Graph-based prediction of reaction barrier heights with on-the-fly prediction of transition states.

ABSTRACT: The accurate prediction of reaction barrier heights is crucial for understanding chemical reactivity and guiding reaction design. Recent advances in machine learning (ML) models, particularly graph neural networks, have shown great promise in capturing complex chemical interactions. Here, directed message-passing neural networks (D-MPNNs) on graph overlays of the reactant and product structures were shown to provide promising accuracies for reaction property prediction. They rely solely on molecular graph changes as input and thus require no additional information during inference. However, the reaction barrier height intrinsically depends on the conformations of the reactants, transition state, and products, which are not taken into account in standard D-MPNNs. In this work, we present a

SUBMITTER: Karwounopoulos J 

PROVIDER: S-EPMC12461184 | biostudies-literature | 2025 Nov

REPOSITORIES: biostudies-literature