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.

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

Allow reblocking TDR/DRS VCFs #1463

Open
wants to merge 2 commits into
base: develop
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
9 changes: 4 additions & 5 deletions tasks/broad/GermlineVariantDiscovery.wdl
Original file line number Diff line number Diff line change
Expand Up @@ -217,20 +217,19 @@ task Reblock {
}

Int disk_size = ceil((size(gvcf, "GiB")) * 4) + additional_disk
String gvcf_basename = basename(gvcf)
String gvcf_index_basename = basename(gvcf_index)

command {
set -e

# We can't always assume the index was located with the gvcf, so make a link so that the paths look the same
ln -s ~{gvcf} ~{gvcf_basename}
ln -s ~{gvcf_index} ~{gvcf_index_basename}
# Use bash basename instead of WDL to support DRS: https://support.terra.bio/hc/en-us/community/posts/4405396480027
ln -s ~{gvcf} $(basename ~{gvcf})
ln -s ~{gvcf_index} $(basename ~{gvcf_index})

gatk --java-options "-Xms3000m -Xmx3000m" \
ReblockGVCF \
-R ~{ref_fasta} \
-V ~{gvcf_basename} \
-V $(basename ~{gvcf}) \
-do-qual-approx \
--floor-blocks -GQB 20 -GQB 30 -GQB 40 \
~{annotations_to_keep_command} \
Expand Down
10 changes: 4 additions & 6 deletions tasks/broad/Qc.wdl
Original file line number Diff line number Diff line change
Expand Up @@ -627,9 +627,6 @@ task ValidateVCF {
Int machine_mem_mb = 7000
}

String calling_interval_list_basename = basename(calling_interval_list)
String calling_interval_list_index_basename = if calling_intervals_defined then "" else basename(select_first([calling_interval_list_index]))

Int command_mem_mb = machine_mem_mb - 2000
Float ref_size = size(ref_fasta, "GiB") + size(ref_fasta_index, "GiB") + size(ref_dict, "GiB")
Int disk_size = ceil(size(input_vcf, "GiB") + size(calling_interval_list, "GiB") + size(dbsnp_vcf, "GiB") + ref_size) + 20
Expand All @@ -639,10 +636,11 @@ task ValidateVCF {

if [ ~{calling_intervals_defined} == "false" ]; then
# We can't always assume the index was located with the vcf, so make a link so that the paths look the same
ln -s ~{calling_interval_list} ~{calling_interval_list_basename}
ln -s ~{calling_interval_list_index} ~{calling_interval_list_index_basename}
# Use bash basename instead of WDL to support DRS: https://support.terra.bio/hc/en-us/community/posts/4405396480027
ln -s ~{calling_interval_list} $(basename ~{calling_interval_list})
ln -s ~{calling_interval_list_index} $(basename ~{calling_interval_list_index})
gatk --java-options "-Xms~{command_mem_mb}m -Xmx~{command_mem_mb}m" \
VcfToIntervalList -I ~{calling_interval_list_basename} -O intervals_from_gvcf.interval_list --VARIANT_ID_METHOD USE_FIRST
VcfToIntervalList -I $(basename ~{calling_interval_list}) -O intervals_from_gvcf.interval_list --VARIANT_ID_METHOD USE_FIRST
INTERVALS="intervals_from_gvcf.interval_list"
else
INTERVALS="~{calling_interval_list}"
Expand Down
Loading