Abstract
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.
Highlights
Quantitative predictions of reaction properties, such as activation energy, have been limited due to a lack of available training data
Achieving reliable activation energy prediction is an integral step toward the complete prediction of kinetics
Choi et al looked at activation energy prediction using machine learning.[21]. Their training data were composed of reactions in the Reaction Mechanism Generator (RMG)[18] database that comprised many similar reactions such that a random test split yielded ostensibly good results
Summary
Quantitative predictions of reaction properties, such as activation energy, have been limited due to a lack of available training data. Gastegger and Marquetand developed a neural network potential for a specific organic reaction involving bond breaking and formation, likely the first of its kind.[19] Allison described a rate constant predictor for a specific reaction type involving reactions with OH radicals.[20] Choi et al looked at activation energy prediction using machine learning.[21] their training data were composed of reactions in the Reaction Mechanism Generator (RMG)[18] database that comprised many similar reactions such that a random test split yielded ostensibly good results.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
