CN: MF split normalised by per-probe reference BAF noise; genotype-based complete loss (CYTO-041)

The mosaic BAF split is now estimated over heterozygous calls against each probe's expected noise (the
reference heterozygous spread scaled to the sample), inverting the median of |N(+-d, sigma)|. A mosaic loss
lacking the heterozygous calls its PFB predicts gets MF 1 and is promoted (CYTO-020).

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

src/simurg/pipeline/cn.py

@@ -288,6 +288,26 @@ def _resolve_sex(si: SampleInput, chroms: npt.NDArray[np.str_], lrr: F64, geno:
     return "U", "unresolved", ["sex_unresolved"]
 
 
+def _baf_noise(
+    baf: npt.NDArray[np.float64], geno: npt.NDArray[np.uint8], auto: npt.NDArray[np.bool_],
+    ref_het_sd: npt.NDArray[np.float32] | None, baf_sd: float,
+) -> npt.NDArray[np.float64]:  # fmt: skip
+    """CYTO-041: expected heterozygous BAF noise per probe, the reference spread scaled to this sample
+    (median |BAF − 0.5| / spread over autosomal heterozygous calls = 0.6745 × scale); ``baf_sd`` without a reference
+    spread or where a probe has none."""
+    out = np.full(len(baf), baf_sd, dtype=np.float64)
+    if ref_het_sd is None:
+        return out
+    h = np.asarray(ref_het_sd, dtype=np.float64)
+    hc = auto & (geno == 2) & np.isfinite(baf) & np.isfinite(h) & (h > 0)
+    if hc.sum() < 100:
+        return out
+    scale = float(np.median(np.abs(baf[hc] - 0.5) / np.maximum(h[hc], 1e-3))) / 0.6745
+    ok = np.isfinite(h) & (h > 0)
+    out[ok] = np.maximum(h[ok], 1e-3) * scale
+    return out
+
+
 def call_sample(si: SampleInput, ctx: dict[str, Any], opts: CnCallOptions) -> dict[str, Any]:
     """One sample: preprocessing, per-region HMM, events, VCF + segments. Returns the summary row + events."""
     from simurg.cn import hmm
@@ -346,6 +366,7 @@ def call_sample(si: SampleInput, ctx: dict[str, Any], opts: CnCallOptions) -> di
     seg_sd = _robust_sd(lrr[auto], 0.05)
     b_het = baf[auto & (baf > 0.3) & (baf < 0.7)]
     baf_sd = _robust_sd(b_het, 0.02)
+    sigma = _baf_noise(baf, geno, auto, model.ref_het_sd, baf_sd)  # CYTO-041
     dip, hap = hmm.diploid_states(opts.mosaic_prior), hmm.haploid_states(opts.mosaic_prior)
     counts: dict[str, int] = {}
     events: list[Any] = []
@@ -392,7 +413,7 @@ def call_sample(si: SampleInput, ctx: dict[str, Any], opts: CnCallOptions) -> di
             post = hmm.forward_backward(e, sw, prior)
             evs = extract(chrom, path, states, p)
             for ev in evs:
-                annotate_stats(ev, p, x_raw, b, gt, post, states, m_sp, ctx["gamma"], haploid, baf_sd, pfb[idx])
+                annotate_stats(ev, p, x_raw, b, gt, post, states, m_sp, ctx["gamma"], haploid, sigma[idx], pfb[idx])
             evs = post_filter(evs, [x_raw[ev.i0 : ev.i1] for ev in evs], th, counts)
             for s_, e_ in _runs(path):
                 st = states[int(path[s_])]