Prof. Xin Hong
Title: Bridging Chemical Knowledge and Machine Learning for Structure-Performance Relationship Prediction in Molecular Synthesis
Bio:
Prof. Xin Hong is a physical organic chemist, whose research focuses on mechanistic models of organic transformations and data-driven design of molecular synthesis. He received his B.S. from the University of Science and Technology of China in 2010 and Ph.D. from the University of California, Los Angeles in 2014 under the guidance of Prof. K. N. Houk. From 2014 to 2016, he conducted postdoctoral research with Prof. Houk at UCLA and Prof. Jens K. Nørskov at Stanford University. Xin joined Zhejiang University in 2016 and was promoted to tenured associate professor in 2022.
Since starting his independent career, Xin has published over 100 papers as corresponding or co-corresponding author in leading journals including Science, Nature Chemistry, Nature Catalysis, Nature Synthesis, Journal of the American Chemical Society, and Angewandte Chemie International Edition. His honors include the Physical Organic Chemistry Rising Star Award (2019), Young Chemist Award of the Chinese Chemical Society (2020), Zhejiang Provincial Youth Science and Technology Talent Award (2021), National Science Foundation for Excellent Young Scientists (2021), and the Thieme Chemistry Journals Award (2022).
He currently serves as Associate Editor of Digital Discovery, Advisory Board Member of Chemical Communications, and as an early career editorial board member for Chemistry – An Asian Journal, National Science Open, and Chemical Synthesis. He is also a committee member of the Physical Organic Chemistry Division of the Chinese Chemical Society. Prof. Hong was elected a Fellow of the Royal Society of Chemistry (FRSC).
Abstract:
Precise prediction of reactivity and selectivity is crucial component of rational design in synthetic chemistry, with significant scientific value and broad application prospects. Benefiting from the rapid accumulation of chemical big data and the vigorous development of artificial intelligence technologies, the integration of AI and synthetic chemistry has provided new approaches for understanding and predicting reactivity and selectivity, thereby advancing rational design in synthesis. In this presentation, I will introduce our recent progress on data-driven prediction of reactivity and selectivity, high-throughput virtual screening, and mechanism-informed reaction design, and discuss how reaction mechanisms can be effectively incorporated into AI-driven synthetic chemistry, along with the key scientific challenges that remain.
Faculty Host: Prof. Shannon Stahl