From e61e9861322989830ea05819e08d866c4cfaa4ac Mon Sep 17 00:00:00 2001
From: Brandi Cantarel <brandi.cantarel@utsouthwestern.edu>
Date: Fri, 22 May 2020 14:00:03 -0500
Subject: [PATCH] update process_scripts
---
astrocyte_pkg.yml | 6 +-
workflow/main.nf | 254 ++++++++++++++++-----------------------
workflow/process_scripts | 2 +-
3 files changed, 109 insertions(+), 153 deletions(-)
diff --git a/astrocyte_pkg.yml b/astrocyte_pkg.yml
index afd00cb..1b88f58 100644
--- a/astrocyte_pkg.yml
+++ b/astrocyte_pkg.yml
@@ -168,12 +168,12 @@ workflow_parameters:
- id: geneset
type: select
choices:
- - ['h.all.v5.1.symbols.gmt','Hallmark Gene Sets']
+ - ['h.all.v6.2.symbols.gmt','Hallmark Gene Sets']
- ['c2.all.v5.1.symbols.gmt','Curated Gene Sets']
- ['c3.all.v5.1.symbols.gmt','Motif Gene Sets']
- - ['c5.all.v5.1.entrez.gmt','Gene Ontology Gene Sets']
+ - ['c5.all.v6.2.symbols.gmt','Gene Ontology Gene Sets']
- ['c6.all.v5.1.symbols.gmt','Oncogenic Signatures']
- - ['c7.all.v5.1.entrez.gmt','Immunological Signatures']
+ - ['c7.all.v5.1.symbols.gmt','Immunological Signatures']
required: true
description: |
diff --git a/workflow/main.nf b/workflow/main.nf
index 1d4104c..c276a1e 100644
--- a/workflow/main.nf
+++ b/workflow/main.nf
@@ -59,34 +59,31 @@ fastqs
if (params.pairs == 'pe') {
spltnames
- .splitCsv()
- .filter { fileMap.get(it[1]) != null & fileMap.get(it[2]) != null }
- .map { it -> tuple(it[0], fileMap.get(it[1]), fileMap.get(it[2])) }
- .set { read }
+ .splitCsv()
+ .filter { fileMap.get(it[1]) != null & fileMap.get(it[2]) != null }
+ .map { it -> tuple(it[0], fileMap.get(it[1]), fileMap.get(it[2])) }
+ .set { read }
} else {
spltnames
- .splitCsv()
- .filter { fileMap.get(it[1]) != null }
- .map { it -> tuple(it[0], fileMap.get(it[1]),'') }
- .set { read }
+ .splitCsv()
+ .filter { fileMap.get(it[1]) != null }
+ .map { it -> tuple(it[0], fileMap.get(it[1]),'') }
+ .set { read }
}
if( ! read ) { error "Didn't match any input files with entries in the design file" }
// Trim raw reads using trimgalore
process trim {
- errorStrategy 'ignore'
-
- input:
- set pair_id, file(read1), file(read2) from read
-
- output:
- set pair_id, file("${pair_id}.trim.R1.fastq.gz"),file("${pair_id}.trim.R2.fastq.gz") into trimread
- set pair_id, file("${pair_id}.trim.R1.fastq.gz"),file("${pair_id}.trim.R2.fastq.gz") into fusionfq
-
- script:
- """
- bash $baseDir/process_scripts/preproc_fastq/trimgalore.sh -p ${pair_id} -a ${read1} -b ${read2}
- """
+ errorStrategy 'ignore'
+ input:
+ set pair_id, file(read1), file(read2) from read
+ output:
+ set pair_id, file("${pair_id}.trim.R1.fastq.gz"),file("${pair_id}.trim.R2.fastq.gz") into trimread
+ set pair_id, file("${pair_id}.trim.R1.fastq.gz"),file("${pair_id}.trim.R2.fastq.gz") into fusionfq
+ script:
+ """
+ bash $baseDir/process_scripts/preproc_fastq/trimgalore.sh -p ${pair_id} -a ${read1} -b ${read2}
+ """
}
// Align trimmed reads to genome indes with hisat2
@@ -95,157 +92,116 @@ process trim {
// Alignment stats with samtools
process starfusion {
- errorStrategy 'ignore'
- publishDir "$params.output", mode: 'copy'
-
- input:
- set pair_id, file(fq1), file(fq2) from fusionfq
-
- output:
- file("${pair_id}.starfusion.txt") into fusionout
-
- when:
- params.fusion == 'detect' && params.pairs == 'pe'
-
- script:
- """
- bash $baseDir/process_scripts/alignment/starfusion.sh -p ${pair_id} -r ${index_path} -a ${fq1} -b ${fq2} -m trinity -f
- """
+ errorStrategy 'ignore'
+ publishDir "$params.output", mode: 'copy'
+ input:
+ set pair_id, file(fq1), file(fq2) from fusionfq
+ output:
+ file("${pair_id}.starfusion.txt") into fusionout
+ when:
+ params.fusion == 'detect' && params.pairs == 'pe'
+ script:
+ """
+ bash $baseDir/process_scripts/alignment/starfusion.sh -p ${pair_id} -r ${index_path} -a ${fq1} -b ${fq2} -m trinity -f
+ """
}
process align {
- errorStrategy 'ignore'
- publishDir "$params.output", mode: 'copy'
-
- input:
- set pair_id, file(fq1), file(fq2) from trimread
-
- output:
- set pair_id, file("${pair_id}.bam") into aligned
- set pair_id, file("${pair_id}.bam") into aligned2
- file("${pair_id}.alignerout.txt") into hsatout
-
- script:
- """
- bash $baseDir/process_scripts/alignment/rnaseqalign.sh -a $params.align -p ${pair_id} -r ${index_path} -x ${fq1} -y ${fq2}
- """
+ errorStrategy 'ignore'
+ publishDir "$params.output", mode: 'copy'
+ input:
+ set pair_id, file(fq1), file(fq2) from trimread
+ output:
+ set pair_id, file("${pair_id}.bam") into aligned
+ set pair_id, file("${pair_id}.bam") into aligned2
+ file("${pair_id}.alignerout.txt") into hsatout
+ script:
+ """
+ bash $baseDir/process_scripts/alignment/rnaseqalign.sh -a $params.align -p ${pair_id} -r ${index_path} -x ${fq1} -y ${fq2}
+ """
}
process alignqc {
- errorStrategy 'ignore'
- publishDir "$params.output", mode: 'copy'
-
- input:
- set pair_id, file(bam) from aligned2
-
- output:
- file("${pair_id}.flagstat.txt") into alignstats
- set file("${pair_id}_fastqc.zip"),file("${pair_id}_fastqc.html") into fastqc
-
- script:
- """
- bash $baseDir/process_scripts/alignment/bamqc.sh -p ${pair_id} -b ${bam} -y rna
- """
+ errorStrategy 'ignore'
+ publishDir "$params.output", mode: 'copy'
+ input:
+ set pair_id, file(bam) from aligned2
+ output:
+ file("${pair_id}.flagstat.txt") into alignstats
+ set file("${pair_id}_fastqc.zip"),file("${pair_id}_fastqc.html") into fastqc
+ script:
+ """
+ bash $baseDir/process_scripts/alignment/bamqc.sh -p ${pair_id} -b ${bam} -y rna
+ """
}
// Summarize all flagstat output
process parse_alignstat {
- publishDir "$params.output", mode: 'copy'
-
- input:
- file(txt) from alignstats.toList()
- file(txt) from hsatout.toList()
-
- output:
- file('alignment.summary.txt')
-
- script:
- """
- perl $baseDir/scripts/parse_flagstat.pl *.flagstat.txt
- """
+ publishDir "$params.output", mode: 'copy'
+ input:
+ file(txt) from alignstats.toList()
+ file(txt) from hsatout.toList()
+ output:
+ file('alignment.summary.txt')
+ script:
+ """
+ perl $baseDir/scripts/parse_flagstat.pl *.flagstat.txt
+ """
}
// Identify duplicate reads with Picard
process markdups {
- publishDir "$params.output", mode: 'copy'
-
- input:
- set pair_id, file(sbam) from aligned
-
- output:
- set pair_id, file("${pair_id}.dedup.bam") into deduped1
- set pair_id, file("${pair_id}.dedup.bam") into deduped2
-
- script:
- """
- bash $baseDir/process_scripts/alignment/markdups.sh -a $params.markdups -b $sbam -p $pair_id
- """
+ publishDir "$params.output", mode: 'copy'
+ input:
+ set pair_id, file(sbam) from aligned
+ output:
+ set pair_id, file("${pair_id}.dedup.bam") into deduped1
+ set pair_id, file("${pair_id}.dedup.bam") into deduped2
+ script:
+ """
+ bash $baseDir/process_scripts/alignment/markdups.sh -a $params.markdups -b $sbam -p $pair_id
+ """
}
// Read summarization with subread
// Assemble transcripts with stringtie
process geneabund {
- errorStrategy 'ignore'
- publishDir "$params.output", mode: 'copy'
-
- input:
- set pair_id, file(sbam) from deduped1
-
- output:
- file("${pair_id}.cts") into counts
- file("${pair_id}.cts.summary") into ctsum
- file("${pair_id}_stringtie") into strcts
- file("${pair_id}.fpkm.txt") into fpkm
-
- script:
- """
- bash $baseDir/process_scripts/genect_rnaseq/geneabundance.sh -s $params.stranded -g ${gtf_file} -p ${pair_id} -b ${sbam}
- """
+ errorStrategy 'ignore'
+ publishDir "$params.output", mode: 'copy'
+ input:
+ set pair_id, file(sbam) from deduped1
+ output:
+ file("${pair_id}.cts") into counts
+ file("${pair_id}.cts.summary") into ctsum
+ file("${pair_id}_stringtie") into strcts
+ file("${pair_id}.fpkm.txt") into fpkm
+ script:
+ """
+ bash $baseDir/process_scripts/genect_rnaseq/geneabundance.sh -s $params.stranded -g ${gtf_file} -p ${pair_id} -b ${sbam}
+ """
}
process statanal {
- errorStrategy 'ignore'
- publishDir "$params.output", mode: 'copy'
-
- input:
- file count_file from counts.toList()
- file count_sum from ctsum.toList()
- file newdesign name 'design.txt'
- file genenames
- file geneset name 'geneset.gmt'
- file fpkm_file from fpkm.toList()
- file stringtie_dir from strcts.toList()
-
- output:
- file "*.txt" into txtfiles
- file "*.png" into psfiles
- file("*.rda") into rdafiles
- file("geneset.shiny.gmt") into gmtfile
-
- script:
- """
- bash $baseDir/process_scripts/genect_rnaseq/statanal.sh -d $params.dea
- """
-}
-
-process gatkbam {
- errorStrategy 'ignore'
- publishDir "$params.output", mode: 'copy'
-
- input:
- set pair_id, file(rbam) from deduped2
-
- output:
- set file("${pair_id}.final.bam"),file("${pair_id}.final.bai") into gatkbam
-
- when:
- params.align == 'hisat' && $index_path == '/project/shared/bicf_workflow_ref/GRCh38/'
-
- script:
- """
- bash $baseDir/process_scripts/variants/gatkrunner.sh -a gatkbam_rna -b $rbam -r ${index_path}/hisat_index -p $pair_id
- """
+ errorStrategy 'ignore'
+ publishDir "$params.output", mode: 'copy'
+ input:
+ file count_file from counts.toList()
+ file count_sum from ctsum.toList()
+ file newdesign name 'design.txt'
+ file genenames
+ file geneset name 'geneset.gmt'
+ file fpkm_file from fpkm.toList()
+ file stringtie_dir from strcts.toList()
+ output:
+ file "*.txt" into txtfiles
+ file "*.png" into psfiles
+ file("*.rda") into rdafiles
+ file("geneset.shiny.gmt") into gmtfile
+ script:
+ """
+ bash $baseDir/process_scripts/genect_rnaseq/statanal.sh -d $params.dea
+ """
}
diff --git a/workflow/process_scripts b/workflow/process_scripts
index 12ef616..c2e0f1f 160000
--- a/workflow/process_scripts
+++ b/workflow/process_scripts
@@ -1 +1 @@
-Subproject commit 12ef61633f4a6008cba307bb4371845163987371
+Subproject commit c2e0f1fac2b0a90fd2d87d2aba9d885855d22272
--
GitLab