mirror of
https://github.com/MillironX/taxprofiler.git
synced 2024-11-11 01:33:09 +00:00
Merge pull request #27 from genomic-medicine-sweden/add_nanopore
Add nanopore reads preprocessing with Porechop
This commit is contained in:
commit
51a0acd05b
10 changed files with 153 additions and 8 deletions
|
@ -15,6 +15,8 @@
|
||||||
* [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
|
* [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
|
||||||
> Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
|
> Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
|
||||||
|
|
||||||
|
* [Porechop](https://github.com/rrwick/Porechop)
|
||||||
|
|
||||||
## Software packaging/containerisation tools
|
## Software packaging/containerisation tools
|
||||||
|
|
||||||
* [Anaconda](https://anaconda.com)
|
* [Anaconda](https://anaconda.com)
|
||||||
|
|
|
@ -30,7 +30,7 @@ On release, automated continuous integration tests run the pipeline on a full-si
|
||||||
|
|
||||||
1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
|
1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
|
||||||
2. Performs optional read pre-processing
|
2. Performs optional read pre-processing
|
||||||
- Adapter clipping and merging
|
- Adapter clipping and merging (short, and nanopore reads)
|
||||||
- Low complexity filtering
|
- Low complexity filtering
|
||||||
- Host read removal
|
- Host read removal
|
||||||
- Run merging
|
- Run merging
|
||||||
|
|
|
@ -50,6 +50,15 @@ process {
|
||||||
]
|
]
|
||||||
}
|
}
|
||||||
|
|
||||||
|
withName: PORECHOP {
|
||||||
|
ext.prefix = { "${meta.id}_${meta.run_accession}" }
|
||||||
|
publishDir = [
|
||||||
|
path: { "${params.outdir}/porechop" },
|
||||||
|
mode: 'copy',
|
||||||
|
pattern: '*.fastq.gz'
|
||||||
|
]
|
||||||
|
}
|
||||||
|
|
||||||
withName: FASTQC_POST {
|
withName: FASTQC_POST {
|
||||||
ext.args = '--quiet'
|
ext.args = '--quiet'
|
||||||
ext.prefix = { "${meta.id}_${meta.run_accession}_processed" }
|
ext.prefix = { "${meta.id}_${meta.run_accession}_processed" }
|
||||||
|
|
|
@ -23,6 +23,9 @@
|
||||||
},
|
},
|
||||||
"multiqc": {
|
"multiqc": {
|
||||||
"git_sha": "20d8250d9f39ddb05dfb437603aaf99b5c0b2b41"
|
"git_sha": "20d8250d9f39ddb05dfb437603aaf99b5c0b2b41"
|
||||||
|
},
|
||||||
|
"porechop": {
|
||||||
|
"git_sha": "e20e57f90b6787ac9a010a980cf6ea98bd990046"
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
35
modules/nf-core/modules/porechop/main.nf
generated
Normal file
35
modules/nf-core/modules/porechop/main.nf
generated
Normal file
|
@ -0,0 +1,35 @@
|
||||||
|
process PORECHOP {
|
||||||
|
tag "$meta.id"
|
||||||
|
label 'process_medium'
|
||||||
|
|
||||||
|
conda (params.enable_conda ? "bioconda::porechop=0.2.4" : null)
|
||||||
|
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
|
||||||
|
'https://depot.galaxyproject.org/singularity/porechop:0.2.4--py39h7cff6ad_2' :
|
||||||
|
'quay.io/biocontainers/porechop:0.2.4--py39h7cff6ad_2' }"
|
||||||
|
|
||||||
|
input:
|
||||||
|
tuple val(meta), path(reads)
|
||||||
|
|
||||||
|
output:
|
||||||
|
tuple val(meta), path("*.fastq.gz"), emit: reads
|
||||||
|
path "versions.yml" , emit: versions
|
||||||
|
|
||||||
|
when:
|
||||||
|
task.ext.when == null || task.ext.when
|
||||||
|
|
||||||
|
script:
|
||||||
|
def args = task.ext.args ?: ''
|
||||||
|
def prefix = task.ext.prefix ?: "${meta.id}"
|
||||||
|
"""
|
||||||
|
porechop \\
|
||||||
|
-i $reads \\
|
||||||
|
-t $task.cpus \\
|
||||||
|
$args \\
|
||||||
|
-o ${prefix}.fastq.gz
|
||||||
|
|
||||||
|
cat <<-END_VERSIONS > versions.yml
|
||||||
|
"${task.process}":
|
||||||
|
porechop: \$( porechop --version )
|
||||||
|
END_VERSIONS
|
||||||
|
"""
|
||||||
|
}
|
50
modules/nf-core/modules/porechop/meta.yml
generated
Normal file
50
modules/nf-core/modules/porechop/meta.yml
generated
Normal file
|
@ -0,0 +1,50 @@
|
||||||
|
name: porechop
|
||||||
|
description: Adapter removal and demultiplexing of Oxford Nanopore reads
|
||||||
|
keywords:
|
||||||
|
- adapter
|
||||||
|
- nanopore
|
||||||
|
- demultiplexing
|
||||||
|
tools:
|
||||||
|
- porechop:
|
||||||
|
description: Adapter removal and demultiplexing of Oxford Nanopore reads
|
||||||
|
homepage: "https://github.com/rrwick/Porechop"
|
||||||
|
documentation: "https://github.com/rrwick/Porechop"
|
||||||
|
tool_dev_url: "https://github.com/rrwick/Porechop"
|
||||||
|
doi: "10.1099/mgen.0.000132"
|
||||||
|
licence: ["GPL v3"]
|
||||||
|
|
||||||
|
input:
|
||||||
|
- meta:
|
||||||
|
type: map
|
||||||
|
description: |
|
||||||
|
Groovy Map containing sample information
|
||||||
|
e.g. [ id:'test', single_end:false ]
|
||||||
|
- reads:
|
||||||
|
type: file
|
||||||
|
description: fastq/fastq.gz file
|
||||||
|
pattern: "*.{fastq,fastq.gz,fq,fq.gz}"
|
||||||
|
|
||||||
|
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"
|
||||||
|
- reads:
|
||||||
|
type: file
|
||||||
|
description: Demultiplexed and/or adapter-trimmed fastq.gz file
|
||||||
|
pattern: "*.{fastq.gz}"
|
||||||
|
|
||||||
|
authors:
|
||||||
|
- "@ggabernet"
|
||||||
|
- "@jasmezz"
|
||||||
|
- "@d4straub"
|
||||||
|
- "@LaurenceKuhl"
|
||||||
|
- "@SusiJo"
|
||||||
|
- "@jonasscheid"
|
||||||
|
- "@jonoave"
|
||||||
|
- "@GokceOGUZ"
|
|
@ -57,6 +57,7 @@ params {
|
||||||
// FASTQ preprocessing
|
// FASTQ preprocessing
|
||||||
fastp_clip_merge = false
|
fastp_clip_merge = false
|
||||||
fastp_exclude_unmerged = true
|
fastp_exclude_unmerged = true
|
||||||
|
remove_adapters = false
|
||||||
|
|
||||||
// MALT
|
// MALT
|
||||||
run_malt = false
|
run_malt = false
|
||||||
|
|
34
subworkflows/local/longread_preprocessing.nf
Normal file
34
subworkflows/local/longread_preprocessing.nf
Normal file
|
@ -0,0 +1,34 @@
|
||||||
|
|
||||||
|
include { FASTQC as FASTQC_POST } from '../../modules/nf-core/modules/fastqc/main'
|
||||||
|
include { PORECHOP } from '../../modules/nf-core/modules/porechop/main'
|
||||||
|
|
||||||
|
workflow LONGREAD_PREPROCESSING {
|
||||||
|
take:
|
||||||
|
reads
|
||||||
|
|
||||||
|
main:
|
||||||
|
ch_versions = Channel.empty()
|
||||||
|
ch_multiqc_files = Channel.empty()
|
||||||
|
|
||||||
|
PORECHOP ( reads )
|
||||||
|
|
||||||
|
ch_processed_reads = PORECHOP.out.reads
|
||||||
|
.dump(tag: "pre_fastqc_check")
|
||||||
|
.map {
|
||||||
|
meta, reads ->
|
||||||
|
def meta_new = meta.clone()
|
||||||
|
meta_new['single_end'] = 1
|
||||||
|
[ meta_new, reads ]
|
||||||
|
}
|
||||||
|
|
||||||
|
FASTQC_POST ( PORECHOP.out.reads )
|
||||||
|
ch_versions = ch_versions.mix(PORECHOP.out.versions.first())
|
||||||
|
ch_multiqc_files = ch_multiqc_files.mix( FASTQC_POST.out.zip.collect{it[1]} )
|
||||||
|
|
||||||
|
|
||||||
|
emit:
|
||||||
|
reads = ch_processed_reads // channel: [ val(meta), [ reads ] ]
|
||||||
|
versions = ch_versions // channel: [ versions.yml ]
|
||||||
|
mqc = ch_multiqc_files
|
||||||
|
}
|
||||||
|
|
|
@ -7,7 +7,7 @@ include { FASTP as FASTP_SINGLE } from '../../modules/nf-core/modules/fast
|
||||||
include { FASTP as FASTP_PAIRED } from '../../modules/nf-core/modules/fastp/main'
|
include { FASTP as FASTP_PAIRED } from '../../modules/nf-core/modules/fastp/main'
|
||||||
include { FASTQC as FASTQC_POST } from '../../modules/nf-core/modules/fastqc/main'
|
include { FASTQC as FASTQC_POST } from '../../modules/nf-core/modules/fastqc/main'
|
||||||
|
|
||||||
workflow FASTQ_PREPROCESSING {
|
workflow SHORTREAD_PREPROCESSING {
|
||||||
take:
|
take:
|
||||||
reads // file: /path/to/samplesheet.csv
|
reads // file: /path/to/samplesheet.csv
|
||||||
|
|
|
@ -39,8 +39,8 @@ ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath(params.multi
|
||||||
include { INPUT_CHECK } from '../subworkflows/local/input_check'
|
include { INPUT_CHECK } from '../subworkflows/local/input_check'
|
||||||
|
|
||||||
include { DB_CHECK } from '../subworkflows/local/db_check'
|
include { DB_CHECK } from '../subworkflows/local/db_check'
|
||||||
include { FASTQ_PREPROCESSING } from '../subworkflows/local/preprocessing'
|
include { SHORTREAD_PREPROCESSING } from '../subworkflows/local/shortread_preprocessing'
|
||||||
|
include { LONGREAD_PREPROCESSING } from '../subworkflows/local/longread_preprocessing'
|
||||||
|
|
||||||
/*
|
/*
|
||||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||||
|
@ -101,13 +101,24 @@ workflow TAXPROFILER {
|
||||||
// PERFORM PREPROCESSING
|
// PERFORM PREPROCESSING
|
||||||
//
|
//
|
||||||
if ( params.fastp_clip_merge ) {
|
if ( params.fastp_clip_merge ) {
|
||||||
FASTQ_PREPROCESSING ( INPUT_CHECK.out.fastq )
|
SHORTREAD_PREPROCESSING ( INPUT_CHECK.out.fastq )
|
||||||
|
}
|
||||||
|
|
||||||
|
ch_multiqc_files = Channel.empty()
|
||||||
|
|
||||||
|
if ( params.remove_adapters ) {
|
||||||
|
ch_longreads_preprocessed = LONGREAD_PREPROCESSING ( INPUT_CHECK.out.nanopore ).reads
|
||||||
|
.map { it -> [ it[0], [it[1]] ] }
|
||||||
|
ch_versions = ch_versions.mix(LONGREAD_PREPROCESSING.out.versions.first())
|
||||||
|
ch_multiqc_files = ch_multiqc_files.mix(LONGREAD_PREPROCESSING.out.mqc)
|
||||||
|
} else {
|
||||||
|
ch_longreads_preprocessed = INPUT_CHECK.out.nanopore
|
||||||
}
|
}
|
||||||
|
|
||||||
//
|
//
|
||||||
// PERFORM RUN MERGING
|
// PERFORM RUN MERGING
|
||||||
//
|
//
|
||||||
ch_processed_for_combine = FASTQ_PREPROCESSING.out.reads
|
ch_processed_for_combine = SHORTREAD_PREPROCESSING.out.reads
|
||||||
.dump(tag: "prep_for_combine_grouping")
|
.dump(tag: "prep_for_combine_grouping")
|
||||||
.map {
|
.map {
|
||||||
meta, reads ->
|
meta, reads ->
|
||||||
|
@ -134,6 +145,7 @@ workflow TAXPROFILER {
|
||||||
|
|
||||||
// output [DUMP: reads_plus_db] [['id':'2612', 'run_accession':'combined', 'instrument_platform':'ILLUMINA', 'single_end':1], <reads_path>/2612.merged.fastq.gz, ['tool':'malt', 'db_name':'mal95', 'db_params':'"-id 90"'], <db_path>/malt90]
|
// output [DUMP: reads_plus_db] [['id':'2612', 'run_accession':'combined', 'instrument_platform':'ILLUMINA', 'single_end':1], <reads_path>/2612.merged.fastq.gz, ['tool':'malt', 'db_name':'mal95', 'db_params':'"-id 90"'], <db_path>/malt90]
|
||||||
ch_input_for_profiling = ch_reads_for_profiling
|
ch_input_for_profiling = ch_reads_for_profiling
|
||||||
|
.mix( ch_longreads_preprocessed )
|
||||||
.combine(DB_CHECK.out.dbs)
|
.combine(DB_CHECK.out.dbs)
|
||||||
.dump(tag: "reads_plus_db")
|
.dump(tag: "reads_plus_db")
|
||||||
.branch {
|
.branch {
|
||||||
|
@ -185,14 +197,13 @@ workflow TAXPROFILER {
|
||||||
workflow_summary = WorkflowTaxprofiler.paramsSummaryMultiqc(workflow, summary_params)
|
workflow_summary = WorkflowTaxprofiler.paramsSummaryMultiqc(workflow, summary_params)
|
||||||
ch_workflow_summary = Channel.value(workflow_summary)
|
ch_workflow_summary = Channel.value(workflow_summary)
|
||||||
|
|
||||||
ch_multiqc_files = Channel.empty()
|
|
||||||
ch_multiqc_files = ch_multiqc_files.mix(Channel.from(ch_multiqc_config))
|
ch_multiqc_files = ch_multiqc_files.mix(Channel.from(ch_multiqc_config))
|
||||||
ch_multiqc_files = ch_multiqc_files.mix(ch_multiqc_custom_config.collect().ifEmpty([]))
|
ch_multiqc_files = ch_multiqc_files.mix(ch_multiqc_custom_config.collect().ifEmpty([]))
|
||||||
ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
|
ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
|
||||||
ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect())
|
ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect())
|
||||||
ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
|
ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
|
||||||
if (params.fastp_clip_merge) {
|
if (params.fastp_clip_merge) {
|
||||||
ch_multiqc_files = ch_multiqc_files.mix(FASTQ_PREPROCESSING.out.mqc)
|
ch_multiqc_files = ch_multiqc_files.mix(SHORTREAD_PREPROCESSING.out.mqc)
|
||||||
}
|
}
|
||||||
if (params.run_kraken2) {
|
if (params.run_kraken2) {
|
||||||
ch_multiqc_files = ch_multiqc_files.mix(KRAKEN2_KRAKEN2.out.txt.collect{it[1]}.ifEmpty([]))
|
ch_multiqc_files = ch_multiqc_files.mix(KRAKEN2_KRAKEN2.out.txt.collect{it[1]}.ifEmpty([]))
|
||||||
|
|
Loading…
Reference in a new issue