Combining Bayesian optimization and automation to simultaneously optimize reaction conditions and routes

Abstract

Reaching optimal reaction conditions is crucial to achieve high yields, minimize by-products, and ensure environmentally sustainable chemical reactions. With the recent rise of artificial intelligence, there has been a shift from traditional Edisonian trial-and-error optimization to data-driven and automated approaches, which offer significant advantages. Here, we combined the ML-driven experiment planner "Atinary SDLabs" and the cloud-based robotic synthesis platform "IBM RoboRXN." This integration of the two platforms allowed us to conduct the simultaneous optimizations of the iodination of four different terminal alkynes and two different reaction routes. Remarkably, we achieved a conversion rate of over 80% for all four substrates in under 23 experiments, covering only ca. 0.2% of the combinatorial space. Further analysis allowed us to identify the influence of different reaction parameters on the reaction outcomes, demonstrating the potential for expedited reaction condition optimization and the prospect of more efficient chemical processes in the future.