Antibody Design with Constrained Bayesian Optimization

Yimeng Zeng, Hunter Elliott, Phillip Maffettone, Peyton Greenside, Osbert Bastani, Jacob R. Gardner

Track: Biology: datasets and/or experimental results

Keywords: Antibody Design, Protein Design, Bayesian Optimization, Generative Modelling, VAE

TL;DR: Designing and synthesizing better antibodies with constrained latent space Bayesian optimization

Abstract: In therapeutic antibody design, achieving a balance between optimizing binding affinity subject to multiple constraints, and sequence diversity within a batch for experimental validation presents an important challenge. Contemporary methods often fall short in simultaneously optimizing these attributes, leading to inefficiencies in experimental exploration and validation. In this work, we tackle this problem using the latest developments in constrained latent space Bayesian optimization. Our methodology leverages a deep generative model to navigate the discrete space of potential antibody sequences, facilitating the selection of diverse, high-potential candidates for synthesis. We also propose a novel way of training VAEs that leads to a lower dimensional latent space and achieves excellent performance under the data-constrained setting. We validate our approach *in vitro* by synthesizing optimized antibodies, demonstrating consistently high binding affinities and preserved thermal stability.

Submission Number: 92