methylation: combine_neg option; oracle compares both background variants and logs sesame's negative controls

src/simurg/signal/methyl.py

@@ -88,9 +88,9 @@ def _finite(a: F64) -> F64:
     return a[np.isfinite(a)]
 
 
-def background(s: MethylSignals) -> tuple[F64, F64]:
-    """Out-of-band background per channel (green, red): Infinium I OOB signal + negative controls."""
-    neg = np.array([t.casefold() == "negative" for t in s.ctrl_type], dtype=np.bool_)
+def background(s: MethylSignals, combine_neg: bool = True) -> tuple[F64, F64]:
+    """Out-of-band background per channel (green, red): Infinium I OOB signal (+ negative controls)."""
+    neg = np.array([combine_neg and t.casefold() == "negative" for t in s.ctrl_type], dtype=np.bool_)
     red_i, grn_i = s.col == "R", s.col == "G"
     oob_g = np.concatenate([s.oob_m[red_i], s.oob_u[red_i], s.ctrl_green[neg]])
     oob_r = np.concatenate([s.oob_m[grn_i], s.oob_u[grn_i], s.ctrl_red[neg]])
@@ -118,9 +118,9 @@ def _ecdf(ref: F64):  # type: ignore[no-untyped-def]
     return f
 
 
-def detection_p(s: MethylSignals) -> F64:
+def detection_p(s: MethylSignals, combine_neg: bool = True) -> F64:
     """pOOBAH detection p-value per probe; 1 where masked."""
-    bg_g, bg_r = background(s)
+    bg_g, bg_r = background(s, combine_neg)
     fg, fr = _ecdf(bg_g), _ecdf(bg_r)
     red_i, t2 = s.col == "R", s.col == ""
     m, u = np.nan_to_num(s.m, nan=0.0), np.nan_to_num(s.u, nan=0.0)
@@ -194,9 +194,11 @@ def noob_fit(ib: F64, oob: F64) -> NoobFit:
     return NoobFit(mu, s, max(huber(ib)[0] - mu, 10.0))
 
 
-def noob(s: MethylSignals, offset: float = NOOB_OFFSET) -> tuple[MethylSignals, NoobFit, NoobFit]:
+def noob(
+    s: MethylSignals, offset: float = NOOB_OFFSET, combine_neg: bool = True
+) -> tuple[MethylSignals, NoobFit, NoobFit]:
     """Background-corrected copy of ``s`` (probe and control signals); returns the green and red fits."""
-    bg_g, bg_r = background(s)
+    bg_g, bg_r = background(s, combine_neg)
     ib_g, ib_r = in_band(s)
     fit_g, fit_r = noob_fit(ib_g, bg_g), noob_fit(ib_r, bg_r)