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.

One of the key features of functional proteins, large biomolecules with complex structures, is their inherent structural flexibility - they wiggle, thumble and change shape. We asked a question whether one could design proteins with a custom flexibility from scratch.We build a model that learns how to generate proteins such that their structures are flexible to a given extent at a given position. We show that the model can generate proteins with the desired flexibility patterns, even for patterns that are uncommon in natural proteins. Our work is a step towards the challenging goal of designing new proteins for applications where flexibility is required, such as enzyme catalysts.