AlphaFold 3
===========

`AlphaFold 3 <https://github.com/google-deepmind/alphafold3>`_ is the latest version from Google DeepMind that can generate highly accurate biomolecular structure predictions containing proteins, DNA, RNA, ligands, ions, and also model chemical modifications for proteins and nucleic acids in one platform.

AlphaFold 3 is also available at `alphafoldserver.com <alphafoldserver.com>`_ for non-commercial use, though with a more limited set of ligands and covalent modifications.


Model Parameters
----------------

To request access to the AlphaFold 3 model parameters please carefully read and agree to the terms and conditions in the form linked below. Once the form is completed you should be automatically added to the `viking-alphafold` group on Viking within 24 hours. You will need to log out and back into Viking to see any changes.

.. important::
    Please complete this form for access to the model parameters: `https://forms.gle/RQr9yaTFs8fJQ1G87 <https://forms.gle/RQr9yaTFs8fJQ1G87>`_

    

Files on Viking
---------------

The following AlphaFold 3 files are in a number of central locations on Viking:

Databases
""""""""""

    ``/mnt/scratch/projects/alphafold3-db/latest``


Model Parameters
"""""""""""""""""

    ``/mnt/scratch/projects/alphafold3-model/latest``


Container
""""""""""

    ``/opt/apps/containers/AlphaFold-3/latest``



Running AlphaFold 3
--------------------

Inside the container directory there are links to the latest version of the following files which you'll need to run AlphaFold 3::

    AlphaFold3-GPU.job          # Example job script
    AlphaFold3-latest.sif       # Apptainer container image
    run_alphafold.py            # Used to run AlphaFold 3

``AlphaFold3-latest.sif`` can be left there, but you'll need to:

    1. Copy ``run_alphafold.py`` to your input directory, the same folder which contains your ``fold_input.json`` file
    2. Make a local copy of the example job script and edit it before you can run AlphaFold 3. Copy it to your home directory or scratch and open it with your chosen text editor, it should look something like the following:

.. code-block:: bash
    :linenos:
    :emphasize-lines: 20,21

    #!/usr/bin/env bash
    
    #----------------------------- SLURM PARAMETERS ------------------------------#
    #SBATCH --job-name=alphafold3-gpu 	# job name
    #SBATCH --nodes=1		  	# request a single node
    #SBATCH --partition=gpuplus	  	# ... from 'gpuplus' (2x H100 per node)
    #SBATCH --gres=gpu:1              	# request 1 GPU
    #SBATCH --cpus-per-task=48	  	# ... and 48 CPU cores
    #SBATCH --time=12:00:00		# max. walltime
    #SBATCH --account=dep-proj-year	# your project code
    
    #-------------------------------- ENVIRONMENT --------------------------------#
    module load Apptainer
    
    AF_CONTAINER="/opt/apps/containers/AlphaFold-3/latest/AlphaFold3-latest.sif"
    AF_DB_DIR="/mnt/scratch/projects/alphafold3-db/latest"
    AF_MODEL_DIR="/mnt/scratch/projects/alphafold3-model/latest"
    
    # Folder containing 'fold_input.json' file
    AF_INPUT_DIR="/path/to/input/folder"
    AF_OUTPUT_DIR="/path/to/output/folder"
    
    export APPTAINER_CACHEDIR="/users/${USER}/localtmp/apptainer-cache"
    
    mkdir -p "${AF_OUTPUT_DIR}"
    
    #------------------------------ RUN ALPHAFOLD --------------------------------#
    apptainer exec \
    	--nv \
    	--bind ${AF_INPUT_DIR}:/root/af_input \
    	--bind ${AF_OUTPUT_DIR}:/root/af_output \
    	--bind ${AF_MODEL_DIR}:/root/models \
    	--bind ${AF_DB_DIR}:/root/public_databases \
    	"${AF_CONTAINER}" \
    	python /root/af_input/run_alphafold.py \
    		--json_path=/root/af_input/fold_input.json \
    		--model_dir=/root/models \
    		--db_dir=/root/public_databases \
    		--output_dir=/root/af_output
    


You'll need to edit lines 20 and 21. Line 20 to point to the folder containing your ``fold_input.json`` and ``run_alphafold.py`` files and line 21 to set your output directory. You can read more about `AlphaFold 3 Input <https://github.com/google-deepmind/alphafold3/blob/main/docs/input.md>`_ in the GitHub.

Please also adjust any options in the **SLURM PARAMETERS** section if necessary, including your project code. The job won't run unless you add in your project code.

When you have everything ready send the job to the :doc:`job scheduler <../using_viking/submitting_jobs>` with the ``sbatch`` command, for example:

.. code-block::

 sbatch AlphaFold3-GPU.job

Further reading
---------------

- `AlphaFold 3 Input <https://github.com/google-deepmind/alphafold3/blob/main/docs/input.md>`_
- `AlphaFold 3 output <https://github.com/google-deepmind/alphafold3/blob/main/docs/output.md>`_
- `Performance <https://github.com/google-deepmind/alphafold3/blob/main/docs/performance.md>`_
- `Known Issues <https://github.com/google-deepmind/alphafold3/blob/main/docs/known_issues.md>`_