CN: per-probe LRR noise from the batch reference (CYTO-042), --probe-lrr-sd/--no-probe-lrr-sd

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

src/simurg/cn/model.py

@@ -86,3 +86,18 @@ def reference_het_spread(baf: npt.NDArray[np.float32]) -> npt.NDArray[np.float32
             mad = np.nanmedian(np.abs(het - med), axis=0)
     n = np.isfinite(het).sum(axis=0)
     return np.where(n >= 5, 1.4826 * mad, np.nan).astype(np.float32)
+
+
+def reference_lrr_spread(lrr: npt.NDArray[np.float32], ref_lrr: npt.NDArray[np.float32]) -> npt.NDArray[np.float32]:
+    """Per-probe robust SD (1.4826·MAD) of LRR across reference samples after removing each sample's median and the
+    probe's reference median [OURS; per-probe noise as in PennCNV's per-marker SD, LIT: Wang et al. 2007]; NaN with
+    fewer than 5 finite values."""
+    import warnings
+
+    x = np.where(np.isfinite(lrr), lrr, np.nan).astype(np.float32)
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore", RuntimeWarning)
+        x = x - np.nanmedian(x, axis=1, keepdims=True) - ref_lrr[None, :]
+        mad = np.nanmedian(np.abs(x - np.nanmedian(x, axis=0)), axis=0)
+    n = np.isfinite(x).sum(axis=0)
+    return np.where(n >= 5, 1.4826 * mad, np.nan).astype(np.float32)