#!/bin/bash
#SBATCH --job-name=af2           # create a short name for your job
#SBATCH --nodes=1                # node count
#SBATCH --ntasks=1               # total number of tasks across all nodes
#SBATCH --cpus-per-task=4        # cpu-cores per task (>1 if multi-threaded tasks)
#SBATCH --gres=gpu:1             # number of gpus per node
#SBATCH --mem=30G                # total memory per node
#SBATCH --time=12:00:00          # total run time limit (HH:MM:SS)
#SBATCH -A molbio

module load anaconda3/2021.5
module load alphafold/2.1.2

echo Starting Time is `date`
echo Directory is `pwd`
echo Number of Cores: "${SLURM_CPUS_ON_NODE}"
starttime=$(date +"%s")

OUTPUT_DIR=/tigress/ab50/datafiles/protein_folding/alphafold2/NTCP_HBV/Marmoset_NTCP_WT_1-387
DOWNLOAD_DIR=/tigress/MOLBIO/databases/alphafold

srun run_alphafold.py --fasta_paths=seq.fasta \
--output_dir=${OUTPUT_DIR} \
--db_preset=full_dbs \
--model_preset=monomer \
--data_dir=${DOWNLOAD_DIR} \
--uniref90_database_path=${DOWNLOAD_DIR}/uniref90/uniref90.fasta \
--mgnify_database_path=${DOWNLOAD_DIR}/mgnify/mgy_clusters.fa \
--template_mmcif_dir=${DOWNLOAD_DIR}/pdb_mmcif/mmcif_files \
--max_template_date=2021-11-01 \
--obsolete_pdbs_path=${DOWNLOAD_DIR}/pdb_mmcif/obsolete.dat \
--bfd_database_path=${DOWNLOAD_DIR}/bfd/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt \
--uniclust30_database_path=${DOWNLOAD_DIR}/uniclust30/uniclust30_2020_06/UniRef30_2020_06 \
--pdb70_database_path=${DOWNLOAD_DIR}/pdb70/pdb70 \
--use_gpu_relax

endtime=$(date +"%s")
diff=$(($endtime - $starttime))
echo Elapsed time is $(($diff/60)) minutes and $(($diff%60)) seconds.