Skip to content

Don't append version/command to VCF header #3

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

Open
MattWellie wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Don't append version/command to VCF header #3

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
11 changes: 4 additions & 7 deletions src/cpg_flow_mito/jobs/bcftools.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@
def naive_merge_vcfs(
input_list: list[str | Path],
output_file: str,
cpu: int = 4,
memory: str = '16Gi',
storage: str = '50Gi',
job_attrs: dict[str, str] | None = None,
Expand All @@ -21,7 +20,6 @@ def naive_merge_vcfs(
Args:
input_list (list[str]): all VCFs to merge, can be pre-localised (see vcfs_localised[bool)
output_file (str): path to a vcf.bgz file to write to
cpu (int): number of cores (threads when merging)
memory (str): RAM requirement
storage (str): storage requirement for the task
job_attrs (dict[str, str]): attributes to pass to the job
Expand All @@ -35,7 +33,6 @@ def naive_merge_vcfs(
merge_job.image(config.config_retrieve(['images', 'bcftools']))

# guessing at resource requirements
merge_job.cpu(cpu)
merge_job.memory(memory)
merge_job.storage(storage)
merge_job.declare_resource_group(output={'vcf.bgz': '{root}.vcf.bgz', 'vcf.bgz.tbi': '{root}.vcf.bgz.tbi'})
Expand All @@ -44,9 +41,9 @@ def naive_merge_vcfs(
reduced_vcfs = []
for index, vcf in enumerate(batch_vcfs):
merge_job.command(f"""
bcftools view -h {vcf} -Oz -o ${{BATCH_TMPDIR}}/{index}.vcf.bgz
bcftools view -H {vcf} | awk -F'\t' '{{split($10, a, ":"); if (gsub("/", "", a[1]) < 2) print}}' | bgzip >> ${{BATCH_TMPDIR}}/{index}.vcf.bgz
bcftools index -t ${{BATCH_TMPDIR}}/{index}.vcf.bgz
bcftools view --no-version -h {vcf} -Oz -o ${{BATCH_TMPDIR}}/{index}.vcf.bgz
bcftools view --no-version -H {vcf} | awk -F'\t' '{{split($10, a, ":"); if (gsub("/", "", a[1]) < 2) print}}' | bgzip >> ${{BATCH_TMPDIR}}/{index}.vcf.bgz
bcftools index --no-version -t ${{BATCH_TMPDIR}}/{index}.vcf.bgz
""") # noqa: E501
reduced_vcfs.append(f'${{BATCH_TMPDIR}}/{index}.vcf.bgz')

Expand All @@ -57,7 +54,7 @@ def naive_merge_vcfs(
# -m: merge strategy
# -0: missing-calls-to-ref, not important for inheritance checking, but useful for AC/AN/AF accuracy
merge_job.command(
f'bcftools merge {" ".join(reduced_vcfs)} -Oz -o {merge_job.output["vcf.bgz"]} --threads {cpu} -0 -W=tbi',
f'bcftools merge --no-version {" ".join(reduced_vcfs)} -Oz -o {merge_job.output["vcf.bgz"]} -0 -W=tbi',
)

# write the result out
Expand Down