Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space

TLDR

Accurate and efficient prediction of molecular properties across chemical compound space is essential for rational compound design in the chemical and pharmaceutical industries. This study develops a systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules. The authors use a progression from simple atom‑level sums to bond energies, pairwise force fields, and advanced machine‑learning models based on a vectorized Bag‑of‑Bonds representation to compute molecular energies. While pairwise force fields match DFT benchmark accuracy for equilibrium geometries, incorporating many‑body interactions is necessary to reach 1 kcal/mol chemical accuracy, and the Bag‑of‑Bonds model also predicts electronic properties such as polarizability and frontier orbital energies accurately.

Abstract

Simultaneously accurate and efficient prediction of molecular properties throughout chemical compound space is a critical ingredient toward rational compound design in chemical and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules. These methods range from a simple sum over atoms, to addition of bond energies, to pairwise interatomic force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equilibrium molecular geometries, even simple pairwise force fields demonstrate prediction accuracy comparable to benchmark energies calculated using density functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the “holy grail” of chemical accuracy of 1 kcal/mol for both equilibrium and out-of-equilibrium geometries. This remarkable accuracy is achieved by a vectorized representation of molecules (so-called Bag of Bonds model) that exhibits strong nonlocality in chemical space. In addition, the same representation allows us to predict accurate electronic properties of molecules, such as their polarizability and molecular frontier orbital energies.