Transferable atomic multipole machine learning models for small organic molecules

TL;DR

This paper presents a machine learning approach to accurately predict atomic multipole moments in small organic molecules, enabling efficient computation of intermolecular interactions across various molecular conformations and charge states.

Contribution

The authors develop transferable ML models for atomic multipoles that work across different molecules and charge states, trained on extensive quantum chemical data.

Findings

High accuracy in predicting intermolecular interaction energies.

Effective modeling across neutral, cationic, and anionic molecules.

Successful application to benzene crystal cohesive energy.

Abstract

Accurate representation of the molecular electrostatic potential, which is often expanded in distributed multipole moments, is crucial for an efficient evaluation of intermolecular interactions. Here we introduce a machine learning model for multipole coefficients of atom types H, C, O, N, S, F, and Cl in any molecular conformation. The model is trained on quantum chemical results for atoms in varying chemical environments drawn from thousands of organic molecules. Multipoles in systems with neutral, cationic, and anionic molecular charge states are treated with individual models. The models' predictive accuracy and applicability are illustrated by evaluating intermolecular interaction energies of nearly 1,000 dimers and the cohesive energy of the benzene crystal.