A Multi-Objective Active Learning Platform and Web App for Reaction Optimization

Abstract

We report the development of an open-source Experimental Design via Bayesian Optimization platform for multi-objective reaction optimization. Using high-throughput experimentation (HTE) and virtual screening datasets containing high-dimensional continuous and discrete variables, we optimized the performance of the platform by fine-tuning the algorithm components such as reaction encodings, surrogate model parameters and initialization techniques. Having established the framework, we applied the optimizer to real-word test scenarios for the simultaneous optimization of reaction yield and enantioselectivity in a Ni/photoredox-catalyzed enantioselective cross-electrophile coupling of styrene oxide with two different aryl iodide substrates. Starting with no previous experimental data, the Bayesian optimizer identified reaction conditions that surpassed the previously human-driven optimization campaigns within 15 and 24 experiments, for each substrate, among 1,728 possible configurations available in each optimization. To make the platform more accessible to non-experts, we developed a Graphical User Interface (GUI) that can be accessed online through a web-based application and incorporated features such as conditions modification on-the-fly and data visualization. This web-application does not require software installation, removing any programming barrier to use the platform, which enables chemists to integrate Bayesian optimization routines into their everyday laboratory practices.