Add MEGAHIT (#810)

* Specify more guidelines on input channels

* Linting

* Updates based on code review

* Update README.md

* Fix broken sentence

* feat: add megahit module, currently decompressed output

* Update main.nf

* Update tests/modules/megahit/test.yml

Co-authored-by: Maxime Borry <maxibor@users.noreply.github.com>

* Apply suggestions from code review

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

* feat: compress all outputs, remove md5sums due to gz stochasicity

* fix: wrong conda channel for pigz

* fix: broken singleend tests and update meta.yml

* Missed one

* Apply suggestions from code review

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

* fix: pigz formatting

* Apply suggestions from code review

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

* Apply suggestions from code review

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

modules/megahit/functions.nf

@@ -0,0 +1,78 @@
+//
+//  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()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/megahit/main.nf

@@ -0,0 +1,76 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process MEGAHIT {
+    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), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::megahit=1.2.9 conda-forge::pigz=2.6" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/mulled-v2-0f92c152b180c7cd39d9b0e6822f8c89ccb59c99:8ec213d21e5d03f9db54898a2baeaf8ec729b447-0"
+    } else {
+        container "quay.io/biocontainers/mulled-v2-0f92c152b180c7cd39d9b0e6822f8c89ccb59c99:8ec213d21e5d03f9db54898a2baeaf8ec729b447-0"
+    }
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("megahit_out/*.contigs.fa.gz")                            , emit: contigs
+    tuple val(meta), path("megahit_out/intermediate_contigs/k*.contigs.fa.gz")      , emit: k_contigs
+    tuple val(meta), path("megahit_out/intermediate_contigs/k*.addi.fa.gz")         , emit: addi_contigs
+    tuple val(meta), path("megahit_out/intermediate_contigs/k*.local.fa.gz")        , emit: local_contigs
+    tuple val(meta), path("megahit_out/intermediate_contigs/k*.final.contigs.fa.gz"), emit: kfinal_contigs
+    path "versions.yml"                                                             , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    if (meta.single_end) {
+        """
+        megahit \\
+            -r ${reads} \\
+            -t $task.cpus \\
+            $options.args \\
+            --out-prefix $prefix
+
+        pigz \\
+            --no-name \\
+            -p $task.cpus \\
+            $options.args2 \\
+            megahit_out/*.fa \\
+            megahit_out/intermediate_contigs/*.fa
+
+        cat <<-END_VERSIONS > versions.yml
+        ${getProcessName(task.process)}:
+            ${getSoftwareName(task.process)}: \$(echo \$(megahit -v 2>&1) | sed 's/MEGAHIT v//')
+        END_VERSIONS
+        """
+    } else {
+        """
+        megahit \\
+            -1 ${reads[0]} \\
+            -2 ${reads[1]} \\
+            -t $task.cpus \\
+            $options.args \\
+            --out-prefix $prefix
+
+        pigz \\
+            --no-name \\
+            -p $task.cpus \\
+            $options.args2 \\
+            megahit_out/*.fa \\
+            megahit_out/intermediate_contigs/*.fa
+
+        cat <<-END_VERSIONS > versions.yml
+        ${getProcessName(task.process)}:
+            ${getSoftwareName(task.process)}: \$(echo \$(megahit -v 2>&1) | sed 's/MEGAHIT v//')
+        END_VERSIONS
+        """
+    }
+}

modules/megahit/meta.yml

@@ -0,0 +1,62 @@
+name: megahit
+description: An ultra-fast metagenomic assembler for large and complex metagenomics
+keywords:
+  - megahit
+  - denovo
+  - assembly
+  - debruijn
+  - metagenomics
+tools:
+  - megahit:
+      description: "An ultra-fast single-node solution for large and complex metagenomics assembly via succinct de Bruijn graph"
+      homepage: https://github.com/voutcn/megahit
+      documentation: https://github.com/voutcn/megahit
+      tool_dev_url: https://github.com/voutcn/megahit
+      doi: "10.1093/bioinformatics/btv033"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information and input single, or paired-end FASTA/FASTQ files (optionally decompressed)
+        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 in gzipped or uncompressed FASTQ or FASTA format.
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - contigs:
+      type: file
+      description: Final final contigs result of the assembly in FASTA format.
+      pattern: "*.contigs.fa.gz"
+  - k_contigs:
+      type: file
+      description: Contigs assembled from the de Bruijn graph of order-K
+      pattern: "k*.contigs.fa.gz"
+  - addi_contigs:
+      type: file
+      description: Contigs assembled after iteratively removing local low coverage unitigs in the de Bruijn graph of order-K
+      pattern: "k*.addi.fa.gz"
+  - local_contigs:
+      type: file
+      description: Contigs of the locally assembled contigs for k=K
+      pattern: "k*.local.fa.gz"
+  - kfinal_contigs:
+      type: file
+      description: Stand-alone contigs for k=K; if local assembly is turned on, the file will be empty
+      pattern: "k*.final.contigs.fa.gz"
+
+authors:
+  - "@jfy133"

tests/config/pytest_modules.yml

@@ -650,6 +650,10 @@ mashtree:
   - modules/mashtree/**
   - tests/modules/mashtree/**
 
+megahit:
+  - modules/megahit/**
+  - tests/modules/megahit/**
+
 metaphlan3:
   - modules/metaphlan3/**
   - tests/modules/metaphlan3/**

tests/modules/megahit/main.nf

@@ -0,0 +1,28 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MEGAHIT } from '../../../modules/megahit/main.nf' addParams( options: [:] )
+
+workflow test_megahit {
+
+    input = [ 
+        [ id:'test', single_end:false ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+            file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
+        ] 
+    ]
+
+    MEGAHIT ( input )
+}
+
+workflow test_megahit_single {
+
+    input = [ 
+        [ id:'test', single_end:true ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+    ]
+
+    MEGAHIT ( input )
+}

tests/modules/megahit/test.yml

@@ -0,0 +1,71 @@
+- name: megahit
+  command: nextflow run ./tests/modules/megahit -entry test_megahit -c tests/config/nextflow.config -process.cpus 1
+  tags:
+    - megahit
+  files:
+    - path: output/megahit/megahit_out/test.contigs.fa.gz
+      md5sum: 8ed114f22130e16df3532d3f6b03e116
+    - path: output/megahit/megahit_out/intermediate_contigs/k21.addi.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k21.contigs.fa.gz
+      md5sum: 4221d45f238045bbdb1eea04e4ce4261
+    - path: output/megahit/megahit_out/intermediate_contigs/k21.final.contigs.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k21.local.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k29.addi.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k29.contigs.fa.gz
+      md5sum: c72aeb242788542af0260098b4d61204
+    - path: output/megahit/megahit_out/intermediate_contigs/k29.final.contigs.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k29.local.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k39.addi.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k39.contigs.fa.gz
+      md5sum: aa188f4c92e69c1a4b396e8f2991236f
+    - path: output/megahit/megahit_out/intermediate_contigs/k39.final.contigs.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k39.local.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+
+- name: megahit_single
+  command: nextflow run ./tests/modules/megahit -entry test_megahit_single -c tests/config/nextflow.config -process.cpus 1
+  tags:
+    - megahit
+  files:
+    - path: output/megahit/megahit_out/test.contigs.fa.gz
+      md5sum: f50352838b778cc67824f631197a8346
+    - path: output/megahit/megahit_out/intermediate_contigs/k21.addi.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k21.contigs.fa.gz
+      md5sum: 61554dc60ba8e95d9c1d9dca8d465bef
+    - path: output/megahit/megahit_out/intermediate_contigs/k21.final.contigs.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k21.local.fa.gz
+      md5sum: b916fc620fdf0d23ef33485352c168b3
+    - path: output/megahit/megahit_out/intermediate_contigs/k29.addi.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k29.contigs.fa.gz
+      md5sum: d916bc564854aa0fabaa5234035aa47b
+    - path: output/megahit/megahit_out/intermediate_contigs/k29.final.contigs.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k29.local.fa.gz
+      md5sum: cccf44441e65913b02fb64eb0835dcc1
+    - path: output/megahit/megahit_out/intermediate_contigs/k39.addi.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k39.contigs.fa.gz
+      md5sum: 4416a9e846ccbeb06b880ac2fdc02925
+    - path: output/megahit/megahit_out/intermediate_contigs/k39.final.contigs.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k39.local.fa.gz
+      md5sum: 590d0a08285226d24f7f984f7b3b4f65
+    - path: output/megahit/megahit_out/intermediate_contigs/k59.addi.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k59.contigs.fa.gz
+      md5sum: 51ef726b87a53b0cbdde762d7973a8a7
+    - path: output/megahit/megahit_out/intermediate_contigs/k59.final.contigs.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a
+    - path: output/megahit/megahit_out/intermediate_contigs/k59.local.fa.gz
+      md5sum: 7029066c27ac6f5ef18d660d5741979a