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

src/simurg/cli/main.py

@@ -838,6 +838,37 @@ def pgx_db_build_cmd(
     run_guarded(rep, lambda: run_db_build(o, rep))
 
 
+pgx_star_app = typer.Typer(help="Star-allele calling (PGX-011).")
+pgx_app.add_typer(pgx_star_app, name="star-allele")
+
+
+@pgx_star_app.command("call")
+def pgx_star_call_cmd(
+    vcfs: Annotated[list[Path], typer.Option("--vcfs", help="Folder(s) with SNV + PGx CN VCFs (repeatable).")],
+    db: Annotated[Path, typer.Option("--db", help="PGx DB from pgx db build (required).")],
+    out: Annotated[Path, typer.Option("--out", help="Output folder (required).")],
+    population: Annotated[str, typer.Option("--population", help="Frequency prior population.")] = "global",
+    max_candidates: Annotated[int, typer.Option("--max-candidates", min=1)] = 10,
+    feasible_ratio: Annotated[float, typer.Option("--feasible-ratio", min=0.0, max=1.0)] = 0.5,
+    low_gs: Annotated[float, typer.Option("--low-gs")] = 0.15,
+    no_cn: Annotated[bool, typer.Option("--no-cn", help="Run without PGx CN VCFs.")] = False,
+    allow_foreign_vcf: Annotated[bool, typer.Option("--allow-foreign-vcf")] = False,
+    gene: Annotated[list[str] | None, typer.Option("--gene", help="Restrict to gene(s).")] = None,
+    force: ForceOpt = False,
+    log_json: LogJson = False,
+    debug: Debug = False,
+    quiet: Quiet = False,
+) -> None:
+    """Call star-allele diplotypes (CLI-033, PGX-012 ... PGX-021)."""
+    from simurg.pipeline.pgx_star import StarOptions, run_star_call
+
+    rep = _reporter("pgx star-allele call", out, log_json, debug, quiet)
+    o = StarOptions(vcfs=vcfs, db=db, out=out, population=population, max_candidates=max_candidates,
+                    feasible_ratio=feasible_ratio, low_gs=low_gs, no_cn=no_cn, allow_foreign_vcf=allow_foreign_vcf,
+                    genes=gene or [], force=force)  # fmt: skip
+    run_guarded(rep, lambda: run_star_call(o, rep))
+
+
 @pgx_cn_app.command("train")
 def pgx_cn_train_cmd(
     gtcs: Annotated[Path, typer.Option("--gtcs", help="Folder searched recursively for training GTCs (required).")],