P6 complete: optional VCF fields, SNV+indel merging, auxiliary MNV loci, PLINK 2 .pgen

- gtc-to-vcf --info-fields ASSAY_TYPE,NORM_BIN,GENTRAIN,CLUSTER_SEP,ILMN_STRAND,PROBE_IDS (--egt) and
  --extra-format X,Y,NORMX,NORMY,THETA,R, in per-sample VCFs and the --merge BCF (OUT-012, plan §8.3);
  equal to gtc2vcf's values (THETA/R missing where both normalized intensities are 0, K-023)
- --merge-snv-indel (OUT-021, EDGE-013): alleles extended to the longest REF; SNV probes read the base at POS
- --auxiliary-loci (OUT-035, EDGE-015): rules (a)-(e), E_AUX_INVALID; rule (d) uses the last plus-strand base
  for minus-strand designs (spec amended, as GTCtoVCF)
- export plink --format bed|pgen|both: PLINK 2 fixed-width .pgen/.pvar/.psam; plink2 reads it back to a .bed
  byte-identical to ours
- cohort store keeps raw/normalized intensities for the BCF path; tests (unit + gtc2vcf oracle); docs

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

tests/oracle/test_p6_vcf.py

@@ -148,3 +148,74 @@ def test_bedgraph_equals_gtc(tmp_path: Path) -> None:  # OUT-050, OUT-052, EDGE-
             assert v == f"{float(g.logr_ratios[single[key]]):.6g}"
             checked += 1
     assert checked > 500_000
+
+
+def test_info_and_extra_format_match_gtc2vcf(tmp_path: Path) -> None:  # OUT-012, plan §8.3
+    """INFO ASSAY_TYPE/GENTRAIN/CLUSTER_SEP and FORMAT X/Y/NORMX/NORMY equal gtc2vcf's; THETA/R too, except where the
+    normalized intensities are both 0 (SimurgArray: missing, plan §7.4; gtc2vcf: 0)."""
+    from tests.conftest import GSA_EGT
+
+    plugin = BCFTOOLS.parent / "plugins" / "gtc2vcf.so"
+    need(GSA_BPM, GSA_CSV, GSA_EGT, FASTA, ORACLE_GTCS)
+    if not plugin.exists():
+        pytest.skip("gtc2vcf plugin not built")
+    import os
+
+    from typer.testing import CliRunner
+
+    from simurg.cli.main import app
+
+    gtcs = tmp_path / "g"
+    gtcs.mkdir()
+    src = sorted(ORACLE_GTCS.glob("*.gtc"))[0]
+    (gtcs / src.name).symlink_to(src)
+    out = tmp_path / "v"
+    res = CliRunner().invoke(
+        app,
+        ["gtc-to-vcf", "--bpm", str(GSA_BPM), "--csv", str(GSA_CSV), "--fasta", str(FASTA), "--gtcs", str(gtcs),
+         "--out", str(out), "--threads", "1", "--unsquash-duplicates", "--quiet", "--egt", str(GSA_EGT),
+         "--info-fields", "ASSAY_TYPE,GENTRAIN,CLUSTER_SEP", "--extra-format", "X,Y,NORMX,NORMY,THETA,R"],
+    )  # fmt: skip
+    assert res.exit_code == 0, res.output
+    env = dict(os.environ, BCFTOOLS_PLUGINS=str(plugin.parent))
+    g2v = subprocess.run(
+        [str(BCFTOOLS), "+gtc2vcf", "--no-version", "-t", "GT,X,Y,NORMX,NORMY,THETA,R", "-b", str(GSA_BPM), "-c",
+         str(GSA_CSV), "-e", str(GSA_EGT), "-f", str(FASTA), "-g", str(gtcs), "-O", "v"],
+        capture_output=True, text=True, env=env, check=True,
+    ).stdout  # fmt: skip
+    ref = {}
+    for line in g2v.splitlines():
+        if line.startswith("#"):
+            continue
+        c = line.split("\t")
+        info = dict(kv.split("=", 1) for kv in c[7].split(";") if "=" in kv)
+        ref[c[2]] = (info, dict(zip(c[8].split(":"), c[9].split(":"), strict=True)))
+
+    def close(a: str, b: str) -> bool:
+        na, nb = a in (".", "") or "nan" in a.lower(), b in (".", "") or "nan" in b.lower()
+        if na or nb:
+            return na and nb
+        return abs(float(a) - float(b)) <= 1e-5 * max(1.0, abs(float(b)))
+
+    checked = zero_norm = 0
+    with gzip.open(out / f"{src.stem}.snv.vcf.gz", "rt") as fh:
+        for line in fh:
+            if line.startswith("#"):
+                continue
+            c = line.rstrip("\n").split("\t")
+            if "," in c[2] or ";" in c[2] or c[2] not in ref:
+                continue
+            info = dict(kv.split("=", 1) for kv in c[7].split(";"))
+            fmt = dict(zip(c[8].split(":"), c[9].split(":"), strict=True))
+            ri, rf = ref[c[2]]
+            assert info["ASSAY_TYPE"] == ri["ASSAY_TYPE"]
+            assert close(info["GENTRAIN"], ri["GenTrain_Score"]) and close(info["CLUSTER_SEP"], ri["Cluster_Sep"])
+            for k in ("X", "Y", "NORMX", "NORMY"):
+                assert close(fmt[k], rf[k]), (c[2], k, fmt[k], rf[k])
+            if fmt["NORMX"] == "0" and fmt["NORMY"] == "0":
+                zero_norm += 1
+                assert fmt["THETA"] == "." and float(rf["THETA"]) == 0.0
+            else:
+                assert close(fmt["THETA"], rf["THETA"]) and close(fmt["R"], rf["R"]), (c[2], fmt, rf)
+            checked += 1
+    assert checked > 600_000 and zero_norm < 1000