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/pipeline/genotype.py

@@ -27,7 +27,14 @@ from simurg.formats.gtc import write_gtc
 from simurg.formats.idat import check_pair, read_idat
 from simurg.genotype.baf_lrr import chrom_core
 from simurg.genotype.clusters import align_clusters
-from simurg.genotype.sample import GenotypeParams, ManifestContext, genotype_sample, manifest_context
+from simurg.genotype.sample import (
+    GenotypeParams,
+    ManifestContext,
+    genotype_sample,
+    manifest_context,
+    params_for_preset,
+    summary_stats,
+)
 from simurg.genotype.sex import SexParams
 from simurg.pipeline.inputs import check_paths, resolve_sample_set, sample_dir, sheet_values
 from simurg.signal.normalization.apply import normalize, polar
@@ -77,9 +84,10 @@ class GenotypeOptions:
     layout: str = "nested"
     on_duplicate_idat: str = "error"
     cutoff: float = 0.15
-    norm_version: str = "1.2.0"
-    sex_version: int = 2
-    gtc_version: int = 5
+    preset: str = "current"
+    norm_version: str | None = None  # None: from the preset
+    sex_version: int | None = None
+    gtc_version: int | None = None
     autocall_date: str | None = None
     assay_control_probes: tuple[str, ...] = ("TGA_Ctrl_5716",)
     argv: list[str] = field(default_factory=list)
@@ -133,11 +141,7 @@ def _process(job: Job) -> dict[str, Any]:
             call_rate=float(g.call_rate),
             logr_dev=float(g.logr_dev),
             sex_est=g.gender_char,
-            gc10=float(g.gc10),
-            gc50=float(g.gc50),
-            n_calls=g.num_calls,
-            n_nocalls=g.num_no_calls,
-            n_intensity_only=g.num_intensity_only,
+            **summary_stats(g, ctx.manifest.intensity_only, params.cutoff),
             p05_x=int(g.percentiles_x[0]),
             p50_x=int(g.percentiles_x[1]),
             p95_x=int(g.percentiles_x[2]),
@@ -261,13 +265,17 @@ def run_genotype(opts: GenotypeOptions, rep: Reporter) -> int:
     auto_1_22 = np.array([chrom_core(c) in {str(i) for i in range(1, 23)} for c in manifest.chroms])
     name_idx = manifest.name_index()
     probes = {p: name_idx[p] for p in opts.assay_control_probes if p in name_idx}
-    params = GenotypeParams(
+    params = params_for_preset(
+        opts.preset,
         cutoff=opts.cutoff,
         norm_version=opts.norm_version,
-        sex=SexParams(version=opts.sex_version),
+        sex=SexParams(version=opts.sex_version) if opts.sex_version else None,
         gtc_version=opts.gtc_version,
         autocall_date=opts.autocall_date,
     )
+    rm.set_option("effective_norm_version", params.norm_version, f"preset:{opts.preset}")
+    rm.set_option("effective_sex_version", params.sex.version, f"preset:{opts.preset}")
+    rm.set_option("effective_gtc_version", params.gtc_version, f"preset:{opts.preset}")
     started = _dt.datetime.now()
 
     workers = max(1, min(opts.threads or (os.cpu_count() or 1), len(jobs) or 1))
@@ -335,7 +343,7 @@ def run_genotype(opts: GenotypeOptions, rep: Reporter) -> int:
         "warnings": rep.warning_counts(),
     }
     rm.add_output(summary_tsv, SUMMARY_SCHEMA)
-    rm.schema_versions["*.gtc"] = f"gtc/{opts.gtc_version}"
+    rm.schema_versions["*.gtc"] = f"gtc/{params.gtc_version}"
     rm.status = "completed"
     rm.write(opts.out / "run_manifest.json")
     rep.info(f"done: {ok}/{len(out_rows)} samples genotyped; summary {summary_tsv}")