Multi-Objective Bayesian Optimization with Independent Tanimoto Kernel Gaussian Processes for Diverse Pareto Front Exploration
By: Anabel Yong
Potential Business Impact:
Finds better drug molecules faster.
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.
Similar Papers
MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search Directions
Machine Learning (CS)
Finds best answers for many goals at once.
The Power of the Pareto Front: Balancing Uncertain Rewards for Adaptive Experimentation in scanning probe microscopy
Machine Learning (CS)
Helps robots find the best ways to do science.
Parametric Pareto Set Learning for Expensive Multi-Objective Optimization
Neural and Evolutionary Computing
Finds best answers for changing problems instantly.