PGx: PharmVar genes (CYP1A2, CYP2A6, CYP2A13, CYP2C8, CYP3A4), CYP2A6 *4 from CN (PGX-001/006)

fetch_sources.sh downloads PharmVar per-gene zips; pgx db build adds core alleles for genes CPIC does not
define (normalised against the FASTA, *1 = reference). Masks re-derived with the new variants. GeT-RM:
CYP3A4 15/15, CYP2A6 7/9; all comparable genes 154/168 (CYP1A2/CYP2C8 definitions differ from GeT-RM's).

src/simurg/pipeline/pgx_star.py

@@ -37,12 +37,15 @@ from simurg.pgx.star import (
 
 MAX_EDIT_DISTANCE = 3  # PGX-019
 
-CN_REGION = {"CYP2D6": "CYP2D6.p5"}  # PGX-013: total gene copies from the 5′ region
-CN_SOLUTION_REGIONS = {"CYP2D6": ("CYP2D6.p5", "CYP2D6.intron.2", "CYP2D6.exon.9")}  # PGX-027 copy_number_solution
+CN_REGION = {"CYP2D6": "CYP2D6.p5", "CYP2A6": "CYP2A6.exon.1"}  # PGX-013: gene copies from the 5′ region
+CN_SOLUTION_REGIONS = {
+    "CYP2D6": ("CYP2D6.p5", "CYP2D6.intron.2", "CYP2D6.exon.9"),
+    "CYP2A6": ("CYP2A6.exon.1", "CYP2A6.intron.7"),
+}  # PGX-027 copy_number_solution
 CN_ONLY_GENES = {"GSTM1": "GSTM1", "GSTT1": "GSTT1", "UGT2B17": "UGT2B17"}  # PGX-006: *0 from whole-gene CN
 ALL_BASES = ("star_allele", "haplotype_named", "variant_based", "tagging_variant")
 TAG_CAVEAT = "tag reliability varies by population"
-DELETION_ALLELE = {"CYP2D6": "*5"}
+DELETION_ALLELE = {"CYP2D6": "*5", "CYP2A6": "*4"}  # named whole-gene deletions (PGX-006)
 
 
 @dataclass
@@ -100,6 +103,10 @@ def load_models(
             if fr.get(n):
                 freq[i] = float(np.mean(fr[n]))
         freq = np.nan_to_num(freq, nan=0.0)
+        if not freq.any() and names:  # no population frequencies (PharmVar genes): reference 0.8, others share 0.2
+            freq = np.full(len(names), 0.2 / max(1, len(names) - 1))
+            if ref in names:
+                freq[names.index(ref)] = 0.8
         fa = {a: (f, v) for a, f, v in con.execute("SELECT allele, function, activity FROM alleles WHERE gene = ?",
                                                     (gene,))}  # fmt: skip
         act = {}