add bakta module (#1085)

* add bakta module

* Update main.nf

* Update main.nf

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

modules/bakta/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+    // Do not publish versions.yml unless running from pytest workflow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/bakta/main.nf

@@ -0,0 +1,77 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process BAKTA {
+    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), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::bakta=1.2.2" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/bakta:1.2.2--pyhdfd78af_0"
+    } else {
+        container "quay.io/biocontainers/bakta:1.2.2--pyhdfd78af_0"
+    }
+
+    input:
+    tuple val(meta), path(fasta)
+    path db
+    path proteins
+    path prodigal_tf
+
+    output:
+    tuple val(meta), path("${prefix}.embl")             , emit: embl
+    tuple val(meta), path("${prefix}.faa")              , emit: faa
+    tuple val(meta), path("${prefix}.ffn")              , emit: ffn
+    tuple val(meta), path("${prefix}.fna")              , emit: fna
+    tuple val(meta), path("${prefix}.gbff")             , emit: gbff
+    tuple val(meta), path("${prefix}.gff3")             , emit: gff
+    tuple val(meta), path("${prefix}.hypotheticals.tsv"), emit: hypotheticals_tsv
+    tuple val(meta), path("${prefix}.hypotheticals.faa"), emit: hypotheticals_faa
+    tuple val(meta), path("${prefix}.tsv")              , emit: tsv
+    path "versions.yml"                                 , emit: versions
+
+    script:
+    prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def proteins_opt = proteins ? "--proteins ${proteins[0]}" : ""
+    def prodigal_opt = prodigal_tf ? "--prodigal-tf ${prodigal_tf[0]}" : ""
+    """
+    bakta \\
+        $options.args \\
+        --threads $task.cpus \\
+        --prefix ${prefix} \\
+        --db $db \\
+        $proteins_opt \\
+        $prodigal_tf \\
+        $fasta
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( echo \$(bakta --version 2>&1) | sed 's/^.*bakta //' )
+    END_VERSIONS
+    """
+
+    stub:
+    prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    touch ${prefix}.embl
+    touch ${prefix}.faa
+    touch ${prefix}.ffn
+    touch ${prefix}.fna
+    touch ${prefix}.gbff
+    touch ${prefix}.gff3
+    touch ${prefix}.hypotheticals.tsv
+    touch ${prefix}.hypotheticals.faa
+    touch ${prefix}.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( echo \$(bakta --version 2>&1) | sed 's/^.*bakta //' )
+    END_VERSIONS
+    """
+}

modules/bakta/meta.yml

@@ -0,0 +1,85 @@
+name: bakta
+description: Rapid annotation of bacterial genomes & plasmids.
+keywords:
+  - annotation
+  - fasta
+  - prokaryote
+tools:
+  - bakta:
+      description: Rapid & standardized annotation of bacterial genomes & plasmids.
+      homepage: https://github.com/oschwengers/bakta
+      documentation: https://github.com/oschwengers/bakta
+      tool_dev_url: https://github.com/oschwengers/bakta
+      doi: "10.1099/mgen.0.000685"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: |
+        FASTA file to be annotated. Has to contain at least a non-empty string dummy value.
+  - db:
+      type: file
+      description: |
+        Path to the Bakta database
+  - proteins:
+      type: file
+      description: FASTA file of trusted proteins to first annotate from (optional)
+  - prodigal_tf:
+      type: file
+      description: Training file to use for Prodigal (optional)
+
+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"
+  - tsv:
+      type: file
+      description: annotations as simple human readble tab separated values
+      pattern: "*.tsv"
+  - gff:
+      type: file
+      description: annotations & sequences in GFF3 format
+      pattern: "*.gff3"
+  - gbff:
+      type: file
+      description: annotations & sequences in (multi) GenBank format
+      pattern: "*.gbff"
+  - embl:
+      type: file
+      description: annotations & sequences in (multi) EMBL format
+      pattern: "*.embl"
+  - fna:
+      type: file
+      description: replicon/contig DNA sequences as FASTA
+      pattern: "*.fna"
+  - faa:
+      type: file
+      description: CDS/sORF amino acid sequences as FASTA
+      pattern: "*.faa"
+  - ffn:
+      type: file
+      description: feature nucleotide sequences as FASTA
+      pattern: "*.ffn"
+  - hypotheticals_tsv:
+      type: file
+      description: further information on hypothetical protein CDS as simple human readble tab separated values
+      pattern: "*.hypotheticals.tsv"
+  - hypotheticals_faa:
+      type: file
+      description: hypothetical protein CDS amino acid sequences as FASTA
+      pattern: "*.hypotheticals.faa"
+
+authors:
+  - "@rpetit3"

tests/config/pytest_modules.yml

@@ -38,6 +38,10 @@ ataqv/ataqv:
   - modules/ataqv/ataqv/**
   - tests/modules/ataqv/ataqv/**
 
+bakta:
+  - modules/bakta/**
+  - tests/modules/bakta/**
+
 bamaligncleaner:
   - modules/bamaligncleaner/**
   - tests/modules/bamaligncleaner/**

tests/modules/bakta/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BAKTA } from '../../../modules/bakta/main.nf' addParams( options: [:] )
+
+workflow test_bakta {
+    
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
+
+    BAKTA ( input, [], [], [] )
+}

tests/modules/bakta/test.yml

@@ -0,0 +1,25 @@
+## TODO nf-core: Please run the following command to build this file:
+#                nf-core modules create-test-yml bakta
+- name: bakta
+  command: nextflow run ./tests/modules/bakta -entry test_bakta -c tests/config/nextflow.config -stub-run
+  tags:
+    - bakta
+  files:
+    - path: output/bakta/test.embl
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/bakta/test.faa
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/bakta/test.ffn
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/bakta/test.fna
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/bakta/test.gbff
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/bakta/test.gff3
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/bakta/test.hypotheticals.tsv
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/bakta/test.hypotheticals.faa
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/bakta/test.tsv
+      md5sum: d41d8cd98f00b204e9800998ecf8427e