PGx: all CPIC gene kinds — G6PD, variant-based, HLA tags, *0 CN genes (PGX-006/007/021)

- 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).

tests/unit/test_pgx_star.py

@@ -2,6 +2,8 @@
 
 from __future__ import annotations
 
+from pathlib import Path
+
 import numpy as np
 
 from simurg.pgx.star import CALLED, MASKED, NOT_COVERED, GeneModel, Observations, call_gene, gs_error
@@ -66,3 +68,32 @@ def test_masked_record() -> None:  # PGX-010
     obs, ploidy = observations(m, recs, masked={"p1b"})
     assert ploidy == 2 and obs.state[0] == MASKED and obs.state[1] == CALLED and obs.dosage[1] == 1
     assert obs.state[2] == NOT_COVERED
+
+
+def test_cn_only_genes() -> None:  # PGX-006
+    from simurg.pipeline.pgx_star import cn_only_gene
+
+    assert [cn_only_gene("s", "s", "GSTM1", c)[0]["genotype"] for c in (0, 1, 2, 3, 5, None)] == [
+        "*0/*0", "*1/*0", "*1/*1", "*1x2/*1", "*1xN/*1", ""]  # fmt: skip
+
+
+def test_variant_based_gene() -> None:  # PGX-021: per-variant notation, diplotype by lowest activity
+    from simurg.pipeline.pgx_star import StarOptions, call_variant_gene
+
+    variants = [("1", 100, "C", "T"), ("1", 200, "G", "A"), ("1", 300, "A", "G")]
+    carries = np.array([[0, 0, 0], [1, 0, 0], [0, 1, 0], [0, 0, 1]], dtype=np.int8)
+    m = GeneModel("DPYD", variants, [("h0", "rs1"), ("h1", "rs2"), ("h2", "rs3")],
+                  ["Reference", "c.A", "c.B", "c.C"], carries, np.array([0.9, 0.05, 0.03, 0.02]), None, "Reference",
+                  "variant_based", {"Reference": 1.0, "c.A": 1.0, "c.B": 0.0, "c.C": 0.5},
+                  {"Reference": "Normal function", "c.A": "Normal function", "c.B": "No function",
+                   "c.C": "Decreased function"})  # fmt: skip
+    recs = {("1", 100): [{"id": "p1", "ref": "C", "alts": ["T"], "gt": "0/1", "gs": "0.5", "baf": "0.5"}],
+            ("1", 200): [{"id": "p2", "ref": "G", "alts": ["A"], "gt": "0/1", "gs": "0.5", "baf": "0.5"}],
+            ("1", 300): [{"id": "p3", "ref": "A", "alts": ["G"], "gt": "0/1", "gs": "0.5", "baf": "0.5"}]}  # fmt: skip
+    gj, rows, sup, _, _ = call_variant_gene("s", "s", m, recs, set(), StarOptions([], Path("x"), Path("y")))
+    assert gj is not None and gj["genotype"] == "rs1 C/T; rs2 G/A; rs3 A/G"
+    assert gj["feasible_solutions"] == ["c.B/c.C"]  # three carried: the two of lowest activity
+    assert rows[0]["call_type"] == "variant" and len(sup) == 3
+    recs = {("1", 100): [{"id": "p1", "ref": "C", "alts": ["T"], "gt": "0/0", "gs": "0.5", "baf": "0"}]}
+    gj, *_ = call_variant_gene("s", "s", m, recs, set(), StarOptions([], Path("x"), Path("y")))
+    assert gj is not None and gj["genotype"] == "Reference" and gj["feasible_solutions"] == ["Reference/Reference"]