2021-02-03 16:02:58 +00:00
|
|
|
#!/usr/bin/env nextflow
|
|
|
|
|
|
|
|
|
|
nextflow.enable.dsl = 2
|
|
|
|
|
|
2021-07-21 12:30:52 +00:00
|
|
|
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'] )
|
|
|
|
|
|
2021-02-03 16:02:58 +00:00
|
|
|
|
|
|
|
|
workflow test_star_alignment_single_end {
|
|
|
|
|
input = [ [ id:'test', single_end:true ], // meta map
|
2021-07-21 12:30:52 +00:00
|
|
|
[ file(params.test_data['homo_sapiens']['illumina']['test_rnaseq_1_fastq_gz'], checkIfExists: true) ]
|
2021-03-24 09:53:41 +00:00
|
|
|
]
|
2021-07-21 12:30:52 +00:00
|
|
|
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
|
|
|
|
|
gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
|
|
|
|
|
|
2021-03-24 09:53:41 +00:00
|
|
|
STAR_GENOMEGENERATE ( fasta, gtf )
|
2021-02-03 16:02:58 +00:00
|
|
|
STAR_ALIGN ( input, STAR_GENOMEGENERATE.out.index, gtf )
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
workflow test_star_alignment_paired_end {
|
2021-03-24 09:53:41 +00:00
|
|
|
input = [ [ id:'test', single_end:false ], // meta map
|
2021-07-21 12:30:52 +00:00
|
|
|
[ 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) ]
|
2021-03-24 09:53:41 +00:00
|
|
|
]
|
2021-07-21 12:30:52 +00:00
|
|
|
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
|
|
|
|
|
gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
|
Converge test data usage (#249)
* initial data restructuing
* fixed bedtools_complement
* fixed bedtools_genomecov
* fixed bedtools_getfasta
* fixed bedtools_intersect
* fixed bedtools maskfasta
* fixed bedtools_merge
* fixed bedtools_slop
* fixed bedtools_sort
* fixed bismark_genome_preparation
* fixed blast
* fixed bowtie data
* fixed bowtie2 data
* fixed bwa data
* fixed bwamem2 data usage
* fixed cat_fastq data
* fixed cutadapt data
* fixed dsh data
* fixed fastp data
* fixed fastqc; fixed bug with wrong fastq format
* fixed gatk
* fixed data for gffread, gunzip
* fixed ivar paths
* fixed data paths for minimap2
* fixed mosdepth
* fixed multiqc, pangolin
* fixed picard data paths
* fixed data paths for qualimap, quast
* fixed salmon data paths
* fixed samtools paths
* fixed seqwish, stringtie paths
* fixed tabix, trimgalore paths
* cleaned up data
* added first description to README
* changed test data naming again; everything up to bwa fixed
* everything up to gatk4
* fixed everything up to ivar
* fixed everything up to picard
* everything up to quast
* everything fixed up to stringtie
* switched everyting to 'test' naming scheme
* fixed samtools and ivar tests
* cleaned up README a bit
* add (simulated) methylation test data
based on SARS-CoV-2 genome; simulated with Sherman --non_dir --genome sarscov2/fasta/ --paired -n 10000 -l 100 --CG 20 --CH 90
* bwameth/align: update data paths and checksums
also, build index on the go
* bwameth/index: update data paths and checksums
* methyldackel/extract: update data paths and checksums
* methyldackel/mbias: update data paths and checksums
* bismark/deduplicate: update data paths and checksums
* remove obsolete testdata
* remove empty 'dummy_file.txt'
* update data/README.md
* methyldackel: fix test
* Revert "methyldackel: fix test"
This reverts commit f175a32d144b1b0bfa0c6885da80c51e3cfe038a.
* methyldackel: fix test
for real
* move test.genome.sizes
* changed test names
* switched genomic to genome and transcriptome
* fix bedtools, blast
* fix gtf, tabix, .paf
* fix bowtie,bwa,bwameth
* fixed: bwa, bwamem, gatk, gffread, quast
* fixed bismark and blast
* fixed remaining tests
* delete bam file
Co-authored-by: phue <patrick.huether@gmail.com>
2021-03-04 10:10:57 +00:00
|
|
|
|
2021-02-03 16:02:58 +00:00
|
|
|
STAR_GENOMEGENERATE ( fasta, gtf )
|
|
|
|
|
STAR_ALIGN ( input, STAR_GENOMEGENERATE.out.index, gtf )
|
|
|
|
|
}
|
2021-07-21 12:30:52 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
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 )
|
|
|
|
|
}
|