lucidrains/alphafold2
An unofficial PyTorch implementation of DeepMind's AlphaFold2 protein folding model using attention mechanisms.
Not currently ranked — collecting fresh signals.
star history
This repository aims to replicate AlphaFold2, DeepMind’s groundbreaking attention-based neural network that solved the 50-year grand challenge of protein structure prediction. It implements the trunk architecture using axial attention with PyTorch, supporting inputs of amino acid sequences and multiple sequence alignments. A contributor has reported training a modified trunk with competitive results against trRosetta.
Frequently asked
- What is lucidrains/alphafold2?
- An unofficial PyTorch implementation of DeepMind's AlphaFold2 protein folding model using attention mechanisms.
- Is alphafold2 open source?
- Yes — lucidrains/alphafold2 is open source, released under the MIT license.
- What language is alphafold2 written in?
- lucidrains/alphafold2 is primarily written in Python.
- How popular is alphafold2?
- lucidrains/alphafold2 has 1.6k stars on GitHub.
- Where can I find alphafold2?
- lucidrains/alphafold2 is on GitHub at https://github.com/lucidrains/alphafold2.