Menu

A new generative AI approach to predicting chemical reactions

September 4, 2025

System developed at MIT could provide realistic predictions for a wide variety of reactions, while maintaining real-world physical constraints.

The MIT SuperCloud and Lincoln Laboratory Supercomputing Center provided HPC resources for the researchers’ results.

Read this story at MIT News

Story image: The FlowER (Flow matching for Electron Redistribution) system allows a researcher to explicitly keep track of all the electrons in a reaction to ensure that none are spuriously added or deleted in the process of predicting the outcome of a chemical reaction. Credits: Image courtesy of the researchers.

Related Publication:

Joung, J.F., Fong, M.H., Casetti, N. et al. (2025), Electron flow matching for generative reaction mechanism prediction, Nature, doi: 10.1038/s41586-025-09426-9 

Tags:
Previous Post:

Research projects

Towards a Whole Brain Cellular Atlas
Generations of Discovery
A Safer Way to See Inside Cells
Modeling an Atmospheric Detergent
Supercomputers Reveal Ancient Atmospheric Battle
Exact Gravitational Lensing by Rotating Black Holes
Tracking Earth's Atmospheric Highways
Watering MIT's AI Garden
All Research Projects

Collaborative projects

ALL Collaborative PROJECTS

OUTREACH & EDUCATION PROJECTS

See ALL Scholarships
100 Bigelow Street, Holyoke, MA 01040