code/probes/cluster_scripts/run_probe9_biosynthesis.sh

#!/bin/bash
#SBATCH --job-name=probe9_biosynth
#SBATCH --partition=nova
#SBATCH --gres=gpu:a100:1
#SBATCH --cpus-per-task=8
#SBATCH --mem=64G
#SBATCH --time=03:00:00
#SBATCH --output=bert_v6_contrastive/analysis/probing_analysis/slurm_logs/probe9_%j.out
#SBATCH --error=bert_v6_contrastive/analysis/probing_analysis/slurm_logs/probe9_%j.err

echo "========================================"
echo "Probe 9: N-Glycan Biosynthesis Pathway"
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 glycanml

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

echo "Python: $(which python3)"
echo "PyTorch: $(python3 -c 'import torch; print(torch.__version__, "CUDA:", torch.cuda.is_available())')"
nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>/dev/null || echo "No GPU"
echo ""

# Run V5 (MLM-only)
echo "========== V5 (MLM-only) =========="
python3 -u bert_v6_contrastive/scripts/probe_9_biosynthesis_order.py \
    --model v5 --device cuda --max-glycans 15000

echo ""
# Run V6 (MLM+SimCLR)
echo "========== V6 (MLM+SimCLR) =========="
python3 -u bert_v6_contrastive/scripts/probe_9_biosynthesis_order.py \
    --model v6 --device cuda --max-glycans 15000

echo ""
echo "Completed: $(date)"
echo "Output dirs:"
ls -la bert_v6_contrastive/analysis/probing_analysis/09_biosynthesis_pathway_v5/ 2>/dev/null
ls -la bert_v6_contrastive/analysis/probing_analysis/09_biosynthesis_pathway_v6/ 2>/dev/null