P4 validated on 2141 vendor GTCs; legacy AutoCall 1.6.2 preset

- vendor comparison (1000 Genomes Omni2.5, AutoCall 1.6.2.2): every
  computed field identical in 2138/2141 samples; the 3 others trace back
  to the single-locus raw-intensity rule (K-009); sex rule 1 matches all
- AutoCall 1.6.2.x leaves GC10/GC50/#calls/#no-calls at 0 in GTC v3:
  new `--preset autocall-1.6.2` (1.1.2 normalization, sex rule 1, GTC v3,
  legacy statistics); the sample summary keeps the real statistics
- NaN sign canonicalised to the x86 pattern (K-014); report P4.md

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

src/simurg/genotype/sample.py

@@ -39,6 +39,27 @@ class GenotypeParams:
     gtc_version: int = 5
     autocall_version: str = f"{PRODUCT_NAME} {__version__}"
     autocall_date: str | None = None  # None: run start time (invariant format, OUT-001)
+    legacy_sample_stats: bool = False  # AutoCall 1.6.2.x left GC10, GC50, #calls and #no-calls at 0 (K-015)
+
+
+PRESETS: dict[str, dict[str, object]] = {
+    # default: current vendor software (normalization 1.2.0 / GenTrain 3, sex rule 2, GTC v5)
+    "current": {},
+    # AutoCall 1.6.2.x as used for the public 1000 Genomes Omni2.5 GTCs (validated on 2141 samples, P4)
+    "autocall-1.6.2": {
+        "norm_version": "1.1.2",
+        "sex": SexParams(version=1),
+        "gtc_version": 3,
+        "legacy_sample_stats": True,
+    },
+}
+
+
+def params_for_preset(name: str, **overrides: object) -> GenotypeParams:
+    if name not in PRESETS:
+        raise ValueError(f"unknown preset {name!r}; choose from {sorted(PRESETS)}")
+    values = {**PRESETS[name], **{k: v for k, v in overrides.items() if v is not None}}
+    return GenotypeParams(**values)  # type: ignore[arg-type]
 
 
 @dataclass
@@ -193,4 +214,23 @@ def genotype_sample(
     g.sample_data["num_calls"] = calls.num_calls
     g.sample_data["num_no_calls"] = m.num_loci - calls.num_intensity_only - calls.num_calls
     g.sample_data["num_intensity_only"] = calls.num_intensity_only
+    if params.legacy_sample_stats:
+        g.gc10 = 0.0
+        g.sample_data["p50gc"] = 0.0
+        g.sample_data["num_calls"] = 0
+        g.sample_data["num_no_calls"] = 0
     return g
+
+
+def summary_stats(g: Gtc, intensity_only: npt.NDArray[np.bool_], cutoff: float) -> dict[str, float | int]:
+    """Sample statistics recomputed from calls and scores (independent of legacy GTC field conventions)."""
+    gs = np.sort(g.genotype_scores[(g.genotype_scores > F32(cutoff)) & ~intensity_only])
+    n_calls = int((g.genotypes > 0).sum())
+    n_io = int(intensity_only.sum())
+    return {
+        "gc10": float(percentile(gs, 10)),
+        "gc50": float(percentile(gs, 50)),
+        "n_calls": n_calls,
+        "n_nocalls": g.num_snps - n_io - n_calls,
+        "n_intensity_only": n_io,
+    }