Abstract:

AI–guided closed-loop experimentation has recently emerged as a promising method to optimize functional properties in materials discovery. However, achieving the full potential of this approach in the chemical sciences requires new methods to efficiently access large chemical spaces. In this talk, I will discuss a closed-loop approach combining automated synthesis, materials characterization, and AI-guided prediction methods to identify organic light-harvesting molecules with optimized photostability. A Bayesian optimization framework is used to efficiently guide the search through a large molecular space using key physicochemical descriptors while maintaining a customizable tradeoff between exploitative and explorative sampling. Candidate molecules suggested by the AI framework are prepared via automated synthesis using a modular, “Lego-like” molecular building block approach based on Suzuki cross-coupling, followed by characterization of photophysical properties. Our results show that high-energy regions of the triplet state manifold are key to controlling molecular photostability in solution across a diverse chemical library of light-harvesting donor-bridge-acceptor oligomers. Remarkably,this insight emerged after automated synthesis and experimental characterization of only ~1.5% of the total chemical space of 2,200oligomers. In the second part of the talk, I will discuss emerging directions including the extension of this framework to the design and development of function-encoded molecular building blocks to enhance photostability and the discovery of new organic electrochromic materials. Overall, this work shows that interfacing physics-based modeling with closed-loop discovery campaigns – unimpeded by synthesis bottlenecks – can rapidly illuminate fundamental chemical insights and guide rational pursuit of frontier molecular