Skip to yearly menu bar Skip to main content

Workshop: Machine Learning in Structural Biology Workshop

Fast protein backbone generation with SE(3) flow matching

Jason Yim · Andrew Campbell · Yue Kwang Foong · Sarah Lewis · Victor Satorras · Michael Gastegger · Bas Veeling · Jose Jimenez-Luna · Regina Barzilay · Tommi Jaakkola · Frank Noe


This work presents a method for fast protein backbone generation using SE(3) flow matching.Specifically, we adapt FrameDiff, a state-of-the-art non-pretrained diffusion model, to perform flow matching with minimal changes.We first develop the theoretical results for SE(3) flow matching then demonstrate modifications during training to effectively learn the conditional vector field.Compared to FrameDiff, we require five times less timesteps to sample while achieving the same designability metrics on unconditional monomer backbone generation.Our work paves way towards faster generative models in de novo protein design.

Chat is not available.