Quantum Computing Meets AI: A New Frontier for Virtual Screening of Photosensitizers and Photocatalysts

A rational design of photocatalysts and phototherapeutic agents requires accurate predictions of excited-state energetics, intersystem crossing pathways, and electrontransfer reactivity. In this work, we will discus the our quantum-boosted activelearning

AI framework tailored to transition-metal complexes where high-quality excited-state data from quantum-enhanced simulations guide machine-learning models that efficiently explore vast design spaces and optimize key photochemical descriptors. More broadly, we will showcase that this strategy ultimately unlocks a scalable, mechanism-guided route for the rational design of transition-metal photocatalysts with commercially relevant applications spanning biomedicine, solar energy conversion, and photoredox chemistry.