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

Jackie Rao, Ferran Gonzalez, Leon Gerard, Alexandra Gessner
Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, PMLR 300:5284-5292, 2026.

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 \emph{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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v300-rao26a, title = { BOAT: Navigating The Sea of in Silico Predictors for Antibody Design via Multi-Objective Bayesian Optimization }, author = {Rao, Jackie and Gonzalez, Ferran and Gerard, Leon and Gessner, Alexandra}, booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics}, pages = {5284--5292}, year = {2026}, editor = {Khan, Emtiyaz and Li, Yingzhen and Solin, Arno and Ramdas, Aaditya}, volume = {300}, series = {Proceedings of Machine Learning Research}, month = {02--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v300/main/assets/rao26a/rao26a.pdf}, url = {https://proceedings.mlr.press/v300/rao26a.html}, 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 \emph{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. } }
Endnote
%0 Conference Paper %T BOAT: Navigating The Sea of in Silico Predictors for Antibody Design via Multi-Objective Bayesian Optimization %A Jackie Rao %A Ferran Gonzalez %A Leon Gerard %A Alexandra Gessner %B Proceedings of The 29th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2026 %E Emtiyaz Khan %E Yingzhen Li %E Arno Solin %E Aaditya Ramdas %F pmlr-v300-rao26a %I PMLR %P 5284--5292 %U https://proceedings.mlr.press/v300/rao26a.html %V 300 %X 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 \emph{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.
APA
Rao, J., Gonzalez, F., Gerard, L. & Gessner, A.. (2026). BOAT: Navigating The Sea of in Silico Predictors for Antibody Design via Multi-Objective Bayesian Optimization . Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 300:5284-5292 Available from https://proceedings.mlr.press/v300/rao26a.html.

Related Material