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).

src/simurg/cn/events.py

@@ -20,8 +20,19 @@ F64 = npt.NDArray[np.float64]
 I64 = npt.NDArray[np.int64]
 GAP_FACTOR = 150
 MIN_MF_PROBES = 20
-LOH_EXPECTED_HETS = 5.0  # CYTO-041: expected heterozygous probes needed to call a loss complete
-LOH_HET_RATIO = 0.25  # CYTO-041: observed / expected heterozygotes below which a loss is complete
+LOSS_EXPECTED_HETS = 3.0  # CYTO-041: expected heterozygous calls needed to call a loss complete
+LOSS_HET_RATIO = 0.25  # CYTO-041: observed / expected heterozygous calls below which a loss is complete
+
+
+def complete_loss(geno: npt.NDArray[np.uint8], pfb: F64) -> bool:
+    """CYTO-041 [OURS]: a loss is complete when its called genotypes lack the heterozygotes the PFB predicts
+    (Σ 2p(1 − p) ≥ 3 expected, fewer than a quarter observed); a mosaic loss keeps its heterozygotes."""
+    called = geno > 0
+    p = np.clip(np.where(np.isfinite(pfb), pfb, 0.5), 0.0, 1.0)[called]
+    expected = float((2 * p * (1 - p)).sum())
+    return expected >= LOSS_EXPECTED_HETS and float((geno[called] == 2).sum()) < LOSS_HET_RATIO * expected
+
+
 TYPES = ("del", "dup", "loh", "gainloh", "mdel", "mdup", "mloh")
 DEFAULTS = {"del": (10, 25_000), "dup": (10, 50_000), "loh": (500, 3_000_000), "gainloh": (300, 500_000),
             "mdel": (10, 25_000), "mdup": (10, 50_000), "mloh": (500, 3_000_000)}  # fmt: skip
@@ -117,21 +128,39 @@ def extract(chrom: str, path: npt.NDArray[np.int32], states: list[State], pos: I
     return out
 
 
-def _mf_from_baf(call: str, baf: F64, baf_sd: float = 0.0, pfb: F64 | None = None) -> float | None:
-    """CYTO-018 with the CYTO-041 refinements [OURS]: the split is corrected for BAF noise (the median |BAF − 0.5| of
-    unsplit heterozygotes is 0.6745·σ_b), and a loss whose expected heterozygotes are absent is complete (MF 1)."""
-    fin = np.isfinite(baf)
-    mid = fin & (baf > 0.1) & (baf < 0.9)
-    b = baf[mid]
-    if call == "MDEL" and pfb is not None and fin.sum() >= MIN_MF_PROBES:
-        p = np.clip(np.where(np.isfinite(pfb), pfb, 0.5), 0.0, 1.0)[fin]
-        expected = float((2 * p * (1 - p)).sum())
-        if expected >= LOH_EXPECTED_HETS and len(b) < LOH_HET_RATIO * expected:
-            return 1.0
+def _phi(x: float) -> float:
+    return 0.5 * (1.0 + math.erf(x / math.sqrt(2.0)))
+
+
+def _split_from_median(m: float) -> float:
+    """δ ≥ 0 with median |N(±δ, 1)| = m (bisection; 0 when m ≤ 0.6745)."""
+    if _phi(m) - _phi(-m) <= 0.5:
+        return 0.0
+    lo, hi = 0.0, m + 10.0
+    for _ in range(60):
+        mid = 0.5 * (lo + hi)
+        if _phi(m - mid) - _phi(-m - mid) > 0.5:
+            lo = mid
+        else:
+            hi = mid
+    return 0.5 * (lo + hi)
+
+
+def _mf_from_baf(call: str, baf: F64, sigma: F64 | float = 0.0) -> float | None:
+    """CYTO-018 with the CYTO-041 noise correction [OURS]. ``baf``: heterozygous-call BAF of the event; ``sigma``:
+    each probe's expected BAF noise (reference heterozygous spread × the sample's scale). With m = median(|BAF − 0.5|
+    / σ), the split δ (in σ units) solves Φ(m − δ) − Φ(−m − δ) = ½ (the median of |N(±δ, 1)|; δ = 0 when
+    m ≤ 0.6745, i.e. no more spread than noise), and d = median(σ)·δ."""
+    sig = np.broadcast_to(np.asarray(sigma, dtype=np.float64), baf.shape)
+    ok = np.isfinite(baf) & (baf > 0.1) & (baf < 0.9) & np.isfinite(sig)
+    b, sg = baf[ok], sig[ok]
     if len(b) < MIN_MF_PROBES:
         return None
-    d_obs = float(np.median(np.abs(b - 0.5)))
-    d = math.sqrt(max(0.0, d_obs**2 - (0.6745 * baf_sd) ** 2))
+    if float(np.median(sg)) > 0:
+        sg = np.maximum(sg, 1e-3)
+        d = float(np.median(sg)) * _split_from_median(float(np.median(np.abs(b - 0.5) / sg)))
+    else:
+        d = float(np.median(np.abs(b - 0.5)))
     if call == "MDEL":
         f = 2 * d / (0.5 + d)
     elif call == "MDUP":
@@ -151,7 +180,7 @@ def _mf_from_lrr(call: str, lrr: F64, gamma: float) -> float | None:
 
 def annotate_stats(
     ev: Event, pos: I64, lrr: F64, baf: F64, geno: npt.NDArray[np.uint8], post: F64, states: list[State], m: float,
-    gamma: float, haploid: bool, baf_sd: float = 0.0, pfb: F64 | None = None,
+    gamma: float, haploid: bool, sigma: F64 | None = None, pfb: F64 | None = None,
 ) -> None:  # fmt: skip
     """CYTO-010/012/018/027 statistics in place (``lrr`` unsmoothed)."""
     sl = slice(ev.i0, ev.i1)
@@ -170,7 +199,11 @@ def annotate_stats(
     p = float(post[sl][:, cls].sum(axis=1).mean()) if cls else 0.0
     ev.quality = 60.0 if p >= 1.0 else float(min(60, max(0, round(-10 * math.log10(max(1e-300, 1 - p))))))
     if ev.mosaic:
-        mf = None if haploid else _mf_from_baf(ev.call, baf[sl], baf_sd, None if pfb is None else pfb[sl])
+        if not haploid and ev.call == "MDEL" and pfb is not None and complete_loss(g, pfb[sl]):
+            ev.mosaic_fraction = 1.0
+            return
+        hb = np.where(g == 2, baf[sl], np.nan) if sigma is not None else baf[sl]
+        mf = None if haploid else _mf_from_baf(ev.call, hb, 0.0 if sigma is None else sigma[sl])
         ev.mosaic_fraction = mf if mf is not None else _mf_from_lrr(ev.call, x, gamma)