Abstract
Recent breakthroughs on protein structure prediction, namely AlphaFold, have led to unprecedented new possibilities in related areas. However, the lack of training utilities in its current open-source code hinders the community from further developing or adapting the model. Here we present Uni-Fold as a thoroughly open-source platform for developing protein folding models beyond AlphaFold. We reimplemented AlphaFold and AlphaFold-Multimer in the PyTorch framework, and successfully reproduced their from-scratch training processes with equivalent or better accuracy. Based on various optimizations, Uni-Fold achieves about 2.2 times training acceleration compared with AlphaFold under similar hardware configuration. On a benchmark using recently released multimeric protein structures, Uni-Fold outperforms AlphaFold-Multimer by approximately 2% on the TM-Score. Uni-Fold is currently the only open-source repository that supports both training and inference of multimeric protein models. The source code, model parameters, test data, and web server of Uni-Fold are publicly available3.
Competing Interest Statement
The authors have declared no competing interest.
Footnotes
↵lizy01{at}dp.tech, liuxy{at}dp.tech, chenwj{at}dp.tech, shenf{at}dp.tech, bihr{at}dp.tech, kegl{at}dp.tech, zhanglf{at}dp.tech
↵3 The source code, model parameters and test data of Uni-Fold are available at https://github.com/dptech-corp/Uni-Fold. The web server is available at the Hermite platform https://hermite.dp.tech.