Flexibility-Conditioned Protein Structure Design with Flow Matching

TL;DR

This paper introduces a novel framework combining neural networks and flow matching to generate protein structures conditioned on desired flexibility profiles, advancing protein design capabilities beyond static properties.

Contribution

It presents BackFlip for flexibility prediction and FliPS for generating flexible protein backbones, enabling targeted control of protein flexibility in design.

Findings

FliPS can generate diverse protein backbones with specified flexibility.

Generated structures are validated by Molecular Dynamics simulations.

Framework advances flexible protein design beyond static property constraints.

Abstract

Recent advances in geometric deep learning and generative modeling have enabled the design of novel proteins with a wide range of desired properties. However, current state-of-the-art approaches are typically restricted to generating proteins with only static target properties, such as motifs and symmetries. In this work, we take a step towards overcoming this limitation by proposing a framework to condition structure generation on flexibility, which is crucial for key functionalities such as catalysis or molecular recognition. We first introduce BackFlip, an equivariant neural network for predicting per-residue flexibility from an input backbone structure. Relying on BackFlip, we propose FliPS, an SE(3)-equivariant conditional flow matching model that solves the inverse problem, that is, generating backbones that display a target flexibility profile. In our experiments, we show that FliPS is able to generate novel and diverse protein backbones with the desired flexibility, verified by Molecular Dynamics (MD) simulations. FliPS and BackFlip are available at https://github.com/graeter-group/flips .