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

src/simurg/cli/main.py

@@ -284,9 +284,18 @@ def genotype_cmd(
     sheet: Annotated[Path | None, typer.Option("--sheet", help="Sample sheet (CSV).")] = None,
     csv: Annotated[Path | None, typer.Option("--csv", help="CSV manifest, checked against the BPM.")] = None,
     cutoff: Annotated[float, typer.Option("--cutoff", help="GenCall score below which a call is a no-call.")] = 0.15,
-    norm_version: Annotated[str, typer.Option("--norm-version", help="1.2.0 (current) or 1.1.2")] = "1.2.0",
-    sex_version: Annotated[int, typer.Option("--sex-version", min=1, max=2, help="Sex estimate rule (1 or 2).")] = 2,
-    gtc_version: Annotated[int, typer.Option("--gtc-version", help="GTC format version (3 or 5).")] = 5,
+    preset: Annotated[
+        str, typer.Option("--preset", help="current (default) or autocall-1.6.2 (legacy vendor behaviour)")
+    ] = "current",
+    norm_version: Annotated[
+        str | None, typer.Option("--norm-version", help="1.2.0 or 1.1.2 (default: from --preset)")
+    ] = None,
+    sex_version: Annotated[
+        int | None, typer.Option("--sex-version", min=1, max=2, help="Sex estimate rule 1 or 2 (default: preset)")
+    ] = None,
+    gtc_version: Annotated[
+        int | None, typer.Option("--gtc-version", help="GTC format 3 or 5 (default: preset)")
+    ] = None,
     autocall_date: Annotated[
         str | None, typer.Option("--autocall-date", help="Fixed value for GTC field 201 (reproducible output).")
     ] = None,
@@ -303,9 +312,13 @@ def genotype_cmd(
 
     if layout not in ("nested", "flat"):
         raise typer.BadParameter("--layout must be nested or flat")
-    if gtc_version not in (3, 5):
+    from simurg.genotype.sample import PRESETS
+
+    if preset not in PRESETS:
+        raise typer.BadParameter(f"--preset must be one of {sorted(PRESETS)}")
+    if gtc_version not in (None, 3, 5):
         raise typer.BadParameter("--gtc-version must be 3 or 5")
-    if norm_version not in ("1.2.0", "1.1.2"):
+    if norm_version not in (None, "1.2.0", "1.1.2"):
         raise typer.BadParameter("--norm-version must be 1.2.0 or 1.1.2")
     rep = Reporter(
         command="genotype",
@@ -327,6 +340,7 @@ def genotype_cmd(
         layout=layout,
         on_duplicate_idat=on_duplicate_idat,
         cutoff=cutoff,
+        preset=preset,
         norm_version=norm_version,
         sex_version=sex_version,
         gtc_version=gtc_version,

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,
+    }

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}")