Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry
This addresses the problem of costly data acquisition in chemistry and materials science by accelerating quantum chemistry predictions, though it is incremental as it builds on existing geometric deep learning with new physics integration.
The paper tackled predicting electronic energies and chemical properties by developing OrbNet-Equi, a physics-inspired equivariant neural network that learns molecular representations from electronic interactions, achieving better accuracy than standard ML methods and orders of magnitude faster speed than density functional theory.
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.