Merge remote-tracking branch 'nf-core/master'

modules/assemblyscan/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/assemblyscan/main.nf

@@ -0,0 +1,38 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process ASSEMBLYSCAN {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::assembly-scan=0.4.1" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/assembly-scan:0.4.1--pyhdfd78af_0"
+    } else {
+        container "quay.io/biocontainers/assembly-scan:0.4.1--pyhdfd78af_0"
+    }
+
+    input:
+    tuple val(meta), path(assembly)
+
+    output:
+    tuple val(meta), path("*.json"), emit: json
+    path "versions.yml"            , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    assembly-scan $assembly > ${prefix}.json
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( assembly-scan --version 2>&1 | sed 's/^.*assembly-scan //; s/Using.*\$//' )
+    END_VERSIONS
+    """
+}

modules/assemblyscan/meta.yml

@@ -0,0 +1,43 @@
+name: assemblyscan
+description: Assembly summary statistics in JSON format
+keywords:
+  - assembly
+  - statistics
+tools:
+  - assemblyscan:
+      description: Assembly summary statistics in JSON format
+      homepage: https://github.com/rpetit3/assembly-scan
+      documentation: https://github.com/rpetit3/assembly-scan
+      tool_dev_url: https://github.com/rpetit3/assembly-scan
+      doi: ""
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - assembly:
+      type: file
+      description: FASTA file for a given assembly
+      pattern: "*.fasta"
+
+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"
+  - json:
+      type: file
+      description: Assembly statistics in JSON format
+      pattern: "*.json"
+
+authors:
+  - "@sateeshperi"
+  - "@mjcipriano"

modules/bedtools/genomecov/main.nf

@@ -19,7 +19,7 @@ process BEDTOOLS_GENOMECOV {
     }
 
     input:
-    tuple val(meta), path(intervals)
+    tuple val(meta), path(intervals), val(scale)
     path  sizes
     val   extension
 
@@ -28,13 +28,21 @@ process BEDTOOLS_GENOMECOV {
     path  "versions.yml"                   , emit: versions
 
     script:
-    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def prefix     = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def args_token = options.args.tokenize()
+    def args       = options.args
+    args += (scale > 0 && scale != 1) ? " -scale $scale" : ""
+
+    if (!args_token.contains('-bg') && (scale > 0 && scale != 1)) {
+        args += " -bg"
+    }
+
     if (intervals.name =~ /\.bam/) {
         """
         bedtools \\
             genomecov \\
             -ibam $intervals \\
-            $options.args \\
+            $args \\
             > ${prefix}.${extension}
 
         cat <<-END_VERSIONS > versions.yml
@@ -48,7 +56,7 @@ process BEDTOOLS_GENOMECOV {
             genomecov \\
             -i $intervals \\
             -g $sizes \\
-            $options.args \\
+            $args \\
             > ${prefix}.${extension}
 
         cat <<-END_VERSIONS > versions.yml

modules/bedtools/genomecov/meta.yml

@@ -20,6 +20,9 @@ input:
         type: file
         description: BAM/BED/GFF/VCF
         pattern: "*.{bam|bed|gff|vcf}"
+    - scale:
+        type: value
+        description: Number containing the scale factor for the output. Set to 1 to disable. Setting to a value other than 1 will also get the -bg bedgraph output format as this is required for this command switch
     - sizes:
         type: file
         description: Tab-delimited table of chromosome names in the first column and chromosome sizes in the second column
@@ -45,3 +48,4 @@ authors:
     - "@sruthipsuresh"
     - "@drpatelh"
     - "@sidorov-si"
+    - "@chris-cheshire"

modules/cellranger/Dockerfile

@@ -0,0 +1,21 @@
+FROM continuumio/miniconda3:4.8.2
+LABEL authors="Gisela Gabernet <gisela.gabernet@gmail.com>" \
+    description="Docker image containing Cell Ranger"
+# Disclaimer: this container is not provided nor supported by 10x Genomics.
+
+# Install procps and clean apt cache
+RUN apt-get update \
+    && apt-get install -y procps \
+    && apt-get clean -y && rm -rf /var/lib/apt/lists/*
+
+# Copy pre-downloaded cellranger file
+ENV CELLRANGER_VER 6.0.2
+COPY cellranger-$CELLRANGER_VER.tar.gz /opt/cellranger-$CELLRANGER_VER.tar.gz
+
+# Install cellranger
+RUN \
+    cd /opt && \
+    tar -xzvf cellranger-$CELLRANGER_VER.tar.gz && \
+    export PATH=/opt/cellranger-$CELLRANGER_VER:$PATH && \
+    ln -s /opt/cellranger-$CELLRANGER_VER/cellranger /usr/bin/cellranger && \
+    rm -rf /opt/cellranger-$CELLRANGER_VER.tar.gz

modules/cellranger/mkref/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/cellranger/mkref/main.nf

@@ -0,0 +1,40 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process CELLRANGER_MKREF {
+    tag 'mkref'
+    label 'process_high'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) }
+
+    if (params.enable_conda) {
+        exit 1, "Conda environments cannot be used when using the Cell Ranger tool. Please use docker or singularity containers."
+    }
+    container "nfcore/cellranger:6.0.2"
+
+    input:
+    path fasta
+    path gtf
+    val(reference_name)
+
+    output:
+    path "versions.yml"     , emit: versions
+    path "${reference_name}", emit: reference
+
+    script:
+    """
+    cellranger mkref \\
+        --genome=${reference_name} \\
+        --fasta=${fasta} \\
+        --genes=${gtf}
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$(echo \$( cellranger --version 2>&1) | sed 's/^.*[^0-9]\\([0-9]*\\.[0-9]*\\.[0-9]*\\).*\$/\\1/' )
+    END_VERSIONS
+    """
+}

modules/cellranger/mkref/meta.yml

@@ -0,0 +1,39 @@
+name: cellranger_mkref
+description: Module to build the reference needed by the 10x Genomics Cell Ranger tool. Uses the cellranger mkref command.
+keywords:
+  - reference
+  - mkref
+  - index
+tools:
+  - cellranger:
+      description: Cell Ranger by 10x Genomics is a set of analysis pipelines that process Chromium single-cell data to align reads, generate feature-barcode matrices, perform clustering and other secondary analysis, and more.
+      homepage: https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/what-is-cell-ranger
+      documentation: https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/tutorial_ov
+      tool_dev_url: https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/tutorial_ov
+      doi: ""
+      licence: 10x Genomics EULA
+
+input:
+  - fasta:
+      type: file
+      description: fasta genome file
+      pattern: "*.{fasta,fa}"
+  - gtf:
+      type: file
+      description: gtf transcriptome file
+      pattern: "*.gtf"
+  - reference_name:
+      type: val
+      description: name to give the reference folder
+      pattern: str
+
+output:
+  - versions:
+      type: file
+      description: File containing software version
+      pattern: "versions.yml"
+  - reference:
+      type: folder
+      description: Folder containing all the reference indices needed by Cell Ranger
+authors:
+  - "@ggabernet"

modules/cellranger/readme.md

@@ -0,0 +1,18 @@
+# Updating the docker container and making a new module release
+
+Cell Ranger is a commercial tool by 10X Genomics. The container provided for the cellranger nf-core module is not provided nor supported by 10x Genomics. Updating the Cell Ranger version in the container and pushing the update to Dockerhub needs to be done manually.
+
+1. Navigate to the [Cell Ranger download page](https://support.10xgenomics.com/single-cell-gene-expression/software/downloads/latest) and download the tar ball of the desired Cell Ranger version with `curl` or `wget`. Place this file in the same folder where the Dockerfile lies.
+
+2. Edit the Dockerfile: update the Cell Ranger version in this line:
+
+    ```bash
+    ENV CELLRANGER_VER <VERSION>
+    ```
+
+3. Create the container:
+
+    ```bash
+    docker build . -t nfcore/cellranger:<VERSION>
+    docker push nfcore/cellranger:<VERSION>
+    ```

modules/dedup/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/dedup/main.nf

@@ -0,0 +1,47 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process DEDUP {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::dedup=0.12.8" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/dedup:0.12.8--hdfd78af_1"
+    } else {
+        container "quay.io/biocontainers/dedup:0.12.8--hdfd78af_1"
+    }
+
+    input:
+    tuple val(meta), path(bam)
+
+    output:
+    tuple val(meta), path("*_rmdup.bam"), emit: bam     // _rmdup is hardcoded output from dedup
+    tuple val(meta), path("*.json")     , emit: json
+    tuple val(meta), path("*.hist")     , emit: hist
+    tuple val(meta), path("*log")       , emit: log
+    path "versions.yml"                 , emit: versions
+
+    script:
+    prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+
+    """
+    dedup \\
+        -Xmx${task.memory.toGiga()}g  \\
+        -i $bam \\
+        -o . \\
+        $options.args
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( echo \$(dedup --version 2>&1) | tail -n 1 | sed 's/.* v//')
+
+    END_VERSIONS
+    """
+}

modules/dedup/meta.yml

@@ -0,0 +1,60 @@
+name: dedup
+description: DeDup is a tool for read deduplication in paired-end read merging (e.g. for ancient DNA experiments).
+keywords:
+  - dedup
+  - deduplication
+  - pcr duplicates
+  - ancient DNA
+  - paired-end
+  - bam
+tools:
+  - dedup:
+      description: DeDup is a tool for read deduplication in paired-end read merging (e.g. for ancient DNA experiments).
+      homepage: https://github.com/apeltzer/DeDup
+      documentation: https://dedup.readthedocs.io/en/latest/
+      tool_dev_url: https://github.com/apeltzer/DeDup
+      doi: "10.1186/s13059-016-0918-z"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: BAM/SAM file
+      pattern: "*.{bam,sam}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - bam:
+      type: file
+      description: Deduplicated BAM file
+      pattern: "*_rmdup.bam"
+  - json:
+      type: file
+      description: JSON file for MultiQC
+      pattern: "*.json"
+  - hist:
+      type: file
+      description: Histogram data of amount of deduplication
+      pattern: "*.hist"
+  - log:
+      type: file
+      description: Dedup log information
+      pattern: "*log"
+
+
+
+authors:
+  - "@jfy133"

modules/fgbio/fastqtobam/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/fgbio/fastqtobam/main.nf

@@ -0,0 +1,51 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process FGBIO_FASTQTOBAM {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::fgbio=1.4.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/fgbio:1.4.0--hdfd78af_0"
+    } else {
+        container "quay.io/biocontainers/fgbio:1.4.0--hdfd78af_0"
+    }
+
+    input:
+    tuple val(meta), path(reads)
+    val(read_structure)
+
+    output:
+    tuple val(meta), path("*_umi_converted.bam"), emit: umibam
+    path "versions.yml"                         , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+
+    """
+    mkdir tmpFolder
+
+    fgbio \\
+        --tmp-dir=${PWD}/tmpFolder \\
+        FastqToBam \\
+        -i $reads \\
+        -o "${prefix}_umi_converted.bam" \\
+        --read-structures $read_structure \\
+        --sample $meta.id \\
+        --library $meta.id \\
+        $options.args
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( echo \$(fgbio --version 2>&1 | tr -d '[:cntrl:]' ) | sed -e 's/^.*Version: //;s/\\[.*\$//')
+    END_VERSIONS
+    """
+}

modules/fgbio/fastqtobam/meta.yml

@@ -0,0 +1,47 @@
+name: fgbio_fastqtobam
+description: |
+      Using the FGBIO tools, converts FASTQ files sequenced with UMIs into BAM files, moving the UMI barcode into the RX field of the BAM file
+keywords:
+  - fastqtobam
+  - fgbio
+tools:
+  - fgbio:
+      description: A set of tools for working with genomic and high throughput sequencing data, including UMIs
+      homepage: http://fulcrumgenomics.github.io/fgbio/
+      documentation: http://fulcrumgenomics.github.io/fgbio/tools/latest/
+      tool_dev_url: https://github.com/fulcrumgenomics/fgbio
+      doi: ""
+      licence: ['MIT']
+
+input:
+  - reads:
+      type: file
+      description: pair of reads to be converted into BAM file
+      pattern: "*.{fastq.gz}"
+
+  - read_structure:
+      type: string
+      description: |
+                  A read structure should always be provided for each of the fastq files.
+                  If single end, the string will contain only one structure (i.e. "2M11S+T"), if paired-end the string
+                  will contain two structures separated by a blank space (i.e. "2M11S+T 2M11S+T").
+                  If the read does not contain any UMI, the structure will be +T (i.e. only template of any length).
+                  https://github.com/fulcrumgenomics/fgbio/wiki/Read-Structures
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.yml}"
+  - umibam:
+      type: file
+      description: Converted, unsorted BAM file with RX tag reporting UMI sequence (if any)
+      pattern: "*.{bam}"
+
+authors:
+  - "@lescai"

modules/filtlong/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/filtlong/main.nf

@@ -0,0 +1,43 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process FILTLONG {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::filtlong=0.2.1" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/filtlong:0.2.1--h9a82719_0"
+    } else {
+        container "quay.io/biocontainers/filtlong:0.2.1--h9a82719_0"
+    }
+
+    input:
+    tuple val(meta), path(shortreads), path(longreads)
+
+    output:
+    tuple val(meta), path("${meta.id}_lr_filtlong.fastq.gz"), emit: reads
+    path "versions.yml"                                     , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def short_reads = meta.single_end ? "-1 $shortreads" : "-1 ${shortreads[0]} -2 ${shortreads[1]}"
+    """
+    filtlong \\
+        $short_reads \\
+        $options.args \\
+        $longreads \\
+        | gzip -n > ${prefix}_lr_filtlong.fastq.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( filtlong --version | sed -e "s/Filtlong v//g" )
+    END_VERSIONS
+    """
+}

modules/filtlong/meta.yml

@@ -0,0 +1,50 @@
+name: filtlong
+description: Filtlong filters long reads based on quality measures or short read data.
+keywords:
+  - nanopore
+  - quality control
+  - QC
+  - filtering
+  - long reads
+  - short reads
+tools:
+  - filtlong:
+      description: Filtlong is a tool for filtering long reads. It can take a set of long reads and produce a smaller, better subset. It uses both read length (longer is better) and read identity (higher is better) when choosing which reads pass the filter.
+      homepage: https://anaconda.org/bioconda/filtlong
+      documentation: None
+      tool_dev_url: https://github.com/rrwick/Filtlong
+      doi: ""
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - shortreads:
+      type: file
+      description: fastq file
+      pattern: "*.{fq,fastq,fq.gz,fastq.gz}"
+  - longreads:
+      type: file
+      description: fastq file
+      pattern: "*.{fq,fastq,fq.gz,fastq.gz}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - reads:
+      type: file
+      description: Filtered (compressed) fastq file
+      pattern: "*.fastq.gz"
+
+authors:
+  - "@d4straub"

modules/gatk4/estimatelibrarycomplexity/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/gatk4/estimatelibrarycomplexity/main.nf

@@ -0,0 +1,54 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process GATK4_ESTIMATELIBRARYCOMPLEXITY {
+    tag "$meta.id"
+    label 'process_medium'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.2.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/gatk4:4.2.2.0--hdfd78af_1"
+    } else {
+        container "quay.io/biocontainers/gatk4:4.2.2.0--hdfd78af_1"
+    }
+
+    input:
+    tuple val(meta), path(cram)
+    path(fasta)
+    path(fai)
+    path(dict)
+
+    output:
+    tuple val(meta), path('*.metrics'), emit: metrics
+    path "versions.yml"                  , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def crams = cram.collect(){ x -> "-I ".concat(x.toString()) }.join(" ")
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[GATK EstimateLibraryComplexity] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+    """
+    gatk EstimateLibraryComplexity \
+        ${crams} \
+        -O ${prefix}.metrics \
+        --REFERENCE_SEQUENCE ${fasta} \
+        --VALIDATION_STRINGENCY SILENT \
+        --TMP_DIR . $options.args
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/gatk4/estimatelibrarycomplexity/meta.yml

@@ -0,0 +1,56 @@
+name: gatk4_estimatelibrarycomplexity
+description: Estimates the numbers of unique molecules in a sequencing library.
+keywords:
+  - gatk4
+  - gatk4_estimatelibrarycomplexity
+  - duplication_metrics
+  - reporting
+tools:
+  - gatk4:
+      description: Genome Analysis Toolkit (GATK4)
+      homepage: https://gatk.broadinstitute.org/hc/en-us
+      documentation: https://gatk.broadinstitute.org/hc/en-us
+      tool_dev_url: https://github.com/broadinstitute/gatk
+      doi: "10.1158/1538-7445.AM2017-3590"
+      licence: ['Apache-2.0']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - cram:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - fasta:
+      type: file
+      description: The reference fasta file
+      pattern: "*.fasta"
+  - fai:
+      type: file
+      description: Index of reference fasta file
+      pattern: "fasta.fai"
+  - dict:
+      type: file
+      description: GATK sequence dictionary
+      pattern: "*.dict"
+
+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"
+  - metrics:
+      type: file
+      description: File containing metrics on the input files
+      pattern: "*.{metrics}"
+
+authors:
+  - "@FriederikeHanssen"

modules/manta/germline/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/manta/germline/main.nf

@@ -0,0 +1,68 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process MANTA_GERMLINE {
+    tag "$meta.id"
+    label 'process_high'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::manta=1.6.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/manta:1.6.0--h9ee0642_1"
+    } else {
+        container "quay.io/biocontainers/manta:1.6.0--h9ee0642_1"
+    }
+
+    input:
+    tuple val(meta), path(cram), path(crai)
+    path fasta
+    path fai
+    path target_bed
+    path target_bed_tbi
+
+    output:
+    tuple val(meta), path("*candidate_small_indels.vcf.gz")    , emit: candidate_small_indels_vcf
+    tuple val(meta), path("*candidate_small_indels.vcf.gz.tbi"), emit: candidate_small_indels_vcf_tbi
+    tuple val(meta), path("*candidate_sv.vcf.gz")              , emit: candidate_sv_vcf
+    tuple val(meta), path("*candidate_sv.vcf.gz.tbi")          , emit: candidate_sv_vcf_tbi
+    tuple val(meta), path("*diploid_sv.vcf.gz")                , emit: diploid_sv_vcf
+    tuple val(meta), path("*diploid_sv.vcf.gz.tbi")            , emit: diploid_sv_vcf_tbi
+    path "versions.yml"                                        , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def options_manta = target_bed ? "--exome --callRegions $target_bed" : ""
+    """
+    configManta.py \
+        --bam $cram \
+        --reference $fasta \
+        $options_manta \
+        --runDir manta
+
+    python manta/runWorkflow.py -m local -j $task.cpus
+
+    mv manta/results/variants/candidateSmallIndels.vcf.gz \
+        ${prefix}.candidate_small_indels.vcf.gz
+    mv manta/results/variants/candidateSmallIndels.vcf.gz.tbi \
+        ${prefix}.candidate_small_indels.vcf.gz.tbi
+    mv manta/results/variants/candidateSV.vcf.gz \
+        ${prefix}.candidate_sv.vcf.gz
+    mv manta/results/variants/candidateSV.vcf.gz.tbi \
+        ${prefix}.candidate_sv.vcf.gz.tbi
+    mv manta/results/variants/diploidSV.vcf.gz \
+        ${prefix}.diploid_sv.vcf.gz
+    mv manta/results/variants/diploidSV.vcf.gz.tbi \
+        ${prefix}.diploid_sv.vcf.gz.tbi
+
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( configManta.py --version )
+    END_VERSIONS
+    """
+}

modules/manta/germline/meta.yml

@@ -0,0 +1,87 @@
+name: manta_germline
+description: Manta calls structural variants (SVs) and indels from mapped paired-end sequencing reads. It is optimized for analysis of germline variation in small sets of individuals and somatic variation in tumor/normal sample pairs.
+keywords:
+  - somatic
+  - wgs
+  - wxs
+  - panel
+  - vcf
+  - structural variants
+  - small indels
+tools:
+  - manta:
+      description: Structural variant and indel caller for mapped sequencing data
+      homepage: https://github.com/Illumina/manta
+      documentation: https://github.com/Illumina/manta/blob/v1.6.0/docs/userGuide/README.md
+      tool_dev_url: https://github.com/Illumina/manta
+      doi: "10.1093/bioinformatics/btv710"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - cram:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - crai:
+      type: file
+      description: BAM/CRAM/SAM index file
+      pattern: "*.{bai,crai,sai}"
+  - fasta:
+      type: file
+      description: Genome reference FASTA file
+      pattern: "*.{fa,fasta}"
+  - fai:
+      type: file
+      description: Genome reference FASTA index file
+      pattern: "*.{fa.fai,fasta.fai}"
+  - target_bed:
+      type: file
+      description: BED file containing target regions for variant calling
+      pattern: "*.{bed}"
+  - target_bed_tbi:
+      type: file
+      description: Index for BED file containing target regions for variant calling
+      pattern: "*.{bed.tbi}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - candidate_small_indels_vcf:
+      type: file
+      description: Gzipped VCF file containing variants
+      pattern: "*.{vcf.gz}"
+  - candidate_small_indels_vcf_tbi:
+      type: file
+      description: Index for gzipped VCF file containing variants
+      pattern: "*.{vcf.gz.tbi}"
+  - candidate_sv_vcf:
+      type: file
+      description: Gzipped VCF file containing variants
+      pattern: "*.{vcf.gz}"
+  - candidate_sv_vcf_tbi:
+      type: file
+      description: Index for gzipped VCF file containing variants
+      pattern: "*.{vcf.gz.tbi}"
+  - diploid_sv_vcf:
+      type: file
+      description: Gzipped VCF file containing variants
+      pattern: "*.{vcf.gz}"
+  - diploid_sv_vcf_tbi:
+      type: file
+      description: Index for gzipped VCF file containing variants
+      pattern: "*.{vcf.gz.tbi}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@maxulysse"

modules/manta/somatic/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/manta/somatic/main.nf

@@ -0,0 +1,67 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process MANTA_SOMATIC {
+    tag "$meta.id"
+    label 'process_high'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::manta=1.6.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/manta:1.6.0--h9ee0642_1"
+    } else {
+        container "quay.io/biocontainers/manta:1.6.0--h9ee0642_1"
+    }
+
+    input:
+    tuple val(meta), path(cram_normal), path(crai_normal), path(cram_tumor), path(crai_tumor)
+    path fasta
+    path fai
+    path target_bed
+    path target_bed_tbi
+
+    output:
+    tuple val(meta), path("*.candidate_small_indels.vcf.gz")     , emit: candidate_small_indels_vcf
+    tuple val(meta), path("*.candidate_small_indels.vcf.gz.tbi") , emit: candidate_small_indels_vcf_tbi
+    tuple val(meta), path("*.candidate_sv.vcf.gz")               , emit: candidate_sv_vcf
+    tuple val(meta), path("*.candidate_sv.vcf.gz.tbi")           , emit: candidate_sv_vcf_tbi
+    tuple val(meta), path("*.diploid_sv.vcf.gz")                 , emit: diploid_sv_vcf
+    tuple val(meta), path("*.diploid_sv.vcf.gz.tbi")             , emit: diploid_sv_vcf_tbi
+    tuple val(meta), path("*.somatic_sv.vcf.gz")                 , emit: somatic_sv_vcf
+    tuple val(meta), path("*.somatic_sv.vcf.gz.tbi")             , emit: somatic_sv_vcf_tbi
+    path "versions.yml"                                          , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def options_manta = target_bed ? "--exome --callRegions $target_bed" : ""
+
+    """
+    configManta.py \
+        --tumorBam $cram_tumor \
+        --normalBam $cram_normal \
+        --reference $fasta \
+        $options_manta \
+        --runDir manta
+
+    python manta/runWorkflow.py -m local -j $task.cpus
+
+    mv manta/results/variants/candidateSmallIndels.vcf.gz     ${prefix}.candidate_small_indels.vcf.gz
+    mv manta/results/variants/candidateSmallIndels.vcf.gz.tbi ${prefix}.candidate_small_indels.vcf.gz.tbi
+    mv manta/results/variants/candidateSV.vcf.gz              ${prefix}.candidate_sv.vcf.gz
+    mv manta/results/variants/candidateSV.vcf.gz.tbi          ${prefix}.candidate_sv.vcf.gz.tbi
+    mv manta/results/variants/diploidSV.vcf.gz                ${prefix}.diploid_sv.vcf.gz
+    mv manta/results/variants/diploidSV.vcf.gz.tbi            ${prefix}.diploid_sv.vcf.gz.tbi
+    mv manta/results/variants/somaticSV.vcf.gz                ${prefix}.somatic_sv.vcf.gz
+    mv manta/results/variants/somaticSV.vcf.gz.tbi            ${prefix}.somatic_sv.vcf.gz.tbi
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( configManta.py --version )
+    END_VERSIONS
+    """
+}

modules/manta/somatic/meta.yml

@@ -0,0 +1,103 @@
+name: manta_somatic
+description: Manta calls structural variants (SVs) and indels from mapped paired-end sequencing reads. It is optimized for analysis of germline variation in small sets of individuals and somatic variation in tumor/normal sample pairs.
+keywords:
+  - somatic
+  - wgs
+  - wxs
+  - panel
+  - vcf
+  - structural variants
+  - small indels
+tools:
+  - manta:
+      description: Structural variant and indel caller for mapped sequencing data
+      homepage: https://github.com/Illumina/manta
+      documentation: https://github.com/Illumina/manta/blob/v1.6.0/docs/userGuide/README.md
+      tool_dev_url: https://github.com/Illumina/manta
+      doi: "10.1093/bioinformatics/btv710"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - cram_normal:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - crai_normal:
+      type: file
+      description: BAM/CRAM/SAM index file
+      pattern: "*.{bai,crai,sai}"
+  - cram_tumor:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - crai_tumor:
+      type: file
+      description: BAM/CRAM/SAM index file
+      pattern: "*.{bai,crai,sai}"
+  - fasta:
+      type: file
+      description: Genome reference FASTA file
+      pattern: "*.{fa,fasta}"
+  - fai:
+      type: file
+      description: Genome reference FASTA index file
+      pattern: "*.{fa.fai,fasta.fai}"
+  - target_bed:
+      type: file
+      description: BED file containing target regions for variant calling
+      pattern: "*.{bed}"
+  - target_bed_tbi:
+      type: file
+      description: Index for BED file containing target regions for variant calling
+      pattern: "*.{bed.tbi}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - candidate_small_indels_vcf:
+      type: file
+      description: Gzipped VCF file containing variants
+      pattern: "*.{vcf.gz}"
+  - candidate_small_indels_vcf_tbi:
+      type: file
+      description: Index for gzipped VCF file containing variants
+      pattern: "*.{vcf.gz.tbi}"
+  - candidate_sv_vcf:
+      type: file
+      description: Gzipped VCF file containing variants
+      pattern: "*.{vcf.gz}"
+  - candidate_sv_vcf_tbi:
+      type: file
+      description: Index for gzipped VCF file containing variants
+      pattern: "*.{vcf.gz.tbi}"
+  - diploid_sv_vcf:
+      type: file
+      description: Gzipped VCF file containing variants
+      pattern: "*.{vcf.gz}"
+  - diploid_sv_vcf_tbi:
+      type: file
+      description: Index for gzipped VCF file containing variants
+      pattern: "*.{vcf.gz.tbi}"
+  - somatic_sv_vcf:
+      type: file
+      description: Gzipped VCF file containing variants
+      pattern: "*.{vcf.gz}"
+  - somatic_sv_vcf_tbi:
+      type: file
+      description: Index for gzipped VCF file containing variants
+      pattern: "*.{vcf.gz.tbi}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@FriederikeHanssen"

modules/manta/tumoronly/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/manta/tumoronly/main.nf

@@ -0,0 +1,68 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process MANTA_TUMORONLY {
+    tag "$meta.id"
+    label 'process_high'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::manta=1.6.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/manta:1.6.0--h9ee0642_1"
+    } else {
+        container "quay.io/biocontainers/manta:1.6.0--h9ee0642_1"
+    }
+
+    input:
+    tuple val(meta), path(cram), path(crai)
+    path fasta
+    path fai
+    path target_bed
+    path target_bed_tbi
+
+    output:
+    tuple val(meta), path("*candidate_small_indels.vcf.gz")    , emit: candidate_small_indels_vcf
+    tuple val(meta), path("*candidate_small_indels.vcf.gz.tbi"), emit: candidate_small_indels_vcf_tbi
+    tuple val(meta), path("*candidate_sv.vcf.gz")              , emit: candidate_sv_vcf
+    tuple val(meta), path("*candidate_sv.vcf.gz.tbi")          , emit: candidate_sv_vcf_tbi
+    tuple val(meta), path("*tumor_sv.vcf.gz")                  , emit: tumor_sv_vcf
+    tuple val(meta), path("*tumor_sv.vcf.gz.tbi")              , emit: tumor_sv_vcf_tbi
+    path "versions.yml"                                        , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def options_manta = target_bed ? "--exome --callRegions $target_bed" : ""
+    """
+    configManta.py \
+        --tumorBam $cram \
+        --reference $fasta \
+        $options_manta \
+        --runDir manta
+
+    python manta/runWorkflow.py -m local -j $task.cpus
+
+    mv manta/results/variants/candidateSmallIndels.vcf.gz \
+        ${prefix}.candidate_small_indels.vcf.gz
+    mv manta/results/variants/candidateSmallIndels.vcf.gz.tbi \
+        ${prefix}.candidate_small_indels.vcf.gz.tbi
+    mv manta/results/variants/candidateSV.vcf.gz \
+        ${prefix}.candidate_sv.vcf.gz
+    mv manta/results/variants/candidateSV.vcf.gz.tbi \
+        ${prefix}.candidate_sv.vcf.gz.tbi
+    mv manta/results/variants/tumorSV.vcf.gz \
+        ${prefix}.tumor_sv.vcf.gz
+    mv manta/results/variants/tumorSV.vcf.gz.tbi \
+        ${prefix}.tumor_sv.vcf.gz.tbi
+
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( configManta.py --version )
+    END_VERSIONS
+    """
+}

modules/manta/tumoronly/meta.yml

@@ -0,0 +1,88 @@
+name: manta_tumoronly
+description: Manta calls structural variants (SVs) and indels from mapped paired-end sequencing reads. It is optimized for analysis of germline variation in small sets of individuals and somatic variation in tumor/normal sample pairs.
+keywords:
+  - somatic
+  - wgs
+  - wxs
+  - panel
+  - vcf
+  - structural variants
+  - small indels
+tools:
+  - manta:
+      description: Structural variant and indel caller for mapped sequencing data
+      homepage: https://github.com/Illumina/manta
+      documentation: https://github.com/Illumina/manta/blob/v1.6.0/docs/userGuide/README.md
+      tool_dev_url: https://github.com/Illumina/manta
+      doi: "10.1093/bioinformatics/btv710"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - cram:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - crai:
+      type: file
+      description: BAM/CRAM/SAM index file
+      pattern: "*.{bai,crai,sai}"
+  - fasta:
+      type: file
+      description: Genome reference FASTA file
+      pattern: "*.{fa,fasta}"
+  - fai:
+      type: file
+      description: Genome reference FASTA index file
+      pattern: "*.{fa.fai,fasta.fai}"
+  - target_bed:
+      type: file
+      description: BED file containing target regions for variant calling
+      pattern: "*.{bed}"
+  - target_bed_tbi:
+      type: file
+      description: Index for BED file containing target regions for variant calling
+      pattern: "*.{bed.tbi}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+
+  - candidate_small_indels_vcf:
+      type: file
+      description: Gzipped VCF file containing variants
+      pattern: "*.{vcf.gz}"
+  - candidate_small_indels_vcf_tbi:
+      type: file
+      description: Index for gzipped VCF file containing variants
+      pattern: "*.{vcf.gz.tbi}"
+  - candidate_sv_vcf:
+      type: file
+      description: Gzipped VCF file containing variants
+      pattern: "*.{vcf.gz}"
+  - candidate_sv_vcf_tbi:
+      type: file
+      description: Index for gzipped VCF file containing variants
+      pattern: "*.{vcf.gz.tbi}"
+  - tumor_sv_vcf:
+      type: file
+      description: Gzipped VCF file containing variants
+      pattern: "*.{vcf.gz}"
+  - tumor_sv_vcf_tbi:
+      type: file
+      description: Index for gzipped VCF file containing variants
+      pattern: "*.{vcf.gz.tbi}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@maxulysse"

modules/paraclu/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/paraclu/main.nf

@@ -0,0 +1,45 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process PARACLU {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::paraclu=10" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/paraclu%3A10--h9a82719_1"
+    } else {
+        container "quay.io/biocontainers/paraclu:10--h9a82719_1"
+    }
+
+    input:
+    tuple val(meta), path(bed)
+    val(min_cluster)
+
+    output:
+    tuple val(meta), path("*.bed"), emit: bed
+    path "versions.yml"           , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def VERSION=10
+    """
+
+    awk -F "\t" '{print\$1"\t"\$6"\t"\$2"\t"\$5}' < $bed > ${bed}_4P
+    sort -k1,1 -k3n ${bed}_4P > ${bed}_4Ps
+    paraclu $min_cluster ${bed}_4Ps > ${prefix}.clustered
+    paraclu-cut  ${prefix}.clustered >  ${prefix}.clustered.simplified
+    awk -F '\t' '{print \$1"\t"\$3"\t"\$4"\t"\$1":"\$3".."\$4","\$2"\t"\$6"\t"\$2}' ${prefix}.clustered.simplified >  ${prefix}.clustered.simplified.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: $VERSION
+    END_VERSIONS
+    """
+}

modules/paraclu/meta.yml

@@ -0,0 +1,45 @@
+name: paraclu
+description: Paraclu finds clusters in data attached to sequences.
+keywords:
+  - sort
+tools:
+  - paraclu:
+      description: Paraclu finds clusters in data attached to sequences.
+      homepage: https://gitlab.com/mcfrith/paraclu
+      documentation: https://gitlab.com/mcfrith/paraclu
+      tool_dev_url: https://gitlab.com/mcfrith/paraclu
+      doi: ""
+      licence: ['GPL v3-or-later']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+  - min_cluster:
+      type: integer
+      description: Minimum size of cluster
+      pattern: "*.bed"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - bed:
+      type: file
+      description: clustered BED file
+      pattern: "*.bed"
+
+authors:
+  - "@mashehu"

modules/porechop/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/porechop/main.nf

@@ -0,0 +1,42 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process PORECHOP {
+    tag "$meta.id"
+    label 'process_medium'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::porechop=0.2.4" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/porechop:0.2.4--py39h7cff6ad_2"
+    } else {
+        container "quay.io/biocontainers/porechop:0.2.4--py38h8c62d01_2"
+    }
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*.fastq.gz")  , emit: reads
+    path "versions.yml"                          , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    porechop \\
+        -i ${reads} \\
+        -t ${task.cpus} \\
+        ${options.args} \\
+        -o ${prefix}.fastq.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( porechop --version )
+    END_VERSIONS
+    """
+}

modules/porechop/meta.yml

@@ -0,0 +1,50 @@
+name: porechop
+description: Adapter removal and demultiplexing of Oxford Nanopore reads
+keywords:
+  - adapter
+  - nanopore
+  - demultiplexing
+tools:
+  - porechop:
+      description: Adapter removal and demultiplexing of Oxford Nanopore reads
+      homepage: "https://github.com/rrwick/Porechop"
+      documentation: "https://github.com/rrwick/Porechop"
+      tool_dev_url: "https://github.com/rrwick/Porechop"
+      doi: "10.1099/mgen.0.000132"
+      licence: ["GPL v3"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: fastq/fastq.gz file
+      pattern: "*.{fastq,fastq.gz,fq,fq.gz}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - reads:
+      type: file
+      description: Demultiplexed and/or adapter-trimmed fastq.gz file
+      pattern: "*.{fastq.gz}"
+
+authors:
+  - "@ggabernet"
+  - "@jasmezz"
+  - "@d4straub"
+  - "@LaurenceKuhl"
+  - "@SusiJo"
+  - "@jonasscheid"
+  - "@jonoave"
+  - "@GokceOGUZ"

modules/samtools/bam2fq/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/samtools/bam2fq/main.nf

@@ -0,0 +1,64 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process SAMTOOLS_BAM2FQ {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::samtools=1.14" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/samtools:1.14--hb421002_0"
+    } else {
+        container "quay.io/biocontainers/samtools:1.14--hb421002_0"
+    }
+
+    input:
+    tuple val(meta), path(inputbam)
+    val(split)
+
+    output:
+    tuple val(meta), path("*.fq.gz"), emit: reads
+    path "versions.yml"          , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+
+    if (split){
+        """
+        samtools \\
+            bam2fq \\
+            $options.args \\
+            -@ $task.cpus \\
+            -1 ${prefix}_1.fq.gz \\
+            -2 ${prefix}_2.fq.gz \\
+            -0 ${prefix}_other.fq.gz \\
+            -s ${prefix}_singleton.fq.gz \\
+            $inputbam
+
+        cat <<-END_VERSIONS > versions.yml
+        ${getProcessName(task.process)}:
+            ${getSoftwareName(task.process)}: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+        END_VERSIONS
+        """
+    } else {
+        """
+        samtools \\
+            bam2fq \\
+            $options.args \\
+            -@ $task.cpus \\
+            $inputbam >${prefix}_interleaved.fq.gz
+
+        cat <<-END_VERSIONS > versions.yml
+        ${getProcessName(task.process)}:
+            ${getSoftwareName(task.process)}: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+        END_VERSIONS
+        """
+    }
+
+}

modules/samtools/bam2fq/meta.yml

@@ -0,0 +1,55 @@
+name: samtools_bam2fq
+description: |
+    The module uses bam2fq method from samtools to
+    convert a SAM, BAM or CRAM file to FASTQ format
+keywords:
+  - bam2fq
+  - samtools
+  - fastq
+tools:
+  - samtools:
+      description: Tools for dealing with SAM, BAM and CRAM files
+      homepage: None
+      documentation: http://www.htslib.org/doc/1.1/samtools.html
+      tool_dev_url: None
+      doi: ""
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - inputbam:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - split:
+      type: boolean
+      description: |
+        TRUE/FALSE value to indicate if reads should be separated into
+        /1, /2 and if present other, or singleton.
+        Note: choosing TRUE will generate 4 different files.
+        Choosing FALSE will produce a single file, which will be interleaved in case
+        the input contains paired reads.
+
+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"
+  - reads:
+      type: file
+      description: |
+        FASTQ files, which will be either a group of 4 files (read_1, read_2, other and singleton)
+        or a single interleaved .fq.gz file if the user chooses not to split the reads.
+      pattern: "*.fq.gz"
+
+authors:
+  - "@lescai"

modules/samtools/depth/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/samtools/depth/main.nf

@@ -0,0 +1,43 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process SAMTOOLS_DEPTH {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::samtools=1.14" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/samtools:1.14--hb421002_0"
+    } else {
+        container "quay.io/biocontainers/samtools:1.14--hb421002_0"
+    }
+
+    input:
+    tuple val(meta), path(bam)
+
+    output:
+    tuple val(meta), path("*.tsv"), emit: tsv
+    path "versions.yml"          , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+
+    """
+    samtools \\
+        depth \\
+        $options.args \\
+        -o ${prefix}.tsv \\
+        $bam
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+}

modules/samtools/depth/meta.yml

@@ -0,0 +1,44 @@
+name: samtools_depth
+description: Computes the depth at each position or region.
+keywords:
+  - depth
+  - samtools
+  - statistics
+  - coverage
+tools:
+  - samtools:
+      description: Tools for dealing with SAM, BAM and CRAM files; samtools depth – computes the read depth at each position or region
+      homepage: http://www.htslib.org
+      documentation: http://www.htslib.org/doc/samtools-depth.html
+      tool_dev_url: https://github.com/samtools/samtools
+      doi: "10.1093/bioinformatics/btp352"
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: sorted BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - tsv:
+      type: file
+      description: The output of samtools depth has three columns - the name of the contig or chromosome, the position and the number of reads aligned at that position
+      pattern: "*.{tsv}"
+
+authors:
+  - "@louperelo"

modules/seqtk/mergepe/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/seqtk/mergepe/main.nf

@@ -0,0 +1,53 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process SEQTK_MERGEPE {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::seqtk=1.3" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/seqtk:1.3--h5bf99c6_3"
+    } else {
+        container "quay.io/biocontainers/seqtk:1.3--h5bf99c6_3"
+    }
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*.fastq.gz"), emit: reads
+    path "versions.yml"          , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    if (meta.single_end) {
+        """
+        ln -s ${reads} ${prefix}.fastq.gz
+
+        cat <<-END_VERSIONS > versions.yml
+        ${getProcessName(task.process)}:
+            ${getSoftwareName(task.process)}: \$(echo \$(seqtk 2>&1) | sed 's/^.*Version: //; s/ .*\$//')
+        END_VERSIONS
+        """
+    } else {
+        """
+        seqtk \\
+            mergepe \\
+            $options.args \\
+            ${reads} \\
+            | gzip -n >> ${prefix}.fastq.gz
+
+        cat <<-END_VERSIONS > versions.yml
+        ${getProcessName(task.process)}:
+            ${getSoftwareName(task.process)}: \$(echo \$(seqtk 2>&1) | sed 's/^.*Version: //; s/ .*\$//')
+        END_VERSIONS
+        """
+    }
+}

modules/seqtk/mergepe/meta.yml

@@ -0,0 +1,40 @@
+name: seqtk_mergepe
+description: Interleave pair-end reads from FastQ files
+keywords:
+  - interleave
+tools:
+  - seqtk:
+      description: Seqtk is a fast and lightweight tool for processing sequences in the FASTA or FASTQ format. Seqtk mergepe command merges pair-end reads into one interleaved file.
+      homepage: https://github.com/lh3/seqtk
+      documentation:  https://docs.csc.fi/apps/seqtk/
+      tool_dev_url: https://github.com/lh3/seqtk
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: List of input FastQ files of size 1 and 2 for single-end and paired-end data,respectively.
+      pattern: "*.{fastq.gz}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - reads:
+      type: file
+      description: If single-end reads, the output is the same as the input, 1 FastQ file for each read. If pair-end reads, the read pairs will be interleaved and output as 1 FastQ file for each read pair.
+      pattern: "*.{fastq.gz}"
+
+authors:
+  - "@emnilsson"

modules/strelka/germline/main.nf

@@ -23,17 +23,19 @@ process STRELKA_GERMLINE {
     path  fasta
     path  fai
     path  target_bed
+    path  target_bed_tbi
+
 
     output:
     tuple val(meta), path("*variants.vcf.gz")    , emit: vcf
     tuple val(meta), path("*variants.vcf.gz.tbi"), emit: vcf_tbi
     tuple val(meta), path("*genome.vcf.gz")      , emit: genome_vcf
     tuple val(meta), path("*genome.vcf.gz.tbi")  , emit: genome_vcf_tbi
-    path  "versions.yml"                         , emit: versions
+    path "versions.yml"                          , emit: versions
 
     script:
     def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
-    def regions  = params.target_bed ? "--exome --callRegions ${target_bed}" : ""
+    def regions  = target_bed ? "--exome --callRegions ${target_bed}" : ""
     """
     configureStrelkaGermlineWorkflow.py \\
         --bam $bam \\

modules/strelka/somatic/main.nf

@@ -19,7 +19,7 @@ process STRELKA_SOMATIC {
     }
 
     input:
-    tuple val(meta), path(cram_normal), path(crai_normal), path(cram_tumor), path(crai_tumor)
+    tuple val(meta), path(cram_normal), path(crai_normal), path(cram_tumor), path(crai_tumor),  path(manta_candidate_small_indels), path(manta_candidate_small_indels_tbi)
     path  fasta
     path  fai
     path  target_bed
@@ -34,13 +34,15 @@ process STRELKA_SOMATIC {
 
     script:
     def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
-    def options_strelka = params.target_bed ? "--exome --callRegions ${target_bed}" : ""
+    def options_target_bed = target_bed ? "--exome --callRegions ${target_bed}" : ""
+    def options_manta = manta_candidate_small_indels ? "--indelCandidates ${manta_candidate_small_indels}" : ""
     """
     configureStrelkaSomaticWorkflow.py \\
         --tumor $cram_tumor \\
         --normal $cram_normal \\
         --referenceFasta $fasta \\
-        $options_strelka \\
+        $options_target_bed \\
+        $options_manta \\
         $options.args \\
         --runDir strelka
 

modules/strelka/somatic/meta.yml

@@ -37,6 +37,14 @@ input:
       type: file
       description: BAM/CRAM/SAM index file
       pattern: "*.{bai,crai,sai}"
+  - manta_candidate_small_indels:
+      type: file
+      description: VCF.gz file
+      pattern: "*.{vcf.gz}"
+  - manta_candidate_small_indels_tbi:
+      type: file
+      description: VCF.gz index file
+      pattern: "*.tbi"
   - fasta:
       type: file
       description: Genome reference FASTA file

tests/config/pytest_modules.yml

@@ -30,6 +30,10 @@ artic/minion:
   - modules/artic/minion/**
   - tests/modules/artic/minion/**
 
+assemblyscan:
+  - modules/assemblyscan/**
+  - tests/modules/assemblyscan/**
+
 bamaligncleaner:
   - modules/bamaligncleaner/**
   - tests/modules/bamaligncleaner/**
@@ -254,6 +258,10 @@ cat/fastq:
   - modules/cat/fastq/**
   - tests/modules/cat/fastq/**
 
+cellranger/mkref:
+  - modules/cellranger/mkref/**
+  - tests/modules/cellranger/mkref/**
+
 checkm/lineagewf:
   - modules/checkm/lineagewf/**
   - tests/modules/checkm/lineagewf/**
@@ -294,6 +302,10 @@ damageprofiler:
   - modules/damageprofiler/**
   - tests/modules/damageprofiler/**
 
+dedup:
+  - modules/dedup/**
+  - tests/modules/dedup/**
+
 deeptools/computematrix:
   - modules/deeptools/computematrix/**
   - tests/modules/deeptools/computematrix/**
@@ -378,10 +390,18 @@ fgbio/callmolecularconsensusreads:
   - modules/fgbio/callmolecularconsensusreads/**
   - tests/modules/fgbio/callmolecularconsensusreads/**
 
+fgbio/fastqtobam:
+  - modules/fgbio/fastqtobam/**
+  - tests/modules/fgbio/fastqtobam/**
+
 fgbio/sortbam:
   - modules/fgbio/sortbam/**
   - tests/modules/fgbio/sortbam/**
 
+filtlong:
+  - modules/filtlong/**
+  - tests/modules/filtlong/**
+
 flash:
   - modules/flash/**
   - tests/modules/flash/**
@@ -414,6 +434,10 @@ gatk4/createsomaticpanelofnormals:
   - modules/gatk4/createsomaticpanelofnormals/**
   - tests/modules/gatk4/createsomaticpanelofnormals/**
 
+gatk4/estimatelibrarycomplexity:
+  - modules/gatk4/estimatelibrarycomplexity/**
+  - tests/modules/gatk4/estimatelibrarycomplexity/**
+
 gatk4/fastqtosam:
   - modules/gatk4/fastqtosam/**
   - tests/modules/gatk4/fastqtosam/**
@@ -678,6 +702,18 @@ maltextract:
   - modules/maltextract/**
   - tests/modules/maltextract/**
 
+manta/germline:
+  - modules/manta/germline/**
+  - tests/modules/manta/germline/**
+
+manta/somatic:
+  - modules/manta/somatic/**
+  - tests/modules/manta/somatic/**
+
+manta/tumoronly:
+  - modules/manta/tumoronly/**
+  - tests/modules/manta/tumoronly/**
+
 mash/sketch:
   - modules/mash/sketch/**
   - tests/modules/mash/sketch/**
@@ -791,6 +827,10 @@ pangolin:
   - modules/pangolin/**
   - tests/modules/pangolin/**
 
+paraclu:
+  - modules/paraclu/**
+  - tests/modules/paraclu/**
+
 pbbam/pbmerge:
   - modules/pbbam/pbmerge/**
   - tests/modules/pbbam/pbmerge/**
@@ -835,6 +875,10 @@ plink/vcf:
   - modules/plink/vcf/**
   - tests/modules/plink/vcf/**
 
+porechop:
+  - modules/porechop/**
+  - tests/modules/porechop/**
+
 preseq/lcextrap:
   - modules/preseq/lcextrap/**
   - tests/modules/preseq/lcextrap/**
@@ -939,6 +983,14 @@ samtools/ampliconclip:
   - modules/samtools/ampliconclip/**
   - tests/modules/samtools/ampliconclip/**
 
+samtools/bam2fq:
+  - modules/samtools/bam2fq/**
+  - tests/modules/samtools/bam2fq/**
+
+samtools/depth:
+  - modules/samtools/depth/**
+  - tests/modules/samtools/depth/**
+
 samtools/faidx:
   - modules/samtools/faidx/**
   - tests/modules/samtools/faidx/**
@@ -987,6 +1039,10 @@ seqkit/split2:
   - modules/seqkit/split2/**
   - tests/modules/seqkit/split2/**
 
+seqtk/mergepe:
+  - modules/seqtk/mergepe/**
+  - tests/modules/seqtk/mergepe/**
+
 seqtk/sample:
   - modules/seqtk/sample/**
   - tests/modules/seqtk/sample/**

tests/config/test_data.config

@@ -135,6 +135,7 @@ params {
                 test_paired_end_umi_histogram_txt                       = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test.paired_end.umi_histogram.txt"
                 test_paired_end_umi_unsorted_bam                        = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test.paired_end.umi_unsorted.bam"
                 test_paired_end_umi_unsorted_tagged_bam                 = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test.paired_end.unsorted_tagged.bam"
+                test_paired_end_hla                                     = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/example_hla_pe.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"

tests/modules/assemblyscan/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ASSEMBLYSCAN } from '../../../modules/assemblyscan/main.nf' addParams( options: [:] )
+
+workflow test_assemblyscan {
+    
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
+
+    ASSEMBLYSCAN ( input )
+}

tests/modules/assemblyscan/test.yml

@@ -0,0 +1,7 @@
+- name: assemblyscan test_assemblyscan
+  command: nextflow run tests/modules/assemblyscan -entry test_assemblyscan -c tests/config/nextflow.config
+  tags:
+    - assemblyscan
+  files:
+    - path: output/assemblyscan/test.json
+      md5sum: 9140e3d43f2d676f62e1325ace5dd8bd

tests/modules/bedtools/genomecov/main.nf

@@ -4,10 +4,37 @@ nextflow.enable.dsl = 2
 
 include { BEDTOOLS_GENOMECOV } from '../../../../modules/bedtools/genomecov/main.nf' addParams( options: [suffix: '_out'] )
 
-workflow test_bedtools_genomecov {
+workflow test_bedtools_genomecov_noscale {
     input = [
         [ id:'test'],
-        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true),
+        1
+    ]
+
+    sizes = []
+    extension = 'txt'
+
+    BEDTOOLS_GENOMECOV ( input, sizes, extension )
+}
+
+workflow test_bedtools_genomecov_nonbam_noscale {
+    input = [
+        [ id:'test'],
+        file(params.test_data['sarscov2']['genome']['baits_bed'], checkIfExists: true),
+        1
+    ]
+
+    sizes = file(params.test_data['sarscov2']['genome']['genome_sizes'], checkIfExists: true)
+    extension = 'txt'
+
+    BEDTOOLS_GENOMECOV ( input, sizes, extension )
+}
+
+workflow test_bedtools_genomecov_scale {
+    input = [
+        [ id:'test'],
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true),
+        0.5
     ]
 
     sizes = file('dummy_chromosome_sizes')
@@ -16,10 +43,11 @@ workflow test_bedtools_genomecov {
     BEDTOOLS_GENOMECOV ( input, sizes, extension )
 }
 
-workflow test_bedtools_genomecov_nonbam {
+workflow test_bedtools_genomecov_nonbam_scale {
     input = [
         [ id:'test'],
-        file(params.test_data['sarscov2']['genome']['baits_bed'], checkIfExists: true)
+        file(params.test_data['sarscov2']['genome']['baits_bed'], checkIfExists: true),
+        0.5
     ]
 
     sizes = file(params.test_data['sarscov2']['genome']['genome_sizes'], checkIfExists: true)

tests/modules/bedtools/genomecov/test.yml

@@ -1,5 +1,5 @@
-- name: bedtools genomecov test_bedtools_genomecov
+- name: bedtools genomecov test_bedtools_genomecov_noscale
-  command: nextflow run ./tests/modules/bedtools/genomecov -entry test_bedtools_genomecov -c tests/config/nextflow.config
+  command: nextflow run ./tests/modules/bedtools/genomecov -entry test_bedtools_genomecov_noscale -c tests/config/nextflow.config
   tags:
     - bedtools
     - bedtools/genomecov
@@ -7,11 +7,29 @@
     - path: output/bedtools/test_out.txt
       md5sum: 66083198daca6c001d328ba9616e9b53
 
-- name: bedtools genomecov test_bedtools_genomecov_nonbam
+- name: bedtools genomecov test_bedtools_genomecov_nonbam_noscale
-  command: nextflow run tests/modules/bedtools/genomecov -entry test_bedtools_genomecov_nonbam -c tests/config/nextflow.config
+  command: nextflow run tests/modules/bedtools/genomecov -entry test_bedtools_genomecov_nonbam_noscale -c tests/config/nextflow.config
   tags:
     - bedtools
     - bedtools/genomecov
   files:
     - path: output/bedtools/test_out.txt
       md5sum: f47b58840087426e5b643d8dfd155c1f
+
+- name: bedtools genomecov test_bedtools_genomecov_scale
+  command: nextflow run ./tests/modules/bedtools/genomecov -entry test_bedtools_genomecov_scale -c tests/config/nextflow.config
+  tags:
+    - bedtools
+    - bedtools/genomecov
+  files:
+    - path: output/bedtools/test_out.txt
+      md5sum: 01291b6e1beab72e046653e709eb0e10
+
+- name: bedtools genomecov test_bedtools_genomecov_nonbam_scale
+  command: nextflow run tests/modules/bedtools/genomecov -entry test_bedtools_genomecov_nonbam_scale -c tests/config/nextflow.config
+  tags:
+    - bedtools
+    - bedtools/genomecov
+  files:
+    - path: output/bedtools/test_out.txt
+      md5sum: de3c59c0ea123bcdbbad27bc0a0a601e

tests/modules/cellranger/mkref/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CELLRANGER_MKREF } from '../../../../modules/cellranger/mkref/main.nf' addParams( options: [:] )
+
+workflow test_cellranger_mkref {
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
+    reference_name = "homo_sapiens_chr22_reference"
+
+    CELLRANGER_MKREF ( fasta,
+                        gtf,
+                        reference_name )
+}

tests/modules/cellranger/mkref/test.yml

@@ -0,0 +1,43 @@
+- name: cellranger mkref test_cellranger_mkref
+  command: nextflow run tests/modules/cellranger/mkref -entry test_cellranger_mkref -c tests/config/nextflow.config
+  tags:
+    - cellranger
+    - cellranger/mkref
+  files:
+    - path: output/cellranger/homo_sapiens_chr22_reference/fasta/genome.fa
+      md5sum: f315020d899597c1b57e5fe9f60f4c3e
+    - path: output/cellranger/homo_sapiens_chr22_reference/fasta/genome.fa.fai
+      md5sum: 3520cd30e1b100e55f578db9c855f685
+    - path: output/cellranger/homo_sapiens_chr22_reference/genes/genes.gtf.gz
+      md5sum: 6d9b5f409bfea95022bc25b9590e194e
+    - path: output/cellranger/homo_sapiens_chr22_reference/reference.json
+      md5sum: a4e2b9bbf016c55b0d4d7bc1fa53896f
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/Genome
+      md5sum: 22102926fadf5890e905ca71b2da3f35
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/SA
+      md5sum: bcf3e1a855783105150b46c905465333
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/SAindex
+      md5sum: b93fb07d342e6c32a00ebc4311c0ad38
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/chrLength.txt
+      md5sum: c81f40f27e72606d7d07097c1d56a5b5
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/chrName.txt
+      md5sum: 5ae68a67b70976ee95342a7451cb5af1
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/chrNameLength.txt
+      md5sum: b190587cae0531f3cf25552d8aa674db
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/chrStart.txt
+      md5sum: bc73df776dd3d5bb9cfcbcba60880519
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/exonGeTrInfo.tab
+      md5sum: d04497f69d6ef889efd4d34fe63edcc4
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/exonInfo.tab
+      md5sum: 0d560290fab688b7268d88d5494bf9fe
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/geneInfo.tab
+      md5sum: 8b608537307443ffaee4927d2b428805
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/genomeParameters.txt
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/sjdbInfo.txt
+      md5sum: 5690ea9d9f09f7ff85b7fd47bd234903
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/sjdbList.fromGTF.out.tab
+      md5sum: 8760c33e966dad0b39f440301ebbdee4
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/sjdbList.out.tab
+      md5sum: 9e4f991abbbfeb3935a2bb21b9e258f1
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/transcriptInfo.tab
+      md5sum: 0c3a5adb49d15e5feff81db8e29f2e36

tests/modules/dedup/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { DEDUP } from '../../../modules/dedup/main.nf' addParams( options: [args: "-m"] )
+
+workflow test_dedup {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true) ]
+
+    DEDUP ( input )
+}

tests/modules/dedup/test.yml

@@ -0,0 +1,13 @@
+- name: dedup test_dedup
+  command: nextflow run tests/modules/dedup -entry test_dedup -c tests/config/nextflow.config
+  tags:
+    - dedup
+  files:
+    - path: output/dedup/test.paired_end.dedup.json
+      md5sum: 2def0b54aba1fafa21b274f260de1b6f
+    - path: output/dedup/test.paired_end.hist
+      md5sum: df3492273a1db0d8152e35d9d5e38aa6
+    - path: output/dedup/test.paired_end.log
+      md5sum: 4b8855bd63b2f4b37da4cfb17e61fb00
+    - path: output/dedup/test.paired_end_rmdup.bam
+      md5sum: 8b0408fe3e258989095303a47e5b5061

tests/modules/fgbio/fastqtobam/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+params.read_structure = "+T 12M11S+T"
+
+include { FGBIO_FASTQTOBAM } from '../../../../modules/fgbio/fastqtobam/main.nf' addParams( options: [:] )
+
+workflow test_fgbio_fastqtobam {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+              [ file(params.test_data['homo_sapiens']['illumina']['test_umi_1_fastq_gz'], checkIfExists: true), 
+                file(params.test_data['homo_sapiens']['illumina']['test_umi_2_fastq_gz'], checkIfExists: true) ] 
+              ]
+
+    FGBIO_FASTQTOBAM ( input, "${params.read_structure}" )
+}

tests/modules/fgbio/fastqtobam/test.yml

@@ -0,0 +1,10 @@
+- name: fgbio fastqtobam test_fgbio_fastqtobam
+  command: nextflow run tests/modules/fgbio/fastqtobam -entry test_fgbio_fastqtobam -c tests/config/nextflow.config
+  tags:
+    - fgbio/fastqtobam
+    - fgbio
+  files:
+    - path: output/fgbio/test_umi_converted.bam
+      md5sum: 9510735554e5eff29244077a72075fb6
+    - path: output/fgbio/versions.yml
+      md5sum: 524815093b96759060d0d800fc6a3f25

tests/modules/filtlong/main.nf

@@ -0,0 +1,36 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { FILTLONG } from '../../../modules/filtlong/main.nf' addParams( options: [:] )
+
+workflow test_filtlong {
+    
+    input = [ [ id:'test', single_end:false ], // meta map
+              [],
+              [ file(params.test_data['sarscov2']['nanopore']['test_fastq_gz'], checkIfExists: true) ]
+            ]
+
+    FILTLONG ( input )
+}
+
+workflow test_filtlong_illumina_se {
+    
+    input = [ [ id:'test', single_end:true ], // meta map
+              [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ],
+              [ file(params.test_data['sarscov2']['nanopore']['test_fastq_gz'], checkIfExists: true) ]
+            ]
+
+    FILTLONG ( input )
+}
+
+workflow test_filtlong_illumina_pe {
+    
+    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) ],
+              [ file(params.test_data['sarscov2']['nanopore']['test_fastq_gz'], checkIfExists: true) ]
+            ]
+
+    FILTLONG ( input )
+}

tests/modules/filtlong/test.yml

@@ -0,0 +1,23 @@
+- name: filtlong test_filtlong
+  command: nextflow run tests/modules/filtlong -entry test_filtlong -c tests/config/nextflow.config
+  tags:
+    - filtlong
+  files:
+    - path: output/filtlong/test_lr_filtlong.fastq.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+
+- name: filtlong test_filtlong_illumina_se
+  command: nextflow run tests/modules/filtlong -entry test_filtlong_illumina_se -c tests/config/nextflow.config
+  tags:
+    - filtlong
+  files:
+    - path: output/filtlong/test_lr_filtlong.fastq.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+
+- name: filtlong test_filtlong_illumina_pe
+  command: nextflow run tests/modules/filtlong -entry test_filtlong_illumina_pe -c tests/config/nextflow.config
+  tags:
+    - filtlong
+  files:
+    - path: output/filtlong/test_lr_filtlong.fastq.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a

tests/modules/gatk4/estimatelibrarycomplexity/main.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_ESTIMATELIBRARYCOMPLEXITY } from '../../../../modules/gatk4/estimatelibrarycomplexity/main.nf' addParams( options: [:] )
+
+workflow test_gatk4_estimatelibrarycomplexity {
+
+    input = [   [ id:'test', single_end:false ], // meta map
+                file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam'], checkIfExists: true)
+            ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fai   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    dict  = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+
+    GATK4_ESTIMATELIBRARYCOMPLEXITY ( input, fasta, fai, dict )
+}

tests/modules/gatk4/estimatelibrarycomplexity/test.yml

@@ -0,0 +1,7 @@
+- name: gatk4 estimatelibrarycomplexity test_gatk4_estimatelibrarycomplexity
+  command: nextflow run tests/modules/gatk4/estimatelibrarycomplexity -entry test_gatk4_estimatelibrarycomplexity -c tests/config/nextflow.config
+  tags:
+    - gatk4/estimatelibrarycomplexity
+    - gatk4
+  files:
+    - path: output/gatk4/test.metrics

tests/modules/manta/germline/main.nf

@@ -0,0 +1,35 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MANTA_GERMLINE } from '../../../../modules/manta/germline/main.nf' addParams( options: [:] )
+
+workflow test_manta_germline {
+    input = [
+        [ id:'test'], // 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)
+    bed     = []
+    bed_tbi = []
+
+    MANTA_GERMLINE ( input, fasta, fai, bed, bed_tbi )
+}
+
+workflow test_manta_germline_target_bed {
+    input = [
+        [ id:'test'], // 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)
+    bed     = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz'], checkIfExists: true)
+    bed_tbi = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz_tbi'], checkIfExists: true)
+
+    MANTA_GERMLINE ( input, fasta, fai, bed, bed_tbi )
+}

tests/modules/manta/germline/test.yml

@@ -0,0 +1,24 @@
+- name: manta germline
+  command: nextflow run ./tests/modules/manta/germline -entry test_manta_germline -c tests/config/nextflow.config
+  tags:
+    - manta
+    - manta/germline
+  files:
+    - path: output/manta/test.candidate_small_indels.vcf.gz
+    - path: output/manta/test.candidate_small_indels.vcf.gz.tbi
+    - path: output/manta/test.candidate_sv.vcf.gz
+    - path: output/manta/test.candidate_sv.vcf.gz.tbi
+    - path: output/manta/test.diploid_sv.vcf.gz
+    - path: output/manta/test.diploid_sv.vcf.gz.tbi
+- name: manta germline target bed
+  command: nextflow run ./tests/modules/manta/germline -entry test_manta_germline_target_bed -c tests/config/nextflow.config
+  tags:
+    - manta
+    - manta/germline
+  files:
+    - path: output/manta/test.candidate_small_indels.vcf.gz
+    - path: output/manta/test.candidate_small_indels.vcf.gz.tbi
+    - path: output/manta/test.candidate_sv.vcf.gz
+    - path: output/manta/test.candidate_sv.vcf.gz.tbi
+    - path: output/manta/test.diploid_sv.vcf.gz
+    - path: output/manta/test.diploid_sv.vcf.gz.tbi

tests/modules/manta/somatic/main.nf

@@ -0,0 +1,23 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MANTA_SOMATIC } from '../../../../modules/manta/somatic/main.nf' addParams( options: [:] )
+
+workflow test_manta_somatic {
+
+    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),
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_cram'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test2_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)
+    bed     = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz'], checkIfExists: true)
+    bed_tbi = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz_tbi'], checkIfExists: true)
+
+    MANTA_SOMATIC ( input, fasta, fai, bed, bed_tbi )
+}

tests/modules/manta/somatic/test.yml

@@ -0,0 +1,18 @@
+- name: manta somatic test_manta_somatic
+  command: nextflow run tests/modules/manta/somatic -entry test_manta_somatic -c tests/config/nextflow.config
+  tags:
+    - manta/somatic
+    - manta
+  files:
+    - path: output/manta/test.candidate_small_indels.vcf.gz
+    - path: output/manta/test.candidate_small_indels.vcf.gz.tbi
+      md5sum: 4cb176febbc8c26d717a6c6e67b9c905
+    - path: output/manta/test.candidate_sv.vcf.gz
+    - path: output/manta/test.candidate_sv.vcf.gz.tbi
+      md5sum: 4cb176febbc8c26d717a6c6e67b9c905
+    - path: output/manta/test.diploid_sv.vcf.gz
+    - path: output/manta/test.diploid_sv.vcf.gz.tbi
+      md5sum: 4cb176febbc8c26d717a6c6e67b9c905
+    - path: output/manta/test.somatic_sv.vcf.gz
+    - path: output/manta/test.somatic_sv.vcf.gz.tbi
+      md5sum: 4cb176febbc8c26d717a6c6e67b9c905

tests/modules/manta/tumoronly/main.nf

@@ -0,0 +1,35 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MANTA_TUMORONLY } from '../../../../modules/manta/tumoronly/main.nf' addParams( options: [:] )
+
+workflow test_manta_tumoronly {
+    input = [
+        [ id:'test'], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_cram'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test2_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)
+    bed     = []
+    bed_tbi = []
+
+    MANTA_TUMORONLY ( input, fasta, fai, bed, bed_tbi )
+}
+
+workflow test_manta_tumoronly_target_bed {
+    input = [
+        [ id:'test'], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_cram'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test2_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)
+    bed     = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz'], checkIfExists: true)
+    bed_tbi = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz_tbi'], checkIfExists: true)
+
+    MANTA_TUMORONLY ( input, fasta, fai, bed, bed_tbi )
+}

tests/modules/manta/tumoronly/test.yml

@@ -0,0 +1,24 @@
+- name: manta tumoronly
+  command: nextflow run ./tests/modules/manta/tumoronly -entry test_manta_tumoronly -c tests/config/nextflow.config
+  tags:
+    - manta
+    - manta/tumoronly
+  files:
+    - path: output/manta/test.candidate_small_indels.vcf.gz
+    - path: output/manta/test.candidate_small_indels.vcf.gz.tbi
+    - path: output/manta/test.candidate_sv.vcf.gz
+    - path: output/manta/test.candidate_sv.vcf.gz.tbi
+    - path: output/manta/test.tumor_sv.vcf.gz
+    - path: output/manta/test.tumor_sv.vcf.gz.tbi
+- name: manta tumoronly target bed
+  command: nextflow run ./tests/modules/manta/tumoronly -entry test_manta_tumoronly_target_bed -c tests/config/nextflow.config
+  tags:
+    - manta
+    - manta/tumoronly
+  files:
+    - path: output/manta/test.candidate_small_indels.vcf.gz
+    - path: output/manta/test.candidate_small_indels.vcf.gz.tbi
+    - path: output/manta/test.candidate_sv.vcf.gz
+    - path: output/manta/test.candidate_sv.vcf.gz.tbi
+    - path: output/manta/test.tumor_sv.vcf.gz
+    - path: output/manta/test.tumor_sv.vcf.gz.tbi

tests/modules/optitype/main.nf

@@ -6,8 +6,8 @@ include { OPTITYPE } from '../../../modules/optitype/main.nf' addParams( options
 
 workflow test_optitype {
     input = [ [ id:'test', seq_type:'dna' ], // meta map
-              file(params.test_data['homo_sapiens']['illumina']['test_paired_end_bam'], checkIfExists: true) 
+              file(params.test_data['homo_sapiens']['illumina']['test_paired_end_hla'], checkIfExists: true)
             ]
-            
+
     OPTITYPE ( input )
 }

tests/modules/optitype/test.yml

@@ -3,5 +3,7 @@
   tags:
     - optitype
   files:
-    - path: output/optitype/test/test_result.tsv
     - path: output/optitype/test/test_coverage_plot.pdf
+    - path: output/optitype/test/test_result.tsv
+      contains:
+        - '1446'

tests/modules/paraclu/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PARACLU } from '../../../modules/paraclu/main.nf' addParams( options: [:] )
+
+workflow test_paraclu {
+
+    input = [[  id:'test' ], // meta map
+                file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)
+                ]
+    min_cluster = 30
+
+    PARACLU ( input, min_cluster )
+}

tests/modules/paraclu/test.yml

@@ -0,0 +1,7 @@
+- name: paraclu test_paraclu
+  command: nextflow run tests/modules/paraclu -entry test_paraclu -c tests/config/nextflow.config
+  tags:
+    - paraclu
+  files:
+    - path: output/paraclu/test.clustered.simplified.bed
+      md5sum: d41d8cd98f00b204e9800998ecf8427e

tests/modules/porechop/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PORECHOP } from '../../../modules/porechop/main.nf' addParams( options: [args: '', suffix: '_porechop'] )
+
+workflow test_porechop {
+
+    input = [ [ id:'test', single_end:true ], // meta map
+                file(params.test_data['sarscov2']['nanopore']['test_fastq_gz'], checkIfExists: true) ]
+
+    PORECHOP ( input )
+}

tests/modules/porechop/test.yml

@@ -0,0 +1,7 @@
+- name: porechop test_porechop
+  command: nextflow run tests/modules/porechop -entry test_porechop -c tests/config/nextflow.config
+  tags:
+    - porechop
+  files:
+    - path: output/porechop/test_porechop.fastq.gz
+      md5sum: 08f314ae9f162c8dcc27e5b513d2064d

tests/modules/samtools/bam2fq/main.nf

@@ -0,0 +1,24 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SAMTOOLS_BAM2FQ } from '../../../../modules/samtools/bam2fq/main.nf' addParams( options: [args: "-T RX"] )
+
+workflow test_samtools_bam2fq_nosplit {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['homo_sapiens']['illumina']['test_paired_end_umi_converted_bam'], checkIfExists: true) ]
+    split = false
+
+    SAMTOOLS_BAM2FQ ( input, split )
+}
+
+
+workflow test_samtools_bam2fq_withsplit {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['homo_sapiens']['illumina']['test_paired_end_umi_converted_bam'], checkIfExists: true) ]
+    split = true
+
+    SAMTOOLS_BAM2FQ ( input, split )
+}

tests/modules/samtools/bam2fq/test.yml

@@ -0,0 +1,23 @@
+- name: samtools bam2fq test_samtools_bam2fq_nosplit
+  command: nextflow run tests/modules/samtools/bam2fq -entry test_samtools_bam2fq_nosplit -c tests/config/nextflow.config
+  tags:
+    - samtools/bam2fq
+    - samtools
+  files:
+    - path: output/samtools/test_interleaved.fq.gz
+      md5sum: d733e66d29a4b366bf9df8c42f845256
+
+- name: samtools bam2fq test_samtools_bam2fq_withsplit
+  command: nextflow run tests/modules/samtools/bam2fq -entry test_samtools_bam2fq_withsplit -c tests/config/nextflow.config
+  tags:
+    - samtools/bam2fq
+    - samtools
+  files:
+    - path: output/samtools/test_1.fq.gz
+      md5sum: 4522edbe158ec4804765794569f67493
+    - path: output/samtools/test_2.fq.gz
+      md5sum: 7e00ef40d5cfe272b67461381019dcc1
+    - path: output/samtools/test_other.fq.gz
+      md5sum: 709872fc2910431b1e8b7074bfe38c67
+    - path: output/samtools/test_singleton.fq.gz
+      md5sum: 709872fc2910431b1e8b7074bfe38c67

tests/modules/samtools/depth/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SAMTOOLS_DEPTH } from '../../../../modules/samtools/depth/main.nf' addParams( options: [:] )
+
+workflow test_samtools_depth {
+    
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_single_end_sorted_bam'], checkIfExists: true) ]
+
+    SAMTOOLS_DEPTH ( input )
+}

tests/modules/samtools/depth/test.yml

@@ -0,0 +1,8 @@
+- name: samtools depth
+  command: nextflow run tests/modules/samtools/depth -entry test_samtools_depth -c tests/config/nextflow.config
+  tags:
+    - samtools/depth
+    - samtools
+  files:
+    - path: output/samtools/test.tsv
+      md5sum: aa27ebf69663ebded553b4d6538219d9

tests/modules/seqtk/mergepe/main.nf

@@ -0,0 +1,31 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SEQTK_MERGEPE } from '../../../../modules/seqtk/mergepe/main.nf' addParams( options: [ 'suffix':'.processed' ] )
+
+//
+// Test with single-end data
+//
+
+workflow test_seqtk_mergepe_single_end {
+
+    input = [ [ id:'test', single_end:true ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
+
+    SEQTK_MERGEPE ( input )
+}
+
+//
+// Test with paired-end data
+//
+
+workflow test_seqtk_mergepe_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) ]
+            ]
+
+    SEQTK_MERGEPE ( input )
+}

tests/modules/seqtk/mergepe/test.yml

@@ -0,0 +1,17 @@
+- name: seqtk mergepe test_seqtk_mergepe_single_end
+  command: nextflow run tests/modules/seqtk/mergepe -entry test_seqtk_mergepe_single_end -c tests/config/nextflow.config
+  tags:
+    - seqtk/mergepe
+    - seqtk
+  files:
+    - path: output/seqtk/test.processed.fastq.gz
+      md5sum: e325ef7deb4023447a1f074e285761af
+
+- name: seqtk mergepe test_seqtk_mergepe_paired_end
+  command: nextflow run tests/modules/seqtk/mergepe -entry test_seqtk_mergepe_paired_end -c tests/config/nextflow.config
+  tags:
+    - seqtk/mergepe
+    - seqtk
+  files:
+    - path: output/seqtk/test.processed.fastq.gz
+      md5sum: 3f094ef62d9bfe06aa25174a06bc7d04

tests/modules/strelka/germline/main.nf

@@ -5,30 +5,32 @@ nextflow.enable.dsl = 2
 include { STRELKA_GERMLINE } from '../../../../modules/strelka/germline/main.nf' addParams( options: [:] )
 
 workflow test_strelka_germline {
-    input = [ 
+    input = [
         [ id:'test'], // meta map
-        file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram'], checkIfExists: true),
-        file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram_crai'], checkIfExists: true),
     ]
-    
+
-    fasta   = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    fasta   = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
-    fai     = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
+    fai     = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
-    targets = []
+    target_bed     = []
-    
+    target_bed_tbi = []
-    STRELKA_GERMLINE ( input, fasta, fai, targets )
+
+    STRELKA_GERMLINE ( input, fasta, fai, target_bed, target_bed_tbi )
 }
 
 workflow test_strelka_germline_target_bed {
-    input = [ 
+    input = [
         [ id:'test'], // meta map
-        file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram'], checkIfExists: true),
-        file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram_crai'], checkIfExists: true),
     ]
 
-    fasta   = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    fasta          = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
-    fai     = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
+    fai            = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
-    targets = file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)
+    target_bed     = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz'], checkIfExists: true)
+    target_bed_tbi = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz_tbi'], checkIfExists: true)
 
-    STRELKA_GERMLINE ( input, fasta, fai, targets )
+    STRELKA_GERMLINE ( input, fasta, fai, target_bed, target_bed_tbi )
 }
 

tests/modules/strelka/germline/test.yml

@@ -1,20 +1,21 @@
-- name: strelka germline
+- name: strelka germline test_strelka_germline
-  command: nextflow run ./tests/modules/strelka/germline -entry test_strelka_germline -c tests/config/nextflow.config
+  command: nextflow run tests/modules/strelka/germline -entry test_strelka_germline -c tests/config/nextflow.config
   tags:
     - strelka
     - strelka/germline
   files:
-    - path: output/strelka/test.variants.vcf.gz
-    - path: output/strelka/test.variants.vcf.gz.tbi
     - path: output/strelka/test.genome.vcf.gz
     - path: output/strelka/test.genome.vcf.gz.tbi
-- name: strelka germline target bed
+    - path: output/strelka/test.variants.vcf.gz
-  command: nextflow run ./tests/modules/strelka/germline -entry test_strelka_germline_target_bed -c tests/config/nextflow.config
+    - path: output/strelka/test.variants.vcf.gz.tbi
+
+- name: strelka germline test_strelka_germline_target_bed
+  command: nextflow run tests/modules/strelka/germline -entry test_strelka_germline_target_bed -c tests/config/nextflow.config
   tags:
     - strelka
     - strelka/germline
   files:
-    - path: output/strelka/test.variants.vcf.gz
-    - path: output/strelka/test.variants.vcf.gz.tbi
     - path: output/strelka/test.genome.vcf.gz
     - path: output/strelka/test.genome.vcf.gz.tbi
+    - path: output/strelka/test.variants.vcf.gz
+    - path: output/strelka/test.variants.vcf.gz.tbi

tests/modules/strelka/somatic/main.nf

@@ -11,7 +11,28 @@ workflow test_strelka_somatic {
         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),
         file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_cram'], checkIfExists: true),
-        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_cram_crai'], checkIfExists: true)
+        file(params.test_data['homo_sapiens']['illumina']['test2_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)
+    bed     = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz'], checkIfExists: true)
+    bed_tbi = file(params.test_data['homo_sapiens']['genome']['genome_bed_gz_tbi'], checkIfExists: true)
+
+    STRELKA_SOMATIC (input, fasta, fai, bed, bed_tbi )
+}
+
+workflow test_strelka__best_practices_somatic {
+
+    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),
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_cram'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_cram_crai'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_gz'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_gz_tbi'], checkIfExists: true)
     ]
 
     fasta   = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)

tests/modules/strelka/somatic/test.yml

@@ -10,3 +10,16 @@
     - path: output/strelka/test.somatic_snvs.vcf.gz
     - path: output/strelka/test.somatic_snvs.vcf.gz.tbi
       md5sum: 4cb176febbc8c26d717a6c6e67b9c905
+
+- name: strelka somatic test_strelka__best_practices_somatic
+  command: nextflow run tests/modules/strelka/somatic -entry test_strelka__best_practices_somatic -c tests/config/nextflow.config
+  tags:
+    - strelka
+    - strelka/somatic
+  files:
+    - path: output/strelka/test.somatic_indels.vcf.gz
+    - path: output/strelka/test.somatic_indels.vcf.gz.tbi
+      md5sum: 4cb176febbc8c26d717a6c6e67b9c905
+    - path: output/strelka/test.somatic_snvs.vcf.gz
+    - path: output/strelka/test.somatic_snvs.vcf.gz.tbi
+      md5sum: 4cb176febbc8c26d717a6c6e67b9c905