ext.args = 'k=21'
+    }
+
+    withName: 'GENOMESCOPE2' {
+        ext.args = '-k 21 -p 1'
+    }
+
+}

tests/modules/genomescope2/test.yml

@@ -0,0 +1,22 @@
+- name: genomescope2 test_genomescope2
+  command: nextflow run tests/modules/genomescope2 -entry test_genomescope2 -c tests/config/nextflow.config
+  tags:
+    - genomescope2
+  files:
+    - path: output/genomescope2/test_linear_plot.png
+      md5sum: 94c165c5028156299a1d4d05766cac51
+    - path: output/genomescope2/test_log_plot.png
+      md5sum: 9d25ca463d92a0c73a893da7fd3979ba
+    - path: output/genomescope2/test_model.txt
+      md5sum: 3caf62f715f64a2f2b8fdff5d079cb84
+    - path: output/genomescope2/test_summary.txt
+      md5sum: 7452860e2cea99b85f3ff60daeac77f5
+    - path: output/genomescope2/test_transformed_linear_plot.png
+      md5sum: 99a64c1c18d8670f64cb863d4334abbb
+    - path: output/genomescope2/test_transformed_log_plot.png
+      md5sum: b4e029c9fb9987ca33b17392a691c1b4
+    - path: output/genomescope2/versions.yml
+      md5sum: 18afeb26f62a47f680b2bb3e27da9cbc
+    - path: output/meryl/test.hist
+      md5sum: f75362ab9cd70d96621b3690e952085f
+    - path: output/meryl/versions.yml

tests/modules/meryl/count/main.nf

@@ -0,0 +1,28 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MERYL_COUNT } from '../../../../modules/meryl/count/main.nf'
+
+workflow test_meryl_count_single_end {
+
+    input = [
+        [ id:'test' , single_end: true ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+    ]
+
+    MERYL_COUNT ( input )
+}
+
+workflow test_meryl_count_paired_end {
+
+    input = [
+        [ id:'test' , single_end: false ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+            file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+
+    MERYL_COUNT ( input )
+}

tests/modules/meryl/count/nextflow.config

@@ -0,0 +1,6 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    ext.args = 'k=21'
+
+}

tests/modules/meryl/count/test.yml

@@ -0,0 +1,17 @@
+- name: meryl count test_meryl_count_single_end
+  command: nextflow run tests/modules/meryl/count -entry test_meryl_count_single_end -c tests/config/nextflow.config
+  tags:
+    - meryl/count
+    - meryl
+  files:
+    - path: output/meryl/versions.yml
+      md5sum: 5fe537d873925ccbcc4edf0983e9eda0
+
+- name: meryl count test_meryl_count_paired_end
+  command: nextflow run tests/modules/meryl/count -entry test_meryl_count_paired_end -c tests/config/nextflow.config
+  tags:
+    - meryl/count
+    - meryl
+  files:
+    - path: output/meryl/versions.yml
+      md5sum: 4961f13cfb60ba8764ed666e70dbf12c

tests/modules/meryl/histogram/main.nf

@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MERYL_COUNT     } from '../../../../modules/meryl/count/main.nf'
+include { MERYL_HISTOGRAM } from '../../../../modules/meryl/histogram/main.nf'
+
+workflow test_meryl_histogram {
+
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+    ]
+
+    MERYL_COUNT ( input )
+    MERYL_HISTOGRAM ( MERYL_COUNT.out.meryl_db )
+}

tests/modules/meryl/histogram/nextflow.config

@@ -0,0 +1,6 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    ext.args = 'k=21'
+
+}

tests/modules/meryl/histogram/test.yml

@@ -0,0 +1,10 @@
+- name: meryl histogram test_meryl_histogram
+  command: nextflow run tests/modules/meryl/histogram -entry test_meryl_histogram -c tests/config/nextflow.config
+  tags:
+    - meryl/histogram
+    - meryl
+  files:
+    - path: output/meryl/test.hist
+      md5sum: 4bfdc8b287ee0cfd9922bbfa8cd64650
+    - path: output/meryl/versions.yml
+      md5sum: 050038f1b1df79977a393cce1b4b2ddb

tests/modules/meryl/unionsum/main.nf

@@ -0,0 +1,31 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MERYL_COUNT    } from '../../../../modules/meryl/count/main.nf'
+include { MERYL_UNIONSUM } from '../../../../modules/meryl/unionsum/main.nf'
+
+workflow test_meryl_unionsum_single_end {
+
+    input = [
+        [ id:'test', single_end: true ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+    ]
+
+    MERYL_COUNT ( input )
+    MERYL_UNIONSUM ( MERYL_COUNT.out.meryl_db )
+}
+
+workflow test_meryl_unionsum_paired_end {
+
+    input = [
+        [ id:'test', single_end: false ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+            file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+
+    MERYL_COUNT ( input )
+    MERYL_UNIONSUM ( MERYL_COUNT.out.meryl_db )
+}

tests/modules/meryl/unionsum/nextflow.config

@@ -0,0 +1,6 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    ext.args = 'k=21'
+
+}

tests/modules/meryl/unionsum/test.yml

@@ -0,0 +1,17 @@
+- name: meryl unionsum test_meryl_unionsum_single_end
+  command: nextflow run tests/modules/meryl/unionsum -entry test_meryl_unionsum_single_end -c tests/config/nextflow.config
+  tags:
+    - meryl
+    - meryl/unionsum
+  files:
+    - path: output/meryl/versions.yml
+      md5sum: 7de859c6d3a29d72f6c9c976609d0913
+
+- name: meryl unionsum test_meryl_unionsum_paired_end
+  command: nextflow run tests/modules/meryl/unionsum -entry test_meryl_unionsum_paired_end -c tests/config/nextflow.config
+  tags:
+    - meryl
+    - meryl/unionsum
+  files:
+    - path: output/meryl/versions.yml
+      md5sum: a16decdec014ccb9bdab69a4a1d30818

tests/modules/rtgtools/vcfeval/main.nf

@@ -0,0 +1,69 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { RTGTOOLS_VCFEVAL } from '../../../../modules/rtgtools/vcfeval/main.nf'
+include { UNTAR } from '../../../modules/untar/main.nf'
+
+workflow test_rtgtools_vcfeval {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_vcf_gz'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_vcf_gz_tbi'], checkIfExists: true),        
+    ]
+
+    truth = [
+        file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_ann_vcf_gz'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_ann_vcf_gz_tbi'], checkIfExists: true)
+    ]
+
+    truth_regions = file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
+
+    evaluation_regions = file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)
+
+    compressed_sdf = [
+        [],
+        file(params.test_data['homo_sapiens']['genome']['genome_21_sdf'])
+    ]
+
+    sdf = UNTAR( compressed_sdf ).untar
+        .map({
+            meta, folder ->
+                folder
+        })
+    
+
+    RTGTOOLS_VCFEVAL ( input, truth, truth_regions, evaluation_regions, sdf )
+}
+
+workflow test_rtgtools_vcfeval_no_optional_inputs {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_vcf_gz'], checkIfExists: true),
+        [],
+    ]
+
+    truth = [
+        file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_ann_vcf_gz'], checkIfExists: true),
+        []
+    ]
+
+    truth_regions = []
+
+    evaluation_regions = []
+
+    compressed_sdf = [
+        [],
+        file(params.test_data['homo_sapiens']['genome']['genome_21_sdf'])
+    ]
+
+    sdf = UNTAR( compressed_sdf ).untar
+        .map({
+            meta, folder ->
+                [folder]
+        })
+
+    RTGTOOLS_VCFEVAL ( input, truth, truth_regions, evaluation_regions, sdf )
+}

tests/modules/rtgtools/vcfeval/nextflow.config

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

tests/modules/rtgtools/vcfeval/test.yml

@@ -0,0 +1,75 @@
+- name: rtgtools vcfeval test_rtgtools_vcfeval
+  command: nextflow run tests/modules/rtgtools/vcfeval -entry test_rtgtools_vcfeval -c tests/config/nextflow.config
+  tags:
+    - rtgtools
+    - rtgtools/vcfeval
+  files:
+    - path: output/rtgtools/test_results/done
+    - path: output/rtgtools/test_results/fn.vcf.gz
+      md5sum: be9c9106055bfad4c5985bc0d33efd56
+    - path: output/rtgtools/test_results/fn.vcf.gz.tbi
+      md5sum: 092a7a3162e7cff25d273525751eb284
+    - path: output/rtgtools/test_results/fp.vcf.gz
+      md5sum: e0f0ff841dc63e9fb61fd3a5db137ced
+    - path: output/rtgtools/test_results/fp.vcf.gz.tbi
+      md5sum: 092a7a3162e7cff25d273525751eb284
+    - path: output/rtgtools/test_results/non_snp_roc.tsv.gz
+      md5sum: ad5bad32c48f05aef232e2c0e708877a
+    - path: output/rtgtools/test_results/phasing.txt
+      md5sum: 133677dbd8be657439ea2b03fdfb8795
+    - path: output/rtgtools/test_results/progress
+    - path: output/rtgtools/test_results/snp_roc.tsv.gz
+      md5sum: 6785b83d66486e7e6c75c5a5b1574c09
+    - path: output/rtgtools/test_results/summary.txt
+      md5sum: f4c8df93c8bdab603036bbc27b4a28c3
+    - path: output/rtgtools/test_results/tp-baseline.vcf.gz
+      md5sum: be9c9106055bfad4c5985bc0d33efd56
+    - path: output/rtgtools/test_results/tp-baseline.vcf.gz.tbi
+      md5sum: 092a7a3162e7cff25d273525751eb284
+    - path: output/rtgtools/test_results/tp.vcf.gz
+      md5sum: e0f0ff841dc63e9fb61fd3a5db137ced
+    - path: output/rtgtools/test_results/tp.vcf.gz.tbi
+      md5sum: 092a7a3162e7cff25d273525751eb284
+    - path: output/rtgtools/test_results/vcfeval.log
+    - path: output/rtgtools/test_results/weighted_roc.tsv.gz
+      md5sum: fa7c046ea0084172f1ef91f19de07b2b
+    - path: output/rtgtools/versions.yml
+      md5sum: 270ed7a5a8e347b251eb4aa2198f98e8
+
+- name: rtgtools vcfeval test_rtgtools_vcfeval_no_optional_inputs
+  command: nextflow run tests/modules/rtgtools/vcfeval -entry test_rtgtools_vcfeval_no_optional_inputs -c tests/config/nextflow.config
+  tags:
+    - rtgtools
+    - rtgtools/vcfeval
+  files:
+    - path: output/rtgtools/test_results/done
+    - path: output/rtgtools/test_results/fn.vcf.gz
+      md5sum: c11c889a4f42c8ea325748bd768ea34d
+    - path: output/rtgtools/test_results/fn.vcf.gz.tbi
+      md5sum: 092a7a3162e7cff25d273525751eb284
+    - path: output/rtgtools/test_results/fp.vcf.gz
+      md5sum: 138e85c1cd79f8fea9a33e81ce0c734c
+    - path: output/rtgtools/test_results/fp.vcf.gz.tbi
+      md5sum: 092a7a3162e7cff25d273525751eb284
+    - path: output/rtgtools/test_results/non_snp_roc.tsv.gz
+      md5sum: 34fb78a008dfc0bef02807b8a7012b07
+    - path: output/rtgtools/test_results/phasing.txt
+      md5sum: 133677dbd8be657439ea2b03fdfb8795
+    - path: output/rtgtools/test_results/progress
+    - path: output/rtgtools/test_results/snp_roc.tsv.gz
+      md5sum: a4c5761c2653e2d04fc84c1cea13b1f0
+    - path: output/rtgtools/test_results/summary.txt
+      md5sum: f33feb32f84958fb931063044fba369b
+    - path: output/rtgtools/test_results/tp-baseline.vcf.gz
+      md5sum: d1c2d990899edf127ea5fcca8866fcb0
+    - path: output/rtgtools/test_results/tp-baseline.vcf.gz.tbi
+      md5sum: 3307008fea47adb75c46d395c5567bc0
+    - path: output/rtgtools/test_results/tp.vcf.gz
+      md5sum: e35b4dab82894eee9b77c81f9bc89cca
+    - path: output/rtgtools/test_results/tp.vcf.gz.tbi
+      md5sum: 45d8f8793140944f129e728299918c88
+    - path: output/rtgtools/test_results/vcfeval.log
+    - path: output/rtgtools/test_results/weighted_roc.tsv.gz
+      md5sum: 5b8efc9e9381f604880412800f58e4e9
+    - path: output/rtgtools/versions.yml
+      md5sum: 55568e4bbe5ab7e634a1f392abb89cc4

tests/modules/samtools/bamtocram/main.nf

@@ -1,17 +0,0 @@
-#!/usr/bin/env nextflow
-
-nextflow.enable.dsl = 2
-
-include { SAMTOOLS_BAMTOCRAM } from '../../../../modules/samtools/bamtocram/main.nf'
-
-workflow test_samtools_bamtocram {
-
-    input = [ [ id:'test', single_end:false ], // meta map
-                file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
-                file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)]
-
-    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
-    fai   = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
-
-    SAMTOOLS_BAMTOCRAM ( input, fasta, fai )
-}

tests/modules/samtools/bamtocram/test.yml

@@ -1,9 +0,0 @@
-- name: samtools bamtocram test_samtools_bamtocram
-  command: nextflow run ./tests/modules/samtools/bamtocram -entry test_samtools_bamtocram -c ./tests/config/nextflow.config -c ./tests/modules/samtools/bamtocram/nextflow.config
-  tags:
-    - samtools/bamtocram
-    - samtools
-  files:
-    - path: output/samtools/test.cram
-    - path: output/samtools/test.cram.crai
-    - path: output/samtools/versions.yml

tests/modules/samtools/convert/main.nf

@@ -0,0 +1,31 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SAMTOOLS_CONVERT as SAMTOOLS_BAMTOCRAM } from '../../../../modules/samtools/convert/main.nf'
+include { SAMTOOLS_CONVERT as SAMTOOLS_CRAMTOBAM } from '../../../../modules/samtools/convert/main.nf'
+
+workflow test_samtools_convert_bamtocram {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+                file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)]
+
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    fai   = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
+
+    SAMTOOLS_BAMTOCRAM ( input, fasta, fai )
+}
+
+workflow test_samtools_convert_cramtobam {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+                file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram'], checkIfExists: true),
+                file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram_crai'], checkIfExists: true)
+            ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fai   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+
+    SAMTOOLS_CRAMTOBAM ( input, fasta, fai )
+}

tests/modules/samtools/convert/nextflow.config

@@ -0,0 +1,12 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName:SAMTOOLS_BAMTOCRAM{
+        ext.args = "-C"
+    }
+
+    withName:SAMTOOLS_CRAMTOBAM{
+        ext.args = "-b"
+    }
+}

tests/modules/samtools/convert/test.yml

@@ -0,0 +1,21 @@
+- name: samtools convert test_samtools_convert_bamtocram
+  command: nextflow run tests/modules/samtools/convert -entry test_samtools_convert_bamtocram -c tests/config/nextflow.config
+  tags:
+    - samtools
+    - samtools/convert
+  files:
+    - path: output/samtools/test.cram
+    - path: output/samtools/test.cram.crai
+    - path: output/samtools/versions.yml
+
+- name: samtools convert test_samtools_convert_cramtobam
+  command: nextflow run tests/modules/samtools/convert -entry test_samtools_convert_cramtobam -c tests/config/nextflow.config
+  tags:
+    - samtools
+    - samtools/convert
+  files:
+    - path: output/samtools/test.bam
+      md5sum: c262b6dc15f9b480bdb47d6d018b4b56
+    - path: output/samtools/test.bam.bai
+      md5sum: 6e8f5034f728401bfa841c8e70c62463
+    - path: output/samtools/versions.yml

tests/modules/samtools/view/main.nf

@@ -25,7 +25,7 @@ workflow test_samtools_view_cram {
 
 workflow test_samtools_view_stubs {
     input = [ [ id:'test', single_end:false ], // meta map
-                "foo_paired_end.bam",
+                file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true),
                 []
             ]
 

tests/modules/samtools/view/test.yml

@@ -16,7 +16,7 @@
     - path: output/samtools/test.cram
 
 - name: samtools view test_samtools_view_stubs
-  command: nextflow run ./tests/modules/samtools/view -entry test_samtools_view -c ./tests/config/nextflow.config -c ./tests/modules/samtools/view/nextflow.config -stub-run
+  command: nextflow run ./tests/modules/samtools/view -entry test_samtools_view_stubs -c ./tests/config/nextflow.config -c ./tests/modules/samtools/view/nextflow.config -stub-run
   tags:
     - samtools/view
     - samtools

tests/modules/sratools/fasterqdump/main.nf

@@ -13,7 +13,7 @@ workflow test_sratools_fasterqdump_single_end {
     def input = Channel.of([ id:'test_single_end', single_end:true ])
         .combine(UNTAR.out.untar.map{ it[1] })
 
-    SRATOOLS_FASTERQDUMP ( input )
+    SRATOOLS_FASTERQDUMP(input, file(params.test_data['generic']['config']['ncbi_user_settings'], checkIfExists: true))
 }
 
 workflow test_sratools_fasterqdump_paired_end {
@@ -24,5 +24,5 @@ workflow test_sratools_fasterqdump_paired_end {
     def input = Channel.of([ id:'test_paired_end', single_end:false ])
         .combine(UNTAR.out.untar.map{ it[1] })
 
-    SRATOOLS_FASTERQDUMP ( input )
+    SRATOOLS_FASTERQDUMP(input, file(params.test_data['generic']['config']['ncbi_user_settings'], checkIfExists: true))
 }

tests/modules/sratools/fasterqdump/test.yml

@@ -8,6 +8,9 @@
       md5sum: 1054c7b71884acdb5eed8a378f18be82
     - path: output/untar/SRR13255544/SRR13255544.sra
       md5sum: 466d05dafb2eec672150754168010b4d
+    - path: output/sratools/versions.yml
+      contains:
+        - "sratools: 2.11.0"
 
 - name: sratools fasterqdump test_sratools_fasterqdump_paired_end
   command: nextflow run ./tests/modules/sratools/fasterqdump -entry test_sratools_fasterqdump_paired_end -c ./tests/config/nextflow.config -c ./tests/modules/sratools/fasterqdump/nextflow.config
@@ -21,3 +24,6 @@
       md5sum: 3e3b3af3413f50a1685fd7b3f1456d4e
     - path: output/untar/SRR11140744/SRR11140744.sra
       md5sum: 065666caf5b2d5dfb0cb25d5f3abe659
+    - path: output/sratools/versions.yml
+      contains:
+        - "sratools: 2.11.0"

tests/modules/sratools/prefetch/main.nf

@@ -8,8 +8,8 @@ workflow test_sratools_prefetch {
 
     input = [
         [ id:'test', single_end:false ], // meta map
-        'ERR2815334'
+        'DRR000774'
     ]
 
-    SRATOOLS_PREFETCH ( input )
+    SRATOOLS_PREFETCH(input, file(params.test_data['generic']['config']['ncbi_user_settings'], checkIfExists: true))
 }

tests/modules/sratools/prefetch/test.yml

@@ -4,5 +4,8 @@
     - sratools/prefetch
     - sratools
   files:
-    - path: output/sratools/ERR2815334/ERR2815334.sra
-      md5sum: 9a98c7f6f4774b7ef94aa915b92a54ea
+    - path: output/sratools/DRR000774/DRR000774.sra
+      md5sum: 7647dba20c89c0e3d7ad13842f060eb0
+    - path: output/sratools/versions.yml
+      contains:
+        - "sratools: 2.11.0"

tests/subworkflows/nf-core/sra_fastq/main.nf

@@ -1,23 +0,0 @@
-#!/usr/bin/env nextflow
-
-nextflow.enable.dsl = 2
-
-include { SRA_FASTQ } from '../../../../subworkflows/nf-core/sra_fastq/main.nf' addParams( [:] )
-
-workflow test_sra_fastq_single_end {
-    input = [
-        [ id:'test_single_end', single_end:true ], // meta map
-        'SRR13255544'
-    ]
-
-    SRA_FASTQ ( input )
-}
-
-workflow test_sra_fastq_paired_end {
-    input = [
-        [ id:'test_paired_end', single_end:false ], // meta map
-        'SRR11140744'
-    ]
-
-    SRA_FASTQ ( input )
-}

tests/subworkflows/nf-core/sra_fastq/test.yml

@@ -1,27 +0,0 @@
-- name: sra fastq single-end
-  command: nextflow run ./tests/subworkflows/nf-core/sra_fastq -entry test_sra_fastq_single_end -c tests/config/nextflow.config
-  tags:
-    - subworkflows
-    # - subworkflows/sra_fastq
-    # Modules
-    # - sratools
-    # - sratools/prefetch
-    # - sratools/fasterqdump
-  files:
-    - path: output/sratools/SRR13255544.fastq.gz
-      md5sum: 1054c7b71884acdb5eed8a378f18be82
-
-- name: sra fastq paired-end
-  command: nextflow run ./tests/subworkflows/nf-core/sra_fastq -entry test_sra_fastq_paired_end -c tests/config/nextflow.config
-  tags:
-    - subworkflows
-    # - subworkflows/sra_fastq
-    # Modules
-    # - sratools
-    # - sratools/prefetch
-    # - sratools/fasterqdump
-  files:
-    - path: output/sratools/SRR11140744_1.fastq.gz
-      md5sum: 193809c784a4ea132ab2a253fa4f55b6
-    - path: output/sratools/SRR11140744_2.fastq.gz
-      md5sum: 3e3b3af3413f50a1685fd7b3f1456d4e

tests/subworkflows/nf-core/srafastq/main.nf

@@ -0,0 +1,29 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SRAFASTQ } from '../../../../subworkflows/nf-core/srafastq/main.nf'
+
+workflow test_srafastq_single_end {
+    input = Channel.of(
+        [
+            [ id:'test_single_end1', single_end:true ], // meta map
+            'DRR000774'
+        ],
+        [
+            [ id:'test_single_end2', single_end:true ], // meta map
+            'DRR000775'
+        ]
+    )
+
+    SRAFASTQ ( input )
+}
+
+workflow test_srafastq_paired_end {
+    input = [
+        [ id:'test_paired_end', single_end:false ], // meta map
+        'SRR11140744'
+    ]
+
+    SRAFASTQ ( input )
+}

tests/subworkflows/nf-core/srafastq/test.yml

@@ -0,0 +1,29 @@
+- name: srafastq single-end
+  command: nextflow run ./tests/subworkflows/nf-core/srafastq -entry test_srafastq_single_end -c tests/config/nextflow.config -c tests/subworkflows/nf-core/srafastq/nextflow.config
+  tags:
+    - subworkflows
+    # - subworkflows/srafastq
+    # Modules
+    # - sratools
+    # - sratools/prefetch
+    # - sratools/fasterqdump
+  files:
+    - path: output/sratools/DRR000774.fastq.gz
+      md5sum: 19029a1132115b55277a0d79ee089b49
+    - path: output/sratools/DRR000775.fastq.gz
+      md5sum: 59ff24c86ecb260752668c059c2a1eaf
+
+- name: srafastq paired-end
+  command: nextflow run ./tests/subworkflows/nf-core/srafastq -entry test_srafastq_paired_end -c tests/config/nextflow.config -c tests/subworkflows/nf-core/srafastq/nextflow.config
+  tags:
+    - subworkflows
+    # - subworkflows/srafastq
+    # Modules
+    # - sratools
+    # - sratools/prefetch
+    # - sratools/fasterqdump
+  files:
+    - path: output/sratools/SRR11140744_1.fastq.gz
+      md5sum: 193809c784a4ea132ab2a253fa4f55b6
+    - path: output/sratools/SRR11140744_2.fastq.gz
+      md5sum: 3e3b3af3413f50a1685fd7b3f1456d4e