v2 methylation control QC (WIP): simurg methyl qc|convert-manifest (MET-001..018)

Methylation CSV manifest reader (MET-002/003), raw M/U assembly with bead masking
(MET-005), pOOBAH detection p-values, noob background correction, linear/nonlinear dye
bias, beta and M-values (MET-010..012), the 21 methylation control metrics (MET-006,
bs-conv red-bg set option), per-sample ctrl/cgs tables, summary tsv/xlsx/html with the
detection histogram and a beta PCA, pcs.tsv.gz, controls_raw/controls_qc.tsv; methylation
datasets load in qc report (MET-014); qc controls --array-type methylation; minfi-style
Sentrix_ID/Sentrix_Position sheet keys. Vendor EPIC manifests carry a 5th field on some
control lines: >= 4 fields accepted. Runs on the public minfiDataEPIC set (3 x NA12878).

src/simurg/qc/controls.py

@@ -71,6 +71,10 @@ METRICS: tuple[Metric, ...] = (
     Metric("bs_conv_2", "bisulfiteConversionII", False, True),
     Metric("bs_conv_2_bg", "bisulfiteConversionIIBg", False, True),
 )
+GTMM_PM = [f"gtmm_{i}_pm" for i in range(1, 7)]
+GTMM_MM = [f"gtmm_{i}_mm" for i in range(1, 7)]
+SPEC2 = ["spec2_1", "spec2_2", "spec2_3"]
+BS2 = ["bs2_1", "bs2_2", "bs2_3", "bs2_4"]
 ASSAY_CONTROL_COLUMN = "assay_control_norm_r"  # QC-005: copied from the sample summary
 COMPAT_METRIC_NAMES = {
     "restoration": "RestorationQC",
@@ -223,14 +227,12 @@ def compute_control_metrics(
     red: npt.NDArray[np.float64],
     array_type: str = "genotyping",
     bg_offset: float = DEFAULT_BG_OFFSET,
+    bs_conv_red_bg_set: str = "U3-U5",
 ) -> ControlQC:
     """QC-003/QC-004 metrics of one sample. Single-probe values are bead means; min/max run over all beads (QC-002)."""
-    if array_type != "genotyping":
-        from simurg.core.errors import SimurgError
-
-        raise SimurgError("E_QC_METHYLATION", "methylation control metrics are planned for v2 (QC-006)")
     p = _Probes(beads, green, red)
     x = bg_offset
+    bs_red_u = ["bs1_U3", "bs1_U4", "bs1_U5"] if bs_conv_red_bg_set == "U3-U5" else ["bs1_U4", "bs1_U5", "bs1_U6"]
     formulas: dict[str, tuple[Any, Any]] = {
         # column: (numerator thunk, denominator thunk); each thunk records the probes it needs
         "restoration": (lambda: p.mean("restoration", "G"), lambda: p.max(["ext_A", "ext_T"], "G") + x),
@@ -246,6 +248,18 @@ def compute_control_metrics(
         "nsb_red": (lambda: p.max(["ext_C", "ext_G"], "R") + x, lambda: p.max(["nsb_bkg"], "R")),
         "np_green": (lambda: p.min(["np_C", "np_G"], "G"), lambda: p.max(["np_A", "np_T"], "G")),
         "np_red": (lambda: p.min(["np_A", "np_T"], "R"), lambda: p.max(["np_C", "np_G"], "R")),
+        # methylation (QC-004 rows 9, 15-24; MET-006)
+        "target_removal_2": (lambda: p.max(["ext_A", "ext_T"], "G") + x, lambda: p.mean("target_removal_2", "G")),
+        "specificity_1_green": (lambda: p.min(GTMM_PM[:3], "G"), lambda: p.max(GTMM_MM[:3], "G")),
+        "specificity_1_red": (lambda: p.min(GTMM_PM[3:], "R"), lambda: p.max(GTMM_MM[3:], "R")),
+        "specificity_2": (lambda: p.min(SPEC2, "R"), lambda: p.max(SPEC2, "G")),
+        "specificity_2_bg": (lambda: p.max(["ext_A", "ext_T"], "G") + x, lambda: p.max(SPEC2, "G")),
+        "bs_conv_1_green": (lambda: p.min(["bs1_C1", "bs1_C2"], "G"), lambda: p.max(["bs1_U1", "bs1_U2"], "G")),
+        "bs_conv_1_green_bg": (lambda: p.max(["ext_A", "ext_T"], "G") + x, lambda: p.max(["bs1_U1", "bs1_U2"], "G")),
+        "bs_conv_1_red": (lambda: p.min(["bs1_C3", "bs1_C4", "bs1_C5"], "R"), lambda: p.max(bs_red_u, "R")),
+        "bs_conv_1_red_bg": (lambda: p.max(["ext_C", "ext_G"], "R") + x, lambda: p.max(bs_red_u, "R")),
+        "bs_conv_2": (lambda: p.min(BS2, "R"), lambda: p.max(BS2, "G")),
+        "bs_conv_2_bg": (lambda: p.max(["ext_A", "ext_T"], "G") + x, lambda: p.max(BS2, "G")),
     }
     res = ControlQC(values={})
     for m in metrics_for(array_type):