PGx: full call detail (PGX-016..020, 027/028, 031), pgx coverage (PGX-009/035), full HGVS

- supporting_variants.tsv, unresolved_variants.tsv, variants_not_covered.tsv with PGX-026 metadata; per-allele
  supporting/unresolved sites for both alleles of every candidate; variant_change vs top, distant_alternative,
  unexplained_variants, alleles_impacted_by_no_call, alleles_tested.
- simurg pgx coverage: callable / not_covered / masked / equivalent_to per allele and manifest.
- HGVS on GRCh38 RefSeq accessions (NC_...:g.).

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01814GKVzZVL3FuF3DeiZXhv

src/simurg/pgx/db.py

@@ -19,7 +19,23 @@ from typing import Any
 Fetch = Callable[[str, int, int], str]
 HGVS_RE = re.compile(r"^([gm])\.(\d+)(?:_(\d+))?(.*)$")
 REPEAT_RE = re.compile(r"^([ACGT]+)\((\d+)\)$")
-IUPAC_WILDCARD = set("RYSWKMBDHVN")  # CPIC core-allele definitions: the position does not constrain the allele
+IUPAC_WILDCARD = set("RYSWKMBDHVN")
+# GRCh38 RefSeq chromosome accessions, for full HGVS (PGX-028 "NC_000022.11:g.42126611C>G")
+REFSEQ_GRCH38 = {"1": "NC_000001.11", "2": "NC_000002.12", "3": "NC_000003.12", "4": "NC_000004.12",
+                 "5": "NC_000005.10", "6": "NC_000006.12", "7": "NC_000007.14", "8": "NC_000008.11",
+                 "9": "NC_000009.12", "10": "NC_000010.11", "11": "NC_000011.10", "12": "NC_000012.12",
+                 "13": "NC_000013.11", "14": "NC_000014.9", "15": "NC_000015.10", "16": "NC_000016.10",
+                 "17": "NC_000017.11", "18": "NC_000018.10", "19": "NC_000019.10", "20": "NC_000020.11",
+                 "21": "NC_000021.9", "22": "NC_000022.11", "X": "NC_000023.11", "Y": "NC_000024.10",
+                 "M": "NC_012920.1", "MT": "NC_012920.1"}  # fmt: skip
+
+
+def full_hgvs(chrom: str, hgvs: str) -> str:
+    """``g.…``/``m.…`` → ``NC_…:g.…`` on the GRCh38 chromosome accession (unchanged when unknown)."""
+    acc = REFSEQ_GRCH38.get(chrom.removeprefix("chr"))
+    return (
+        f"{acc}:{hgvs.split(';')[0].strip()}" if acc and not hgvs.startswith("NC_") else hgvs
+    )  # CPIC core-allele definitions: the position does not constrain the allele
 
 
 @dataclass(frozen=True)

src/simurg/pgx/star.py

@@ -59,6 +59,7 @@ class Solution:
     raw_score: float = 0.0
     score: float = 0.0
     copy_number: int = 2
+    copies: tuple[int, ...] = ()  # haplotype index of every gene copy of the representative (SNV model)
 
     @property
     def genotype(self) -> str:
@@ -157,8 +158,8 @@ def call_gene(
                 p *= 2
             pri.append(p)
         best = members[int(np.argmax(pri))]
-        sols.append(Solution(cands[best][1], float(ll[best]), float(sum(pri)),
-                             [cands[k][1] for k in members], copy_number=cn if cn is not None else 2))  # fmt: skip
+        sols.append(Solution(cands[best][1], float(ll[best]), float(sum(pri)), [cands[k][1] for k in members],
+                             copy_number=cn if cn is not None else 2, copies=cands[best][0]))  # fmt: skip
     lls = np.array([s.ll for s in sols])
     lp = lls + np.log([s.prior for s in sols])
     raw = np.exp(lls - lls.max())