BetterBodies: Reinforcement Learning guided Diffusion for Antibody Sequence Design

24 Sept 2024 (modified: 26 Nov 2024)ICLR 2025 Conference Withdrawn SubmissionEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Reinforcement Learning, Generative Models, Diffusion Models, Antibody Design
TL;DR: Our novel method combines Variational Autoencoders with offline Reinforcement Learning guided latent Diffusion to generate novel sets of antibody CDRH3 sequences from different data distributions.
Abstract:

Antibodies offer great potential for the treatment of various diseases. However, the discovery of therapeutic antibodies through traditional wet lab methods is expensive and time-consuming. The use of generative models in designing antibodies therefore holds great promise, as it can reduce the time and resources required. Recently, the class of diffusion models has gained considerable traction for their ability to synthesize diverse and high-quality samples. In their basic form, however, they lack mechanisms to optimize for specific properties, such as binding affinity to an antigen. In contrast, the class of offline Reinforcement Learning (RL) methods has demonstrated strong performance in navigating large search spaces, including scenarios where frequent real-world interaction, such as interaction with a wet lab, is impractical. Our novel method, BetterBodies, which combines Variational Autoencoders (VAEs) with offline RL guided latent diffusion, can generate novel sets of antibody CDRH3 sequences from different data distributions. Furthermore, we reflect biophysical properties in the VAE latent space using a contrastive loss and add a novel Q-function based filtering to enhance the affinity of generated sequences. Using the Absolut! simulator, we demonstrate that BetterBodies generates sequences with improved binding affinity to the SARS-CoV spike receptor-binding domain and matches or outperforms the state-of-the-art method Generative Flow Network (GFlowNet). In conclusion, our method has the potential for great implications in real-world biological sequence design, where the generation of novel high-affinity binders is a cost-intensive endeavor.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 3663
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview