Skip to content

fix: correct _is_phased() early return and prevent KeyError on duplicate variants #227

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

fix: correct _is_phased() early return and prevent KeyError on duplicate variants #227

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
13 changes: 7 additions & 6 deletions preprocessor/pcat/utilities.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -879,14 +879,15 @@ def normalize_vcf(reference_genome: Path, vcf_file: Path, output_dir: Path, outp
def _is_phased(gt_field) -> bool | None:
"""
Determines the phasing status of a position.
If any GT fields have a '/', this means at least one sample is unphased.
Returns False if any sample is unphased (contains '/'),
True if all samples are phased, None if gt_field is empty.
"""
if not gt_field:
return None
for x in gt_field:
if '/' in x:
return False
else:
return True
return None
return True


def _is_haploid(gt_field) -> bool:
Expand Down Expand Up @@ -1094,7 +1095,7 @@ def extract_pgx_variants(pharmcat_positions: Path, reference_fasta: Path, vcf_fi
out_f.write('\t'.join(fields) + '\n')
# elimination: remove the dictionary item so that the variant won't be matched again
if input_chr_pos in ref_pos_dynamic:
ref_pos_dynamic[input_chr_pos].pop(input_ref_alt)
ref_pos_dynamic[input_chr_pos].pop(input_ref_alt, None)
# remove a position if all of its alts are present in the input
if ref_pos_dynamic[input_chr_pos] == {}:
del ref_pos_dynamic[input_chr_pos]
Expand All @@ -1117,7 +1118,7 @@ def extract_pgx_variants(pharmcat_positions: Path, reference_fasta: Path, vcf_fi

# for hom ref SNPs, remove the position from the dict for record
if input_chr_pos in ref_pos_dynamic:
ref_pos_dynamic[input_chr_pos].pop((ref_alleles[i], alt_alleles[i]))
ref_pos_dynamic[input_chr_pos].pop((ref_alleles[i], alt_alleles[i]), None)
# remove a position if all of its alts are present in the input
if ref_pos_dynamic[input_chr_pos] == {}:
del ref_pos_dynamic[input_chr_pos]
Expand Down