new module: gubbins (#377)

* new gubbins module

* new gubbins module

* new gubbins module

* Update software/gubbins/main.nf

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

* Update software/gubbins/main.nf

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

* Update software/gubbins/main.nf

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

* Update software/gubbins/meta.yml

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

* new gubbins module

* new gubbins module

* new gubbins module

* new gubbins module

* new gubbins module

* new gubbins module

* new gubbins module

* Update tests/config/test_data.config

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

* Update tests/software/gubbins/main.nf

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

* new gubbins module

* new gubbins module

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

software/gubbins/functions.nf

@@ -0,0 +1,60 @@
+/*
+ * -----------------------------------------------------
+ *  Utility functions used in nf-core DSL2 module files
+ * -----------------------------------------------------
+ */
+
+/*
+ * Extract name of software tool from process name using $task.process
+ */
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+/*
+ * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+ */
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args          = args.args ?: ''
+    options.args2         = args.args2 ?: ''
+    options.args3         = args.args3 ?: ''
+    options.publish_by_id = args.publish_by_id ?: false
+    options.publish_dir   = args.publish_dir ?: ''
+    options.publish_files = args.publish_files
+    options.suffix        = args.suffix ?: ''
+    return options
+}
+
+/*
+ * Tidy up and join elements of a list to return a path string
+ */
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }  // Remove empty entries
+    paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+/*
+ * Function to save/publish module results
+ */
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_id) {
+            path_list.add(args.publish_id)
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

software/gubbins/main.nf

@@ -0,0 +1,44 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process GUBBINS {
+    label 'process_medium'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:'') }
+
+    conda (params.enable_conda ? "bioconda::gubbins=2.4.1" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/gubbins:2.4.1--py38h197edbe_1"
+    } else {
+        container "quay.io/biocontainers/gubbins:2.4.1--py38h197edbe_1"
+    }
+
+    input:
+    path alignment
+
+    output:
+    path "*.fasta"                          , emit: fasta
+    path "*.gff"                            , emit: gff
+    path "*.vcf"                            , emit: vcf
+    path "*.csv"                            , emit: stats
+    path "*.phylip"                         , emit: phylip
+    path "*.recombination_predictions.embl" , emit: embl_predicted
+    path "*.branch_base_reconstruction.embl", emit: embl_branch
+    path "*.final_tree.tre"                 , emit: tree
+    path "*.node_labelled.final_tree.tre"   , emit: tree_labelled
+    path "*.version.txt"                    , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    """
+    run_gubbins.py \\
+        --threads $task.cpus \\
+        $options.args \\
+        $alignment
+    echo \$(run_gubbins.py --version 2>&1) > ${software}.version.txt
+    """
+}

software/gubbins/meta.yml

@@ -0,0 +1,61 @@
+name: gubbins
+description: Gubbins (Genealogies Unbiased By recomBinations In Nucleotide Sequences) is an algorithm that iteratively identifies
+            loci containing elevated densities of base substitutions while concurrently constructing a phylogeny based on the
+            putative point mutations outside of these regions.
+keywords:
+  - recombination
+  - alignment
+tools:
+  - gubbins:
+      description: Rapid phylogenetic analysis of large samples of recombinant bacterial whole genome sequences using Gubbins.
+      homepage: https://sanger-pathogens.github.io/gubbins/
+      documentation: https://sanger-pathogens.github.io/gubbins/
+input:
+  - alignment:
+      type: file
+      description: fasta alignment file
+      pattern: "*.{fasta,fas,fa,aln}"
+output:
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+  - fasta:
+      type: file
+      description: Filtered variant alignment in fasta format
+      pattern: "*.{fasta}"
+  - embl_predicted:
+      type: file
+      description: Recombination predictions in embl format
+      pattern: "*.{recombination_predictions.embl}"
+  - gff:
+      type: file
+      description: Recombination predictions in gff format
+      pattern: "*.{gff}"
+  - embl_branch:
+      type: file
+      description: Branch base reconstruction
+      pattern: "*.{branch_base_reconstruction.embl}"
+  - vcf:
+      type: file
+      description: SNP distribution
+      pattern: "*.{vcf}"
+  - stats:
+      type: file
+      description: Per branch statistics
+      pattern: "*.{csv}"
+  - phylip:
+      type: file
+      description: Filtered variant alignment in phylip format
+      pattern: "*.{phylip}"
+  - tree:
+      type: file
+      description: Recombination removed RAxML phylogenetic tree
+      pattern: "*.{final_tree.tre}"
+  - tree_labelled:
+      type: file
+      description: Recombination removed RAxML phylogenetic tree (nodes labelled)
+      pattern: "*.{node_labelled.final_tree.tre}"
+authors:
+  - "@avantonder"
+

tests/config/pytest_software.yml

@@ -246,6 +246,10 @@ gffread:
   - software/gffread/**
   - tests/software/gffread/**
 
+gubbins:
+  - software/gubbins/**
+  - tests/software/gubbins/**
+
 gunzip:
   - software/gunzip/**
   - tests/software/gunzip/**

tests/config/test_data.config

@@ -25,6 +25,8 @@ params {
                 kraken2_tar_gz                            = "${test_data_dir}/genomics/sarscov2/genome/db/kraken2.tar.gz"
                 
                 test_wig_gz                               = "${test_data_dir}/genomics/sarscov2/genome/gcwiggle/test.wig.gz"
+
+                test_fas                                  = "${test_data_dir}/genomics/sarscov2/genome/alignment/test.fas"
             }
             'illumina' {
                 test_single_end_bam                       = "${test_data_dir}/genomics/sarscov2/illumina/bam/test_single_end.bam"

tests/software/gubbins/main.nf

@@ -0,0 +1,11 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GUBBINS } from '../../../software/gubbins/main.nf' addParams( options: [:] )
+
+workflow test_gubbins { 
+    input = file(params.test_data['sarscov2']['genome']['test_fas'], checkIfExists: true)
+
+    GUBBINS ( input )
+}

tests/software/gubbins/test.yml

@@ -0,0 +1,23 @@
+- name: gubbins
+  command: nextflow run ./tests/software/gubbins -entry test_gubbins -c tests/config/nextflow.config
+  tags:
+    - gubbins
+  files:
+    - path: output/gubbins/test.filtered_polymorphic_sites.fasta
+      md5sum: c9dff2294307eb2200a6e19efce47796
+    - path: output/gubbins/test.recombination_predictions.embl
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/gubbins/test.recombination_predictions.gff
+      md5sum: a2ca9c119674f4d121a8f78e4078fe05
+    - path: output/gubbins/test.branch_base_reconstruction.embl
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/gubbins/test.summary_of_snp_distribution.vcf
+      md5sum: afee50e92fb919a5df487fbda0b9dbb5
+    - path: output/gubbins/test.per_branch_statistics.csv
+      md5sum: 0f364b5e0b01a6be9b6a4407658ab25f
+    - path: output/gubbins/test.filtered_polymorphic_sites.phylip
+      md5sum: 85db9d0896cfec34a73641496b7498bb
+    - path: output/gubbins/test.final_tree.tre
+      md5sum: dce7164a0c69bb3d642a419907364aa3
+    - path: output/gubbins/test.node_labelled.final_tree.tre
+      md5sum: beef5ce05aca4598bb3f42caf126e045