Skip to content

Migrate from DSL1 to DSL2 #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Migrate from DSL1 to DSL2 #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
37b8f36
Migrating main processes from DSL1 to DSL2.
TheoC35 Jun 2, 2023
a7d8039
Migrating QC to DSL2
TheoC35 Jun 2, 2023
0381749
Split process
TheoC35 Jun 2, 2023
839203c
Update version
TheoC35 Jun 3, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
78 changes: 46 additions & 32 deletions main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
#!/usr/bin/env nextflow

// Copyright (C) 2022 CRCL
// Copyright (C) 2023 CRCL

// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU General Public License as published by
Expand Down Expand Up @@ -112,32 +112,21 @@ log.info ""


/* +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
MAIN
PROCESSES
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ */

Channel
.fromPath( fqdir + "/*${params.fastq_pattern}" )
.ifEmpty { error "No fastq file matching \'${params.fastq_pattern}\' in: ${fqdir}" }
.map { fq -> [
file(fq).getName().replaceAll("${params.fastq_pattern}\$",''),
file(fq)
]}
.view()
.into { reads_ch; reads_ch2; reads_ch3 }


process fastqc {
tag { sample_id }

publishDir "${outdir}/fastqc", mode: 'copy', pattern: '*_fastqc.html', enabled : params.fastqcoutput
publishDir "${outdir}/fastqc/zip", mode: 'copy', pattern: '*_fastqc.zip', enabled : params.fastqcoutput

input:
set sample_id, file(reads) from reads_ch
tuple val(sample_id), file(reads)

output:
file "*_fastqc.html"
file "*_fastqc.zip" into fastqc_ch, fastqc_ch2
path "*_fastqc.zip"

"""
fastqc --threads ${params.fastqc_threads} \\
Expand All @@ -152,11 +141,11 @@ process trim {
publishDir "${outdir}/trimmomatic/logs", mode: 'copy', pattern : "${sample_id}.trimmomatic.stats.log", enabled : params.trimoutput

input:
set sample_id, file(reads) from reads_ch2
tuple val(sample_id), file(reads)

output:
set sample_id, file("${sample_id}.trim.fastq.gz") into trimmed_files, trimmed_files2
file("${sample_id}.trimmomatic.stats.log") into trimmomatic_logs, trimmomatic_logs2
tuple val(sample_id), file("${sample_id}.trim.fastq.gz"), emit: trim_files
file("${sample_id}.trimmomatic.stats.log")

"""
trimmomatic SE -phred33 -threads ${params.trimmo_threads} \\
Expand All @@ -176,28 +165,28 @@ process bowtie2 {
publishDir "${outdir}/bowtie2/logs", mode: 'copy', pattern : "${sample_id}.bowtie2.stats.log", enabled: params.bowtieoutput

input:
set sample_id, file(reads) from trimmed_files
tuple val(sample_id), file(reads)

output:
set sample_id, file("${sample_id}.sam") into bowtie_files
file("${sample_id}.bowtie2.stats.log") into bowtie_logs, bowtie_logs2
tuple val(sample_id), file("${sample_id}.sam"), emit: aligned_files
file("${sample_id}.bowtie2.stats.log")

"""
bowtie2 -x ${params.bowtie_index} --threads ${params.bowtie_threads} \\
${params.bowtie_opts} ${reads} -S ${sample_id}.sam 2>> ${sample_id}.bowtie2.stats.log
"""
}

process filter {
process filter_sam {
tag { sample_id }

publishDir "${outdir}/bowtie2", mode: 'copy', pattern : "${sample_id}.uniq.{bam,bam.bai}", enabled : params.samtoolsoutput

input:
set sample_id, file(sam) from bowtie_files
tuple val(sample_id), file(sam)

output:
set sample_id, file("${sample_id}.uniq.bam") into filtered_bam_ch
tuple val(sample_id), file("${sample_id}.uniq.bam"), emit: filtered_files

"""
set -o pipefail
Expand All @@ -212,9 +201,10 @@ process multiqc {
publishDir "${outdir}", mode: 'copy', pattern: 'multiqc_report.html'

input:
file('*') from fastqc_ch.collect()
file('*') from trimmomatic_logs.collect()
file('*') from bowtie_logs.collect()
file('*')
file('*')
file('*')


output:
file('multiqc_report.html')
Expand All @@ -231,11 +221,11 @@ process counts {
publishDir "${outdir}/counts/3p/", mode:'copy', pattern: "${sample_id}.3_counts.csv", enabled: params.threeendcount

input:
set sample_id, file(filtered_bam) from filtered_bam_ch
tuple val(sample_id), file(filtered_bam)

output:
set sample_id, file("${sample_id}.5_counts.csv"), file("${sample_id}.3_counts.csv") into counts_ch
set sample_id, file("${sample_id}.5_counts.csv") into counts_ch2
tuple val(sample_id), file("${sample_id}.5_counts.csv"), file("${sample_id}.3_counts.csv")
tuple val(sample_id), file("${sample_id}.5_counts.csv")
script:
"""
bedtools genomecov -d -3 -ibam ${filtered_bam} > ${sample_id}.3_counts.csv
Expand All @@ -251,7 +241,7 @@ process split {
when: params.split

input:
set sample_id, file(counts5), file(counts3) from counts_ch
tuple val(sample_id), file(counts5), file(counts3)

output:
file("${sample_id}.58S.csv")
Expand All @@ -271,7 +261,7 @@ process report {
publishDir "${outdir}", mode: 'move'

input:
file('*') from counts_ch2.collect()
file('*')

output:
file("rms_report.html")
Expand All @@ -282,6 +272,30 @@ process report {
"""
}

/* +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
WORKFLOW
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ */

workflow {
fastq_files = Channel
.fromPath( fqdir + "/*${params.fastq_pattern}" )
.ifEmpty { error "No fastq file matching \'${params.fastq_pattern}\' in: ${fqdir}" }
.map { fq -> [
file(fq).getName().replaceAll("${params.fastq_pattern}\$",''),
file(fq)
]}
fastqc(fastq_files)
trim(fastq_files)
bowtie2(trim.out.trim_files)
filter_sam(bowtie2.out.aligned_files)
counts(filter_sam.out.filtered_files)
if(params.split) {
split(counts.out[0])
}
multiqc(fastqc.out[1].collect(),trim.out[1].collect(),bowtie2.out[1].collect())
report(counts.out[1].collect())
}

/* +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
UTILS
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ */
Expand Down
6 changes: 3 additions & 3 deletions nextflow.config
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
manifest {
homePage = 'https://github.com/EpiRnaTools/ribomethseq-nf'
homePage = 'https://github.com/RibosomeCRCL/ribomethseq-nf'
description = 'RiboMethSeq data processing'
mainScript = 'main.nf'
name = 'ribomethseq-nf'
author = 'Hermes Paraqindes, Theo Combe'
version = '1.0'
version = '1.5'
}

/***************************************************************/
Expand Down Expand Up @@ -36,7 +36,7 @@ profiles {
conda.enabled = true

process {
withName: 'fastqc|trim|bowtie2|filter|multiqc|counts' {
withName: 'fastqc|trim|bowtie2|filter_sam|multiqc|counts' {
conda = "$baseDir/docker/rms-processing.yml"
// conda = "/path/to/your/conda/envs/rms-processing"
}
Expand Down
2 changes: 1 addition & 1 deletion nf-config/exec.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ process {
withName: 'trim' {cpus = params.trimmo_threads; time = '4h'}
withName: 'multiqc' {cpus = 2; time = '1h'}
withName: 'bowtie2' {cpus = params.bowtie_threads; memory = 12.GB; time = '12h'}
withName: 'filter' {cpus = params.samtools_threads; memory = 12.GB; time = '6h'}
withName: 'filter_sam' {cpus = params.samtools_threads; memory = 12.GB; time = '6h'}
withName: 'counts' {cpus = 2; memory = 12.GB}
withName: 'split' {cpus = 4; memory = 4.GB}
withName: 'report' {cpus = 2; time = '1h'}
Expand Down