Add kraken2 run module (#266)

* Add kraken2 run module

* Add kraken2 run module

* Add coronavirus kraken2 db

* Adding kraken2 run tests

* Update software/kraken2/run/meta.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Fixing files commited by mistake

* Remove params for meta.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

software/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/kraken2/run/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/kraken2/run/main.nf

@@ -0,0 +1,52 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process KRAKEN2_RUN {
+    tag "$meta.id"
+    label 'process_high'
+    publishDir "${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::kraken2=2.1.1' : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container 'https://depot.galaxyproject.org/singularity/kraken2:2.1.1--pl526hc9558a2_0'
+    } else {
+        container 'quay.io/biocontainers/kraken2:2.1.1--pl526hc9558a2_0'
+    }
+
+    input:
+    tuple val(meta), path(reads)
+    path  db
+
+    output:
+    tuple val(meta), path('*classified*')  , emit: classified
+    tuple val(meta), path('*unclassified*'), emit: unclassified
+    tuple val(meta), path('*report.txt')   , emit: txt
+    path '*.version.txt'                   , emit: version
+
+    script:
+    def software     = getSoftwareName(task.process)
+    def prefix       = options.suffix  ? "${meta.id}${options.suffix}"  : "${meta.id}"
+    def paired       = meta.single_end ? "" : "--paired"
+    def classified   = meta.single_end ? "${prefix}.classified.fastq"   : "${prefix}.classified#.fastq"
+    def unclassified = meta.single_end ? "${prefix}.unclassified.fastq" : "${prefix}.unclassified#.fastq"
+    """
+    kraken2 \\
+        --db $db \\
+        --threads $task.cpus \\
+        --unclassified-out $unclassified \\
+        --classified-out $classified \\
+        --report ${prefix}.kraken2.report.txt \\
+        --gzip-compressed \\
+        $paired \\
+        $options.args \\
+        $reads
+
+    gzip *.fastq
+    echo \$(kraken2 --version 2>&1) | sed 's/^.*Kraken version //; s/ .*\$//' > ${software}.version.txt
+    """
+}

software/kraken2/run/meta.yml

@@ -0,0 +1,59 @@
+name: kraken2_run
+description: Classifies metagenomic sequence data
+keywords:
+    - classify
+    - metagenomics
+    - fastq
+    - db
+tools:
+    - kraken2:
+        description: |
+            Kraken2 is a taxonomic sequence classifier that assigns taxonomic labels to sequence reads
+        homepage: https://ccb.jhu.edu/software/kraken2/
+        documentation: https://github.com/DerrickWood/kraken2/wiki/Manual
+        doi: 10.1186/s13059-019-1891-0
+input:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: |
+            List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+            respectively.
+    - db:
+        type: directory
+        description: Kraken2 database
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - classified:
+        type: file
+        description: |
+            Reads classified to belong to any of the taxa
+            on the Kraken2 database.
+        pattern: "*{fastq.gz}"
+    - unclassified:
+        type: file
+        description: |
+            Reads not classified to belong to any of the taxa
+            on the Kraken2 database.
+        pattern: "*{fastq.gz}"
+    - txt:
+        type: file
+        description: |
+            Kraken2 report containing stats about classified
+            and not classifed reads.
+        pattern: "*.{report.txt}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@joseespinosa"
+    - "@drpatelh"

tests/config/pytest_software.yml

@@ -180,6 +180,10 @@ ivar_variants:
   - software/ivar/variants/**
   - tests/software/ivar/variants/**
 
+kraken2_run:
+  - software/kraken2/run/**
+  - tests/software/kraken2/run/**
+
 methyldackel_extract:
   - software/methyldackel/extract/**
   - tests/software/methyldackel/extract/**

tests/software/kraken2/run/main.nf

@@ -0,0 +1,25 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { KRAKEN2_RUN } from '../../../../software/kraken2/run/main.nf' addParams( options: [:] )
+
+workflow test_kraken2_run_single_end {
+    def input = []
+    input = [ [ id:'test', single_end:true ], // meta map
+                file("${launchDir}/tests/data/genomics/sarscov2/fastq/test_1.fastq.gz", checkIfExists: true) ]
+
+    db = [ file("${launchDir}/tests/data/genomics/sarscov2/db/kraken2", checkIfExists: true) ]
+
+    KRAKEN2_RUN ( input, db )
+}
+
+workflow test_kraken2_run_paired_end {
+    def input, db = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              file("${launchDir}/tests/data/genomics/sarscov2/fastq/test_*.fastq.gz", checkIfExists: true) ]
+
+    db = [ file("${launchDir}/tests/data/genomics/sarscov2/db/kraken2", checkIfExists: true) ]
+
+    KRAKEN2_RUN ( input, db )
+}

tests/software/kraken2/run/test.yml

@@ -0,0 +1,31 @@
+- name: kraken2 run single-end
+  command: nextflow run ./tests/software/kraken2/run -entry test_kraken2_run_single_end -c tests/config/nextflow.config
+  tags:
+    - kraken2
+    - kraken2_run
+    - kraken2_run_single_end
+  files:
+    - path: output/kraken2/test.classified.fastq.gz
+      should_exist: true
+    - path: output/kraken2/test.unclassified.fastq.gz
+      should_exist: true
+    - path: output/kraken2/test.kraken2.report.txt
+      md5sum: 4227755fe40478b8d7dc8634b489761e
+
+- name: kraken2 run paired-end
+  command: nextflow run ./tests/software/kraken2/run -entry test_kraken2_run_paired_end -c tests/config/nextflow.config
+  tags:
+    - kraken2
+    - kraken2_run
+    - kraken2_run_paired_end
+  files:
+    - path: output/kraken2/test.classified_1.fastq.gz
+      should_exist: true
+    - path: output/kraken2/test.classified_2.fastq.gz
+      should_exist: true
+    - path: output/kraken2/test.unclassified_1.fastq.gz
+      should_exist: true
+    - path: output/kraken2/test.unclassified_2.fastq.gz
+      should_exist: true
+    - path: output/kraken2/test.kraken2.report.txt
+      md5sum: 5fb165fd0bdf920ff6cf6f734371a4cf