Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Replacing tab with spaces #7

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Replacing tab with spaces #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fd8d58a
Replacing tab with spaces
Arun-George-Zachariah Feb 15, 2021
77ac913
Adding ReadGroup to the workflow.
Arun-George-Zachariah Feb 21, 2021
5b667fa
Changes done for including hg38 references.
Arun-George-Zachariah Apr 11, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
54 changes: 46 additions & 8 deletions gatk4-rna-best-practices.wdl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,7 +132,6 @@
gatk_path = gatk_path
}


call SplitNCigarReads {
input:
input_bam = MarkDuplicates.output_bam,
Expand All @@ -147,11 +146,19 @@
gatk_path = gatk_path
}

call AddOrReplaceReadGroups {
input:
input_bam = SplitNCigarReads.output_bam,
input_bam_index = SplitNCigarReads.output_bam_index,
arg_output_file = sampleName + ".SplitNCigarReads.read-group",
gatk_path = gatk_path,
docker = gatk4_docker,
preemptible_count = preemptible_count
}

call BaseRecalibrator {
input:
input_bam = SplitNCigarReads.output_bam,
input_bam_index = SplitNCigarReads.output_bam_index,
input_bam = AddOrReplaceReadGroups.output_bam,
recal_output_file = sampleName + ".recal_data.csv",
dbSNP_vcf = dbSnpVcf,
dbSNP_vcf_index = dbSnpVcfIndex,
Expand All @@ -167,8 +174,7 @@

call ApplyBQSR {
input:
input_bam = SplitNCigarReads.output_bam,
input_bam_index = SplitNCigarReads.output_bam_index,
input_bam = AddOrReplaceReadGroups.output_bam,
base_name = sampleName + ".aligned.duplicates_marked.recalibrated",
ref_fasta = refFasta,
ref_fasta_index = refFastaIndex,
Expand Down Expand Up @@ -257,7 +263,7 @@ task gtfToCallingIntervals {

command <<<

set -e
set -e

Rscript --no-save -<<'RCODE'
gtf = read.table("${gtf}", sep="\t")
Expand Down Expand Up @@ -527,10 +533,43 @@ task SplitNCigarReads {
}
}

task AddOrReplaceReadGroups {
File input_bam
File input_bam_index
String arg_output_file

String gatk_path

String docker
Int preemptible_count

command <<<
${gatk_path} \
AddOrReplaceReadGroups \
-I ${input_bam} \
-O ${arg_output_file}.bam \
--RGSM sample \
--RGPU unit \
--RGID groupID \
--RGLB lib \
--RGPL Illumina
>>>

output {
File output_bam = "${arg_output_file}.bam"
}

runtime {
memory: "6 GB"
disks: "local-disk " + sub((size(input_bam,"GB")*3)+30, "\\..*", "") + " HDD"
docker: docker
preemptible: preemptible_count
}
}

task BaseRecalibrator {

File input_bam
File input_bam_index
String recal_output_file

File dbSNP_vcf
Expand Down Expand Up @@ -576,7 +615,6 @@ task BaseRecalibrator {
task ApplyBQSR {

File input_bam
File input_bam_index
String base_name
File recalibration_report

Expand Down
0 ...-rna-germline-variant-calling.inputs.json → ...germline-variant-calling.inputs-hg19.json
View file
Open in desktop
File renamed without changes.
48 changes: 48 additions & 0 deletions gatk4-rna-germline-variant-calling.inputs-hg38.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,48 @@
{
"##_COMMENT1": "Input",
"RNAseq.inputBam": "gs://gatk-test-data/rna_bam/NA12878_b37/NA12878.unmapped.bam",

"##_COMMENT2": "REFERENCE FILES",
"RNAseq.refFasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta",
"RNAseq.refFastaIndex": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.fai",
"RNAseq.refDict": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict",

"##_COMMENT4": "RESOURCE FILES",
"RNAseq.dbSnpVcf": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf",
"RNAseq.dbSnpVcfIndex": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf.idx",
"RNAseq.knownVcfs": [
"gs://gcp-public-data--broad-references/hg38/v0/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz",
"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.known_indels.vcf.gz"
],
"RNAseq.knownVcfsIndices": [
"gs://gcp-public-data--broad-references/hg38/v0/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi",
"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.known_indels.vcf.gz.tbi"
],
"##Download Link": "ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_37/gencode.v37.annotation.gtf.gz",
"RNAseq.annotationsGTF": "gs://gcp-public-data--broad-references/hg38/v0/gencode.v37.annotation.gtf",

"##_COMMENT4": "DOCKERS",
"#RNAseq.gatk4_docker_override": "String? (optional)",
"#RNAseq.star_docker_override": "String? (optional)",
"#RNAseq.gitc_docker_override": "String? (optional)",

"##_COMMENT5": "PATHS",
"#RNAseq.gatk_path_override": "/gatk/gatk",

"##_COMMENT6": "PREEMPTIBLES",
"##RNAseq.preemptible_tries": "(optional) Int?",

"##_COMMENT7": "Misc",
"#RNAseq.StarAlign.num_threads": "(optional) Int?",
"#RNAseq.StarAlign.star_limitOutSJcollapsed": "(optional) Int?",
"RNAseq.StarAlign.additional_disk": "50",
"#RNAseq.StarAlign.star_mem_max_gb": "(optional) Int?",
"RNAseq.StarGenerateReferences.addtional_disk": 50,
"#RNAseq.StarGenerateReferences.num_threads": "(optional) Int?",
"#RNAseq.StarGenerateReferences.mem_gb": "(optional) Int?",
"#RNAseq.haplotypeScatterCount": "(optional) Int?",
"#RNAseq.use_gatk4_for_all_tools": "(optional) Boolean",
"#RNAseq.minConfidenceForVariantCalling": "(optional) Int?",
"#RNAseq.zippedStarReferences": "(optional) File?",
"#RNAseq.readLength": "(optional) Int?"
}