Transdecoder predict (#1251)

* create transdecoder/longorf module

* module transdecoder

* main.nf

* transdecoder/longorf ready to PR

* review comments update

* transdecoder/predict module create

* test transdecoder/predict module

* fix pytest

* pytest passed

* removed whitespace

* Update meta.yml

* Update meta.yml

Co-authored-by: Danilo Di Leo <danilo.dileo@lnu.se>
Co-authored-by: Daniel Lundin <erik.rikard.daniel@gmail.com>

modules/transdecoder/predict/main.nf

@@ -0,0 +1,37 @@
+process TRANSDECODER_PREDICT {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::transdecoder=5.5.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/transdecoder:5.5.0--pl5262hdfd78af_4':
+        'quay.io/comp-bio-aging/transdecoder' }"
+
+    input:
+    tuple val(meta), path(fasta)
+    path(fold)
+
+    output:
+    tuple val(meta), path("*.transdecoder.pep")  , emit: pep
+    tuple val(meta), path("*.transdecoder.gff3") , emit: gff3
+    tuple val(meta), path("*.transdecoder.cds")  , emit: cds
+    tuple val(meta), path("*.transdecoder.bed")  , emit: bed
+    path "versions.yml"                          , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    TransDecoder.Predict \\
+        $args \\
+        -O ${prefix} \\
+        -t \\
+        $fasta
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        transdecoder: \$(echo \$(TransDecoder.Predict --version) | sed -e "s/TransDecoder.Predict //g")
+    END_VERSIONS
+    """
+}

modules/transdecoder/predict/meta.yml

@@ -0,0 +1,59 @@
+name: transdecoder_predict
+description: TransDecoder identifies candidate coding regions within transcript sequences. It is used to build gff file. You can use this module after transdecoder_longorf
+keywords:
+  - eukaryotes
+  - gff
+
+tools:
+  - transdecoder:
+      description: TransDecoder identifies candidate coding regions within transcript sequences, such as those generated by de novo RNA-Seq transcript assembly using Trinity, or constructed based on RNA-Seq alignments to the genome using Tophat and Cufflinks.
+      homepage: https://github.com/TransDecoder
+      documentation: https://github.com/TransDecoder/TransDecoder/wiki
+      tool_dev_url: https://github.com/TransDecoder/TransDecoder
+      doi: ""
+      licence: ['Broad Institute']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: fasta file
+      pattern: "*.{fasta}"
+  - fold:
+      type: folder
+      description: Output from the module transdecoder_longorf
+      pattern: "*"
+
+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"
+  - pep:
+      type: amino acids fasta file
+      description: All ORFs meeting the minimum length criteria, regardless of coding potential
+      pattern: "*.{pep}"
+  - gff3:
+      type: gff3 file
+      description: Positions of all ORFs as found in the target transcripts
+      pattern: "*.{gff3}"
+  - cds:
+      type: nucleotide fasta file
+      description: the nucleotide coding sequence for all detected ORFs
+      pattern: "*{cds}"
+  - bed:
+      type: bed file
+      description: bed file
+      pattern: "*{bed}"
+
+authors:
+  - "@Danilo2771"

tests/config/pytest_modules.yml

@@ -1457,6 +1457,10 @@ tbprofiler/profile:
   - modules/tbprofiler/profile/**
   - tests/modules/tbprofiler/profile/**
 
+test/template:
+  - modules/test/template/**
+  - tests/modules/test/template/**
+
 tiddit/cov:
   - modules/tiddit/cov/**
   - tests/modules/tiddit/cov/**
@@ -1469,6 +1473,10 @@ transdecoder/longorf:
   - modules/transdecoder/longorf/**
   - tests/modules/transdecoder/longorf/**
 
+transdecoder/predict:
+  - modules/transdecoder/predict/**
+  - tests/modules/transdecoder/predict/**
+
 trimgalore:
   - modules/trimgalore/**
   - tests/modules/trimgalore/**

tests/modules/transdecoder/predict/main.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { TRANSDECODER_PREDICT } from '../../../../modules/transdecoder/predict/main.nf'
+include { TRANSDECODER_LONGORF } from '../../../../modules/transdecoder/longorf/main.nf'
+
+workflow test_transdecoder_predict {
+    
+    input = [ 
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)]
+    
+    TRANSDECODER_LONGORF ( input )
+    TRANSDECODER_PREDICT ( input, TRANSDECODER_LONGORF.out.folder )
+
+}
+

tests/modules/transdecoder/predict/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}

tests/modules/transdecoder/predict/test.yml

@@ -0,0 +1,12 @@
+- name: transdecoder predict test_transdecoder_predict
+  command: nextflow run tests/modules/transdecoder/predict -entry test_transdecoder_predict -c tests/config/nextflow.config
+  tags:
+    - transdecoder
+    - transdecoder/predict
+  files:
+    - path: output/transdecoder/genome.fasta.transdecoder.bed
+    - path: output/transdecoder/genome.fasta.transdecoder.cds
+    - path: output/transdecoder/genome.fasta.transdecoder.gff3
+    - path: output/transdecoder/genome.fasta.transdecoder.pep
+    - path: output/transdecoder/versions.yml
+      md5sum: 2847cc159dc93e9014b57d76987623ea