Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry

TL;DR

OrbNet-Equi is a physics-inspired equivariant neural network that efficiently predicts quantum chemical properties with high accuracy, outperforming traditional methods and enabling faster, cost-effective chemical and materials research.

Contribution

We introduce OrbNet-Equi, a novel equivariant neural network leveraging electronic interactions and tight-binding simulations for accurate, rapid quantum property prediction.

Findings

OrbNet-Equi achieves higher accuracy than standard ML methods.

It operates significantly faster than density functional theory.

It performs well on diverse chemical processes and complex systems.

Abstract

Predicting electronic energies, densities, and related chemical properties can facilitate the discovery of novel catalysts, medicines, and battery materials. By developing a physics-inspired equivariant neural network, we introduce a method to learn molecular representations based on the electronic interactions among atomic orbitals. Our method, OrbNet-Equi, leverages efficient tight-binding simulations and learned mappings to recover high fidelity quantum chemical properties. OrbNet-Equi models a wide spectrum of target properties with an accuracy consistently better than standard machine learning methods and a speed orders of magnitude greater than density functional theory. Despite only using training samples collected from readily available small-molecule libraries, OrbNet-Equi outperforms traditional methods on comprehensive downstream benchmarks that encompass diverse main-group chemical processes. Our method also describes interactions in challenging charge-transfer complexes and open-shell systems. We anticipate that the strategy presented here will help to expand opportunities for studies in chemistry and materials science, where the acquisition of experimental or reference training data is costly.