.. _`alphafold-quickstart`:

=====================
AlphaFold Quickstart
=====================

.. contents::
   :depth: 1
   :local:

.. admonition:: Compute Resources

    - Have questions or need help with compute, including activation or issues? Follow `this link. <https://washu.atlassian.net/servicedesk/customer/portal/2/group/6/create/43>`__
    - :ref:`User Agreement <compute-user-agreement>`

.. admonition:: 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.
    - :ref:`Docker and the RIS Compute Service <docker-on-compute>`
    - :ref:`Docker Basics: Building, Tagging, & Pushing A Custom Docker Image <ris-docker-basics>`


Software Included
-----------------

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


Getting Started
---------------

- Connect to compute client.

.. code::

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

- Prepare the computing environment before submitting an AlphaFold job.

.. code::

    # 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=/storage1/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``.

.. code::

    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.

.. code::

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

- A list of GPU models can be found :ref:`here <gpu-resources>`.

- Jobs can be managed using :ref:`job groups <job-groups>`. Job groups are a way
  to submit a large number of jobs at once.


Additional Information
----------------------

Please refer to official `AlphaFold documentation <https://github.com/deepmind/alphafold/tree/v2.2.0>`__
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.

.. toctree::
    :maxdepth: 1

    deprecated-tools/alphafold-deprecated-quickstart