Teaching a neural network to attach and detach electrons from molecules

Roman Zubatyuk,Justin S Smith,Benjamin T Nebgen,Sergei Tretiak,Olexandr Isayev

doi:10.1038/s41467-021-24904-0

Abstract

Interatomic potentials derived with Machine Learning algorithms such as Deep-Neural Networks (DNNs), achieve the accuracy of high-fidelity quantum mechanical (QM) methods in areas traditionally dominated by empirical force fields and allow performing massive simulations. Most DNN potentials were parametrized for neutral molecules or closed-shell ions due to architectural limitations. In this work, we propose an improved machine learning framework for simulating open-shell anions and cations. We introduce the AIMNet-NSE (Neural Spin Equilibration) architecture, which can predict molecular energies for an arbitrary combination of molecular charge and spin multiplicity with errors of about 2–3 kcal/mol and spin-charges with error errors ~0.01e for small and medium-sized organic molecules, compared to the reference QM simulations. The AIMNet-NSE model allows to fully bypass QM calculations and derive the ionization potential, electron affinity, and conceptual Density Functional Theory quantities like electronegativity, hardness, and condensed Fukui functions. We show that these descriptors, along with learned atomic representations, could be used to model chemical reactivity through an example of regioselectivity in electrophilic aromatic substitution reactions.

Highlights

Interatomic potentials derived with Machine Learning algorithms such as Deep-Neural Networks (DNNs), achieve the accuracy of high-fidelity quantum mechanical (QM) methods in areas traditionally dominated by empirical force fields and allow performing massive simulations
The ANI model (Fig. 1a) transforms coordinates R of the atoms in the molecule into atomic environment vectors (AEVs): a set of translation, rotation, and permutation invariant two-body radial g ðrÞ ij and three-body angular g ðaÞ ijk symmetry functions, where index i corresponds to a “central” atom and j and k refer to the atoms from its environment
We recently witnessed that machine learning models trained to quantum-mechanical data achieve formidable success in quantitative predictions of ground-state energies and interatomic potentials for common, typically charge-neutral organic molecules

Summary

Introduction

Interatomic potentials derived with Machine Learning algorithms such as Deep-Neural Networks (DNNs), achieve the accuracy of high-fidelity quantum mechanical (QM) methods in areas traditionally dominated by empirical force fields and allow performing massive simulations. The AIMNet-NSE model allows to fully bypass QM calculations and derive the ionization potential, electron affinity, and conceptual Density Functional Theory quantities like electronegativity, hardness, and condensed Fukui functions. We show that these descriptors, along with learned atomic representations, could be used to model chemical reactivity through an example of regioselectivity in electrophilic aromatic substitution reactions. Standard DFT methods for the treatment of the Nelectron system typically require ~O(N3) numerical cost This cubic scaling has become a critical challenge that limits the applicability of DFT to a few hundred atom systems. Deep-neural networks (DNN)[9,10] are a particular class of ML algorithms proven to be universal function approximators[11]

Methods

Results

Conclusion