Updated the version of STAR in align and genomegenerate modules (#604)

* Updated the version of STAR in align and genomegenerate modules

* Changes in test.yml

* Changes in test.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>
This commit is contained in:
praveenraj2018 2021-07-21 14:30:52 +02:00 committed by GitHub
parent 1a26d48104
commit f43778b0e6
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 184 additions and 104 deletions

View file

@ -12,11 +12,11 @@ process STAR_ALIGN {
saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
// Note: 2.7X indices incompatible with AWS iGenomes.
conda (params.enable_conda ? 'bioconda::star=2.6.1d' : null)
conda (params.enable_conda ? 'bioconda::star=2.7.9a' : null)
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container 'https://depot.galaxyproject.org/singularity/star:2.6.1d--0'
container 'https://depot.galaxyproject.org/singularity/star:2.7.9a--h9ee0642_0'
} else {
container 'quay.io/biocontainers/star:2.6.1d--0'
container 'quay.io/biocontainers/star:2.7.9a--h9ee0642_0'
}
input:

View file

@ -12,11 +12,11 @@ process STAR_GENOMEGENERATE {
saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'index', meta:[:], publish_by_meta:[]) }
// Note: 2.7X indices incompatible with AWS iGenomes.
conda (params.enable_conda ? "bioconda::star=2.6.1d bioconda::samtools=1.10 conda-forge::gawk=5.1.0" : null)
conda (params.enable_conda ? "bioconda::star=2.7.9a bioconda::samtools=1.13 conda-forge::gawk=5.1.0" : null)
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0"
container "https://depot.galaxyproject.org/singularity/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:a7908dfb0485a80ca94e4d17b0ac991532e4e989-0"
} else {
container "quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0"
container "quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:a7908dfb0485a80ca94e4d17b0ac991532e4e989-0"
}
input:

View file

@ -2,28 +2,43 @@
nextflow.enable.dsl = 2
include { STAR_GENOMEGENERATE } from '../../../../modules/star/genomegenerate/main.nf' addParams( options: [args: '--genomeSAindexNbases 9'] )
include { STAR_ALIGN } from '../../../../modules/star/align/main.nf' addParams( options: [args: '--readFilesCommand zcat'] )
include { STAR_GENOMEGENERATE } from '../../../../modules/star/genomegenerate/main.nf' addParams( options: [args: '--genomeSAindexNbases 9'] )
include { STAR_ALIGN } from '../../../../modules/star/align/main.nf' addParams( options: [args: '--readFilesCommand zcat'] )
include { STAR_ALIGN as STAR_FOR_ARRIBA } from '../../../../modules/star/align/main.nf' addParams( options: [args: '--readFilesCommand zcat --outSAMtype BAM Unsorted --outSAMunmapped Within --outBAMcompression 0 --outFilterMultimapNmax 50 --peOverlapNbasesMin 10 --alignSplicedMateMapLminOverLmate 0.5 --alignSJstitchMismatchNmax 5 -1 5 5 --chimSegmentMin 10 --chimOutType WithinBAM HardClip --chimJunctionOverhangMin 10 --chimScoreDropMax 30 --chimScoreJunctionNonGTAG 0 --chimScoreSeparation 1 --chimSegmentReadGapMax 3 --chimMultimapNmax 50'] )
workflow test_star_alignment_single_end {
input = [ [ id:'test', single_end:true ], // meta map
[ file("${launchDir}/tests/data/generic/fastq/test_single_end.fastq.gz", checkIfExists: true) ]
[ file(params.test_data['homo_sapiens']['illumina']['test_rnaseq_1_fastq_gz'], checkIfExists: true) ]
]
fasta = file("${launchDir}/tests/data/generic/fasta/GCF_000019425.1_ASM1942v1_genomic.fna", checkIfExists: true)
gtf = file("${launchDir}/tests/data/generic/gtf/GCF_000019425.1_ASM1942v1_genomic.gtf", checkIfExists: true)
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
STAR_GENOMEGENERATE ( fasta, gtf )
STAR_ALIGN ( input, STAR_GENOMEGENERATE.out.index, gtf )
}
workflow test_star_alignment_paired_end {
input = [ [ id:'test', single_end:false ], // meta map
[ file("${launchDir}/tests/data/generic/fastq/test_R1.fastq.gz", checkIfExists: true),
file("${launchDir}/tests/data/generic/fastq/test_R2.fastq.gz", checkIfExists: true) ]
[ file(params.test_data['homo_sapiens']['illumina']['test_rnaseq_1_fastq_gz'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test_rnaseq_2_fastq_gz'], checkIfExists: true) ]
]
fasta = file("${launchDir}/tests/data/generic/fasta/GCF_000019425.1_ASM1942v1_genomic.fna", checkIfExists: true)
gtf = file("${launchDir}/tests/data/generic/gtf/GCF_000019425.1_ASM1942v1_genomic.gtf", checkIfExists: true)
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
STAR_GENOMEGENERATE ( fasta, gtf )
STAR_ALIGN ( input, STAR_GENOMEGENERATE.out.index, gtf )
}
workflow test_star_alignment_paired_end_for_fusion {
input = [ [ id:'test', single_end:false ], // meta map
[ file(params.test_data['homo_sapiens']['illumina']['test_rnaseq_1_fastq_gz'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test_rnaseq_2_fastq_gz'], checkIfExists: true) ]
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
STAR_GENOMEGENERATE ( fasta, gtf )
STAR_FOR_ARRIBA ( input, STAR_GENOMEGENERATE.out.index, gtf )
}

View file

@ -1,73 +1,132 @@
- name: star align single-end
command: nextflow run ./tests/modules/star/align -entry test_star_alignment_single_end -c tests/config/nextflow.config
- name: star align test_star_alignment_single_end
command: nextflow run tests/modules/star/align -entry test_star_alignment_single_end -c tests/config/nextflow.config
tags:
- star
- star/align
files:
- path: output/star/star/Genome
md5sum: 323c992bac354f93073ce0fc43f222f8
- path: output/star/star/SA
md5sum: 3e70e4fc6d031e1915bb510727f2c559
- path: output/star/star/SAindex
md5sum: a94198b95a245d4f64af2a7133b6ec7b
- path: output/star/star/chrLength.txt
md5sum: f2bea3725fe1c01420c57fb73bdeb31a
- path: output/star/star/chrNameLength.txt
md5sum: c7ceb0a8827b2ea91c386933bee48742
- path: output/star/star/chrStart.txt
md5sum: faf5c55020c99eceeef3e34188ac0d2f
- path: output/star/star/exonGeTrInfo.tab
md5sum: aec6e7a1ae3fc8c638ce5a9ce9c886b6
- path: output/star/star/exonInfo.tab
md5sum: 42eca6ebc2dc72d9d6e6b3acd3714343
- path: output/star/star/genomeParameters.txt
md5sum: 05e1041cbfb7f81686e17bc80b3ddcea
- path: output/star/star/sjdbInfo.txt
md5sum: 1082ab459363b3f2f7aabcef0979c1ed
- path: output/star/star/sjdbList.fromGTF.out.tab
md5sum: d41d8cd98f00b204e9800998ecf8427e
- path: output/star/star/sjdbList.out.tab
md5sum: d41d8cd98f00b204e9800998ecf8427e
- path: output/star/star/transcriptInfo.tab
md5sum: 8fbe69abbbef4f89da3854873984dbac
- path: output/index/star/Genome
md5sum: a654229fbca6071dcb6b01ce7df704da
- path: output/index/star/Log.out
- path: output/index/star/SA
md5sum: 8c3edc46697b72c9e92440d4cf43506c
- path: output/index/star/SAindex
md5sum: 2a0c675d8b91d8e5e8c1826d3500482e
- path: output/index/star/chrLength.txt
md5sum: c81f40f27e72606d7d07097c1d56a5b5
- path: output/index/star/chrName.txt
md5sum: 5ae68a67b70976ee95342a7451cb5af1
- path: output/index/star/chrNameLength.txt
md5sum: b190587cae0531f3cf25552d8aa674db
- path: output/index/star/chrStart.txt
md5sum: 8d3291e6bcdbe9902fbd7c887494173f
- path: output/index/star/exonGeTrInfo.tab
md5sum: d04497f69d6ef889efd4d34fe63edcc4
- path: output/index/star/exonInfo.tab
md5sum: 0d560290fab688b7268d88d5494bf9fe
- path: output/index/star/geneInfo.tab
md5sum: 8b608537307443ffaee4927d2b428805
- path: output/index/star/genomeParameters.txt
md5sum: 3097677f4d8b2cb66770b9e55d343a7f
- path: output/index/star/sjdbInfo.txt
md5sum: 5690ea9d9f09f7ff85b7fd47bd234903
- path: output/index/star/sjdbList.fromGTF.out.tab
md5sum: 8760c33e966dad0b39f440301ebbdee4
- path: output/index/star/sjdbList.out.tab
md5sum: 9e4f991abbbfeb3935a2bb21b9e258f1
- path: output/index/star/transcriptInfo.tab
md5sum: 0c3a5adb49d15e5feff81db8e29f2e36
- path: output/star/test.Aligned.out.bam
md5sum: b7f113f12ff62e09d16fa0ace290d03e
md5sum: 509d7f1fba3350913c8ea13f01917085
- path: output/star/test.Log.final.out
- path: output/star/test.Log.out
- path: output/star/test.Log.progress.out
- path: output/star/test.SJ.out.tab
md5sum: d41d8cd98f00b204e9800998ecf8427e
- name: star align paired-end
command: nextflow run ./tests/modules/star/align -entry test_star_alignment_paired_end -c tests/config/nextflow.config
- name: star align test_star_alignment_paired_end
command: nextflow run tests/modules/star/align -entry test_star_alignment_paired_end -c tests/config/nextflow.config
tags:
- star
- star/align
files:
- path: output/star/star/Genome
md5sum: 323c992bac354f93073ce0fc43f222f8
- path: output/star/star/SA
md5sum: 3e70e4fc6d031e1915bb510727f2c559
- path: output/star/star/SAindex
md5sum: a94198b95a245d4f64af2a7133b6ec7b
- path: output/star/star/chrLength.txt
md5sum: f2bea3725fe1c01420c57fb73bdeb31a
- path: output/star/star/chrNameLength.txt
md5sum: c7ceb0a8827b2ea91c386933bee48742
- path: output/star/star/chrStart.txt
md5sum: faf5c55020c99eceeef3e34188ac0d2f
- path: output/star/star/exonGeTrInfo.tab
md5sum: aec6e7a1ae3fc8c638ce5a9ce9c886b6
- path: output/star/star/exonInfo.tab
md5sum: 42eca6ebc2dc72d9d6e6b3acd3714343
- path: output/star/star/genomeParameters.txt
md5sum: 05e1041cbfb7f81686e17bc80b3ddcea
- path: output/star/star/sjdbInfo.txt
md5sum: 1082ab459363b3f2f7aabcef0979c1ed
- path: output/star/star/sjdbList.fromGTF.out.tab
md5sum: d41d8cd98f00b204e9800998ecf8427e
- path: output/star/star/sjdbList.out.tab
md5sum: d41d8cd98f00b204e9800998ecf8427e
- path: output/star/star/transcriptInfo.tab
md5sum: 8fbe69abbbef4f89da3854873984dbac
- path: output/index/star/Genome
md5sum: a654229fbca6071dcb6b01ce7df704da
- path: output/index/star/Log.out
- path: output/index/star/SA
md5sum: 8c3edc46697b72c9e92440d4cf43506c
- path: output/index/star/SAindex
md5sum: 2a0c675d8b91d8e5e8c1826d3500482e
- path: output/index/star/chrLength.txt
md5sum: c81f40f27e72606d7d07097c1d56a5b5
- path: output/index/star/chrName.txt
md5sum: 5ae68a67b70976ee95342a7451cb5af1
- path: output/index/star/chrNameLength.txt
md5sum: b190587cae0531f3cf25552d8aa674db
- path: output/index/star/chrStart.txt
md5sum: 8d3291e6bcdbe9902fbd7c887494173f
- path: output/index/star/exonGeTrInfo.tab
md5sum: d04497f69d6ef889efd4d34fe63edcc4
- path: output/index/star/exonInfo.tab
md5sum: 0d560290fab688b7268d88d5494bf9fe
- path: output/index/star/geneInfo.tab
md5sum: 8b608537307443ffaee4927d2b428805
- path: output/index/star/genomeParameters.txt
md5sum: 3097677f4d8b2cb66770b9e55d343a7f
- path: output/index/star/sjdbInfo.txt
md5sum: 5690ea9d9f09f7ff85b7fd47bd234903
- path: output/index/star/sjdbList.fromGTF.out.tab
md5sum: 8760c33e966dad0b39f440301ebbdee4
- path: output/index/star/sjdbList.out.tab
md5sum: 9e4f991abbbfeb3935a2bb21b9e258f1
- path: output/index/star/transcriptInfo.tab
md5sum: 0c3a5adb49d15e5feff81db8e29f2e36
- path: output/star/test.Aligned.out.bam
md5sum: a1f92e8dbeb954b6b8d3d7cc6b9814fb
md5sum: 64b408fb1d61e2de8ff51c847cd5bc52
- path: output/star/test.Log.final.out
- path: output/star/test.Log.out
- path: output/star/test.Log.progress.out
- path: output/star/test.SJ.out.tab
md5sum: d41d8cd98f00b204e9800998ecf8427e
- name: star align test_star_alignment_paired_end_for_fusion
command: nextflow run tests/modules/star/align -entry test_star_alignment_paired_end_for_fusion -c tests/config/nextflow.config
tags:
- star
- star/align
files:
- path: output/index/star/Genome
md5sum: a654229fbca6071dcb6b01ce7df704da
- path: output/index/star/Log.out
- path: output/index/star/SA
md5sum: 8c3edc46697b72c9e92440d4cf43506c
- path: output/index/star/SAindex
md5sum: 2a0c675d8b91d8e5e8c1826d3500482e
- path: output/index/star/chrLength.txt
md5sum: c81f40f27e72606d7d07097c1d56a5b5
- path: output/index/star/chrName.txt
md5sum: 5ae68a67b70976ee95342a7451cb5af1
- path: output/index/star/chrNameLength.txt
md5sum: b190587cae0531f3cf25552d8aa674db
- path: output/index/star/chrStart.txt
md5sum: 8d3291e6bcdbe9902fbd7c887494173f
- path: output/index/star/exonGeTrInfo.tab
md5sum: d04497f69d6ef889efd4d34fe63edcc4
- path: output/index/star/exonInfo.tab
md5sum: 0d560290fab688b7268d88d5494bf9fe
- path: output/index/star/geneInfo.tab
md5sum: 8b608537307443ffaee4927d2b428805
- path: output/index/star/genomeParameters.txt
md5sum: 3097677f4d8b2cb66770b9e55d343a7f
- path: output/index/star/sjdbInfo.txt
md5sum: 5690ea9d9f09f7ff85b7fd47bd234903
- path: output/index/star/sjdbList.fromGTF.out.tab
md5sum: 8760c33e966dad0b39f440301ebbdee4
- path: output/index/star/sjdbList.out.tab
md5sum: 9e4f991abbbfeb3935a2bb21b9e258f1
- path: output/index/star/transcriptInfo.tab
md5sum: 0c3a5adb49d15e5feff81db8e29f2e36
- path: output/star/test.Aligned.out.bam
md5sum: d724ca90a102347b9c5052a33ea4d308
- path: output/star/test.Log.final.out
- path: output/star/test.Log.out
- path: output/star/test.Log.progress.out
- path: output/star/test.SJ.out.tab
md5sum: 5155c9fd1f787ad6d7d80987fb06219c

View file

@ -1,31 +1,37 @@
- name: star genomegenerate
command: nextflow run ./tests/modules/star/genomegenerate -entry test_star_genomegenerate -c tests/config/nextflow.config
- name: star genomegenerate test_star_genomegenerate
command: nextflow run tests/modules/star/genomegenerate -entry test_star_genomegenerate -c tests/config/nextflow.config
tags:
- star
- star/genomegenerate
- star
files:
- path: ./output/index/star/Genome
md5sum: 323c992bac354f93073ce0fc43f222f8
- path: ./output/index/star/SA
md5sum: 3e70e4fc6d031e1915bb510727f2c559
- path: ./output/index/star/SAindex
md5sum: a94198b95a245d4f64af2a7133b6ec7b
- path: ./output/index/star/chrLength.txt
md5sum: f2bea3725fe1c01420c57fb73bdeb31a
- path: ./output/index/star/chrNameLength.txt
md5sum: c7ceb0a8827b2ea91c386933bee48742
- path: ./output/index/star/chrStart.txt
md5sum: faf5c55020c99eceeef3e34188ac0d2f
- path: ./output/index/star/exonGeTrInfo.tab
md5sum: aec6e7a1ae3fc8c638ce5a9ce9c886b6
- path: ./output/index/star/exonInfo.tab
md5sum: 42eca6ebc2dc72d9d6e6b3acd3714343
- path: ./output/index/star/sjdbInfo.txt
md5sum: 1082ab459363b3f2f7aabcef0979c1ed
- path: ./output/index/star/sjdbList.fromGTF.out.tab
md5sum: d41d8cd98f00b204e9800998ecf8427e
- path: ./output/index/star/sjdbList.out.tab
md5sum: d41d8cd98f00b204e9800998ecf8427e
- path: ./output/index/star/transcriptInfo.tab
md5sum: 8fbe69abbbef4f89da3854873984dbac
- path: ./output/index/star/genomeParameters.txt
- path: output/index/star/Genome
md5sum: a654229fbca6071dcb6b01ce7df704da
- path: output/index/star/Log.out
- path: output/index/star/SA
md5sum: 8c3edc46697b72c9e92440d4cf43506c
- path: output/index/star/SAindex
md5sum: d0fbf2789ee1e9f60c352ba3655d9de4
- path: output/index/star/chrLength.txt
md5sum: c81f40f27e72606d7d07097c1d56a5b5
- path: output/index/star/chrName.txt
md5sum: 5ae68a67b70976ee95342a7451cb5af1
- path: output/index/star/chrNameLength.txt
md5sum: b190587cae0531f3cf25552d8aa674db
- path: output/index/star/chrStart.txt
md5sum: 8d3291e6bcdbe9902fbd7c887494173f
- path: output/index/star/exonGeTrInfo.tab
md5sum: d04497f69d6ef889efd4d34fe63edcc4
- path: output/index/star/exonInfo.tab
md5sum: 0d560290fab688b7268d88d5494bf9fe
- path: output/index/star/geneInfo.tab
md5sum: 8b608537307443ffaee4927d2b428805
- path: output/index/star/genomeParameters.txt
md5sum: 5a1ec027e575c3d7c1851e6b80fb8c5d
- path: output/index/star/sjdbInfo.txt
md5sum: 5690ea9d9f09f7ff85b7fd47bd234903
- path: output/index/star/sjdbList.fromGTF.out.tab
md5sum: 8760c33e966dad0b39f440301ebbdee4
- path: output/index/star/sjdbList.out.tab
md5sum: 9e4f991abbbfeb3935a2bb21b9e258f1
- path: output/index/star/transcriptInfo.tab
md5sum: 0c3a5adb49d15e5feff81db8e29f2e36