Bridging Quantum Mechanics to Organic Liquid Properties via a Universal Force Field

TL;DR

This paper introduces ByteFF-Pol, a graph neural network-based force field trained on quantum mechanics data, which accurately predicts liquid properties and bridges microscopic quantum calculations with macroscopic behaviors, advancing materials discovery.

Contribution

The development of ByteFF-Pol, a GNN-parameterized force field trained solely on high-level QM data, offering superior accuracy and zero-shot prediction for liquid properties.

Findings

Outperforms state-of-the-art classical and ML force fields.

Accurately predicts thermodynamic and transport properties.

Enables exploration of new chemical spaces without additional training.

Abstract

Molecular dynamics (MD) simulations are essential tools for unraveling atomistic insights into the structure and dynamics of condensed-phase systems. However, the universal and accurate prediction of macroscopic properties from ab initio calculations remains a significant challenge, often hindered by the trade-off between computational cost and simulation accuracy. Here, we present ByteFF-Pol, a graph neural network (GNN)-parameterized polarizable force field, trained exclusively on high-level quantum mechanics (QM) data. Leveraging physically-motivated force field forms and training strategies, ByteFF-Pol exhibits exceptional performance in predicting thermodynamic and transport properties for a wide range of small-molecule liquids and electrolytes, outperforming state-of-the-art (SOTA) classical and machine learning force fields. The zero-shot prediction capability of ByteFF-Pol bridges the gap between microscopic QM calculations and macroscopic liquid properties, enabling the exploration of previously intractable chemical spaces. This advancement holds transformative potential for applications such as electrolyte design and custom-tailored solvent, representing a pivotal step toward data-driven materials discovery.