PGx validation on GSE165845: WGS-derived star truth, 2-fold masks, array-resolvable concordance

- scripts/pgx/wgs_star_truth.py: star alleles from the 1000G 30x phased panel with the DB definitions
  (wildcard-aware haplotype assignment; checked against GeT-RM on the demo CEPH individuals).
- validate_star_getrm.py: --all-genes, --individuals, --coverage (projection onto what the array can see);
  replicate_concordance.py.
- 120 individuals x 3 GSA v1 arrays: array-resolvable 1637/1710 (95.7 %), top 1223/1800 (chip lacks many
  defining variants), GeT-RM subset 28/35, replicates 99.2 % without the failed array (V2_pgx_star.md, K-029).

scripts/pgx/replicate_concordance.py

@@ -0,0 +1,53 @@
+#!/usr/bin/env python3
+"""Replicate concordance of `pgx star-allele call`: the top genotype of every gene compared between the replicate
+arrays of one individual (PGX-029 reproducibility on real replicates).
+
+    python scripts/pgx/replicate_concordance.py --calls STAR_DIR/pgx_calls.json --identity identity.tsv --out rep.json
+"""
+
+from __future__ import annotations
+
+import argparse
+import csv
+import itertools
+import json
+from collections import defaultdict
+from pathlib import Path
+
+
+def main() -> int:
+    ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    ap.add_argument("--calls", 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:
+        ident = {r["sample_id"]: r["individual"] for r in csv.DictReader((ln for ln in fh if not ln.startswith("#")),
+                                                                           delimiter="\t")}  # fmt: skip
+    calls: dict[str, dict[str, dict[str, str]]] = defaultdict(dict)
+    for s in json.loads(a.calls.read_text())["samples"]:
+        ind = ident.get(s["sample_id"])
+        if ind:
+            calls[ind][s["sample_id"]] = {g["gene"]: (g["candidates"][0]["genotype"] if g["candidates"] else "")
+                                          for g in s["genes"]}  # fmt: skip
+    per_gene: dict[str, list[int]] = defaultdict(lambda: [0, 0])
+    discord = []
+    for ind, reps in sorted(calls.items()):
+        for (_s1, c1), (_s2, c2) in itertools.combinations(sorted(reps.items()), 2):
+            for gene in sorted(set(c1) & set(c2)):
+                ok = c1[gene] == c2[gene]
+                per_gene[gene][0] += ok
+                per_gene[gene][1] += 1
+                if not ok:
+                    discord.append({"individual": ind, "gene": gene, "a": c1[gene], "b": c2[gene]})
+    tot = [sum(v[0] for v in per_gene.values()), sum(v[1] for v in per_gene.values())]
+    out = {"pairs_by_gene": {g: {"concordant": v[0], "pairs": v[1]} for g, v in sorted(per_gene.items())},
+           "total": {"concordant": tot[0], "pairs": tot[1], "rate": round(tot[0] / tot[1], 4) if tot[1] else None},
+           "discordant": discord}  # fmt: skip
+    a.out.write_text(json.dumps(out, indent=1))
+    print(json.dumps(out["total"]), f"{len(discord)} discordant gene pair(s)")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

scripts/pgx/validate_star_getrm.py

@@ -79,13 +79,42 @@ def main() -> int:
     ap.add_argument("--truth", required=True, type=Path)
     ap.add_argument("--identity", required=True, type=Path)
     ap.add_argument("--out", required=True, type=Path)
+    ap.add_argument("--all-genes", action="store_true",
+                    help="truth with the same definitions (wgs_star_truth.py): no legacy-name exclusions")  # fmt: skip
+    ap.add_argument("--individuals", type=Path, help="only these individuals (one per line)")
+    ap.add_argument("--coverage", type=Path, help="pgx_coverage.tsv of the array: also report array-resolvable "
+                    "concordance (both diplotypes projected onto the alleles the array can tell apart)")  # fmt: skip
     a = ap.parse_args()
+    if a.all_genes:
+        LEGACY_NOMENCLATURE.clear()
+    only = set(a.individuals.read_text().split()) if a.individuals else None
+    proj: dict[tuple[str, str], str] = {}
+    refs: dict[str, str] = {}
+    if a.coverage:
+        with a.coverage.open() as fh:
+            for r in csv.DictReader((ln for ln in fh if not ln.startswith("#")), delimiter="\t"):
+                if r["allele_kind"] == "reference":
+                    refs[r["gene"]] = r["allele"]
+                st = r["status"]
+                proj[(r["gene"], r["allele"])] = st.split(":", 1)[1] if st.startswith("equivalent_to:") else (
+                    r["allele"] if st == "callable" else "")  # fmt: skip
+
+    def project(gene: str, allele: str) -> str:
+        core = re.sub(r"x\d+$|xN$", "", allele.split("+")[-1])
+        v = proj.get((gene, core), core)
+        if v:
+            return v
+        ref = refs.get(gene, core)  # not covered: indistinguishable from the reference's class
+        return proj.get((gene, ref)) or ref
+
     with a.identity.open() as fh:
         ident = {r["sample_id"]: r["individual"] for r in csv.DictReader((ln for ln in fh if not ln.startswith("#")),
                                                                            delimiter="\t")}  # fmt: skip
     truth: dict[tuple[str, str], str] = {}
     with a.truth.open() as fh:
         for r in csv.DictReader(fh, delimiter="\t"):
+            if r.get("flag") == "incomplete" or (only is not None and r["individual"] not in only):
+                continue
             truth[(r["individual"], r["gene"])] = r["diplotype"]
     calls = json.loads(a.calls.read_text())
     per_gene: dict[str, dict[str, int]] = defaultdict(lambda: defaultdict(int))
@@ -135,11 +164,21 @@ def main() -> int:
                                   if len(e.split("/")) >= 2)  # fmt: skip
             st["top"] += ok_top
             st["equivalent"] += ok_eq
+            if a.coverage and len(top) == 2 and len(opts) == 1 and all(len(x) == 1 for x in opts[0]):
+                tt = sorted(project(g["gene"], next(iter(x))) for x in opts[0])
+                cc = sorted(project(g["gene"], x) for x in top)
+                st["array_resolvable_n"] += 1
+                st["array_resolvable"] += tt == cc
             if not ok_top:
                 detail.append({"individual": ind, "gene": g["gene"], "truth": t, "call": g["genotype"],
                                "within_equivalents": ok_eq})  # fmt: skip
     comparable = {k: v for k, v in per_gene.items() if k not in LEGACY_NOMENCLATURE}
+    tot_ar = [
+        sum(v.get("array_resolvable", 0) for v in comparable.values()),
+        sum(v.get("array_resolvable_n", 0) for v in comparable.values()),
+    ]
     summary = {"individuals": len(seen), "genes": {k: dict(v) for k, v in sorted(per_gene.items())},
+               "array_resolvable_total": {"concordant": tot_ar[0], "n": tot_ar[1]},
                "legacy_nomenclature_genes": sorted(LEGACY_NOMENCLATURE),
                "total": {k: sum(v.get(k, 0) for v in comparable.values()) for k in ("n", "top", "equivalent")},
                "discordant": detail}  # fmt: skip
@@ -147,8 +186,12 @@ def main() -> int:
     for g, v in sorted(per_gene.items()):
         print(f"{g:8s} top {v['top']}/{v['n']}  within equivalents {v['equivalent']}/{v['n']}"
               + (f"  (not comparable {v['not_comparable']})" if v.get("not_comparable") else "")
+              + (f"  array-resolvable {v.get('array_resolvable', 0)}/{v.get('array_resolvable_n', 0)}"
+                 if a.coverage else "")
               + ("  [legacy nomenclature]" if g in LEGACY_NOMENCLATURE else ""))  # fmt: skip
     print("total (excluding legacy-nomenclature genes)", summary["total"])
+    if a.coverage:
+        print("array-resolvable total", summary["array_resolvable_total"])
     return 0
 
 

scripts/pgx/wgs_star_truth.py

@@ -0,0 +1,130 @@
+#!/usr/bin/env python3
+"""Star-allele truth from 1000 Genomes 30x phased genotypes with the PGx DB definitions (SNV/indel alleles only).
+
+    python scripts/pgx/wgs_star_truth.py --db DB.sqlite --individuals ids.txt --out wgs_truth.tsv [--genes G,G]
+
+For every star-allele gene of the DB the defining variants are fetched from the NYGC phased panel (pysam over HTTPS,
+one window per gene; ``uv pip install pysam``). Each phased haplotype gets the allele whose defining variants it
+carries completely and that explains most of the haplotype's carried variants — its defining ones plus those at its
+wildcard (IUPAC) positions, so a *4 haplotype carrying the *10 variants stays *4 (ties: more defining variants,
+higher CPIC/PharmVar frequency, natural order); a haplotype carrying none is the reference allele. A variant absent
+from the filtered panel counts as reference only when rare (max allele frequency < 5 %); a gene with a common
+defining variant missing from the panel is written with ``incomplete`` (not comparable). Structural alleles (CYP2D6
+*5, xN, hybrids; CYP2A6 *4) are invisible to this truth: the diplotypes are SNV-level only.
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+import re
+import sqlite3
+from collections import defaultdict
+from pathlib import Path
+
+PANEL = (
+    "https://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000G_2504_high_coverage/working/"
+    "20220422_3202_phased_SNV_INDEL_SV/1kGP_high_coverage_Illumina.{c}.filtered.SNV_INDEL_SV_phased_panel.vcf.gz"
+)
+
+
+def natural(a: str) -> tuple[object, ...]:
+    return tuple(int(x) if x.isdigit() else x for x in re.split(r"(\d+)", a))
+
+
+def main() -> int:
+    import pysam
+
+    ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    ap.add_argument("--db", required=True, type=Path)
+    ap.add_argument("--individuals", required=True, type=Path)
+    ap.add_argument("--out", required=True, type=Path)
+    ap.add_argument("--genes", default="")
+    ap.add_argument("--cache", type=Path, default=Path("data/pgx/cache"))
+    a = ap.parse_args()
+    inds = sorted(set(a.individuals.read_text().split()))
+    out_path = a.out.resolve()
+    con = sqlite3.connect(a.db)
+    genes = [g for (g,) in con.execute("SELECT gene FROM genes WHERE result_basis = 'star_allele' ORDER BY gene")]
+    if a.genes:
+        genes = [g for g in genes if g in a.genes.split(",")]
+    a.cache.mkdir(parents=True, exist_ok=True)
+    os.chdir(a.cache)
+    rows = []
+    for gene in genes:
+        q_alle = "SELECT allele FROM alleles WHERE gene = ? AND defined = 1 AND structural = 0"
+        alle = [x for (x,) in con.execute(q_alle, (gene,))]
+        q_ref = "SELECT allele FROM alleles WHERE gene = ? AND kind = 'reference'"
+        ref_allele = next((x for (x,) in con.execute(q_ref, (gene,))), "*1")
+        defs: dict[str, set[tuple[int, str, str]]] = defaultdict(set)
+        chrom = None
+        loc_keys: dict[int, set[tuple[int, str, str]]] = defaultdict(set)
+        q_var = "SELECT allele, chrom, pos, ref, alt, location_id FROM allele_variants WHERE gene = ?"
+        for allele, c, p, r, al, lid in con.execute(q_var, (gene,)):
+            defs[allele].add((p, r, al))
+            loc_keys[lid].add((p, r, al))
+            chrom = c
+        wild: dict[str, set[tuple[int, str, str]]] = defaultdict(set)
+        for allele, lid in con.execute("SELECT allele, location_id FROM allele_wildcards WHERE gene = ?", (gene,)):
+            wild[allele] |= loc_keys.get(lid, set())
+        if chrom is None:
+            continue
+        freq: dict[str, float] = defaultdict(float)
+        for allele, f in con.execute("SELECT allele, AVG(freq) FROM frequencies WHERE gene = ? GROUP BY allele",
+                                     (gene,)):  # fmt: skip
+            freq[allele] = float(f or 0)
+        vmax: dict[tuple[int, str, str], float] = defaultdict(float)
+        for allele, vs in defs.items():
+            for v in vs:
+                vmax[v] = max(vmax[v], freq.get(allele, 0.0))
+        keys = set().union(*defs.values()) if defs else set()
+        core = chrom.removeprefix("chr")
+        vf = pysam.VariantFile(PANEL.format(c=f"chr{core}"))
+        present = [s for s in inds if s in vf.header.samples]
+        vf.subset_samples(present)
+        lo = min(p for p, _, _ in keys) - 10
+        hi = max(p + len(r) for p, r, _ in keys) + 10
+        hap_alts: dict[tuple[str, int], set[tuple[int, str, str]]] = defaultdict(set)
+        seen = set()
+        for rec in vf.fetch(f"chr{core}", lo, hi):
+            for ai, alt in enumerate(rec.alts or (), start=1):
+                k = (rec.pos, rec.ref, alt)
+                if k not in keys:
+                    continue
+                seen.add(k)
+                for s in present:
+                    gt = rec.samples[s]["GT"]
+                    for h, x in enumerate(gt[:2]):
+                        if x == ai:
+                            hap_alts[(s, h)].add(k)
+        missing_common = [k for k in keys - seen if vmax[k] >= 0.05]
+        for s in present:
+            haps = []
+            for h in (0, 1):
+                carried = hap_alts[(s, h)]
+                # the allele that explains most carried variants (its defining ones plus those at its wildcard
+                # positions), then the most specific, then the most frequent
+                best = (0, 0, 0.0)
+                pick = ref_allele
+                for x in alle:
+                    d = defs.get(x, set())
+                    if not d or not d <= carried:
+                        continue
+                    score = (len(carried & (d | wild.get(x, set()))), len(d), freq.get(x, 0.0))
+                    if score > best or (score == best and natural(x) < natural(pick)):
+                        best, pick = score, x
+                haps.append(pick)
+            dip = "/".join(sorted(haps, key=natural))
+            rows.append((s, gene, dip, "incomplete" if missing_common else ""))
+        print(f"{gene}: {len(keys)} defining variant(s), {len(seen)} in the panel, "
+              f"{len(missing_common)} common missing", flush=True)  # fmt: skip
+    with out_path.open("w") as fh:
+        fh.write("individual\tgene\tdiplotype\tflag\n")
+        for r in sorted(rows):
+            fh.write("\t".join(r) + "\n")
+    print(f"{len(rows)} gene call(s) -> {out_path}")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())