add seqsero2 module (#1016)

* add seqsero2 module

* correct lint errors

* Update modules/seqsero2/main.nf

Co-authored-by: Sébastien Guizard <sguizard@ed.ac.uk>

* set output directory

Co-authored-by: Sébastien Guizard <sguizard@ed.ac.uk>

modules/seqsero2/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+    // Do not publish versions.yml unless running from pytest workflow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/seqsero2/main.nf

@@ -0,0 +1,45 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process SEQSERO2 {
+    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::seqsero2=1.2.1" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/seqsero2:1.2.1--py_0"
+    } else {
+        container "quay.io/biocontainers/seqsero2:1.2.1--py_0"
+    }
+
+    input:
+    tuple val(meta), path(seqs)
+
+    output:
+    tuple val(meta), path("results/*_log.txt")   , emit: log
+    tuple val(meta), path("results/*_result.tsv"), emit: tsv
+    tuple val(meta), path("results/*_result.txt"), emit: txt
+    path "versions.yml"                          , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    SeqSero2_package.py \\
+        $options.args \\
+        -d results/ \\
+        -n $prefix \\
+        -p $task.cpus \\
+        -i $seqs
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( echo \$( SeqSero2_package.py --version 2>&1) | sed 's/^.*SeqSero2_package.py //' )
+    END_VERSIONS
+    """
+}

modules/seqsero2/meta.yml

@@ -0,0 +1,52 @@
+name: seqsero2
+description: Salmonella serotype prediction from reads and assemblies
+keywords:
+  - fasta
+  - fastq
+  - salmonella
+  - sertotype
+tools:
+  - seqsero2:
+      description: Salmonella serotype prediction from genome sequencing data
+      homepage: https://github.com/denglab/SeqSero2
+      documentation: https://github.com/denglab/SeqSero2
+      tool_dev_url: https://github.com/denglab/SeqSero2
+      doi: "10.1128/AEM.01746-19"
+      licence: ['GPL v2']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - seqs:
+      type: file
+      description: FASTQ or FASTA formated sequences
+      pattern: "*.{fq.gz,fastq.gz,fna.gz,fna,fasta.gz,fasta,fa.gz,fa}"
+
+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: A log of serotype antigen results
+      pattern: "*_log.txt"
+  - tsv:
+      type: file
+      description: Tab-delimited summary of the SeqSero2 results
+      pattern: "*_result.tsv"
+  - txt:
+      type: file
+      description: Detailed summary of the SeqSero2 results
+      pattern: "*_result.txt"
+
+authors:
+  - "@rpetit3"

tests/config/pytest_modules.yml

@@ -446,14 +446,14 @@ gatk4/fastqtosam:
   - modules/gatk4/fastqtosam/**
   - tests/modules/gatk4/fastqtosam/**
 
-gatk4/genomicsdbimport:
-  - modules/gatk4/genomicsdbimport/**
-  - tests/modules/gatk4/genomicsdbimport/**
-
 gatk4/filtermutectcalls:
   - modules/gatk4/filtermutectcalls/**
   - tests/modules/gatk4/filtermutectcalls/**
 
+gatk4/genomicsdbimport:
+  - modules/gatk4/genomicsdbimport/**
+  - tests/modules/gatk4/genomicsdbimport/**
+
 gatk4/getpileupsummaries:
   - modules/gatk4/getpileupsummaries/**
   - tests/modules/gatk4/getpileupsummaries/**
@@ -1083,6 +1083,10 @@ seqkit/split2:
   - modules/seqkit/split2/**
   - tests/modules/seqkit/split2/**
 
+seqsero2:
+  - modules/seqsero2/**
+  - tests/modules/seqsero2/**
+
 seqtk/mergepe:
   - modules/seqtk/mergepe/**
   - tests/modules/seqtk/mergepe/**

tests/modules/seqsero2/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SEQSERO2 } from '../../../modules/seqsero2/main.nf' addParams( options: [args: '-m k -t 4'] )
+
+workflow test_seqsero2 {
+    
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
+
+    SEQSERO2 ( input )
+}

tests/modules/seqsero2/test.yml

@@ -0,0 +1,11 @@
+- name: seqsero2 test_seqsero2
+  command: nextflow run tests/modules/seqsero2 -entry test_seqsero2 -c tests/config/nextflow.config
+  tags:
+    - seqsero2
+  files:
+    - path: output/seqsero2/results/SeqSero_log.txt
+      md5sum: d00242dfa734b5abb3622a6048f0b4fb
+    - path: output/seqsero2/results/SeqSero_result.tsv
+      contains: ['Sample', 'Predicted', 'Note']
+    - path: output/seqsero2/results/SeqSero_result.txt
+      contains: ['Sample', 'Predicted', 'Note']