Update shovill module (#337)

* add shovill module

* removed deprecated shovill module

* fix line ending in functions.nf

* fix yaml indentation

* reduce spades memory usage

* update md5sums

* remove non reproducible md5sum

* Update test.yml

Remove last non-reproducible md5sum.

* purely cosmetic order change

* proper process label, improve output readability

Co-authored-by: Florian Wuennemann <flowuenne@gmail.com>

deprecated/shovill/main.nf

@@ -1,20 +0,0 @@
-process shovill {
-
-    tag "$shovill"
-
-    publishDir "${params.outdir}", pattern: '*.fasta', mode: 'copy'
-
-    container "quay.io/biocontainers/shovill:1.0.9--0"
-
-    input:
-    tuple val(sample_id), path(forward), path(reverse)
-
-    output:
-    path "${sample_id}.fasta"
-
-    script:
-    """
-    shovill --R1 ${forward} --R2 ${reverse} --outdir shovill_out
-    mv shovill_out/contigs.fa ${sample_id}.fasta
-    """
-}

deprecated/shovill/meta.yml

@@ -1,30 +0,0 @@
-name: Shovill
-description: Create a bacterial assembly from paired fastq using shovill
-keywords:
-    - Genome Assembly
-    - Bacterial Isolates
-tools:
-    - fastqc:
-        description: |
-            Shovill assembles bacterial isolate genomes from Illumina
-            paired-end reads. Shovill uses the SPAdes genome assembler,
-            providing pre and post-processing to the SPAdes assembly.
-            It also supports SKESA, Velvet and Megahit.
-        homepage: https://github.com/tseemann/shovill
-        documentation: https://github.com/tseemann/shovill/blob/master/README.md
-input:
-    -
-        - sample_id:
-            type: string
-            description: Sample identifier
-        - reads:
-            type: file
-            description: pair of fastq files
-output:
-    -
-        - assembly:
-            type: file
-            description: fasta file
-            pattern: ${sample_id}.fasta
-authors:
-    - "@annacprice"

deprecated/shovill/test/main.nf

@@ -1,17 +0,0 @@
-#!/usr/bin/env nextflow
-
-nextflow.preview.dsl = 2
-
-// import shovill
-include {shovill} from '../main.nf' params(params)
-
-// define input channel
-readsPath = '../../../test-datasets/tools/shovill/input/SRR3609257_{1,2}.fastq.gz'
-Channel
-  .fromFilePairs( "${readsPath}", flat: true )
-  .set{ ch_reads  }
- 
-// main workflow
-workflow {
-    shovill(ch_reads)
-}

deprecated/shovill/test/nextflow.config

@@ -1,5 +0,0 @@
-// docker
-docker.enabled = true
-
-// output directory
-params.outdir = './results'

software/shovill/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/shovill/main.nf

@@ -0,0 +1,47 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process SHOVILL {
+    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), publish_id:meta.id) }
+
+    conda (params.enable_conda ? "bioconda::shovill=1.1.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/shovill:1.1.0--0"
+    } else {
+        container "quay.io/biocontainers/shovill:1.1.0--0"
+    }
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("contigs.fa")                         , emit: contigs
+    tuple val(meta), path("shovill.corrections")                , emit: corrections
+    tuple val(meta), path("shovill.log")                        , emit: log
+    tuple val(meta), path("{skesa,spades,megahit,velvet}.fasta"), emit: raw_contigs
+    tuple val(meta), path("contigs.{fastg,gfa,LastGraph}")      , optional:true, emit: gfa
+    path "*.version.txt"                                        , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def memory = task.memory.toGiga()
+    """
+    shovill \\
+        --R1 ${reads[0]} \\
+        --R2 ${reads[1]} \\
+        $options.args \\
+        --cpus $task.cpus \\
+        --ram $memory \\
+        --outdir ./ \\
+        --force
+
+    echo \$(shovill --version 2>&1) | sed 's/^.*shovill //'  > ${software}.version.txt
+    """
+}

software/shovill/meta.yml

@@ -0,0 +1,59 @@
+name: shovill
+## TODO nf-core: Add a description of the module and list keywords
+description: Assemble bacterial isolate genomes from Illumina paired-end reads
+keywords:
+  - bacterial
+  - assembly
+  - illumina
+
+tools:
+  - shovill:
+      ## TODO nf-core: Add a description and other details for the software below
+      description: Microbial assembly pipeline for Illumina paired-end reads
+      homepage: https://github.com/tseemann/shovill
+      documentation: https://github.com/tseemann/shovill/blob/master/README.md
+      licence: ['GPL v2']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+        type: file
+        description: List of input paired-end FastQ files
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+  - contigs:
+      type: file
+      description: The final assembly produced by Shovill
+      pattern: "contigs.fa"
+  - corrections:
+      type: file
+      description: List of post-assembly corrections made by Shovill
+      pattern: "shovill.corrections"
+  - log:
+      type: file
+      description: Full log file for bug reporting
+      pattern: "shovill.log"
+  - raw_contigs:
+      type: file
+      description: Raw assembly produced by the assembler (SKESA, SPAdes, MEGAHIT, or Velvet)
+      pattern: "{skesa,spades,megahit,velvet}.fasta"
+  - gfa:
+      type: file
+      description: Assembly graph produced by MEGAHIT, SPAdes, or Velvet
+      pattern: "contigs.{fastg,gfa,LastGraph}"
+
+authors:
+  - "@rpetit3"

tests/config/pytest_software.yml

@@ -383,6 +383,10 @@ seqwish_induce:
   - software/seqwish/induce/**
   - tests/software/seqwish/induce/**
 
+shovill:
+  - software/shovill/**
+  - tests/software/shovill/**
+
 spades:
   - software/spades/**
   - tests/software/spades/**

tests/software/shovill/main.nf

@@ -0,0 +1,52 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SHOVILL } from '../../../software/shovill/main.nf' addParams( options: [args: '--gsize 2800000 --kmers 31'] )
+include { SHOVILL as SHOVILL_SKESA } from '../../../software/shovill/main.nf' addParams( options: [args: '--assembler skesa --gsize 2800000'] )
+include { SHOVILL as SHOVILL_MEGAHIT } from '../../../software/shovill/main.nf' addParams( options: [args: '--assembler megahit --gsize 2800000'] )
+include { SHOVILL as SHOVILL_VELVET } from '../../../software/shovill/main.nf' addParams( options: [args: '--assembler velvet --gsize 2800000'] )
+
+workflow test_shovill {
+    
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              [ file("https://github.com/nf-core/test-datasets/raw/bacass/ERR044595_1M_1.fastq.gz", checkIfExists: true),
+                file("https://github.com/nf-core/test-datasets/raw/bacass/ERR044595_1M_2.fastq.gz", checkIfExists: true) ] ]
+
+    SHOVILL ( input )
+
+}
+
+workflow test_shovill_megahit {
+    
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              [ file("${launchDir}/tests/data/generic/fastq/test_R1.fastq.gz", checkIfExists: true),
+                file("${launchDir}/tests/data/generic/fastq/test_R2.fastq.gz", checkIfExists: true) ] ]
+
+    SHOVILL_MEGAHIT ( input )
+
+}
+
+workflow test_shovill_skesa {
+    
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              [ file("${launchDir}/tests/data/generic/fastq/test_R1.fastq.gz", checkIfExists: true),
+                file("${launchDir}/tests/data/generic/fastq/test_R2.fastq.gz", checkIfExists: true) ] ]
+
+    SHOVILL_SKESA ( input )
+
+}
+
+workflow test_shovill_velvet {
+    
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+              [ file("${launchDir}/tests/data/generic/fastq/test_R1.fastq.gz", checkIfExists: true),
+                file("${launchDir}/tests/data/generic/fastq/test_R2.fastq.gz", checkIfExists: true) ] ]
+
+    SHOVILL_VELVET ( input )
+
+}

tests/software/shovill/test.yml

@@ -0,0 +1,55 @@
+- name: shovill with spades
+  command: nextflow run ./tests/software/shovill -entry test_shovill -c tests/config/nextflow.config
+  tags:
+    - shovill
+    - shovill_spades
+  files:
+    - path: output/shovill/contigs.gfa
+      md5sum: 277af5d8ae8a0d2432db59a316226828
+    - path: output/shovill/spades.fasta
+      md5sum: 2506fc2af3a24397a3c5d3fbda0861fb
+    # MD5sum not reproducible (timestamp)
+    - path: output/shovill/contigs.fa
+    - path: output/shovill/shovill.corrections
+    - path: output/shovill/shovill.log
+
+- name: shovill with megahit
+  command: nextflow run ./tests/software/shovill -entry test_shovill_megahit -c tests/config/nextflow.config
+  tags:
+    - shovill
+    - shovill_megahit
+  files:
+    - path: output/shovill/shovill.corrections
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    # MD5sum not reproducible (timestamp, contig order)
+    - path: output/shovill/contigs.fa
+    - path: output/shovill/contigs.fastg
+    - path: output/shovill/megahit.fasta
+    - path: output/shovill/shovill.log
+  
+- name: shovill with skesa
+  command: nextflow run ./tests/software/shovill -entry test_shovill_skesa -c tests/config/nextflow.config
+  tags:
+    - shovill
+    - shovill_skesa
+  files:
+    - path: output/shovill/shovill.corrections
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/shovill/skesa.fasta
+      md5sum: c0c2d11b633310eb1437345cb599c33c
+    # MD5sum not reproducible (timestamp)
+    - path: output/shovill/contigs.fa
+    - path: output/shovill/shovill.log
+
+- name: shovill with velvet
+  command: nextflow run ./tests/software/shovill -entry test_shovill_velvet -c tests/config/nextflow.config
+  tags:
+    - shovill
+    - shovill_velvet
+  files:
+    # MD5sum not reproducible (timestamp, contig order)
+    - path: output/shovill/contigs.fa
+    - path: output/shovill/contigs.LastGraph
+    - path: output/shovill/shovill.corrections
+    - path: output/shovill/shovill.log
+    - path: output/shovill/velvet.fasta