BOAT: Navigating the Sea of In Silico Predictors for Antibody Design via Multi-Objective Bayesian Optimization

TL;DR

BOAT is a Bayesian optimization framework designed for multi-property antibody engineering, efficiently balancing multiple drug-like properties in antibody design.

Contribution

It introduces a versatile, plug-and-play Bayesian optimization approach that couples surrogate modeling with genetic algorithms for multi-objective antibody property optimization.

Findings

BOAT outperforms genetic algorithms and generative approaches in certain regimes.

Surrogate-driven optimization can be more efficient than generative methods under specific conditions.

Practical limits are identified based on sequence dimensionality and oracle costs.

Abstract

Antibody lead optimization is inherently a multi-objective challenge in drug discovery. Achieving a balance between different drug-like properties is crucial for the development of viable candidates, and this search becomes exponentially challenging as desired properties grow. The ever-growing zoo of sophisticated in silico tools for predicting antibody properties calls for an efficient joint optimization procedure to overcome resource-intensive sequential filtering pipelines. We present BOAT, a versatile Bayesian optimization framework for multi-property antibody engineering. Our `plug-and-play' framework couples uncertainty-aware surrogate modeling with a genetic algorithm to jointly optimize various predicted antibody traits while enabling efficient exploration of sequence space. Through systematic benchmarking against genetic algorithms and newer generative learning approaches, we demonstrate competitive performance with state-of-the-art methods for multi-objective protein optimization. We identify clear regimes where surrogate-driven optimization outperforms expensive generative approaches and establish practical limits imposed by sequence dimensionality and oracle costs.