module: MALT/BUILD (#645)

* Specify more guidelines on input channels

* Linting

* Updates based on code review

* Update README.md

* Fix broken sentence

* Start MALT-build

* Start MALT build (missing meta files and outputs specS)

* Local tests

* Correct test map_type

* Finished module, just waiting for UNZIP module to finalise tests

* Correct tests in preparation for Unzip

* Ouptut log file too

* Update meta.yml

* Rename log file

* Rename log file

* Remove debugging stuff

* Add Unzip module

* Linting update

* Linting update

* Fix input db

* Fix db file in cmd

* Update modules/malt/build/main.nf

* Update modules/malt/build/main.nf

* Update main.nf

.nf-core.yml

@@ -7,3 +7,4 @@ bump-versions:
   rseqc/inferexperiment: False
   rseqc/innerdistance: False
   sortmerna: False
+  malt/build: False

modules/malt/build/functions.nf

@@ -0,0 +1,68 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions  = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_meta) {
+            def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+            for (key in key_list) {
+                if (args.meta && key instanceof String) {
+                    def path = key
+                    if (args.meta.containsKey(key)) {
+                        path = args.meta[key] instanceof Boolean ? "${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/malt/build/main.nf

@@ -0,0 +1,58 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process MALT_BUILD {
+
+    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:[:], publish_by_meta:[]) }
+
+    // Do not **auto-bump** due to problem with change of version numbering between 0.4.1 and 0.5.2
+    // (originally 0.4.1 was listed as 0.41, so is always selected as 'latest' even though it is not!)
+    conda (params.enable_conda ? "bioconda::malt=0.5.2" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/malt:0.5.2--0"
+    } else {
+        container "quay.io/biocontainers/malt:0.5.2--0"
+    }
+
+    input:
+    path fastas
+    val seq_type
+    path gff
+    path map_db
+
+    output:
+    path "malt_index/"   , emit: index
+    path "*.version.txt" , emit: version
+    path "malt-build.log", emit: log
+
+    script:
+    def software = getSoftwareName(task.process)
+    def avail_mem = 6
+    if (!task.memory) {
+        log.info '[MALT_BUILD] Available memory not known - defaulting to 6GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+    def igff = gff ? "-igff ${gff}" : ""
+
+    """
+    malt-build \\
+        -J-Xmx${avail_mem}g \\
+        -v \\
+        --input ${fastas.join(' ')} \\
+        -s $seq_type \\
+        $igff \\
+        -d 'malt_index/' \\
+        -t ${task.cpus} \\
+        $options.args \\
+        -mdb ${map_db}/*.db |&tee malt-build.log
+
+    malt-build --help |& tail -n 3 | head -n 1 | cut -f 2 -d'(' | cut -f 1 -d ',' | cut -d ' ' -f 2 > ${software}.version.txt
+    """
+}

modules/malt/build/meta.yml

@@ -0,0 +1,55 @@
+name: malt_build
+description: MALT, an acronym for MEGAN alignment tool, is a sequence alignment and analysis tool designed for processing high-throughput sequencing data, especially in the context of metagenomics.
+keywords:
+  - malt
+  - alignment
+  - metagenomics
+  - ancient DNA
+  - aDNA
+  - palaeogenomics
+  - archaeogenomics
+  - microbiome
+  - database
+tools:
+  - malt:
+      description: A tool for mapping metagenomic data
+      homepage: https://www.wsi.uni-tuebingen.de/lehrstuehle/algorithms-in-bioinformatics/software/malt/
+      documentation: https://software-ab.informatik.uni-tuebingen.de/download/malt/manual.pdf
+      tool_dev_url: None
+      doi: "10.1038/s41559-017-0446-6"
+      licence: ['GPL v3']
+
+input:
+  - fastas:
+      type: file
+      description: Directory of, or FASTA reference files for indexing
+      pattern: "*/|*.fasta"
+  - seq_type:
+      type: string
+      description: Type of input data
+      pattern: "DNA|Protein"
+  - gff:
+      type: file
+      description: Directory of, or GFF3 files of input FASTA files
+      pattern: "*/|*.gff|*.gff3"
+  - map_db:
+      type: file
+      description: MEGAN .db file from https://software-ab.informatik.uni-tuebingen.de/download/megan6/welcome.html
+      pattern:
+
+output:
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+  - index:
+      type: directory
+      description: Directory containing MALT database index directory
+      pattern: "malt_index/"
+  - log:
+      type: file
+      description: Log file from STD out of malt-build
+      pattern: "malt-build.log"
+
+authors:
+  - "@jfy133"

tests/config/pytest_modules.yml

@@ -474,6 +474,10 @@ lofreq/indelqual:
   - modules/lofreq/indelqual/**
   - tests/modules/lofreq/indelqual/**
 
+malt/build:
+  - modules/malt/build/**
+  - tests/modules/malt/build_test/**
+
 mash/sketch:
   - modules/mash/sketch/**
   - tests/modules/mash/sketch/**

tests/modules/malt/build

@@ -0,0 +1 @@
+build_test/

tests/modules/malt/build_test/main.nf

@@ -0,0 +1,26 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { UNZIP } from '../../../../modules/unzip/main.nf' addParams( options: [:] )
+include { MALT_BUILD } from '../../../../modules/malt/build/main.nf' addParams( options: [:] )
+
+workflow test_malt_build {
+    fastas = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    seq_type = "DNA"
+    gff = []
+    map_db = file("https://software-ab.informatik.uni-tuebingen.de/download/megan6/megan-nucl-Jan2021.db.zip", checkIfExists: true)
+
+    UNZIP ( map_db )
+    MALT_BUILD ( fastas, seq_type, gff, UNZIP.out.unzipped_archive )
+}
+
+workflow test_malt_build_gff {
+    fastas = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    seq_type = "DNA"
+    gff = file(params.test_data['sarscov2']['genome']['genome_gff3'], checkIfExists: true)
+    map_db = file("https://software-ab.informatik.uni-tuebingen.de/download/megan6/megan-nucl-Jan2021.db.zip", checkIfExists: true)
+
+    UNZIP ( map_db )
+    MALT_BUILD ( fastas, seq_type, gff, UNZIP.out.unzipped_archive )
+}

tests/modules/malt/build_test/test.yml

@@ -0,0 +1,48 @@
+- name: malt build
+  command: nextflow run ./tests/modules/malt/build_test -entry test_malt_build -c tests/config/nextflow.config
+  tags:
+    - malt
+    - malt/build
+  files:
+    - path: output/malt/malt_index/index0.idx
+      md5sum: 1954f2c00b418d00112829b0a6adb8ce
+    - path: output/malt/malt_index/ref.db
+      md5sum: 772a09aeb162515485b037604399f2bd
+    - path: output/malt/malt_index/ref.idx
+      md5sum: 7dea362b3fac8e00956a4952a3d4f474
+    - path: output/malt/malt_index/ref.inf
+      md5sum: b146842067cf278ef1d23e6c2e7c0c35
+    - path: output/malt/malt_index/table0.db
+    - path: output/malt/malt_index/table0.idx
+    - path: output/malt/malt_index/taxonomy.idx
+      md5sum: bb335e7c378a5bd85761b6eeed16d984
+    - path: output/malt/malt_index/taxonomy.map
+      md5sum: ae2ea08b2119eba932a9cbcd9e634917
+    - path: output/malt/malt_index/taxonomy.tre
+      md5sum: 511ec8ff4fd8aaa20d59b5a91ed4e852
+- name: malt build gff
+  command: nextflow run ./tests/modules/malt/build_test -entry test_malt_build_gff -c tests/config/nextflow.config
+  tags:
+    - malt
+    - malt/build
+  files:
+    - path: output/malt/malt_index/aadd.dbx
+      md5sum: 4e2ed57e713d5372bd09350f447cdf53
+    - path: output/malt/malt_index/aadd.idx
+      md5sum: 0994061bc8673ebd283fa6546c3dd12c
+    - path: output/malt/malt_index/index0.idx
+      md5sum: 1954f2c00b418d00112829b0a6adb8ce
+    - path: output/malt/malt_index/ref.db
+      md5sum: 772a09aeb162515485b037604399f2bd
+    - path: output/malt/malt_index/ref.idx
+      md5sum: 7dea362b3fac8e00956a4952a3d4f474
+    - path: output/malt/malt_index/ref.inf
+      md5sum: b146842067cf278ef1d23e6c2e7c0c35
+    - path: output/malt/malt_index/table0.db
+    - path: output/malt/malt_index/table0.idx
+    - path: output/malt/malt_index/taxonomy.idx
+      md5sum: bb335e7c378a5bd85761b6eeed16d984
+    - path: output/malt/malt_index/taxonomy.map
+      md5sum: ae2ea08b2119eba932a9cbcd9e634917
+    - path: output/malt/malt_index/taxonomy.tre
+      md5sum: 511ec8ff4fd8aaa20d59b5a91ed4e852