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/core/errors.py

@@ -116,7 +116,6 @@ CATALOGUE: dict[str, MessageDef] = dict(
         _m("W_CTRL_MISSING", "warning", "Controls needed by a metric are absent; metric not evaluable", "QC-007"),
         _m("W_CTRL_ZERO_DIVISOR", "warning", "Control metric has a zero denominator (NaN)", "QC-008"),
         _m("W_CTRL_DEFS_DIFFER", "warning", "BPM and CSV control definitions differ; the BPM wins", "QC-001"),
-        _m("E_QC_METHYLATION", "error", "Methylation control metrics are not available yet (v2)", "QC-006"),
         _m("E_QC_NO_DATASETS", "error", "No QC dataset folder found", "QC-041"),
         _m("E_QC_DATASET_INCOMPLETE", "error", "Dataset folder lacks a required file", "QC-041"),
         _m("E_QC_LABEL_COUNT", "error", "Number of labels does not match number of datasets", "QC-042"),
@@ -136,6 +135,37 @@ CATALOGUE: dict[str, MessageDef] = dict(
         _m("W_QC_PEDIGREE", "warning", "Parent1/Parent2/Replicate value does not name a sample in the set", "IN-018"),
         _m("W_QC_NO_BAF", "warning", "GTC has no B-allele frequencies; contamination not estimated", "QC-064"),
         _m("W_QC_TOO_FEW", "warning", "Too few samples or sites for a cohort QC statistic", "QC-026"),
+        # --- methylation control QC (MET-001 .. MET-018) -------------------------------------------------
+        _m("E_METH_NO_ASSAY", "error", "Probe section not found", "MET-002"),
+        _m("E_METH_NO_CONTROLS", "error", "Missing control probes in manifest", "MET-002"),
+        _m("E_METH_MISSING_COLUMNS", "error", "Missing required columns in the methylation manifest", "MET-002"),
+        _m(
+            "E_METH_CONTROLS_FORMAT",
+            "error",
+            "Controls not formatted correctly. Must have 4 columns (Address,Type,Color_Channel,Name)",
+            "MET-002",
+        ),
+        _m("E_METH_NO_IDATS", "error", "No IDATs found", "MET-004"),
+        _m(
+            "W_METH_MISSING_SAMPLE",
+            "warning",
+            "Missing sample: IDATs absent; the sample fails, the run continues",
+            "MET-015",
+        ),
+        _m("E_METH_PREP_FAILED", "error", "Prep failed (sample)", "MET-010"),
+        _m(
+            "W_METH_MISSING_CONTROL_TYPES",
+            "warning",
+            "Control types missing from the manifest; metric set to NA",
+            "MET-009",
+        ),
+        _m(
+            "W_METH_MISSING_CONTROL_NAMES",
+            "warning",
+            "Control names missing from the manifest; metric set to NA",
+            "MET-009",
+        ),
+        _m("W_METH_NO_FEATURES", "warning", "No features, skipping PCA plot", "MET-013"),
     ]
 )