Tool/snap aligner single (#1510)

* first commit

* add tool

* fix tests

* fix indents

* Update modules/snapaligner/single/meta.yml

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* fix comments

* fix versions

* prettier

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>
This commit is contained in:
Matthias De Smet 2022-04-12 11:20:35 +02:00 committed by GitHub
parent 09125979cc
commit b59713e623
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 124 additions and 0 deletions

View file

@ -0,0 +1,41 @@
process SNAPALIGNER_SINGLE {
tag '$meta.id'
label 'process_high'
conda (params.enable_conda ? "bioconda::snap-aligner=2.0.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/snap-aligner:2.0.1--hd03093a_1':
'quay.io/biocontainers/snap-aligner:2.0.1--hd03093a_1' }"
input:
tuple val(meta), path(reads)
path index
output:
tuple val(meta), path("*.bam"), emit: bam
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}"
"""
mkdir -p index
mv $index index/
snap-aligner single \\
index \\
${reads.join(" ")} \\
-o -bam ${prefix}.bam \\
-t ${task.cpus} \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
snapaligner: \$(snap-aligner 2>&1| head -n 1 | sed 's/^.*version //;s/.\$//')
END_VERSIONS
"""
}

View file

@ -0,0 +1,48 @@
name: "snapaligner_single"
description: Performs single end fastq alignment to a fasta reference using SNAP
keywords:
- alignment
- map
- fastq
- bam
- sam
tools:
- "snapaligner":
description: "Scalable Nucleotide Alignment Program -- a fast and accurate read aligner for high-throughput sequencing data"
homepage: "http://snap.cs.berkeley.edu"
documentation: "https://1drv.ms/b/s!AhuEg_0yZD86hcpblUt-muHKYsG8fA?e=R8ogug"
tool_dev_url: "https://github.com/amplab/snap"
doi: "10.1101/2021.11.23.469039"
licence: "['Apache v2']"
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- reads:
type: file
description: List of single end input files
pattern: "*.{fastq.gz,fq.gz,fastq,fq,bam}"
- index:
type: file
description: List of SNAP genome index files
pattern: "{Genome,GenomeIndex,GenomeIndexHash,OverflowTable}"
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"
- bam:
type: file
description: Aligned BAM file
pattern: "*.{bam}"
authors:
- "@matthdsm"

View file

@ -1679,6 +1679,10 @@ snapaligner/paired:
- modules/snapaligner/paired/**
- tests/modules/snapaligner/paired/**
snapaligner/single:
- modules/snapaligner/single/**
- tests/modules/snapaligner/single/**
snpdists:
- modules/snpdists/**
- tests/modules/snpdists/**

View file

@ -0,0 +1,17 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { SNAPALIGNER_INDEX } from '../../../../modules/snapaligner/index/main.nf'
include { SNAPALIGNER_SINGLE } from '../../../../modules/snapaligner/single/main.nf'
workflow test_snapaligner_single {
input = [
[ id:'test', single_end:false ], // meta map
[file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)]
]
SNAPALIGNER_INDEX ( file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true),[],[],[])
SNAPALIGNER_SINGLE ( input, SNAPALIGNER_INDEX.out.index )
}

View file

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

View file

@ -0,0 +1,9 @@
- name: snapaligner single test_snapaligner_single
command: nextflow run tests/modules/snapaligner/single -entry test_snapaligner_single -c tests/config/nextflow.config
tags:
- snapaligner/single
- snapaligner
files:
- path: output/snapaligner/test.bam
md5sum: 696f7ea8e1aa5f9d7dafb9d0134fe25d
- path: output/snapaligner/versions.yml