Merge pull request #37 from CCBR/consensus-peaks

feat: add consensus peaks subworkflow

CHANGELOG.md

@@ -2,8 +2,20 @@
 
 ### New modules
 
+- bedops/bedmap (#37)
+- bedtools/map (#37)
+- bedtools/merge (#37)
+- bedtools/sort (#37)
+- cat/cat (#37)
+- cat/fastq (#37)
+- custom/combinepeakcounts (#37)
+- custom/consensuspeaks (#37)
+- custom/normalizepeaks (#37)
+
 ### New subworkflows
 
+- consensus_peaks (#37)
+
 ## nf-modules 0.1.0
 
 Our documentation website is now live: <https://ccbr.github.io/nf-modules/> (#16)
@@ -24,4 +36,4 @@ Our documentation website is now live: <https://ccbr.github.io/nf-modules/> (#16
 
 ### New subworkflows
 
-- custom/filter_blacklist (#17,#27)
+- filter_blacklist (#17,#27)

README.md

@@ -46,7 +46,9 @@ Want to **contribute** to this project? Check out the [contributing guidelines](
 Many of the modules and subworkflows in this project reuse and adapt code from [nf-core/modules](https://github.com/nf-core/modules).
 In those cases, credit is noted in the `meta.yml` file of the module/subworkflow and also listed here:
 
+- [bedtools](modules/CCBR/bedtools) adapts the [nf-core bedtools module](https://github.com/nf-core/modules/tree/fff2c3fc7cdcb81a2a37c3263b8ace9b353af407/modules/nf-core/bedtools)
 - [bwa](modules/CCBR/bwa) adapts the [nf-core bwa module](https://github.com/nf-core/chipseq/tree/51eba00b32885c4d0bec60db3cb0a45eb61e34c5/modules/nf-core/modules/bwa)
+- [cat](modules/cat) adapts the [nf-core cat module](https://github.com/nf-core/modules/tree/9326d73af3fbe2ee90d9ce0a737461a727c5118e/modules/nf-core/cat)
 - [cutadapt](modules/CCBR/cutadapt) adapts the [nf-core cutadapt module](https://github.com/nf-core/modules/tree/ef007b1ce5316506b8c27c3e7a62482409c6153c/modules/nf-core/cutadapt)
 - [khmer](modules/CCBR/khmer) adapts the [nf-core khmer module](https://github.com/nf-core/modules/tree/b48a1efc8e067502e1a9bafbac788c1e0abdfc6a/modules/nf-core/khmer)
 - [picard/samtofastq](modules/picard/samtofastq) adapts the [nf-core gatk4 samtofastq module](https://github.com/nf-core/modules/tree/ef007b1ce5316506b8c27c3e7a62482409c6153c/modules/nf-core/gatk4/samtofastq)

modules/CCBR/bedops/bedmap/main.nf

@@ -0,0 +1,41 @@
+process BEDOPS_BEDMAP {
+    tag "${meta.id}.${refmeta.id}"
+    label 'process_single'
+    container 'nciccbr/ccbr_ubuntu_base_20.04:v6.1'
+
+    input:
+    tuple val(meta), path(mapbed), val(refmeta), path(refbed)
+
+    output:
+    tuple val(meta), path("*.mapped.bed"), emit: bed
+    path "versions.yml"                  , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    """
+    bedmap \\
+        --delim '\t' \\
+        --echo-ref-name \\
+        --count \\
+        ${refbed} \\
+        ${mapbed} \\
+        > ${meta.id}.${refmeta.id}.mapped.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedops: \$(echo \$(bedops --version 2>&1 | grep version | sed 's/version: //'))
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    touch ${meta.id}.${refmeta.id}.mapped.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedops: \$(echo \$(bedops --version 2>&1 | grep version | sed 's/version: //'))
+    END_VERSIONS
+    """
+}

modules/CCBR/bedops/bedmap/meta.yml

@@ -0,0 +1,55 @@
+---
+name: "bedops_bedmap"
+description: The bedmap program is used to retrieve and process signal or other features over regions of interest in BED files
+keywords:
+  - bedops
+  - bedmap
+  - bed
+  - intervals
+tools:
+  - bedops:
+      description: |
+        fast, highly scalable and easily-parallelizable genome analysis toolkit
+      documentation: https://bedops.readthedocs.io/
+      tool_dev_url: https://github.com/bedops/bedops
+      licence: ["GPLv2"]
+      doi: 10.1093/bioinformatics/bts277
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test', single_end:false ]`
+
+  - refbed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+  - mapbed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+
+output:
+  #Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test', single_end:false ]`
+
+  - mapped_bed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@kelly-sovacool"
+maintainers:
+  - "@kelly-sovacool"

modules/CCBR/bedtools/map/main.nf

@@ -0,0 +1,55 @@
+process BEDTOOLS_MAP {
+    tag { meta.id }
+    label 'process_single'
+
+    container 'nciccbr/ccbr_ubuntu_base_20.04:v6.1'
+
+    input:
+    tuple val(meta), path(intervals1), path(intervals2)
+    tuple val(meta2), path(chrom_sizes)
+
+    output:
+    tuple val(meta), path("*.${extension}"), emit: map
+    path  "versions.yml"                   , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}.mapped"
+    extension = intervals1.getExtension()
+    def sizes = chrom_sizes ? "-g ${chrom_sizes}" : ''
+    if ("$intervals1" == "${prefix}.${extension}" ||
+        "$intervals2" == "${prefix}.${extension}")
+        error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    """
+    bedtools \\
+        map \\
+        -a ${intervals1} \\
+        -b ${intervals2} \\
+        ${args} \\
+        ${sizes} \\
+        > ${prefix}.${extension}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}.mapped"
+    extension = intervals1.getExtension()
+    if ("${intervals1}" == "${prefix}.${extension}" ||
+        "${intervals2}" == "${prefix}.${extension}")
+        error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    """
+    touch ${prefix}.${extension}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
+    END_VERSIONS
+    """
+}

modules/CCBR/bedtools/map/meta.yml

@@ -0,0 +1,55 @@
+name: bedtools_map
+description: Allows one to screen for overlaps between two sets of genomic features. Adapted from https://github.com/nf-core/modules/tree/fff2c3fc7cdcb81a2a37c3263b8ace9b353af407/modules/nf-core/bedtools
+keywords:
+  - bed
+  - vcf
+  - gff
+  - map
+  - bedtools
+tools:
+  - bedtools:
+      description: |
+        A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types.
+      documentation: https://bedtools.readthedocs.io/en/latest/content/tools/map.html
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - intervals1:
+      type: file
+      description: BAM/BED/GFF/VCF
+      pattern: "*.{bed|gff|vcf}"
+  - intervals2:
+      type: file
+      description: BAM/BED/GFF/VCF
+      pattern: "*.{bed|gff|vcf}"
+  - meta2:
+      type: map
+      description: |
+        Groovy Map containing reference chromosome sizes
+        e.g. [ id:'test' ]
+  - chrom_sizes:
+      type: file
+      description: Chromosome sizes file
+      pattern: "*{.sizes,.txt}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - map:
+      type: file
+      description: File containing the description of overlaps found between the features in A and the features in B, with statistics
+      pattern: "*.${extension}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@kelly-sovacool"
+maintainers:
+  - "@kelly-sovacool"

modules/CCBR/bedtools/merge/main.nf

@@ -0,0 +1,44 @@
+process BEDTOOLS_MERGE {
+    tag { meta.id }
+    label 'process_single'
+
+    container 'nciccbr/ccbr_ubuntu_base_20.04:v6.1'
+
+    input:
+    tuple val(meta), path(bed)
+
+    output:
+    tuple val(meta), path('*.bed'), emit: bed
+    path  "versions.yml"          , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}.merged"
+    if ("$bed" == "${prefix}.bed") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    """
+    bedtools \\
+        merge \\
+        -i ${bed} \\
+        ${args} \\
+        > ${prefix}.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}.merged"
+    """
+    touch ${prefix}.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
+    END_VERSIONS
+    """
+}

modules/CCBR/bedtools/merge/meta.yml

@@ -0,0 +1,41 @@
+name: bedtools_merge
+description: combines overlapping or “book-ended” features in an interval file into a single feature which spans all of the combined features. Adapted from https://github.com/nf-core/modules/tree/fff2c3fc7cdcb81a2a37c3263b8ace9b353af407/modules/nf-core/bedtools
+keywords:
+  - bed
+  - merge
+  - bedtools
+  - overlapped bed
+tools:
+  - bedtools:
+      description: |
+        A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types.
+      documentation: https://bedtools.readthedocs.io/en/latest/content/tools/merge.html
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bed:
+      type: file
+      description: Input BED file
+      pattern: "*.{bed}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bed:
+      type: file
+      description: Overlapped bed file with combined features
+      pattern: "*.{bed}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@kelly-sovacool"
+maintainers:
+  - "@kelly-sovacool"

modules/CCBR/bedtools/sort/main.nf

@@ -0,0 +1,51 @@
+process BEDTOOLS_SORT {
+    tag { meta.id }
+    label 'process_single'
+
+    container 'nciccbr/ccbr_ubuntu_base_20.04:v6.1'
+
+    input:
+    tuple val(meta), path(intervals)
+    path genome_file
+
+    output:
+    tuple val(meta), path("*.${extension}"), emit: sorted
+    path  "versions.yml"                   , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args       = task.ext.args   ?: ''
+    def prefix     = task.ext.prefix ?: "${meta.id}.sorted"
+    def genome_cmd = genome_file     ?  "-g $genome_file" : ""
+    extension      = task.ext.suffix ?: intervals.extension
+    if ("$intervals" == "${prefix}.${extension}") {
+        error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    }
+    """
+    bedtools \\
+        sort \\
+        -i ${intervals} \\
+        ${genome_cmd} \\
+        ${args} \\
+        > ${prefix}.${extension}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}.sorted"
+    extension  = task.ext.suffix ?: intervals.extension
+    """
+    touch ${prefix}.${extension}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
+    END_VERSIONS
+    """
+}