Theoretical and Computational Chemistry

Deep Learning of Activation Energies

Authors

Abstract

Quantitative prediction 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 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 development of methods that leverage such data, we expect many more methods for reactivity prediction to become available in the near future.

Content

Thumbnail image of Grambow2020_deep_learning_of_activation_energies.pdf

Supplementary material

Thumbnail image of Grambow2020_Supporting_Information.pdf
Grambow2020 Supporting Information