PGx: CYP2D6 structures from sub-region CN — *68+*4, *36+*10, *13 (PGX-013/018)

Sub-region CNs (p5, intron 2, exon 9) resolve full copies and *36/*68/*13 units; candidates carry the
tandem names, background alleles, and CPIC activity sums. GeT-RM: CYP2D6 13/15 top (NA12878 *3/*68+*4 and
NA11832 *1/*68+*4 exact), 15/15 within feasible; all genes 132/144.

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

src/simurg/pipeline/pgx_star.py

@@ -23,11 +23,22 @@ import numpy.typing as npt
 from simurg import __version__
 from simurg.core.errors import ExitCode, SimurgError
 from simurg.core.log import Reporter
-from simurg.pgx.star import CALLED, MASKED, NO_CALL, NOT_COVERED, GeneModel, Observations, Solution, call_gene
+from simurg.pgx.star import (
+    CALLED,
+    MASKED,
+    NO_CALL,
+    NOT_COVERED,
+    GeneModel,
+    Observations,
+    Solution,
+    call_gene,
+    cyp2d6_structure,
+)
 
 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_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"
@@ -350,8 +361,11 @@ def call_one_gene(
     vrec = variant_records(m, recs)
     region = CN_REGION.get(gene)
     gcn = cn.get(region) if region else None
-    sols, feasible = call_gene(m, obs, cn=gcn if region else None, ploidy=ploidy,
-                               max_candidates=o.max_candidates, feasible_ratio=o.feasible_ratio)  # fmt: skip
+    structure = None
+    if gene == "CYP2D6" and gcn is not None:
+        structure = cyp2d6_structure(gcn, cn.get("CYP2D6.intron.2"), cn.get("CYP2D6.exon.9"))
+    sols, feasible = call_gene(m, obs, cn=gcn if region else None, ploidy=ploidy, max_candidates=o.max_candidates,
+                               feasible_ratio=o.feasible_ratio, structure=structure)  # fmt: skip
     if not sols:
         return None, [], [], [], []
     top = sols[0]
@@ -398,7 +412,8 @@ def call_one_gene(
                                                     if al["background_allele"]),
                      "variant_change": ";".join(d["variant_change"] or []),
                      "score": f"{s_.score:.4f}", "raw_score": f"{s_.raw_score:.4f}",
-                     "copy_number_solution": f"{region}={gcn}" if region and gcn is not None else "",
+                     "copy_number_solution": ";".join(f"{r}={cn.get(r)}" for r in CN_SOLUTION_REGIONS.get(gene, ())
+                                                      if cn.get(r) is not None),
                      "flags": ";".join(sflags)})  # fmt: skip
         for al in d["alleles"]:
             for sv in al["supporting_variants"]: