Cost-Informed Bayesian Reaction Optimization

Bayesian optimization (BO) is an increasingly popular method for optimization and development of chemical reactions. Although effective in guiding experimental design, BO does not account for experimentation costs: testing readily available reagents under different conditions might be more cost and time-effective than synthesizing or buying additional ones. To address this issue, we present cost-informed BO (CIBO), an approach tailored for the rational planning of chemical experimentation that prioritizes the most cost-effective experiments. Reagents are used only when their anticipated improvement in reaction performance sufficiently outweighs their costs. Our algorithm tracks the available reagents, including recently acquired ones, and dynamically updates their cost during the optimization. Using literature data of Pd-catalyzed reactions, we show that CIBO reduces the cost of reaction optimization by up to 90% compared to standard BO. Our approach is compatible with any type of cost, e.g., the cost of buying equipment or compounds, waiting time, and environmental or security concerns. We believe CIBO supersedes BO in chemistry and envision applications in both traditional and self-driving laboratories for experiment planning.