Merge pull request #30 from FelixKrueger/bowtie2

Added Bowtie2 module and test workflow
This commit is contained in:
Phil Ewels 2020-07-11 13:27:20 +02:00 committed by GitHub
commit edda7433d3
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 122 additions and 0 deletions

52
tools/bowtie2/main.nf Normal file
View file

@ -0,0 +1,52 @@
nextflow.preview.dsl=2
params.genome = ''
process BOWTIE2 {
// depending on the genome used one might want/need to adjust the memory settings.
// For the E. coli test data this is probably not required
// label 'bigMem'
// label 'multiCore'
input:
tuple val(name), path(reads)
val (outdir)
val (bowtie2_args)
val (verbose)
output:
path "*bam", emit: bam
path "*stats.txt", emit: stats
publishDir "$outdir/bowtie2",
mode: "copy", overwrite: true
script:
if (verbose){
println ("[MODULE] BOWTIE2 ARGS: " + bowtie2_args)
}
cores = 4
readString = ""
// Options we add are
bowtie2_options = bowtie2_args
bowtie2_options += " --no-unal " // We don't need unaligned reads in the BAM file
// single-end / paired-end distinction. Might also be handled via params.single_end
if (reads instanceof List) {
readString = "-1 " + reads[0] + " -2 " + reads[1]
}
else {
readString = "-U " + reads
}
index = params.genome["bowtie2"]
bowtie2_name = name + "_" + params.genome["name"]
"""
bowtie2 -x ${index} -p ${cores} ${bowtie2_options} ${readString} 2>${bowtie2_name}_bowtie2_stats.txt | samtools view -bS -F 4 -F 8 -F 256 -> ${bowtie2_name}_bowtie2.bam
"""
}

37
tools/bowtie2/meta.yml Normal file
View file

@ -0,0 +1,37 @@
name: Bowtie 2
description: Ultrafast alignment to reference genome
keywords:
- Alignment
- Short reads
- FM Index
tools:
- fastqc:
description: |
Bowtie 2 is an ultrafast and memory-efficient tool for aligning sequencing reads
to long reference sequences. It is particularly good at aligning reads of about
50 up to 100s or 1,000s of characters, and particularly good at aligning to relatively
long (e.g. mammalian) genomes. Bowtie 2 indexes the genome with an FM Index to keep
its memory footprint small: for the human genome, its memory footprint is typically
around 3.2 GB. Bowtie 2 supports gapped, local, and paired-end alignment modes.
homepage: http://bowtie-bio.sourceforge.net/bowtie2/index.shtml
documentation: http://bowtie-bio.sourceforge.net/bowtie2/manual.shtml
input:
-
- sample_id:
type: string
description: Sample identifier
- reads:
type: file
description: Input FastQ file, or pair of files
output:
-
- report:
type: file
description: mapping statistics report
pattern: *bowtie2_stats.txt
- alignment:
type: file
description: alignment file in BAM format
pattern: *bowtie2.bam
authors:
- @FelixKrueger

31
tools/bowtie2/test/main.nf Executable file
View file

@ -0,0 +1,31 @@
#!/usr/bin/env nextflow
nextflow.preview.dsl=2
params.outdir = "."
params.genome = ""
params.bowtie2_args = ''
// Bowtie2 arguments should be supplied in the following format to work:
// --bowtie2_args="--score-min L,0,-0.8"
params.verbose = false
if (params.verbose){
println ("[WORKFLOW] BOWTIE2 ARGS: " + params.bowtie2_args)
}
// for other genomes this needs to be handled somehow to return all possible genomes
genomeValues = ["name" : params.genome]
genomeValues["bowtie2"] = "/bi/home/fkrueger/VersionControl/nf-core-modules/test-datasets/indices/bowtie2/E_coli/${params.genome}";
include '../main.nf' params(genome: genomeValues)
ch_read_files = Channel
.fromFilePairs('../../../test-datasets/Ecoli*{1,2}.fastq.gz',size:-1)
// .view() // to check whether the input channel works
workflow {
main:
BOWTIE2(ch_read_files, params.outdir, params.bowtie2_args, params.verbose)
}

View file

@ -0,0 +1,2 @@
docker.enabled = true
params.outdir = './results'