kemalandClaude Opus 5.5
58dbd8f514
- DB build resolves the PGX-007 tag variants from the manifest's probes; coverage over all gene kinds. - Variant-based genes reported per variant (rs.. REF/ALT | Reference) with the CPIC lowest-activity diplotype; tagging genes as positive/negative with the population caveat; GSTM1/GSTT1/UGT2B17 *0 from targeted CN. - Case-insensitive phenotype keys (MT-RNR1). GeT-RM check extended to VKORC1 and the CN genes: 131/144 gene calls (docs/validation/V2_pgx_star.md). Co-Authored-By: Claude Opus 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01814GKVzZVL3FuF3DeiZXhv
56 lines
2.3 KiB
Python
56 lines
2.3 KiB
Python
#!/usr/bin/env python3
|
|
"""Extract GeT-RM consensus diplotypes (CDC Genetic Testing Reference Material program, consolidated PGx/HLA table,
|
|
public) for the individuals of an identity table.
|
|
|
|
python scripts/pgx/getrm_truth.py --xlsx Consolidated_PGx-HLA_table_1-22-25-V4.xlsx \
|
|
--identity scripts/pgx/demo36_identity.tsv --out getrm_truth.tsv
|
|
Writes ``individual, gene, diplotype`` (the table's text, trimmed) for the star-allele genes.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import csv
|
|
from pathlib import Path
|
|
|
|
GENES = ("CYP2B6", "CYP2C9", "CYP2C19", "CYP2D6", "CYP3A4", "CYP3A5", "CYP4F2", "NAT2", "NUDT15", "SLCO1B1", "TPMT",
|
|
"UGT1A1", "DPYD", "CYP2A6", "CYP1A2", "CYP2C8", "GSTM1", "GSTT1", "UGT2B17") # fmt: skip
|
|
|
|
|
|
def main() -> int:
|
|
import openpyxl
|
|
|
|
ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
|
|
ap.add_argument("--xlsx", required=True, type=Path)
|
|
ap.add_argument("--identity", required=True, type=Path)
|
|
ap.add_argument("--out", required=True, type=Path)
|
|
a = ap.parse_args()
|
|
with a.identity.open() as fh:
|
|
inds = {r["individual"] for r in csv.DictReader((ln for ln in fh if not ln.startswith("#")), delimiter="\t")}
|
|
wb = openpyxl.load_workbook(a.xlsx, read_only=True)
|
|
rows = list(wb[wb.sheetnames[0]].iter_rows(values_only=True))
|
|
head = [str(h or "").split("\n")[0].strip() for h in rows[1]]
|
|
col = {g: head.index(g) for g in GENES if g in head}
|
|
vk = next((i for i, h in enumerate(rows[1]) if str(h or "").startswith("VKORC1") and "rs9923231" in str(h)
|
|
and "Reference" not in str(h)), None) # fmt: skip
|
|
if vk is not None:
|
|
col["VKORC1"] = vk # c.-1639G>A genotype, e.g. "GA"
|
|
out = []
|
|
for r in rows[2:]:
|
|
if not r or not r[1] or str(r[1]).strip() not in inds:
|
|
continue
|
|
for g, i in col.items():
|
|
v = r[i]
|
|
if v is not None and str(v).strip():
|
|
out.append((str(r[1]).strip(), g, " ".join(str(v).split())))
|
|
with a.out.open("w") as fh:
|
|
fh.write("individual\tgene\tdiplotype\n")
|
|
for t in sorted(out):
|
|
fh.write("\t".join(t) + "\n")
|
|
print(f"{len({t[0] for t in out})} individual(s), {len(out)} gene call(s) -> {a.out}")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|