ABSTRACT:

Transition state (TS) search is key in chemistry for elucidating reaction mechanisms and exploring reaction networks. The search for accurate 3D TS structures, however, requires numerous com- putationally intensive quantum chemistry calculations due to the complexity of potential energy surfaces. Here, we developed an object-aware SE(3) equivariant diffusion model that satisfies all physical symmetries and constraints for generating sets of structures – reactant, TS, and product – in an elementary reaction. Provided reactant and product, this model generates a TS structure in seconds instead of hours, which is typically required when performing quantum chemistry-based optimizations. The generated TS structures achieve a median of 0.08 Å root mean square deviation compared to the true TS. With a confidence scoring model for uncertainty quantification, we approach an accuracy required for reaction barrier estimation (2.6 kcal/mol) by only performing quantum chemistry-based optimizations on 14% of the most challenging reactions. We envision the proposed approach useful in constructing large reaction networks with unknown mechanisms.

BIO:

Chenru Duan got his PhD with Prof. Heather Kulik at MIT chemistry and chemical engineering at 2022, where his research focused on integrating machine learning decision-making models in high throughput computation for accelerated chemical discovery. After graduated, he worked in Microsoft as a research scientist to develop machine learning and computational chemistry solutions for industry. In his spare time, he likes engaging with AI4Science community and is one of the organizers of the AI4Science series workshop at ICML and NeurIPS.

Hosted by Professor Wei Wang