new module fargene (#1068)

* new module fargene

* Update main.nf

* Update modules/fargene/main.nf

* Update main.nf

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

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+    // Do not publish versions.yml unless running from pytest workflow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

@@ -0,0 +1,63 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+def VERSION = '0.1'
+
+process FARGENE {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${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::fargene=0.1" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/fargene:0.1--py27h21c881e_4"
+    } else {
+        container "quay.io/biocontainers/fargene:0.1--py27h21c881e_4"
+    }
+
+    input:
+    // input may be fasta (for genomes or longer contigs) or paired-end fastq (for metagenome), the latter in addition with --meta flag
+    tuple val(meta), path(input)
+    val hmm_model
+
+    output:
+    path "*.log"                                                                                 , emit: log
+    path "${prefix}/results_summary.txt"                                                         , emit: txt
+    tuple val(meta), path("${prefix}/hmmsearchresults/*.out")                                    , optional: true, emit: hmm
+    tuple val(meta), path("${prefix}/predictedGenes/predicted-orfs.fasta")                       , optional: true, emit: orfs
+    tuple val(meta), path("${prefix}/predictedGenes/predicted-orfs-amino.fasta")                 , optional: true, emit: orfs_amino
+    tuple val(meta), path("${prefix}/predictedGenes/retrieved-contigs.fasta")                    , optional: true, emit: contigs
+    tuple val(meta), path("${prefix}/predictedGenes/retrieved-contigs-peptides.fasta")           , optional: true, emit: contigs_pept
+    tuple val(meta), path("${prefix}/predictedGenes/*filtered.fasta")                            , optional: true, emit: filtered
+    tuple val(meta), path("${prefix}/predictedGenes/*filtered-peptides.fasta")                   , optional: true, emit: filtered_pept
+    tuple val(meta), path("${prefix}/retrievedFragments/all_retrieved_*.fastq")                  , optional: true, emit: fragments
+    tuple val(meta), path("${prefix}/retrievedFragments/retrievedFragments/trimmedReads/*.fasta"), optional: true, emit: trimmed
+    tuple val(meta), path("${prefix}/spades_assembly/*")                                         , optional: true, emit: spades
+    tuple val(meta), path("${prefix}/tmpdir/*.fasta")                                            , optional: true, emit: metagenome
+    tuple val(meta), path("${prefix}/tmpdir/*.out")                                              , optional: true, emit: tmp
+    path "versions.yml"                                                                          , emit: versions
+
+    script:
+    prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    gzip \\
+        -cdf $input \\
+        > unziped.fa |
+        fargene \\
+            $options.args \\
+            -p $task.cpus \\
+            -i unziped.fa \\
+            --hmm-model $hmm_model \\
+            -o $prefix
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$(echo $VERSION)
+    END_VERSIONS
+    """
+}

modules/fargene/meta.yml

@@ -0,0 +1,101 @@
+name: fargene
+description: tool that takes either fragmented metagenomic data or longer sequences as input and predicts and delivers full-length antiobiotic resistance genes as output.
+keywords:
+  - antibiotic resistance genes
+  - ARGs
+  - identifier
+  - metagenomic
+  - contigs
+tools:
+  - fargene:
+      description: Fragmented Antibiotic Resistance Gene Identifier takes either fragmented metagenomic data or longer sequences as input and predicts and delivers full-length antiobiotic resistance genes as output
+      homepage: https://github.com/fannyhb/fargene
+      documentation: https://github.com/fannyhb/fargene
+      tool_dev_url: https://github.com/fannyhb/fargene
+      doi: ""
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: fasta or paired-end fastq file containing either genomes or longer contigs as nucleotide or protein sequences (fasta) or fragmented metagenomic reads (fastq)
+      pattern: "*.{fasta}"
+  - hmm_model:
+      type: string
+      description: name of custom hidden markov model to be used [pre-defined class_a, class_b_1_2, class_b_3, class_c, class_d_1, class_d_2, qnr, tet_efflux, tet_rpg, tet_enzyme]
+
+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"
+  - log:
+      type: file
+      description: log file
+      pattern: "*.{log}"
+  - txt:
+      type: file
+      description: analysis summary text file
+      pattern: "*.{txt}"
+  - hmm:
+      type: file
+      description: output from hmmsearch
+      pattern: "*.{out}"
+  - orfs:
+      type: file
+      description: open reading frames (ORFs)
+      pattern: "*.{fasta}"
+  - orfs_amino:
+      type: file
+      description: protein translation of open reading frames (ORFs)
+      pattern: "*.{fasta}"
+  - contigs:
+      type: file
+      description: (complete) contigs that passed the final full-length classification
+      pattern: "*.{fasta}"
+  - contigs_pept:
+      type: file
+      description: parts of the contigs that passed the final classification step that aligned with the HMM, as amino acid sequences
+      pattern: "*.{fasta}"
+  - filtered:
+      type: file
+      description: sequences that passed the final classification step, but only the parts that where predicted by the HMM to be part of the gene
+      pattern: "*.{fasta}"
+  - filtered_pept:
+      type: file
+      description: sequences from filtered.fasta, translated in the same frame as the gene is predicted to be located
+      pattern: "*.{fasta}"
+  - fragments:
+      type: file
+      description: All quality controlled retrieved fragments that were classified as positive, together with its read-pair, gathered in two files
+      pattern: "*.{fastq}"
+  - trimmed:
+      type: file
+      description: The quality controlled retrieved fragments from each input file.
+      pattern: "*.{fasta}"
+  - spades:
+      type: directory
+      description: The output from the SPAdes assembly
+      pattern: "spades_assembly"
+  - metagenome:
+      type: file
+      description: The FASTQ to FASTA converted input files from metagenomic reads.
+      pattern: "*.{fasta}"
+  - tmp:
+      type: file
+      description: The from FASTQ to FASTA converted input files and their translated input sequences. Are only saved if option --store-peptides is used.
+      pattern: "*.{fasta}"
+
+
+authors:
+  - "@louperelo"

tests/config/pytest_modules.yml

@@ -390,6 +390,10 @@ expansionhunter:
   - modules/expansionhunter/**
   - tests/modules/expansionhunter/**
 
+fargene:
+  - modules/fargene/**
+  - tests/modules/fargene/**
+
 fastani:
   - modules/fastani/**
   - tests/modules/fastani/**

tests/modules/fargene/main.nf

@@ -0,0 +1,14 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { FARGENE } from '../../../modules/fargene/main.nf' addParams( options: [:] )
+
+workflow test_fargene {
+    
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['bacteroides_fragilis']['illumina']['test1_contigs_fa_gz'], checkIfExists: true) ]
+    hmm_model = 'class_a'
+
+    FARGENE ( input, hmm_model )
+}

tests/modules/fargene/test.yml

@@ -0,0 +1,12 @@
+- name: fargene
+  command: nextflow run tests/modules/fargene -entry test_fargene -c tests/config/nextflow.config
+  tags:
+    - fargene
+  files:
+    - path: output/fargene/fargene_analysis.log
+    - path: output/fargene/test/hmmsearchresults/unziped-class_A-hmmsearched.out
+    - path: output/fargene/test/results_summary.txt
+      md5sum: 690d351cfc52577263ef4cfab1c81f50
+    - path: output/fargene/test/tmpdir/tmp.out
+    - path: output/fargene/test/tmpdir/unziped-positives.out
+      md5sum: d41d8cd98f00b204e9800998ecf8427e