kyegomez/Open-AF3
PyTorch implementation of AlphaFold3 for predicting protein and biomolecular structures using deep learning.
Not currently ranked — collecting fresh signals.
star history
This repository provides an open-source reimplementation of Google DeepMind’s AlphaFold3 model, which uses neural network architectures (attention mechanisms, diffusion) to predict 3D structures of proteins and biomolecular complexes. The implementation includes the full AlphaFold3 model architecture with pair representations, single representations, and genetic diffusion modules for atomic coordinate generation, written in PyTorch for training and inference.
Frequently asked
- What is kyegomez/Open-AF3?
- PyTorch implementation of AlphaFold3 for predicting protein and biomolecular structures using deep learning.
- Is Open-AF3 open source?
- Yes — kyegomez/Open-AF3 is open source, released under the MIT license.
- What language is Open-AF3 written in?
- kyegomez/Open-AF3 is primarily written in Python.
- How popular is Open-AF3?
- kyegomez/Open-AF3 has 804 stars on GitHub.
- Where can I find Open-AF3?
- kyegomez/Open-AF3 is on GitHub at https://github.com/kyegomez/Open-AF3.