AlphaFold 3

AlphaFold 3 is an artificial intelligence model that predicts the 3D structure of molecules, such as proteins, DNA, and RNA. AlphaFold 3 is computational heavy and requires a GPU to run, so it is suitable to run on the Seneca GPU nodes.

Launching AlphaFold 3

In the top navigation bar, click Interactive Apps and choose AlphaFold 3. Fill out the resource form:

• Project ID / Account: your CAC project name. The project must be enabled for Seneca access.
• GPU Resource: AlphaFold 3 requires a GPU; select from the list of available GPU configurations.
• Walltime (Hours): session length, up to 24 hours. Default is 8.
• GPU Job Memory (GB): host memory requested for the job. Default is 32 GB.
• AlphaFold 3 Input JSON: the path to a JSON file describing the prediction. For the full reference, see the Google Deepmind's official documentation](https://github.com/google-deepmind/alphafold3/blob/main/docs/input.md).