OrbNet: Deep learning for quantum chemistry using symmetry-adapted atomic-orbital features

Zhuoran Qiao; Matthew Welborn; Animashree Anandkumar; Frederick R Manby; Thomas F Miller 3rd

doi:10.1063/5.0021955

OrbNet: Deep learning for quantum chemistry using symmetry-adapted atomic-orbital features

J Chem Phys. 2020 Sep 28;153(12):124111. doi: 10.1063/5.0021955.

Authors

Zhuoran Qiao¹, Matthew Welborn², Animashree Anandkumar³, Frederick R Manby², Thomas F Miller 3rd¹

Affiliations

¹ Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, California 91125, USA.
² Entos, Inc., 4470 W Sunset Blvd., Suite 107 PMB 94758, Los Angeles, California 90027, USA.
³ Division of Engineering and Applied Sciences, California Institute of Technology, Pasadena, California 91125, USA.

PMID: 33003742
DOI: 10.1063/5.0021955

Abstract

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.