CoeffNet: predicting activation barriers through a chemically-interpretable, equivariant and physically constrained graph neural network

Abstract

CoeffNet uses coefficients of molecular orbitals of reactants and products to predict activation barriers.

3DReact: Geometric Deep Learning for Chemical Reactions

“…Despite these advances for molecular property prediction, the prediction of computed reaction properties (principally, reaction barriers ,,− ) is still in its infancy . Machine learning approaches span from utilizing simple two-dimensional fingerprints of reaction components , (reactants and products) to physical-organic descriptors, ,,,,− or electronic structure-inspired features, to transformer models , adapted for regression, and 2D graph-based approaches. ,,, The latter, particularly the ChemProp model, , are often best-in-class in predicting reaction properties . It has been shown that these models achieve their impressive performance by exploiting atom-mapping information, − which provide information analogous to the reaction mechanism.…”

“…Another category of reaction fingerprints arises from discretization of physically inspired functions − ,, constructed using a cheap estimate of the transition state (TS) structure or rather the structures of the reaction components ,, The SLATM d representation , in particular has been shown to yield accurate predictions of reaction barriers, particularly for data sets , relying on subtle changes in the geometry of reactants and/or products. End-to-end models based on three-dimensional structures of reactants and products have also recently emerged. ,, In a different vein, several works − aim to directly predict the TS structure, which together with the reactant structure gives the reaction barrier. These approaches lie outside the scope of the property prediction focus here.…”

“…Endto-end models based on three-dimensional structures of reactants and products have also recently emerged. 72,99,109 In a different vein, several works 110−115 aim to directly predict the TS structure, which together with the reactant structure gives the reaction barrier. These approaches lie outside the scope of the property prediction focus here.…”