Merge pull request #250 from FriederikeHanssen/seqkit

Seqkit Split2

.github/filters.yml

@@ -281,6 +281,10 @@ seacr_callpeak:
   - software/seacr/callpeak/**
   - tests/software/seacr/callpeak/**
 
+seqkit_split2:
+  - software/seqkit/split2/**
+  - tests/software/seqkit/split2/**
+
 seqwish_induce:
   - software/seqwish/induce/**
   - tests/software/seqwish/induce/**

software/seqkit/split2/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/seqkit/split2/main.nf

@@ -0,0 +1,59 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process SEQKIT_SPLIT2 {
+    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::seqkit=0.15.0" : null)
+
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/seqkit:0.15.0--0"
+    } else {
+        container "quay.io/biocontainers/seqkit:0.15.0--0"
+    }
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*.split/*.gz"), emit: reads
+    path("*.version.txt")                      , emit: version
+
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+
+    if(meta.single_end){
+    """
+    seqkit \
+        split2 \
+        $options.args \
+        --threads $task.cpus \
+        -1 ${reads} \
+        --out-dir ${prefix}.split
+
+    echo \$(seqkit --version 2>&1) | sed 's/^.*seqkit //; s/Using.*\$//' > ${software}.version.txt
+    """
+    } else {
+    """
+    seqkit \
+        split2 \
+        $options.args \
+        --threads $task.cpus \
+        -1 ${reads[0]} \
+        -2 ${reads[1]} \
+        --out-dir ${prefix}.split
+
+    echo \$(seqkit --version 2>&1) | sed 's/^.*seqkit //; s/Using.*\$//' > ${software}.version.txt
+    """
+    }
+}

software/seqkit/split2/meta.yml

@@ -0,0 +1,59 @@
+name: seqkit_split2
+description: Split single or paired-end fastq.gz files
+keywords:
+    - split
+    - fastq
+tools:
+    - seqkit:
+        description: |
+            Cross-platform and ultrafast toolkit for FASTA/Q file manipulation, written by Wei Shen.
+        homepage: https://github.com/shenwei356/seqkit
+        documentation: https://bioinf.shenwei.me/seqkit/
+        doi: 10.1371/journal.pone.0163962
+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 ]
+    - reads:
+        type: file
+        description: FastQ files
+        pattern: "*.{fq.gz/fastq.gz}"
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: Split fastq files
+        pattern: "*.{fq.gz/fastq.gz}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@FriederikeHanssen"

tests/software/seqkit/split2/main.nf

@@ -0,0 +1,55 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SEQKIT_SPLIT2 as SEQKIT_SPLIT2_LENGTH } from '../../../../software/seqkit/split2/main.nf' addParams( options: ['args': '--by-length 26K'] )
+include { SEQKIT_SPLIT2 as SEQKIT_SPLIT2_SIZE } from '../../../../software/seqkit/split2/main.nf' addParams( options: ['args': '--by-size 200' ] )
+include { SEQKIT_SPLIT2 as SEQKIT_SPLIT2_PART } from '../../../../software/seqkit/split2/main.nf' addParams( options: ['args': '--by-part 3'] )
+
+workflow test_seqkit_split2_single_end_length {
+    def input = []
+    input = [ [ id:'test', single_end:true ], // meta map
+              file("${launchDir}/tests/data/fastq/dna/SRR396636_R1.fastq.gz", checkIfExists: true) ]
+
+    SEQKIT_SPLIT2_LENGTH ( input )
+}
+
+workflow test_seqkit_split2_single_end_size {
+    def input = []
+    input = [ [ id:'test', single_end:true ], // meta map
+              file("${launchDir}/tests/data/fastq/dna/SRR396636_R1.fastq.gz", checkIfExists: true) ]
+
+    SEQKIT_SPLIT2_SIZE ( input )
+}
+
+workflow test_seqkit_split2_single_end_part {
+    def input = []
+    input = [ [ id:'test', single_end:true ], // meta map
+              file("${launchDir}/tests/data/fastq/dna/SRR396636_R1.fastq.gz", checkIfExists: true) ]
+
+    SEQKIT_SPLIT2_PART ( input )
+}
+
+workflow test_seqkit_split2_paired_end_length {
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              file("${launchDir}/tests/data/fastq/dna/SRR396636_*", checkIfExists: true) ]
+
+    SEQKIT_SPLIT2_LENGTH ( input )
+}
+
+workflow test_seqkit_split2_paired_end_size {
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              file("${launchDir}/tests/data/fastq/dna/SRR396636_*", checkIfExists: true) ]
+
+    SEQKIT_SPLIT2_SIZE ( input )
+}
+
+workflow test_seqkit_split2_paired_end_part {
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              file("${launchDir}/tests/data/fastq/dna/SRR396636_*", checkIfExists: true) ]
+
+    SEQKIT_SPLIT2_PART ( input )
+}

tests/software/seqkit/split2/test.yml

@@ -0,0 +1,102 @@
+- name: seqkit split2 single-end length
+  command: nextflow run ./tests/software/seqkit/split2 -entry test_seqkit_split2_single_end_length -c tests/config/nextflow.config
+  tags:
+    - seqkit
+    - seqkit_split2
+    - seqkit_split2_single_end
+    - length
+  files:
+    - path: output/seqkit/test.split/SRR396636_R1.part_001.fastq.gz
+      md5sum: fb45cfec0d0d37f85abe81a0d299137e
+    - path: output/seqkit/test.split/SRR396636_R1.part_002.fastq.gz
+      md5sum: 0dfb5284ee0bb7e1b77b57dc1bd16311
+
+
+- name: seqkit split2 single-end size
+  command: nextflow run ./tests/software/seqkit/split2 -entry test_seqkit_split2_single_end_size -c tests/config/nextflow.config
+  tags:
+    - seqkit
+    - seqkit_split2
+    - seqkit_split2_single_end
+    - size
+  files:
+    - path: output/seqkit/test.split/SRR396636_R1.part_001.fastq.gz
+      md5sum: e76ac276819eb862c0a931755a220b50
+    - path: output/seqkit/test.split/SRR396636_R1.part_002.fastq.gz
+      md5sum: 79eb15ff1aac645308fab188915f9edf
+    - path: output/seqkit/test.split/SRR396636_R1.part_003.fastq.gz
+      md5sum: f01fa62d34012a2e9cc48972dfe8c14c
+
+- name: seqkit split2 single-end part
+  command: nextflow run ./tests/software/seqkit/split2 -entry test_seqkit_split2_single_end_part -c tests/config/nextflow.config
+  tags:
+    - seqkit
+    - seqkit_split2
+    - seqkit_split2_single_end
+    - part
+  files:
+    - path: output/seqkit/test.split/SRR396636_R1.part_001.fastq.gz
+      md5sum: c394bc973e1f0f9bda835e4a7610d2e1
+    - path: output/seqkit/test.split/SRR396636_R1.part_002.fastq.gz
+      md5sum: 152e4470b8caeed1fc1c0326f34aa4e6
+    - path: output/seqkit/test.split/SRR396636_R1.part_003.fastq.gz
+      md5sum: 6d8a9f6ed0f4eadbb8b1c560bfea384d
+
+- name: seqkit split2 paired-end length
+  command: nextflow run ./tests/software/seqkit/split2 -entry test_seqkit_split2_paired_end_length -c tests/config/nextflow.config
+  tags:
+    - seqkit
+    - seqkit_split2
+    - seqkit_split2_paired_end
+    - length
+  files:
+    - path: output/seqkit/test.split/SRR396636_R1.part_001.fastq.gz
+      md5sum: fb45cfec0d0d37f85abe81a0d299137e
+    - path: output/seqkit/test.split/SRR396636_R1.part_002.fastq.gz
+      md5sum: 0dfb5284ee0bb7e1b77b57dc1bd16311
+    - path: output/seqkit/test.split/SRR396636_R2.part_001.fastq.gz
+      md5sum: 4e9704a4a0f4bcab4900b6fcd9323d8a
+    - path: output/seqkit/test.split/SRR396636_R2.part_002.fastq.gz
+      md5sum: da93241d0cfa84d4b806e1e102c16977
+
+- name: seqkit split2 paired-end size
+  command: nextflow run ./tests/software/seqkit/split2 -entry test_seqkit_split2_paired_end_size -c tests/config/nextflow.config
+  tags:
+    - seqkit
+    - seqkit_split2
+    - seqkit_split2_paired_end
+    - size
+  files:
+    - path: output/seqkit/test.split/SRR396636_R1.part_001.fastq.gz
+      md5sum: e76ac276819eb862c0a931755a220b50
+    - path: output/seqkit/test.split/SRR396636_R1.part_002.fastq.gz
+      md5sum: 79eb15ff1aac645308fab188915f9edf
+    - path: output/seqkit/test.split/SRR396636_R1.part_003.fastq.gz
+      md5sum: f01fa62d34012a2e9cc48972dfe8c14c
+    - path: output/seqkit/test.split/SRR396636_R2.part_001.fastq.gz
+      md5sum: 357bfa5b981f34d87f682aebcf5e46fe
+    - path: output/seqkit/test.split/SRR396636_R2.part_002.fastq.gz
+      md5sum: f48f3389d2870f4934139a901e5c4bb2
+    - path: output/seqkit/test.split/SRR396636_R2.part_003.fastq.gz
+      md5sum: d161aa05bac2f7d1823da0479949512b
+
+- name: seqkit split2 paired-end part
+  command: nextflow run ./tests/software/seqkit/split2 -entry test_seqkit_split2_paired_end_part -c tests/config/nextflow.config
+  tags:
+    - seqkit
+    - seqkit_split2
+    - seqkit_split2_paired_end
+    - part
+  files:
+    - path: output/seqkit/test.split/SRR396636_R1.part_001.fastq.gz
+      md5sum: c394bc973e1f0f9bda835e4a7610d2e1
+    - path: output/seqkit/test.split/SRR396636_R1.part_002.fastq.gz
+      md5sum: 152e4470b8caeed1fc1c0326f34aa4e6
+    - path: output/seqkit/test.split/SRR396636_R1.part_003.fastq.gz
+      md5sum: 6d8a9f6ed0f4eadbb8b1c560bfea384d
+    - path: output/seqkit/test.split/SRR396636_R2.part_001.fastq.gz
+      md5sum: 228aff8f1e56050967476fcad164a4fc
+    - path: output/seqkit/test.split/SRR396636_R2.part_002.fastq.gz
+      md5sum: 41047f3df10126c0df7f8e9bfd752b83
+    - path: output/seqkit/test.split/SRR396636_R1.part_003.fastq.gz
+      md5sum: 6d8a9f6ed0f4eadbb8b1c560bfea384d