Improved motif-scaffolding with SE(3) flow matching

Jason Yim, Andrew Campbell, Emile Mathieu, Andrew Y. K. Foong, Michael Gastegger, Jose Jimenez-Luna, Sarah Lewis, Victor Garcia Satorras, Bastiaan S. Veeling, Frank Noe, Regina Barzilay, Tommi Jaakkola

Track: Machine learning: computational method and/or work

Keywords: Inpainting, flow matching, Riemannian, SE3, protein, protein generation

TL;DR: We develop a state-of-the-art generative model for protein motif-scaffolding. Our method is twice as fast, achieves same success rate and produces 2.5 times more diverse proteins than state-of-the-art.

Abstract: Protein design often begins with knowledge of a desired function from a motif which motif scaffolding aims to construct a functional protein around. Recently, generative models have achieved breakthrough success in designing scaffolds for a diverse range of motifs. However, the generated scaffolds tend to lack structural diversity, which can hinder success in wet-lab validation. In this work, we extend FrameFlow, an SE(3) flow matching model for protein backbone generation, to perform motif-scaffolding with two complementary approaches. The first is motif amortization, in which FrameFlow is trained with the motif as input using a data augmentation strategy. The second is motif guidance, which performs scaffolding using an estimate of the conditional score from FrameFlow, and requires no additional training. Our method achieves equivalent success rate than previous state-of-the-art methods, with 2.5 times more structurally diverse scaffolds.

Submission Number: 19