Fast evaluation of the adsorption energy of organic molecules on metals via graph neural networks
Journal article, 2023
Modeling in heterogeneous catalysis requires the extensive evaluation of the energy of molecules adsorbed on surfaces. This is done via density functional theory but for large organic molecules it requires enormous computational time, compromising the viability of the approach. Here we present GAME-Net, a graph neural network to quickly evaluate the adsorption energy. GAME-Net is trained on a well-balanced chemically diverse dataset with C1–4 molecules with functional groups including N, O, S and C6–10 aromatic rings. The model yields a mean absolute error of 0.18 eV on the test set and is 6 orders of magnitude faster than density functional theory. Applied to biomass and plastics (up to 30 heteroatoms), adsorption energies are predicted with a mean absolute error of 0.016 eV per atom. The framework represents a tool for the fast screening of catalytic materials, particularly for systems that cannot be simulated by traditional methods.
Author
Sergio Pablo-García
Institut Català d’Investigació Química (ICIQ)
University of Toronto
Santiago Morandi
Institut Català d’Investigació Química (ICIQ)
Rovira i Virgili University
Rodrigo A. Vargas-Hernández
Vector Institute for AI
University of Toronto
Kjell Jorner
University of Toronto
Chalmers, Chemistry and Chemical Engineering, Chemistry and Biochemistry
Žarko Ivković
Institut Català d’Investigació Química (ICIQ)
Núria López
Institut Català d’Investigació Química (ICIQ)
Alán Aspuru-Guzik
Canadian Institute for Advanced Research
University of Toronto
Vector Institute for AI
Nature Computational Science
26628457 (eISSN)
Vol. 3 5 433-442Inverse design of molecules and reactions
Swedish Research Council (VR) (2020-00314), 2021-01-01 -- 2023-12-31.
Subject Categories
Chemical Sciences
DOI
10.1038/s43588-023-00437-y