Alphafold

Alphafold

AlphaFold is an artificial intelligence (AI) program developed by Alphabets's/Google's DeepMind which performs predictions of protein structure.

Databases:

Mounted on nodes with gpu, located at /alphafold_storage/alphafold_db.

Usage:

use run_alphafold.sh script located at /powerapps/share/centos7/alphafold/alphafold-2.3.1/run_alphafold.sh

Script reference:

Required Parameters:
-d <data_dir>         Path to directory of supporting data
-o <output_dir>       Path to a directory that will store the results.
-f <fasta_paths>      Path to FASTA files containing sequences. If a FASTA file contains multiple sequences, then it will be folded as a multimer. To fold more sequences one after another, write the files separated by a comma
-t <max_template_date> Maximum template release date to consider (ISO-8601 format - i.e. YYYY-MM-DD). Important if folding historical test sets
Optional Parameters:
-g <use_gpu>          Enable NVIDIA runtime to run with GPUs (default: true)
-r <run_relax>        Whether to run the final relaxation step on the predicted models. Turning relax off might result in predictions with distracting stereochemical violations but might help in case you are having issues with the relaxation stage (default: true)
-e <enable_gpu_relax> Run relax on GPU if GPU is enabled (default: true)
-n <openmm_threads>   OpenMM threads (default: all available cores)
-a <gpu_devices>      Comma separated list of devices to pass to 'CUDA_VISIBLE_DEVICES' (default: 0)
-m <model_preset>     Choose preset model configuration - the monomer model, the monomer model with extra ensembling, monomer model with pTM head, or multimer model (default: 'monomer')
-c <db_preset>        Choose preset MSA database configuration - smaller genetic database config (reduced_dbs) or full genetic database config (full_dbs) (default: 'full_dbs')
-p <use_precomputed_msas> Whether to read MSAs that have been written to disk. WARNING: This will not check if the sequence, database or configuration have changed (default: 'false')
-l <num_multimer_predictions_per_model> How many predictions (each with a different random seed) will be generated per model. E.g. if this is 2 and there are 5 models then there will be 10 predictions per input. Note: this FLAG only applies if model_preset=multimer (default: 5)
-b <benchmark>        Run multiple JAX model evaluations to obtain a timing that excludes the compilation time, which should be more indicative of the time required for inferencing many proteins (default: 'false')

Sample Qsub Script:

create folder for output in your home dir mkdir ~/alphafold_output then run the script

• you may download dummy_test folder from this github as well for the output

https://github.com/kalininalab/alphafold_non_docker

• /home/alphafold_folder/alphafold_multimer_non_docker/example/query.fasta = this is sample data, please point to the data you need to query.
• The lines export CUDA_VISIBLE_DEVICES=$(python3 /powerapps/scripts/check_avail_gpu.py) and the flag a $CUDA_VISIBLE_DEVICES make it so you can use the next free GPU on the server, please leave it as is.
• $ALPHAFOLD_SCRIPT_PATH = /powerapps/share/centos7/alphafold/alphafold-2.3.1/
• $ALPHAFOLD_DB_PATH = /alphafold_storage/alphafold_db

#!/bin/bash
#PBS -l select=1:ncpus=4:ngpus=1
##choose any gpu queue: gpu/gpu2
#PBS -q gpu2

# Description: AlphaFold-Multimer (Non-Docker) with auto-gpu selection

# load conda env
module load alphafold/alphafold_non_docker_2.3.1

# call to check_available_gpu python script
# returns the param for CUDA_VISIBLE_DEVICE which the run alphafold script uses

export CUDA_VISIBLE_DEVICES=$(python3 /powerapps/scripts/check_avail_gpu.py)
# echo "CUDA_VISIBLE_DEVICES: $CUDA_VISIBLE_DEVICES"
bash $ALPHAFOLD_SCRIPT_PATH/run_alphafold.sh -d $ALPHAFOLD_DB_PATH -o ~/output_dir -f $ALPHAFOLD_SCRIPT_PATH/examples/query.fasta -t 2020-05-14 -a $CUDA_VISIBLE_DEVICES

Sample Slurm Script

#!/bin/bash
#SBATCH --job-name=AlphaFold-Multimer     # Job name
#SBATCH --partition=gpu2                  # Specify GPU partition
#SBATCH --nodes=1                         # Number of nodes
#SBATCH --ntasks=1                        # Number of tasks (processes)
#SBATCH --cpus-per-task=4                 # Number of CPU cores per task
#SBATCH --gres=gpu:1                      # Request 1 GPU
#SBATCH --output=alphafold_%j.out         # Standard output (with job ID)
#SBATCH --error=alphafold_%j.err          # Standard error (with job ID)

# Description: AlphaFold-Multimer (Non-Docker) with auto-gpu selection

# Load the required module/environment
module load alphafold/alphafold_non_docker_2.3.1

# Run the AlphaFold script
bash $ALPHAFOLD_SCRIPT_PATH/run_alphafold.sh -d $ALPHAFOLD_DB_PATH -o ~/output_dir -f $ALPHAFOLD_SCRIPT_PATH/examples/query.fasta -t 2020-05-14 -a $CUDA_VISIBLE_DEVICES