New Module: gstama/polyacleanup (#1468)

* 📦 NEW: Add gstama/polyacleanup

polyacleanup script remove remaining polyA tails from FLNC reads (Pacbio isoseq3)

* 🐛 FIX: Prettier: replace simple quote by double quote

* 🐛 FIX: Update TEMPLATE to nf-core 2.4

* 👌 IMPROVE: Compress outputs

Co-authored-by: Sateesh Peri <33637490+sateeshperi@users.noreply.github.com>

modules/gstama/polyacleanup/main.nf

@@ -0,0 +1,40 @@
+process GSTAMA_POLYACLEANUP {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::gs-tama=1.0.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gs-tama:1.0.3--hdfd78af_0':
+        'quay.io/biocontainers/gs-tama:1.0.3--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(fasta)
+
+    output:
+    tuple val(meta), path("*_tama.fa.gz")                   , emit: fasta
+    tuple val(meta), path("*_tama_polya_flnc_report.txt.gz"), emit: report
+    tuple val(meta), path("*_tama_tails.fa.gz")             , emit: tails
+    path "versions.yml"                                     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    if( "$fasta" == "${prefix}.fasta" | "$fasta" == "${prefix}.fa" ) error "Input and output names are the same, set prefix in module configuration"
+    """
+    tama_flnc_polya_cleanup.py \\
+        -f $fasta \\
+        -p ${prefix} \\
+        $args
+    gzip ${prefix}.fa
+    gzip ${prefix}_polya_flnc_report.txt
+    gzip ${prefix}_tails.fa
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gstama: \$( tama_collapse.py -version | grep 'tc_version_date_'|sed 's/tc_version_date_//g' )
+    END_VERSIONS
+    """
+}

modules/gstama/polyacleanup/meta.yml

@@ -0,0 +1,55 @@
+name: gstama_polyacleanup
+description: Helper script, remove remaining polyA sequences from Full Length Non Chimeric reads (Pacbio isoseq3)
+keywords:
+  - gstama
+  - gstama/polyacleanup
+  - long-read
+  - isoseq
+  - tama
+  - trancriptome
+  - annotation
+tools:
+  - gstama:
+      description: Gene-Switch Transcriptome Annotation by Modular Algorithms
+      homepage: https://github.com/sguizard/gs-tama
+      documentation: https://github.com/GenomeRIK/tama/wiki
+      tool_dev_url: https://github.com/sguizard/gs-tama
+      doi: "https://doi.org/10.1186/s12864-020-07123-7"
+      licence: ["GPL v3 License"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: Full Length Non Chimeric reads in fasta format
+      pattern: "*.{fa,fasta}"
+
+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"
+  - fasta:
+      type: file
+      description: The Full Length Non Chimeric reads clened from remaining polyA tails. The sequences are in FASTA format compressed with gzip.
+      pattern: "*_tama.fa.gz"
+  - report:
+      type: file
+      description: A text file describing the number of polyA tails removed and their length. Compressed with gzip.
+      pattern: "*_tama_polya_flnc_report.txt.gz"
+  - tails:
+      type: file
+      description: A gzip compressed FASTA file of trimmed polyA tails.
+      pattern: "*_tama_tails.fa.gz"
+
+authors:
+  - "@sguizard"

tests/config/pytest_modules.yml

@@ -811,6 +811,10 @@ gstama/merge:
   - modules/gstama/merge/**
   - tests/modules/gstama/merge/**
 
+gstama/polyacleanup:
+  - modules/gstama/polyacleanup/**
+  - tests/modules/gstama/polyacleanup/**
+
 gtdbtk/classifywf:
   - modules/gtdbtk/classifywf/**
   - tests/modules/gtdbtk/classifywf/**

tests/modules/gstama/polyacleanup/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GSTAMA_POLYACLEANUP } from '../../../../modules/gstama/polyacleanup/main.nf'
+
+workflow test_gstama_polyacleanup {
+
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['genome']['transcriptome_fasta'], checkIfExists: true)
+    ]
+
+    GSTAMA_POLYACLEANUP ( input )
+}

tests/modules/gstama/polyacleanup/nextflow.config

@@ -0,0 +1,6 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    ext.prefix = { "${meta.id}_tama" }
+
+}

tests/modules/gstama/polyacleanup/test.yml

@@ -0,0 +1,14 @@
+- name: gstama polyacleanup test_gstama_polyacleanup
+  command: nextflow run tests/modules/gstama/polyacleanup -entry test_gstama_polyacleanup -c tests/config/nextflow.config
+  tags:
+    - gstama
+    - gstama/polyacleanup
+  files:
+    - path: output/gstama/test_tama.fa.gz
+      md5sum: 9c768387478e5f966a42c369c0270b09
+    - path: output/gstama/test_tama_polya_flnc_report.txt.gz
+      md5sum: fe3606979ed11538aacd83159f4cff03
+    - path: output/gstama/test_tama_tails.fa.gz
+      md5sum: ba21256c0afe0bda71b3ee66b4c761bf
+    - path: output/gstama/versions.yml
+      md5sum: 07ebb812ae13a350d955fab7600b2542