Add bedtools getfasta module

.github/filters.yml

@@ -34,6 +34,10 @@ bedtools_genomecov:
   - software/bedtools/genomecov/**
   - tests/software/bedtools/genomecov/**
 
+bedtools_getfasta:
+  - software/bedtools/getfasta/**
+  - tests/software/bedtools/getfasta/**
+
 bedtools_intersect:
   - software/bedtools/intersect/**
   - tests/software/bedtools/intersect/**

software/bedtools/getfasta/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/getfasta/main.nf

@@ -0,0 +1,42 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process BEDTOOLS_GETFASTA {
+    tag "$bed"
+    label 'process_medium'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:'') }
+
+    conda (params.enable_conda ? "bioconda::bedtools=2.30.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/bedtools:2.30.0--hc088bd4_0"
+    } else {
+        container "quay.io/biocontainers/bedtools:2.30.0--hc088bd4_0"
+    }
+
+    input:
+    path bed
+    path fasta
+
+    output:
+    path "*.fa"         , emit: fasta
+    path "*.version.txt", emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${bed.baseName}${options.suffix}" : "${bed.baseName}"
+    """
+    bedtools \\
+        getfasta \\
+        $options.args \\
+        -fi $fasta \\
+        -bed $bed \\
+        -fo ${prefix}.fa
+
+    bedtools --version | sed -e "s/bedtools v//g" > ${software}.version.txt
+    """
+}

software/bedtools/getfasta/meta.yml

@@ -0,0 +1,54 @@
+name: bedtools_getfasta
+description: extract sequences in a FASTA file based on intervals defined in a feature file.
+keywords:
+    - bed
+    - fasta
+    - getfasta
+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/intersect.html
+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
+    - singularity_pull_docker_container:
+          type: boolean
+          description: |
+              Instead of directly downloading Singularity images for use with Singularity,
+              force the workflow to pull and convert Docker containers instead.
+input:
+    - bed:
+        type: file
+        description: Bed feature file
+        pattern: "*.{bed}"
+    - fasta:
+        type: file
+        description: Input fasta file
+        pattern: "*.{fa,fasta}"
+
+output:
+    - fasta:
+        type: file
+        description: Output fasta file with extracted sequences
+        pattern: "*.{fa}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@joseespinosa"
+    - "@drpatelh"

tests/software/bedtools/getfasta/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BEDTOOLS_GETFASTA } from '../../../../software/bedtools/getfasta/main.nf' addParams( options: [:] )
+
+workflow test_bedtools_getfasta {
+    def bed,fasta = []
+    bed   = [ file("${launchDir}/tests/data/bed/C.bed", checkIfExists: true) ]
+    fasta =  [ file("${launchDir}/tests/data/fasta/E_coli/NC_010473.fa", checkIfExists: true) ]
+
+    BEDTOOLS_GETFASTA( bed, fasta )
+}

tests/software/bedtools/getfasta/test.yml

@@ -0,0 +1,8 @@
+- name: bedtools getfasta
+  command: nextflow run ./tests/software/bedtools/getfasta -entry test_bedtools_getfasta -c tests/config/nextflow.config
+  tags:
+    - bedtools
+    - bedtools_getfasta
+  files:
+    - path: output/bedtools/C.fa
+      md5sum: 2257190c8d9fc6f177a518440cf1f3f3