#!/bin/bash
#
#SBATCH --job-name=esm.msa
# Default in slurm
#SBATCH --mail-user=gz2294@cumc.columbia.edu
#SBATCH --mail-type=ALL
#SBATCH -t 72:0:0 # Request 5 hours run time
# Define threads and memeory
#SBATCH --ntasks=1
#SBATCH --nodes=1
#SBATCH --cpus-per-task=5
#SBATCH --mem=10gb
# Define Output Log
#SBATCH --output=esm2.log
date;hostname;pwd

PROTEIN=$1
DATASET=$2

PLMC_DIR="$HOME"
    
mkdir -p inference/$DATASET/plmc

#$PLMC_DIR/plmc/bin/plmc \
/share/descartes/Users/gz2294/miniconda3/envs/protein_fitness_prediction/bin/plmc \
    -o inference/$DATASET/plmc/uniref100.model_params \
    -c inference/$DATASET/plmc/uniref100.EC \
    -f $PROTEIN \
    -le 16.2 -lh 0.01 -m 200 -t 0.2 \
    -g msa/$PROTEIN.a2m