Multi-Objective Bayesian Optimization with Independent Tanimoto Kernel Gaussian Processes for Diverse Pareto Front Exploration
This work addresses complex multi-objective optimization challenges in molecular design, offering an incremental improvement over existing methods for researchers in computational chemistry.
The paper tackles multi-objective molecular optimization by introducing GP-MOBO, a Bayesian optimization algorithm that uses independent Tanimoto kernel Gaussian processes to explore diverse Pareto fronts, resulting in higher-quality SMILES and superior proximity to the Pareto front with minimal computational overhead, as shown by higher geometric mean values in experiments.
We present GP-MOBO, a novel multi-objective Bayesian Optimization algorithm that advances the state-of-the-art in molecular optimization. Our approach integrates a fast minimal package for Exact Gaussian Processes (GPs) capable of efficiently handling the full dimensionality of sparse molecular fingerprints without the need for extensive computational resources. GP-MOBO consistently outperforms traditional methods like GP-BO by fully leveraging fingerprint dimensionality, leading to the identification of higher-quality and valid SMILES. Moreover, our model achieves a broader exploration of the chemical search space, as demonstrated by its superior proximity to the Pareto front in all tested scenarios. Empirical results from the DockSTRING dataset reveal that GP-MOBO yields higher geometric mean values across 20 Bayesian optimization iterations, underscoring its effectiveness and efficiency in addressing complex multi-objective optimization challenges with minimal computational overhead.