PGx star alleles: pgx star-allele call (PGX-011..021), probe masks vs 1000G, GeT-RM validation (K-029)

- simurg/pgx/star.py: solver-free diplotype enumeration incl. CN forms (deletion, xN), wildcards, array-equivalence classes, raw_score/score with CPIC frequency priors; calibrated error model (spec PGX-012 amended). - pipeline/pgx_star.py: DB gene models, SNV + PGx CN VCF evidence, masks, diplotype_summary.tsv + pgx_calls.json. - scripts/pgx: derive_masks.py (array vs 1000G 30x over HTTPS, GS calibration), getrm_truth.py, validate_star_getrm.py. - GSA v4 PGx demo vs GeT-RM (16 CEPH): 100/109 gene calls; CYP2D6/2C19/2C9 41/45 (docs/validation/V2_pgx_star.md). Co-Authored-By: Claude Opus 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01814GKVzZVL3FuF3DeiZXhv
2026-09-29 14:08:03 +01:00
1 parent bf9fdaa2f3
commit d91c8ea576
@@ -0,0 +1,240 @@
+{
+ "individuals": 30,
+ "genes": {
+  "CYP2B6": {
+   "n": 14,
+   "top": 12,
+   "equivalent": 12,
+   "not_comparable": 1
+  },
+  "CYP2C19": {
+   "n": 15,
+   "top": 14,
+   "equivalent": 15
+  },
+  "CYP2C9": {
+   "n": 15,
+   "top": 15,
+   "equivalent": 15
+  },
+  "CYP2D6": {
+   "n": 15,
+   "top": 12,
+   "equivalent": 14
+  },
+  "CYP3A5": {
+   "n": 15,
+   "top": 15,
+   "equivalent": 15
+  },
+  "CYP4F2": {
+   "n": 9,
+   "top": 8,
+   "equivalent": 8
+  },
+  "NAT2": {
+   "n": 9,
+   "top": 8,
+   "equivalent": 8
+  },
+  "NUDT15": {
+   "n": 1,
+   "top": 1,
+   "equivalent": 1
+  },
+  "SLCO1B1": {
+   "n": 15,
+   "top": 9,
+   "equivalent": 9
+  },
+  "TPMT": {
+   "n": 16,
+   "top": 15,
+   "equivalent": 15
+  },
+  "UGT1A1": {
+   "n": 9,
+   "top": 0,
+   "equivalent": 1
+  }
+ },
+ "legacy_nomenclature_genes": [
+  "SLCO1B1",
+  "UGT1A1"
+ ],
+ "total": {
+  "n": 109,
+  "top": 100,
+  "equivalent": 103
+ },
+ "discordant": [
+  {
+   "individual": "NA12156",
+   "gene": "CYP4F2",
+   "truth": "(*2)/*3",
+   "call": "*1/*3",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA12156",
+   "gene": "SLCO1B1",
+   "truth": "*1/*21",
+   "call": "*1/*37",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA12156",
+   "gene": "UGT1A1",
+   "truth": "*60/*28",
+   "call": "*28/*80",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA12044",
+   "gene": "TPMT",
+   "truth": "*1/*21",
+   "call": "*1/*1",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA07019",
+   "gene": "UGT1A1",
+   "truth": "*1/*60",
+   "call": "*1/*1",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA06991",
+   "gene": "UGT1A1",
+   "truth": "*60/*60",
+   "call": "*1/*1",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA12878",
+   "gene": "CYP2D6",
+   "truth": "*3/(*68)+*4",
+   "call": "*4x2/*1;*4x2/*82",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA12878",
+   "gene": "UGT1A1",
+   "truth": "*60/*28",
+   "call": "*28/*80",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA11993",
+   "gene": "SLCO1B1",
+   "truth": "*1/*17",
+   "call": "*1/*15",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA11993",
+   "gene": "UGT1A1",
+   "truth": "(*28 + *60)/*60",
+   "call": "*28/*80",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA12003",
+   "gene": "UGT1A1",
+   "truth": "*60/*28",
+   "call": "*28/*80",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA07029",
+   "gene": "CYP2B6",
+   "truth": "*6/(*27)",
+   "call": "*1/*6",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA07029",
+   "gene": "CYP2C19",
+   "truth": "*8/*17",
+   "call": "*1/*17",
+   "within_equivalents": true
+  },
+  {
+   "individual": "NA07029",
+   "gene": "UGT1A1",
+   "truth": "*1/*1",
+   "call": "*1/*28",
+   "within_equivalents": true
+  },
+  {
+   "individual": "NA12892",
+   "gene": "CYP2B6",
+   "truth": "*1/*1",
+   "call": "*1/*5",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA11832",
+   "gene": "NAT2",
+   "truth": "*5/(*12)",
+   "call": "*1/*5",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA11832",
+   "gene": "SLCO1B1",
+   "truth": "*1/*1",
+   "call": "*14/*20",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA11832",
+   "gene": "UGT1A1",
+   "truth": "(*28 + *60)/*60",
+   "call": "*28/*80",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA10838",
+   "gene": "CYP2D6",
+   "truth": "*2/*4",
+   "call": "*1/*4;*2/*4",
+   "within_equivalents": true
+  },
+  {
+   "individual": "NA10838",
+   "gene": "SLCO1B1",
+   "truth": "*1/*1",
+   "call": "*1/*14",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA12813",
+   "gene": "CYP2D6",
+   "truth": "*2/*4",
+   "call": "*1/*4;*2/*4",
+   "within_equivalents": true
+  },
+  {
+   "individual": "NA12813",
+   "gene": "SLCO1B1",
+   "truth": "*1/*21",
+   "call": "*1/*20",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA12813",
+   "gene": "UGT1A1",
+   "truth": "(*28 + *60)/(*28 + *60)",
+   "call": "*80/*80",
+   "within_equivalents": false
+  },
+  {
+   "individual": "NA11881",
+   "gene": "SLCO1B1",
+   "truth": "*1/(*15)",
+   "call": "*14/*15",
+   "within_equivalents": false
+  }
+ ]
+}