code/probes/cluster_scripts/run_probe8.sh

#!/bin/bash
#SBATCH --job-name=probe8_disease
#SBATCH --partition=nova
#SBATCH --gres=gpu:a100:1
#SBATCH --cpus-per-task=8
#SBATCH --mem=64G
#SBATCH --time=02:00:00
#SBATCH --output=bert_v6_contrastive/scripts/probe8_%j.out
#SBATCH --error=bert_v6_contrastive/scripts/probe8_%j.err

echo "========================================"
echo "Probe 8: Disease/Tissue Embedding Analysis"
echo "Job ID: $SLURM_JOB_ID"
echo "Node:   $(hostname)"
echo "Start:  $(date)"
echo "========================================"

source /work/ratul1/supantha/miniconda3/etc/profile.d/conda.sh
conda activate blade

cd /work/ratul1/supantha/glycan-SD-VS/bert_training_v3/v3.1_cluster_training

echo "Python: $(which python3)"
nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>/dev/null || echo "No GPU"

ls -lh bert_v6_contrastive/analysis/probe8_disease_tissue_data.csv || { echo "ERROR: Data file missing"; exit 1; }

pip install -q scikit-learn umap-learn 2>/dev/null

echo ""
echo "========== V5-A (MLM-only) =========="
python3 -u bert_v6_contrastive/scripts/probe_8_disease_tissue.py --model v5 --device cuda

echo ""
echo "========== V6 (MLM+SimCLR) =========="
python3 -u bert_v6_contrastive/scripts/probe_8_disease_tissue.py --model v6 --device cuda

echo ""
echo "Completed: $(date)"
ls -la bert_v6_contrastive/analysis/probe8_disease_tissue_v5/ 2>/dev/null
ls -la bert_v6_contrastive/analysis/probe8_disease_tissue_v6/ 2>/dev/null