Low-cost prediction of molecular and transition state partition functions via machine learning
This work provides a low-cost method for computational chemists to estimate reaction rates, though it is incremental as it applies existing machine learning techniques to a new dataset in a specific domain.
The authors tackled the high computational cost of predicting molecular and transition state partition functions in organic chemistry by training deep neural networks on a dataset of over 30,000 partition functions, achieving a maximum mean absolute error of 2.7% on test sets and 98.3% accuracy for reaction rate constants.
We have generated an open-source dataset of over 30000 organic chemistry gas phase partition functions. With this data, a machine learning deep neural network estimator was trained to predict partition functions of unknown organic chemistry gas phase transition states. This estimator only relies on reactant and product geometries and partition functions. A second machine learning deep neural network was trained to predict partition functions of chemical species from their geometry. Our models accurately predict the logarithm of test set partition functions with a maximum mean absolute error of 2.7%. Thus, this approach provides a means to reduce the cost of computing reaction rate constants ab initio. The models were also used to compute transition state theory reaction rate constants prefactors and the results were in quantitative agreement with the corresponding ab initio calculations with an accuracy of 98.3% on the log scale.