P5: cloud task for cohort QC validation; configurable gp3 throughput; batched contamination map

- scripts/cloud/tasks/p5.sh: P4 preset re-check, genotype (v5) with QC, validate_p5_large.py - scripts/validate_p5_large.py: identify samples via het pattern vs 1000G VCF; sex, parent-offspring, Mendel, contamination/control distributions - trial.sh: DISK_MBPS / DISK_IOPS - qc/contamination: bounded map batches (executor.map submits eagerly) Co-Authored-By: Claude Opus 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01814GKVzZVL3FuF3DeiZXhv
2026-09-28 09:10:02 +01:00
1 parent 0c004f6398
commit 56d250c621
@@ -0,0 +1,38 @@
+#!/bin/bash
+# Phase P5 bundle on the 1000 Genomes Omni2.5 set (2141 samples):
+#   1. P4 re-check with --preset autocall-1.6.2 (expect byte-identical GTCs except the K-009 samples);
+#   2. `simurg genotype` (legacy preset, GTC v5 so BAF exists) with control tables and cohort QC;
+#   3. P5 validation against the 1000G pedigree and VCF (scripts/validate_p5_large.py).
+# Args: <data dir with bpm/egt and data/>  <results dir>
+set -uo pipefail
+D=$1; OUT=$2
+SRC=s3://1000genomes/release/20130502/supporting/hd_genotype_chip
+mkdir -p $OUT/p4 $OUT/p5 $D/egt
+cp $D/HumanOmni2.5-4v1-Multi_B.egt $D/egt/
+
+echo "=== P4 preset re-check $(date -u +%T) ==="
+/usr/bin/time -v .venv/bin/python scripts/validate_p4_large.py --root $D/data --bpm $D/HumanOmni2.5-4v1-Multi_B.bpm \
+  --egt-dir $D/egt --out $OUT/p4/summary.json --workers "$(nproc)" 2> $OUT/p4/time.txt \
+  || echo "P4 validation reported differences"
+tail -22 $OUT/p4/time.txt
+
+echo "=== P5 genotype + QC $(date -u +%T) ==="
+GT=/work/gt
+/usr/bin/time -v .venv/bin/simurg genotype --bpm $D/HumanOmni2.5-4v1-Multi_B.bpm --egt $D/HumanOmni2.5-4v1-Multi_B.egt \
+  --idats $D/data --out $GT --preset autocall-1.6.2 --gtc-version 5 --autocall-date "1/1/2026 12:00:00 AM" \
+  --qc-profile genotyping --threads "$(nproc)" --quiet 2> $OUT/p5/genotype_time.txt || echo "genotype exit $?"
+tail -22 $OUT/p5/genotype_time.txt
+cp $GT/sample_summary.tsv $GT/controls_qc.tsv $GT/relatedness.tsv $GT/run_manifest.json $OUT/p5/ 2>/dev/null
+cp $GT/mendel.tsv $OUT/p5/ 2>/dev/null
+cp -r $GT/logs $OUT/p5/ 2>/dev/null
+gzip -c $GT/controls_raw.tsv > $OUT/p5/controls_raw.tsv.gz 2>/dev/null
+df -h /work | tail -1
+
+echo "=== P5 validation $(date -u +%T) ==="
+aws s3 cp --no-sign-request "$SRC/broad_intensities/Omni25_genotypes_2141_samples.b37.v2.vcf.gz" /work/ --only-show-errors
+aws s3 cp --no-sign-request "s3://1000genomes/release/20130502/integrated_call_samples.20130502.ALL.ped" /work/ --only-show-errors
+/usr/bin/time -v .venv/bin/python scripts/validate_p5_large.py --gt-dir $GT --bpm $D/HumanOmni2.5-4v1-Multi_B.bpm \
+  --vcf /work/Omni25_genotypes_2141_samples.b37.v2.vcf.gz --ped /work/integrated_call_samples.20130502.ALL.ped \
+  --out $OUT/p5/summary.json --workers "$(nproc)" 2> $OUT/p5/validate_time.txt || echo "P5 validation reported differences"
+tail -22 $OUT/p5/validate_time.txt
+echo "=== task done $(date -u +%T) ==="