Add Prodigal

CHANGELOG.md

@@ -7,6 +7,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
+-[#240](https://github.com/nf-core/mag/pull/240) - Add prodigal to predict protein-coding genes for assemblies
+
 ### `Changed`
 
 ### `Fixed`

CITATIONS.md

@@ -55,6 +55,8 @@
 
 * [Porechop](https://github.com/rrwick/Porechop)
 
+* [Prodigal](https://github.com/hyattpd/Prodigal)
+
 * [SAMtools](https://doi.org/10.1093/bioinformatics/btp352)
     > Li, H., Handsaker, B., Wysoker, A., Fennell, T., Ruan, J., Homer, N., … 1000 Genome Project Data Processing Subgroup. (2009). The Sequence Alignment/Map format and SAMtools. Bioinformatics , 25(16), 2078–2079. doi: 10.1093/bioinformatics/btp352.
 

README.md

@@ -33,6 +33,7 @@ The pipeline then:
 
 * assigns taxonomy to reads using [Centrifuge](https://ccb.jhu.edu/software/centrifuge/) and/or [Kraken2](https://github.com/DerrickWood/kraken2/wiki)
 * performs assembly using [MEGAHIT](https://github.com/voutcn/megahit) and [SPAdes](http://cab.spbu.ru/software/spades/), and checks their quality using [Quast](http://quast.sourceforge.net/quast)
+* predicts protein-coding genes for the assemblies using [Prodigal](https://github.com/hyattpd/Prodigal)
 * performs metagenome binning using [MetaBAT2](https://bitbucket.org/berkeleylab/metabat/src/master/), and checks the quality of the genome bins using [Busco](https://busco.ezlab.org/)
 * assigns taxonomy to bins using [GTDB-Tk](https://github.com/Ecogenomics/GTDBTk) and/or [CAT](https://github.com/dutilh/CAT)
 

conf/modules.config

@@ -161,5 +161,9 @@ params {
         'multiqc' {
             args            = ""
         }
+        prodigal {
+            publish_dir     = "Prodigal"
+            output_format   = "gff"
+        }
     }
 }

docs/output.md

@@ -13,6 +13,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 * [Quality control](#quality-control) of input reads - trimming and contaminant removal
 * [Taxonomic classification of trimmed reads](#taxonomic-classification-of-trimmed-reads)
 * [Assembly](#assembly) of trimmed reads
+* [Protein-coding gene prediction](#gene-prediction) of assemblies
 * [Binning](#binning) of assembled contigs
 * [Taxonomic classification of binned genomes](#taxonomic-classification-of-binned-genomes)
 * [Additional summary for binned genomes](#additional-summary-for-binned-genomes)
@@ -214,6 +215,21 @@ SPAdesHybrid is a part of the [SPAdes](http://cab.spbu.ru/software/spades/) soft
 
 </details>
 
+## Gene prediction
+
+Protein-coding genes are predicted for each assembly.
+
+<details markdown="1">
+<summary>Output files</summary>
+
+* `Prodigal/`
+    * `[sample/group].gff`: Gene Coordinates in GFF format
+    * `[sample/group].faa`: The protein translation file consists of all the proteins from all the sequences in multiple FASTA format.
+    * `[sample/group].fna`: Nucleotide sequences of the predicted proteins using the DNA alphabet, not mRNA (so you will see 'T' in the output and not 'U').
+    * `[sample/group]_all.txt`: Starts file
+
+</details>
+
 ## Binning
 
 ### Contig sequencing depth

modules.json

@@ -8,6 +8,9 @@
             },
             "fastqc": {
                 "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d"
+            },
+            "prodigal": {
+                "git_sha": "49da8642876ae4d91128168cd0db4f1c858d7792"
             }
         }
     }

modules/nf-core/modules/prodigal/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/nf-core/modules/prodigal/main.nf

@@ -0,0 +1,48 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process PRODIGAL {
+    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::prodigal=2.6.3" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/prodigal:2.6.3--h516909a_2"
+    } else {
+        container "quay.io/biocontainers/prodigal:2.6.3--h516909a_2"
+    }
+
+    input:
+    tuple val(meta), path(genome)
+    val(output_format)
+
+    output:
+    tuple val(meta), path("${prefix}.${output_format}"), emit: gene_annotations
+    tuple val(meta), path("${prefix}.fna"), emit: nucleotide_fasta
+    tuple val(meta), path("${prefix}.faa"), emit: amino_acid_fasta
+    tuple val(meta), path("${prefix}_all.txt"), emit: all_gene_annotations
+    path "versions.yml"           , emit: versions
+
+    script:
+    prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    prodigal -i "${genome}" \\
+        $options.args \\
+        -f $output_format \\
+        -d "${prefix}.fna" \\
+        -o "${prefix}.${output_format}" \\
+        -a "${prefix}.faa" \\
+        -s "${prefix}_all.txt"
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$(prodigal -v 2>&1 | sed -n 's/Prodigal V\\(.*\\):.*/\\1/p')
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/prodigal/meta.yml

@@ -0,0 +1,41 @@
+name: prodigal
+description: Prodigal (Prokaryotic Dynamic Programming Genefinding Algorithm) is a microbial (bacterial and archaeal) gene finding program
+keywords:
+  - sort
+tools:
+  - prodigal:
+      description: Prodigal (Prokaryotic Dynamic Programming Genefinding Algorithm) is a microbial (bacterial and archaeal) gene finding program
+      homepage: {}
+      documentation: {}
+      tool_dev_url: {}
+      doi: ""
+      licence: ["GPL v3"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+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"
+  - bam:
+      type: file
+      description: Sorted BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+authors:
+  - "@grst"

workflows/mag.nf

@@ -107,6 +107,7 @@ include { GTDBTK              } from '../subworkflows/local/gtdbtk'
 include { FASTQC as FASTQC_RAW     } from '../modules/nf-core/modules/fastqc/main'              addParams( options: modules['fastqc_raw']            )
 include { FASTQC as FASTQC_TRIMMED } from '../modules/nf-core/modules/fastqc/main'              addParams( options: modules['fastqc_trimmed']        )
 include { FASTP                    } from '../modules/nf-core/modules/fastp/main'               addParams( options: modules['fastp']                 )
+include { PRODIGAL                 } from '../modules/nf-core/modules/prodigal/main'            addParams( options: modules['prodigal']              )
 
 ////////////////////////////////////////////////////
 /* --  Create channel for reference databases  -- */
@@ -466,6 +467,18 @@ workflow MAG {
         ch_software_versions = ch_software_versions.mix(QUAST.out.version.first().ifEmpty(null))
     }
 
+    /*
+    ================================================================================
+                                    Predict proteins
+    ================================================================================
+    */
+
+    PRODIGAL (
+        ch_assemblies,
+        modules['prodigal']['output_format']
+    )
+    ch_software_versions = ch_software_versions.mix(PRODIGAL.out.versions.first().ifEmpty(null))
+
     /*
     ================================================================================
                                     Binning