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/pipeline/qc.py

@@ -36,6 +36,7 @@ from simurg.qc.controls import (
     ControlBead,
     ControlQC,
     beads_from_definitions,
+    canonical_id,
     compare_definitions,
     compute_control_metrics,
     control_intensities,
@@ -123,9 +124,10 @@ def control_sample(
     beads: Sequence[ControlBead],
     bg_offset: float,
     sheet_values: Mapping[str, str] | None = None,
+    array_type: str = "genotyping",
 ) -> ControlSample:
     g, r = control_intensities(grn, red, beads)
-    qc = compute_control_metrics(beads, g, r, "genotyping", bg_offset)
+    qc = compute_control_metrics(beads, g, r, array_type, bg_offset)
     return ControlSample(sample_id, idat_metadata(grn, red, sheet_values), g, r, qc)
 
 
@@ -250,8 +252,8 @@ def run_qc_controls(opts: QcControlsOptions, rep: Reporter) -> int:
 
     rm = RunManifest(command="qc controls", argv=opts.argv)
     rep.run_id = rm.run_id
-    if opts.array_type == "methylation":
-        raise SimurgError("E_QC_METHYLATION", "methylation control metrics are planned for v2 (QC-006)")
+    if opts.array_type == "methylation" and opts.csv is None:
+        raise SimurgError("E_NO_INPUT", "methylation control QC needs the methylation CSV manifest (--csv)")
     if opts.bpm is None and opts.csv is None:
         raise SimurgError("E_NO_INPUT", "give --bpm or --csv for the control definitions (QC-001)")
     if opts.bg_offset < 0:
@@ -261,8 +263,15 @@ def run_qc_controls(opts: QcControlsOptions, rep: Reporter) -> int:
     names = (COMPAT_RAW, COMPAT_QC) if opts.compat else (CONTROLS_RAW, CONTROLS_QC)
     targets = [opts.out / n for n in names]
     check_outputs_absent(targets, force=opts.force)  # QC-014: other files in the folder are fine
-    manifest = read_bpm(opts.bpm) if opts.bpm else None
-    beads = load_control_beads(manifest, opts.csv, rep)
+    if opts.array_type == "methylation":
+        from simurg.formats.methyl_manifest import read_methyl_manifest
+
+        assert opts.csv is not None
+        mman = read_methyl_manifest(opts.csv)
+        beads = [ControlBead(c.type, c.color_channel, c.name, c.address, canonical_id(c.name)) for c in mman.controls]
+    else:
+        manifest = read_bpm(opts.bpm) if opts.bpm else None
+        beads = load_control_beads(manifest, opts.csv, rep)
     if not beads:
         raise SimurgError("E_BPM_FORMAT", "the manifest has no control definitions")
     samples: list[ControlSample] = []
@@ -273,7 +282,9 @@ def run_qc_controls(opts: QcControlsOptions, rep: Reporter) -> int:
         assert s.pair.grn is not None and s.pair.red is not None
         grn, red = read_idat(s.pair.grn), read_idat(s.pair.red)
         check_pair(grn, red)
-        samples.append(control_sample(s.sample_id, grn, red, beads, opts.bg_offset, sheet_values(s, sset.sheet)))
+        samples.append(
+            control_sample(s.sample_id, grn, red, beads, opts.bg_offset, sheet_values(s, sset.sheet), opts.array_type)
+        )
     # QC-014: sample IDs of an existing summary must match
     summary = opts.out / "sample_summary.tsv"
     if summary.exists():
@@ -282,7 +293,9 @@ def run_qc_controls(opts: QcControlsOptions, rep: Reporter) -> int:
         if ids ^ mine:
             rep.warn("W_QC_UNMATCHED_SAMPLES", f"{len(ids ^ mine)} sample ID(s) differ from {summary}")
     opts.out.mkdir(parents=True, exist_ok=True)
-    written = write_control_tables(opts.out, samples, beads, opts.bg_offset, rep, compat=opts.compat)
+    written = write_control_tables(
+        opts.out, samples, beads, opts.bg_offset, rep, array_type=opts.array_type, compat=opts.compat
+    )
     for p in written:
         rm.add_output(p, "simurg.controls/1")
     rm.summary = {"samples": len(samples)}