SE(3)-Stochastic Flow Matching for Protein Backbone Generation

arXiv:2310.02391v3 Announce Type: replace
Abstract: The computational design of novel protein structures has the potential to impact numerous scientific disciplines greatly. Toward this goal, we introduce FoldFlow, a series of novel generative models of increasing modeling power based on the flow-matching paradigm over $3\mathrm{D}$ rigid motions -- i.e. the group $\text{SE}(3)$ -- enabling accurate modeling of protein backbones. We first introduce FoldFlow-Base, a simulation-free approach to learning deterministic continuous-time dynamics and matching invariant target distributions on $\text{SE}(3)$. We next accelerate …

abstract arxiv computational cs.ai cs.lg design enabling flow generative generative models impact modeling novel paradigm power protein protein structures scientific series stochastic text type