Deep Learning of Activation Energies
Author(s)Grambow, Colin A.; Pattanaik, Lagnajit; Green, William H.
MetadataShow full item record
Quantitative predictions of reaction properties, such as activation energy, have been limited due to a lack of available training data. Such predictions would be useful for computer-assisted reaction mechanism generation and organic synthesis planning. We develop a template-free deep learning model to predict the activation energy given reactant and product graphs and train the model on a new, diverse data set of gas-phase quantum chemistry reactions. We demonstrate that our model achieves accurate predictions and agrees with an intuitive understanding of chemical reactivity. With the continued generation of quantitative chemical reaction data and the development of methods that leverage such data, we expect many more methods for reactivity prediction to become available in the near future.
DepartmentMassachusetts Institute of Technology. Department of Chemical Engineering
Journal of Physical Chemistry Letters
American Chemical Society (ACS)
Grambow, Colin A. et al. "Deep Learning of Activation Energies." Journal of Physical Chemistry Letters 11, 8 (March 2020): 2992-2997 © 2020 American Chemical Society
Author's final manuscript