We present FrameFlow, a method for fast protein backbone generation using SE(3) flow matching. Specifically, we adapt FrameDiff, a state-of-the-art diffusion model, to the flow-matching generative modeling paradigm. We show how flow matching can be applied on SE(3) and propose modifications during training to effectively learn the vector field. Compared to FrameDiff, FrameFlow requires five times fewer sampling timesteps while achieving two fold better designability. The ability to generate high quality protein samples at a fraction of the cost of previous methods paves the way towards more efficient generative models in de novo protein design.
@article{arxiv.2310.05297,
title = {Fast protein backbone generation with SE(3) flow matching},
author = {Jason Yim and Andrew Campbell and Andrew Y. K. Foong and Michael Gastegger and José Jiménez-Luna and Sarah Lewis and Victor Garcia Satorras and Bastiaan S. Veeling and Regina Barzilay and Tommi Jaakkola and Frank Noé},
journal= {arXiv preprint arXiv:2310.05297},
year = {2023}
}