AlphaFold Quickstart

Compute Resources

• Have questions or need help with compute, including activation or issues? Follow this link.

• User Agreement

Docker Usage

• The information contained on this page assumes that you have a knowledge base of using Docker to create images and push them to a repository for use. If you need to review that information, please see the links below.

• Docker and the RIS Compute Service

• Docker Basics: Building, Tagging, & Pushing A Custom Docker Image

storageN

• The use of storageN within these documents indicates that any storage platform can be used.

• Current available storage platforms:

  • storage1

  • storage2

Software Included

• AlphaFold v2.2.0 (https://github.com/deepmind/alphafold)

Getting Started

• Connect to compute client.Ω

ssh wustlkey@compute1-client-1.ris.wustl.edu

• Prepare the computing environment before submitting an AlphaFold job.

  # Set the AlphaFold base directory
  export ALPHAFOLD_BASE_DIR=/app/alphafold

  # Use the scratch file system for temp space
  export SCRATCH1=/scratch1/fs1/${COMPUTE_ALLOCATION}

  # Use your Active storage for input and output data
  export STORAGE1=/storageN/fs1/${STORAGE_ALLOCATION}/Active

  # Mount scratch, Active storage, home directory and AlphaFold database reference files
  export LSF_DOCKER_VOLUMES="/scratch1/fs1/ris/references/alphafold_db:/scratch1/fs1/ris/references/alphafold_db $SCRATCH1:$SCRATCH1 $STORAGE1:$STORAGE1 $HOME:$HOME"

  # Update $PATH with folders containing AlphaFold, CUDA, and conda executables
  export PATH="/usr/local/cuda/bin/:/opt/conda/bin:/app/alphafold:$PATH"

  # Use the debug flag when trying to figure out why your job failed to launch on the cluster
  #export LSF_DOCKER_RUN_LOGLEVEL=DEBUG


- The following run example implements AlphaFold's suggested system requirements for database preset ``reduced_dbs``.

bsub -q general -n 8 -M 8GB -R "gpuhost rusage[mem=8GB] span[hosts=1]" -gpu 'num=1' -a "docker(gcr.io/ris-registry-shared/alphafold:2.2.0)" python3 /app/alphafold/run_alphafold.py --output_dir /path/to/output/folder --model_preset monomer --fasta_paths /path/to/input/protein_sequence.fa --max_template_date 2021-08-18 --db_preset reduced_dbs

• AlphaFold can run by default on both V100 and A100 GPU architectures. Modify the -gpu argument to specify the GPU architecture.

-gpu 'num=1:gmodel=<gpu_model>'

• A list of GPU models can be found here.

• Jobs can be managed using job groups. Job groups are a way to submit a large number of jobs at once.

Additional Information

Please refer to official AlphaFold documentation for direction on setting up run options, expected output, example runs, etc.

Earlier Versions

Earlier versions are still available but no longer directly supported by RIS. Please refer to the latest version for direct support.

• AlphaFold Quickstart: Earlier Versions