Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry

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.

References in corpus (19)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Long-Range Corrected Hybrid Density Functionals with Improved Dispersion Corrections
• Machine Learning Unifies the Modelling of Materials and Molecules
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules
• Equivariant message passing for the prediction of tensorial properties and molecular spectra
• Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
• Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules
• A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules
• Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry
• A numerical algorithm for the explicit calculation of SU(N) and SL(N,C) Clebsch-Gordan coefficients
• Ground state energy functional with Hartree-Fock efficiency and chemical accuracy
• An orbital-based representation for accurate Quantum Machine Learning
• A Wigner-Eckart Theorem for Group Equivariant Convolution Kernels
• DeepDFT: Neural Message Passing Network for Accurate Charge Density Prediction
• Automated Synthetic-to-Real Generalization
• Multi-task learning for electronic structure to predict and explore molecular potential energy surfaces

Cited by in corpus (16)

• General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian
• Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry
• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• Fast Uncertainty Estimates in Deep Learning Interatomic Potentials
• Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids
• Force-Field-Enhanced Neural Network Interactions: from Local Equivariant Embedding to Atom-in-Molecule properties and long-range effects
• Towards DMC accuracy across chemical space with scalable $\Delta$-QML
• MGNN: Moment Graph Neural Network for Universal Molecular Potentials
• Unified Deep Learning Framework for Many-Body Quantum Chemistry via Green's Functions
• FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentials
• Molecular-orbital-based Machine Learning for Open-shell and Multi-reference Systems with Kernel Addition Gaussian Process Regression
• Low-data deep quantum chemical learning for accurate MP2 and coupled-cluster correlations
• A smooth basis for atomistic machine learning
• Equivariant Machine Learning Interatomic Potentials with Global Charge Redistribution
• Linear programming with unitary-equivariant constraints
• Predictive Free Energy Simulations Through Hierarchical Distillation of Quantum Hamiltonians