AlphaFold3

1. Introduction
   1. Local Installation
   2. Environment
   3. Data Base Location
   4. run_alphafold.py
2. How to Run
   1. Example on Partition "gpu"
   2. Example on Partition "fct"
   3. Example on Partition "hpc"
   4. sbatch Options
3. Benchmarks
4. References

1. Introduction

This package provides an implementation of the inference pipeline of AlphaFold 3. See below for how to access the model parameters. You may only use AlphaFold 3 model parameters if received directly from Google. Use is subject to these terms of use.

Any publication that discloses findings arising from using this source code, the model parameters or outputs produced by those should cite the Accurate structure prediction of biomolecular interactions with AlphaFold 3 paper.

Please also refer to the Supplementary Information for a detailed description of the method.

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

If you have any questions, please contact the AlphaFold team at alphafold@google.com.

1.1 Local Installation

The CNCA team prepared a local installation of AlphaPhold3 using a container based on singularity including the Genetic Database.

The Model Parameters is not included, users must request access filling a form and comply with the Google DeepMind terms of use at all times.

The local installation provide the AlphaFold3 version 3.0.1 over a container based on Ubuntu 22.04 distribution with cuda-11.0 and cudnn-8.

The main resource target of AlphaFold is the GPU but the application also execute only on the CPU although the performance is substantially worst, see the Benchmarks section bellow.

1.2 Environment

The environment is activate with command

$ module load udocker/alphaphold/2.1.1

this will activate automatically a virtual environment ready to start the AlphaFold container throught the python script run_udocker.py.