Condensed-phase molecular representation to link structure and thermodynamics in molecular dynamics

TL;DR

This paper introduces a molecular representation based on SLATM for predicting thermodynamic properties from molecular-liquid simulations, enabling interpretable insights into structure-property relationships.

Contribution

It adapts the SLATM atomic representation for liquids to learn thermodynamic properties using linear models, demonstrating broad applicability and interpretability.

Findings

Successfully predicts thermodynamic properties from molecular-liquid data.

Reveals key structural interactions influencing selectivity.

Provides a two-dimensional projection separating different basins.

Abstract

Molecular design requires systematic and broadly applicable methods to extract structure-property relationships. The focus of this study is on learning thermodynamic properties from molecular-liquid simulations. The methodology relies on an atomic representation originally developed for electronic properties: the Spectrum of London and Axilrod-Teller-Muto representation (SLATM). SLATM's expansion in one-, two-, and three-body interactions makes it amenable to probing structural ordering in molecular liquids. We show that such representation encodes enough critical information to permit the learning of thermodynamic properties via linear methods. We demonstrate our approach on the preferential insertion of small solute molecules toward cardiolipin membranes and monitor selectivity against a similar lipid. Our analysis reveals simple, interpretable relationships between two- and three-body interactions and selectivity, identifies key interactions to build optimal prototypical solutes, and charts a two-dimensional projection that displays clearly separated basins. The methodology is generally applicable to a variety of thermodynamic properties.