Yiming Zhang, Jun Jin Choong, Kaushalya Madhawa, Keisuke Ozawa
The process of lead optimization in drug discovery is a complex, multiobjective challenge that remains a major bottleneck in the development of new therapeutics. Traditional approaches often struggle to efficiently explore the vast chemical space while simultaneously optimizing multiple, and sometimes conflicting, molecular properties. In this work, we present AutoLead, a novel framework that integrates large language models (LLMs) with multiobjective Bayesian optimization to tackle this challenge. By leveraging the chemical reasoning capabilities of LLMs, AutoLead effectively guides the search for novel drug-like molecules that satisfy multiple objectives. We evaluate our approach on two molecular optimization tasks, achieving state-of-the-art results. Furthermore, we introduce a new benchmark data set designed around a more realistic lead optimization scenario, where the task is to modify compounds that violate Lipinski's rule of five to simultaneously meet all criteria and improve their QED score. Through extensive experiments and a detailed case study, we demonstrate the potential of combining LLMs with black-box optimization techniques for more efficient and practical drug discovery.