We introduce a machine learning method in which energy solutions from the Schrödinger equation are predicted using symmetry adapted atomic orbital features and a graph neural-network architecture. OrbNet is shown to outperform existing methods in terms of learning efficiency and transferability for the prediction of density functional theory results while employing low-cost features that are obtained from semi-empirical electronic structure calculations. For applications to datasets of drug-like molecules, including QM7b-T, QM9, GDB-13-T, DrugBank, and the conformer benchmark dataset of Folmsbee and Hutchison [Int. J. Quantum Chem. (published online) (2020)], OrbNet predicts energies within chemical accuracy of density functional theory at a computational cost that is 1000-fold or more reduced.
OrbNet: Deep learning for quantum chemistry using symmetry-adapted atomic-orbital features
Zhuoran Qiao, Matthew Welborn, Animashree Anandkumar, Frederick R. Manby, Thomas F. Miller; OrbNet: Deep learning for quantum chemistry using symmetry-adapted atomic-orbital features. J. Chem. Phys. 28 September 2020; 153 (12): 124111. https://doi.org/10.1063/5.0021955
Download citation file: