Skip to content

unzip submission summary before join #816

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

Merged
merged 1 commit into from
Jun 24, 2024
Merged

unzip submission summary before join #816

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
20 changes: 13 additions & 7 deletions v03_pipeline/lib/reference_data/clinvar.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
import gzip
import os
import shutil
import subprocess
import tempfile
import urllib
Expand Down Expand Up @@ -176,14 +177,21 @@ def download_and_import_clinvar_submission_summary() -> hl.Table:
with tempfile.NamedTemporaryFile(
suffix='.txt.gz',
delete=False,
) as tmp_file:
) as tmp_file, tempfile.NamedTemporaryFile(
suffix='.txt',
delete=False,
) as unzipped_tmp_file:
urllib.request.urlretrieve(CLINVAR_SUBMISSION_SUMMARY_URL, tmp_file.name) # noqa: S310
# Unzip the gzipped file first to fix gzip files being read by hail with single partition
with gzip.open(tmp_file.name, 'rb') as f_in, open(unzipped_tmp_file.name, 'wb') as f_out:
shutil.copyfileobj(f_in, f_out)

gcs_tmp_file_name = os.path.join(
Env.HAIL_TMPDIR,
os.path.basename(tmp_file.name),
os.path.basename(unzipped_tmp_file.name),
)
safely_move_to_gcs(tmp_file.name, gcs_tmp_file_name)
ht = hl.import_table(
safely_move_to_gcs(unzipped_tmp_file.name, gcs_tmp_file_name)
return hl.import_table(
gcs_tmp_file_name,
force=True,
filter='^(#[^:]*:|^##).*$', # removes all comments except for the header line
Expand All @@ -193,7 +201,5 @@ def download_and_import_clinvar_submission_summary() -> hl.Table:
'ReportedPhenotypeInfo': hl.tstr,
},
missing='-',
min_partitions=MIN_HT_PARTITIONS,
)
# NB: min_partitions fails with force=True during `import_table`, but
# an immediate repartition here works.
return ht.repartition(MIN_HT_PARTITIONS)
Loading