add pirate module (#777)

* new module pirate

* remove md5 check for non reproducible binary files

* get those to-dos out

* Update main.nf

* Update meta.yml

* Apply suggestions from code review

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

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+    // Do not publish versions.yml unless running from pytest workflow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

@@ -0,0 +1,43 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process PIRATE {
+    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::pirate=1.0.4" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/pirate%3A1.0.4--hdfd78af_1"
+    } else {
+        container "quay.io/biocontainers/pirate:1.0.4--hdfd78af_1"
+    }
+
+    input:
+    tuple val(meta), path(gff)
+
+    output:
+    tuple val(meta), path("results/*")                                   , emit: results
+    tuple val(meta), path("results/core_alignment.fasta"), optional: true, emit: aln
+    path "versions.yml"                                                  , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    PIRATE \\
+        $options.args \\
+        --threads $task.cpus \\
+        --input ./ \\
+        --output results/
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$( echo \$( PIRATE --version 2>&1) | sed 's/PIRATE //' )
+    END_VERSIONS
+    """
+}

modules/pirate/meta.yml

@@ -0,0 +1,47 @@
+name: pirate
+description: Pangenome toolbox for bacterial genomes
+keywords:
+  - gff
+  - pan-genome
+  - alignment
+tools:
+  - pirate:
+      description: Pangenome analysis and threshold evaluation toolbox
+      homepage: https://github.com/SionBayliss/PIRATE
+      documentation: https://github.com/SionBayliss/PIRATE/wiki
+      tool_dev_url: https://github.com/SionBayliss/PIRATE
+      doi: "https://doi.org/10.1093/gigascience/giz119"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - gff:
+      type: file
+      description: A set of GFF3 formatted files
+      pattern: "*.{gff}"
+
+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"
+  - results:
+      type: directory
+      description: Directory containing PIRATE result files
+      pattern: "*/*"
+  - aln:
+      type: file
+      description: Core-genome alignment produced by PIRATE (Optional)
+      pattern: "*.{fasta}"
+
+authors:
+  - "@rpetit3"

tests/config/pytest_modules.yml

@@ -755,6 +755,10 @@ picard/sortsam:
   - modules/picard/sortsam/**
   - tests/modules/picard/sortsam/**
 
+pirate:
+  - modules/pirate/**
+  - tests/modules/pirate/**
+
 plasmidid:
   - modules/plasmidid/**
   - tests/modules/plasmidid/**

tests/modules/pirate/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PIRATE } from '../../../modules/pirate/main.nf' addParams( options: [:] )
+
+workflow test_pirate {
+    
+    input = [ [ id:'test', single_end:false ], // meta map
+              [ file("https://github.com/bactopia/bactopia-tests/raw/main/data/reference/gff/GCF_000292685.gff", checkIfExists: true),
+                file("https://github.com/bactopia/bactopia-tests/raw/main/data/reference/gff/GCF_000298385.gff", checkIfExists: true),
+                file("https://github.com/bactopia/bactopia-tests/raw/main/data/reference/gff/GCF_002849995.gff", checkIfExists: true) ]
+    ]
+
+    PIRATE ( input )
+}

tests/modules/pirate/test.yml

@@ -0,0 +1,98 @@
+- name: pirate test_pirate
+  command: nextflow run tests/modules/pirate -entry test_pirate -c tests/config/nextflow.config
+  tags:
+    - pirate
+  files:
+    - path: output/pirate/results/PIRATE.gene_families.ordered.tsv
+      contains: ['allele_name']
+    - path: output/pirate/results/PIRATE.gene_families.tsv
+      contains: ['allele_name']
+    - path: output/pirate/results/PIRATE.genomes_per_allele.tsv
+      contains: ['g0197']
+    - path: output/pirate/results/PIRATE.log
+      contains: ['PIRATE input options']
+    - path: output/pirate/results/PIRATE.pangenome_summary.txt
+      md5sum: 4551c291bc06b21f984f25c09329ed7d
+    - path: output/pirate/results/PIRATE.unique_alleles.tsv
+      contains: ['allele_name']
+    - path: output/pirate/results/binary_presence_absence.fasta
+      contains: ['GCF_000292685']
+    - path: output/pirate/results/binary_presence_absence.nwk
+      md5sum: 5b5d86bf97d97de37bb9db514abb7762
+    - path: output/pirate/results/cluster_alleles.tab
+      contains: ['g0001']
+    - path: output/pirate/results/co-ords/GCF_000292685.co-ords.tab
+      md5sum: d5ca0f06ca7ea1f5486683d5859bc9b8
+    - path: output/pirate/results/co-ords/GCF_000298385.co-ords.tab
+      md5sum: a24d6048b3074242bb558c7fa27a8b03
+    - path: output/pirate/results/co-ords/GCF_002849995.co-ords.tab
+      md5sum: 0c08228585f4fa95686e9b025e0fe9c1
+    - path: output/pirate/results/genome2loci.tab
+      md5sum: bbcea5bfcdcafe14a9aa7261c8e931b8
+    - path: output/pirate/results/genome_list.txt
+      md5sum: 6534b1635c258ad92b829077addc1ff5
+    - path: output/pirate/results/link_clusters.log
+      contains: ['parsing paralog file']
+    - path: output/pirate/results/loci_list.tab
+      contains: ['GCF_000298385_00242']
+    - path: output/pirate/results/loci_paralog_categories.tab
+      md5sum: 6404d2a32526a398f42d7da768a389bd
+    - path: output/pirate/results/modified_gffs/GCF_000292685.gff
+      md5sum: 2b73bda2f84dc634303dc90e641040ca
+    - path: output/pirate/results/modified_gffs/GCF_000298385.gff
+      md5sum: b1a9d6557d47e09249f08a7acdbbd618
+    - path: output/pirate/results/modified_gffs/GCF_002849995.gff
+      md5sum: 68532fc9bb639e6d83c731a069f60cf8
+    - path: output/pirate/results/pan_sequences.fasta
+      md5sum: ed835c77fdb20c36aa9d5208eb7ca0cb
+    - path: output/pirate/results/pangenome.connected_blocks.tsv
+      contains: ['block_number']
+    - path: output/pirate/results/pangenome.edges
+      contains: ['g0259']
+    - path: output/pirate/results/pangenome.gfa
+      contains: ['g0001']
+    - path: output/pirate/results/pangenome.order.tsv
+      contains: ['g0172']
+    - path: output/pirate/results/pangenome.reversed.tsv
+      md5sum: b2396ce09a6e4178761eca6dc7f4434f
+    - path: output/pirate/results/pangenome.syntenic_blocks.tsv
+      contains: ['g0091']
+    - path: output/pirate/results/pangenome.temp
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.50.reclustered.reinflated
+      contains: ['GCF_000298385_00242']
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.60.reclustered.reinflated
+      contains: ['GCF_000298385_00242']
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.70.reclustered.reinflated
+      contains: ['GCF_000298385_00242']
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.80.reclustered.reinflated
+      contains: ['GCF_000298385_00242']
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.90.reclustered.reinflated
+      contains: ['GCF_000298385_00242']
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.95.reclustered.reinflated
+      contains: ['GCF_000298385_00242']
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.98.reclustered.reinflated
+      contains: ['GCF_000298385_00242']
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.blast.output
+      md5sum: 9da25d27684bfcc5488987ab2d1fd3a1
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.cdhit_clusters
+      contains: ['GCF_000298385_00081']
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.core_clusters.tab
+      contains: ['GCF_000298385_00242']
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.mcl_log.txt
+      contains: ['chaos']
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.representative.fasta
+      md5sum: 84668b6c65b57026a17a50b0edd02541
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.representative.fasta.pdb
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.representative.fasta.pot
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.representative.fasta.ptf
+    - path: output/pirate/results/pangenome_iterations/pan_sequences.representative.fasta.pto
+    - path: output/pirate/results/pangenome_log.txt
+      contains: ['Creating pangenome on amino acid']
+    - path: output/pirate/results/paralog_clusters.tab
+      contains: ['g0216']
+    - path: output/pirate/results/representative_sequences.faa
+      contains: ['representative_genome']
+    - path: output/pirate/results/representative_sequences.ffn
+      contains: ['representative_genome']
+    - path: output/pirate/results/split_groups.log
+      contains: ['g0213']