add methyldackel/extract + tests + testdata

.github/filters.yml

@@ -148,6 +148,10 @@ ivar_variants:
   - software/ivar/variants/**
   - tests/software/ivar/variants/**
 
+methyldackel_extract:
+  - software/methyldackel/extract/**
+  - tests/software/methyldackel/extract/**
+
 minimap2_align:
   - software/minimap2/align/**
   - tests/software/minimap2/align/**

software/methyldackel/extract/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/methyldackel/extract/main.nf

@@ -0,0 +1,40 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process METHYLDACKEL_EXTRACT {
+    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::methyldackel=0.5.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/methyldackel:0.5.0--hed50d52_0"
+    } else {
+        container "quay.io/biocontainers/methyldackel:0.5.0--hed50d52_0"
+    }
+
+    input:
+    tuple val(meta), path(bam), path(bai)
+    path fasta
+    path fai
+
+    output:
+    tuple val(meta), path("*.bedGraph"), emit: bedgraph
+    path  "*.version.txt"              , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    """
+    MethylDackel extract \\
+        $options.args \\
+        $fasta \\
+        $bam
+
+    echo \$(methyldackel --version 2>&1) | cut -f1 -d" " > ${software}.version.txt
+    """
+}

software/methyldackel/extract/meta.yml

@@ -0,0 +1,78 @@
+name: methyldackel_extract
+description: Extracts per-base methylation metrics from alignments
+keywords:
+    - methylation
+    - 5mC
+    - methylseq
+    - bisulphite
+    - consensus
+    - bedGraph
+    - bam
+    - cram
+tools:
+    - methyldackel:
+        description: |
+            A (mostly) universal methylation extractor
+            for BS-seq experiments.
+        homepage: https://github.com/brentp/bwa-meth
+        documentation: https://github.com/brentp/bwa-meth
+        arxiv: arXiv:1401.1129
+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:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - fasta:
+        type: file
+        description: Input genome fasta file
+        pattern: "*.{fasta,fa}"
+    - fai:
+        type: file
+        description: FASTA index file
+        pattern: "*.{fai}"
+    - bam:
+        type: file
+        description: BAM/CRAM file
+        pattern: "*.{bam,cram}"
+    - bai:
+        type: file
+        description: BAM/CRAM index file
+        pattern: "*.{bai,crai}"
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - bedgraph:
+        type: file
+        description: bedGraph file containing per-base methylation metrics
+        pattern: "*.{bedGraph}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@phue"

tests/data/fasta/E_coli/NC_010473.fa.fai

@@ -0,0 +1 @@
+gi|170079663|ref|NC_010473.1|	4686137	89	70	71

tests/software/methyldackel/extract/main.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { METHYLDACKEL_EXTRACT } from '../../../../software/methyldackel/extract/main.nf' addParams( options: [:] )
+
+workflow test_methyldackel_extract {
+
+    def input = []
+    def fasta = file("${launchDir}/tests/data/fasta/E_coli/NC_010473.fa", checkIfExists: true)
+    def fai   = file("${launchDir}/tests/data/fasta/E_coli/NC_010473.fa.fai", checkIfExists: true)
+
+    input     = [ [ id:'test', single_end:false ], // meta map
+                  file("${launchDir}/tests/data/bam/test.paired_end_methylated.sorted.bam", checkIfExists: true),
+                  file("${launchDir}/tests/data/bam/test.paired_end_methylated.sorted.bam.bai", checkIfExists: true) ]
+
+    METHYLDACKEL_EXTRACT ( input, fasta, fai )
+}

tests/software/methyldackel/extract/test.yml

@@ -0,0 +1,8 @@
+- name: Run methyldackel extract test workflow
+  command: nextflow run ./tests/software/methyldackel/extract -entry test_methyldackel_extract -c tests/config/nextflow.config
+  tags:
+    - methyldackel
+    - methyldackel_extract
+  files:
+    - path: output/methyldackel/test.paired_end_methylated.sorted_CpG.bedGraph
+      md5sum: a83c1c9abe632e1996402185ddc4d2b6