Added all modules using bedtools in the enhancer transcript identification section

software/bedtools/ernas/functions.nf

@@ -0,0 +1,59 @@
+/*
+ * -----------------------------------------------------
+ *  Utility functions used in nf-core DSL2 module files
+ * -----------------------------------------------------
+ */
+
+/*
+ * Extract name of software tool from process name using $task.process
+ */
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+/*
+ * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+ */
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args          = args.args ?: ''
+    options.args2         = args.args2 ?: ''
+    options.publish_by_id = args.publish_by_id ?: false
+    options.publish_dir   = args.publish_dir ?: ''
+    options.publish_files = args.publish_files
+    options.suffix        = args.suffix ?: ''
+    return options
+}
+
+/*
+ * Tidy up and join elements of a list to return a path string
+ */
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }  // Remove empty entries
+    paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+/*
+ * Function to save/publish module results
+ */
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_id) {
+            path_list.add(args.publish_id)
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

software/bedtools/ernas/main.nf

@@ -0,0 +1,36 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+params.options = [:]
+def options    = initOptions(params.options)
+
+process BEDTOOLS_ERNAS {
+    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), publish_id:meta.id) }
+
+    conda (params.enable_conda ? "bioconda::bedtools =2.29.2" : null)
+    if (workflow.containerEngine == 'singularity' && !params.pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/bedtools:2.29.2--hc088bd4_0 "
+    } else {
+        container "quay.io/biocontainers/bedtools:2.29.2--hc088bd4_0"
+    }
+
+    input:
+        tuple val(meta), path(nogenesbed)
+        path "H3K27ac" 
+        path "H3K4me1"
+
+    output:
+        tuple val(meta), path("*.erna.bed"), emit: ernabed
+        path  "*.version.txt", emit: version
+
+    script:
+        def software = getSoftwareName(task.process)
+        def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+        """
+        bedtools intersect -a $nogenesbed -b $nogenesbed $H3K27ac $H3K4me1 -sorted -u -bed > ${prefix}.erna.bed
+        bedtools --version | sed -e "s/Bedtools v//g" > ${software}.version.txt
+        """
+}

software/bedtools/ernas/meta.yml

@@ -0,0 +1,55 @@
+name: bedtools_ernas
+description: Takes in units with genes removed
+Keeps anything that intersects with H3K27ac or H3K4me1
+
+
+
+keywords:
+    - bed
+    - bedtoolsintersect
+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/
+
+params:
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - enable_conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
+input:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - bed:
+        type: file
+        description: List of bed files
+        pattern: "*.{bed}"
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - bed:
+        type: file
+        description: Edited bed file
+        pattern: "*.{bed}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"

software/bedtools/histonestobed/functions.nf

@@ -0,0 +1,59 @@
+/*
+ * -----------------------------------------------------
+ *  Utility functions used in nf-core DSL2 module files
+ * -----------------------------------------------------
+ */
+
+/*
+ * Extract name of software tool from process name using $task.process
+ */
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+/*
+ * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+ */
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args          = args.args ?: ''
+    options.args2         = args.args2 ?: ''
+    options.publish_by_id = args.publish_by_id ?: false
+    options.publish_dir   = args.publish_dir ?: ''
+    options.publish_files = args.publish_files
+    options.suffix        = args.suffix ?: ''
+    return options
+}
+
+/*
+ * Tidy up and join elements of a list to return a path string
+ */
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }  // Remove empty entries
+    paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+/*
+ * Function to save/publish module results
+ */
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_id) {
+            path_list.add(args.publish_id)
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

software/bedtools/histonestobed/main.nf

@@ -0,0 +1,35 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process BEDTOOLS_HISTONESTOBED {
+    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), publish_id:meta.id) }
+
+    conda (params.enable_conda ? "bioconda::bedtools =2.29.2" : null)
+    if (workflow.containerEngine == 'singularity' && !params.pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/bedtools:2.29.2--hc088bd4_0 "
+    } else {
+        container "quay.io/biocontainers/bedtools:2.29.2--hc088bd4_0"
+    }
+    // In the case of use for cell lines, the second input can also be replaced with the tuple (val) format.
+    input:
+        tuple val(meta), path(bams)
+
+    output:
+        tuple val(meta), path("*.bed"), emit: bed
+        path  "*.version.txt", emit: version
+
+    script:
+        def software = getSoftwareName(task.process)
+        def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+        """
+        bamToBed -i ${bams[0]} | sortBed -i > ${prefix}.bed 
+        bedtools --version | sed -e "s/Bedtools v//g" > ${software}.version.txt
+        """
+}

software/bedtools/histonestobed/meta.yml

@@ -0,0 +1,53 @@
+name: bedtools_histonestoned
+description: Coverts Histone Bam files to BED format
+
+
+keywords:
+    - bed
+    - bedtoolsintersect
+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/
+
+params:
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - enable_conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
+input:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - bed:
+        type: file
+        description: List of bed files
+        pattern: "*.{bed}"
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - bed:
+        type: file
+        description: Edited bed file
+        pattern: "*.{bed}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"

software/bedtools/test/input/B.bed

@@ -0,0 +1 @@
+chr1	999	1010

software/bedtools/test/input/H3K27ac.bed

@@ -0,0 +1,5 @@
+chr1	951	1061
+chr1	1300	1420
+chr1	1400	1500
+
+

software/bedtools/test/input/H3K4me1.bed

@@ -0,0 +1,5 @@
+chr1	951	1061
+chr1	1300	1420
+chr1	1400	1500
+
+

software/bedtools/test/main.nf

@@ -4,6 +4,10 @@ nextflow.preview.dsl = 2
 
 include { BEDTOOLS_SLOP } from '../slop/main.nf' addParams( options: [publish_dir:'test_bed_file'])
 include { BEDTOOLS_REMOVEGENES } from '../removegenes/main.nf' addParams( options: [publish_dir:'test_bed_file'])
+include { BEDTOOLS_ERNAS } from '../ernas/main.nf' addParams( options: [publish_dir:'test_bed_file'])
+include { BEDTOOLS_TESTERNA } from '../testerna/main.nf' addParams( options: [publish_dir:'test_bed_file'])
+include { BEDTOOLS_HISTONESTOBED} from '../histonestobed/main.nf' addParams( options: [publish_dir:'test_histones_to_bed'])
+include { BEDTOOLS_ERNAGENEGROUPS} from '../ernagenegroups/main.nf' addParams( options: [publish_dir:'test_erna_gene_groups'])
 
 // Define input channels
 
@@ -21,9 +25,31 @@ workflow test_bed_file {
         BEDTOOLS_SLOP.out.slopbed,
         file("${baseDir}/input/B.metatranscripts", checkIfExists: true)
         )
+        
+    BEDTOOLS_ERNAS(
+        BEDTOOLS_REMOVEGENES.out.nogenesbed,
+        file("${baseDir}/input/H3K27ac.bed", checkIfExists: true),
+        file("${baseDir}/input/H3K4me1.bed", checkIfExists: true)
+    )
+
+    BEDTOOLS_TESTERNA(
+        BEDTOOLS_ERNAS.out.ernabed, 
+        file("${baseDir}/input/B.bed", checkIfExists: true)
+    )
 
 }
 
+workflow test_histones_to_bed {
+    def input = []
+    input = [ [ id:'test', single_end:true ], 
+              [ file("${baseDir}/input/test.single_end.sorted.bam", checkIfExists: true),] ]
+    BEDTOOLS_HISTONESTOBED( input )
+}
+
+
 workflow {
     test_bed_file()
+    test_histones_to_bed()
 }
+
+

software/bedtools/test/output/test_erna_prediction/test.erna_overlaps.bed

@@ -0,0 +1 @@
+chr1	999	1010

software/bedtools/testerna/functions.nf

@@ -0,0 +1,59 @@
+/*
+ * -----------------------------------------------------
+ *  Utility functions used in nf-core DSL2 module files
+ * -----------------------------------------------------
+ */
+
+/*
+ * Extract name of software tool from process name using $task.process
+ */
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+/*
+ * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+ */
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args          = args.args ?: ''
+    options.args2         = args.args2 ?: ''
+    options.publish_by_id = args.publish_by_id ?: false
+    options.publish_dir   = args.publish_dir ?: ''
+    options.publish_files = args.publish_files
+    options.suffix        = args.suffix ?: ''
+    return options
+}
+
+/*
+ * Tidy up and join elements of a list to return a path string
+ */
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }  // Remove empty entries
+    paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+/*
+ * Function to save/publish module results
+ */
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_id) {
+            path_list.add(args.publish_id)
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

software/bedtools/testerna/main.nf

@@ -0,0 +1,37 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process BEDTOOLS_TESTERNA {
+    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), publish_id:meta.id) }
+
+    conda (params.enable_conda ? "bioconda::bedtools =2.29.2" : null)
+    if (workflow.containerEngine == 'singularity' && !params.pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/bedtools:2.29.2--hc088bd4_0 "
+    } else {
+        container "quay.io/biocontainers/bedtools:2.29.2--hc088bd4_0"
+    }
+    // In the case of use for cell lines, the second input can also be replaced with the tuple (val) format.
+    input:
+        tuple val(meta), path(ernabed)
+        path ernareferencebed
+
+    output:
+        tuple val(meta), path("*.erna.overlaps.bed"), emit: ernaoverlapsbed
+        path  "*.version.txt", emit: version
+
+    script:
+        def software = getSoftwareName(task.process)
+        def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+        """
+        bedtools intersect -a $ernareferencebed -b $ernabed \\
+        -sorted -u > ${prefix}.erna.overlaps.bed 
+        bedtools --version | sed -e "s/Bedtools v//g" > ${software}.version.txt
+        """
+}

software/bedtools/testerna/meta.yml

@@ -0,0 +1,53 @@
+name: bedtools_testerna
+description: Compares identified ernas across cell lines/across legacy ernas
+
+
+keywords:
+    - bed
+    - bedtoolsintersect
+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/
+
+params:
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - enable_conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
+input:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - bed:
+        type: file
+        description: List of bed files
+        pattern: "*.{bed}"
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - bed:
+        type: file
+        description: Edited bed file
+        pattern: "*.{bed}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"