Machine Learning Applications for Chemical Reactions.

Machine learning (ML) approaches have enabled rapid and efficient molecular property predictions as well as the design of new novel materials. In addition to great success for molecular problems, ML techniques are applied to various chemical reaction problems that require huge costs to solve with the existing experimental and simulation methods. In this review, starting with basic representations of chemical reactions, we summarized recent achievements of ML studies on two different problems; predicting reaction properties and synthetic routes.

Transfer Learning from Simulation to Experimental Data: NMR Chemical Shift Predictions.

An accurate prediction of chemical shifts (δ) to elucidate molecular structures has been a challenging problem. Recently, noble machine learning architectures achieve accurate prediction performance, but the difficulty of building a huge chemical database limits the applicability of machine learning approaches. In this work, we demonstrate that the prior knowledge gained from the simulation database is successfully transferred into the problem of predicting an experimentally measured δ.

Solvation-Mediated Tuning of the Range-Separated Hybrid Functional: Self-Sufficiency through Screened Exchange.

We propose a simple procedure that restores the ionization potential theorem as the sole tuning criterion for both the long- and short-range Fock exchange of the range-separated hybrid functional. The procedure works by screening out an opposing effect of the short-range Fock fraction at long range, through the 1/ εr dielectric correction in combination with a popular continuum solvation model. Our method proves to be a consistent and accurate way of tuning for both the isolated and solvated molecules.