#!/usr/bin/env bash
# CN tuning round on the Pi (GSE165845): reference = replicate-3 arrays of all 120 individuals, test = replicates 1
# and 2 of the first N individuals; truth = NYGC SV rows (data/v2cn/cloud1/truth.tsv).
#   bash scripts/v2/cn_tune.sh TAG [extra `simurg cn call` options...]      (env: N=20, MODEL=...)
set -euo pipefail
cd "$(dirname "$0")/../.."
TAG=${1:?tag}; shift
N=${N:-20}
G=data/v2cn/gse_gt; M=data/v2cn/gse_idats/samples_map.tsv; W=data/v2cn/tune
BPM=data/p8/gsa1/GSA-24v1-0_C2.bpm
mkdir -p $W/ref $W/test
if [[ ! -f $W/.dirs ]]; then
  inds=$(tail -n +2 $M | cut -f3 | awk '!s[$0]++' | head -n "$N")
  tail -n +2 $M | while IFS=$'\t' read -r sid gsm ind rep; do
    [[ $rep == 3 ]] && ln -sfn "$(realpath $G/samples/$sid)" $W/ref/$sid
    if [[ $rep != 3 ]] && grep -qx "$ind" <<< "$inds"; then ln -sfn "$(realpath $G/samples/$sid)" $W/test/$sid; fi
  done
  touch $W/.dirs
fi
MODEL=${MODEL:-$W/ref.simurg-cyto}
if [[ ! -f $MODEL ]]; then
  MEM=${MEM:-5G} MIN_FREE_MB=1500 bash scripts/pi_run.sh .venv/bin/simurg cn build-model --bpm $BPM --fasta data/p6/GRCh38.primary.fa \
    --egt data/p8/gsa1/GSA-24v1-0_C1_ClusterFile.egt --reference-gtcs $W/ref --max-reference 120 --out $MODEL --quiet
fi
MEM=${MEM:-5G} MIN_FREE_MB=1500 bash scripts/pi_run.sh .venv/bin/simurg cn call --bpm $BPM --model $MODEL --gtcs $W/test \
  --summary $G/sample_summary.tsv --out $W/$TAG --threads 3 --force --quiet "$@"
.venv/bin/python scripts/v2/cn_validate_truth.py --calls $W/$TAG --map $M --truth data/v2cn/cloud1/truth.tsv --bpm $BPM \
  --min-qual 20 --out $W/$TAG/val > /dev/null
.venv/bin/python scripts/v2/cn_tune_report.py $W/$TAG $M