P5a: QC — control metrics, thresholds, status, contamination, relatedness, locus summary

- qc/controls: canonical control names (QC-002), bkg/offset (QC-003), 13 genotyping metrics (QC-004/005),
  missing/zero-divisor handling (QC-007/008); controls_raw.tsv / controls_qc.tsv (QC-009/011) incl. compat CSVs
- qc/thresholds + profiles: YAML schema, validation codes, precedence, shipped profiles, auto (QC-020..025)
- qc/status: functional PASS/FAIL/NA, control CLEAR/FLAGGED, flags (QC-030..033)
- qc/contamination: BAF regression; bit-compatible with gtc2vcf BAFregress (36/36, K-017), exact mode too
- qc/relatedness: KING-robust, duplicates, Mendelian errors, pedigree from sheet (IN-018)
- qc/locus_summary: OUT-072, bit-identical to BeadArrayFiles except ChiTest (K-018)
- qc/suggest: suggest-thresholds (QC-026)
- pipeline/qc: disk-backed cohort store; CLI qc controls|samples|contamination|relatedness|loci|suggest-thresholds
- genotype: control tables (OUT-070), het_rate, QC columns, cohort QC
- tests: unit + oracle (BAFregress plugin, BeadArrayFiles locus summary)

scripts/make_oracle_gtcs.sh

@@ -9,14 +9,14 @@ cd "$(dirname "$0")/.."
 V=1.22
 T=refs/tools
 B=$T/bcftools-$V
-if [[ ! -x $B/bcftools || ! -f $B/plugins/idat2gtc.so ]]; then
+if [[ ! -x $B/bcftools || ! -f $B/plugins/idat2gtc.so || ! -f $B/plugins/BAFregress.so ]]; then
   [[ -d refs/gtc2vcf ]] || bash scripts/bootstrap_refs.sh
   mkdir -p $T
   [[ -f $T/bcftools.tar.bz2 ]] || curl -sL -o $T/bcftools.tar.bz2 \
     "https://github.com/samtools/bcftools/releases/download/$V/bcftools-$V.tar.bz2"
   tar -xjf $T/bcftools.tar.bz2 -C $T
-  rm -f $B/plugins/{idat2gtc,gtc2vcf,affy2vcf}.{c,h}
-  cp refs/gtc2vcf/{idat2gtc,gtc2vcf,affy2vcf}.c refs/gtc2vcf/*.h $B/plugins/
+  rm -f $B/plugins/{idat2gtc,gtc2vcf,affy2vcf,BAFregress}.{c,h}
+  cp refs/gtc2vcf/{idat2gtc,gtc2vcf,affy2vcf,BAFregress}.c refs/gtc2vcf/*.h $B/plugins/
   (cd $B/htslib-$V && ./configure --disable-libcurl --disable-bz2 --disable-lzma --disable-ref-cache >/dev/null)
   (cd $B && ./configure --without-gsl >/dev/null && make -j"$(nproc)" CFLAGS="-g -O2 -ffp-contract=off" >/dev/null)
 fi

scripts/make_oracle_qc.sh

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+# Oracle outputs for phase P5 (QC) on the P0 GSA demo data:
+#  * BeadArrayFiles (BSD-2) examples/locus_summary.py over the 36 oracle GTCs, run in a separate venv with
+#    scipy/pandas (oracle-only dependencies; never needed by SimurgArray itself);
+#  * the gtc2vcf BAFregress plugin (MIT) is built by scripts/make_oracle_gtcs.sh and run by the tests directly.
+set -euo pipefail
+cd "$(dirname "$0")/.."
+V=refs/tools/oracle-venv
+[[ -x $V/bin/python ]] || { uv venv -q $V && uv pip install -q --python $V/bin/python numpy scipy pandas; }
+SHIM=refs/tools/shim
+mkdir -p $SHIM && ln -sfn "$PWD/refs/BeadArrayFiles/module" $SHIM/IlluminaBeadArrayFiles
+D=data/p0/gsa_v4_pgx
+OUT=data/p0/oracle/locus_summary
+mkdir -p $OUT
+PYTHONPATH=$SHIM $V/bin/python refs/BeadArrayFiles/examples/locus_summary.py data/p0/oracle/gsa_gt3_nofma \
+  $D/GSA-PGx-48v4-0_20079540_E2_bpm/GSA-PGx-48v4-0_20079540_E2.bpm \
+  $D/GSA-PGx-48v4-0_20079540_E2_ClusterFile/GSA-PGx-48v4-0_20079540_E2_ClusterFile.egt \
+  $OUT/gsa36_beadarrayfiles.csv
+echo "wrote $OUT/gsa36_beadarrayfiles.csv"