An Extendible, Graph-Neural-Network-Based Approach for Accurate Force Field Development of Large Flexible Organic Molecules

TL;DR

This paper introduces a novel extendible force field for large flexible organic molecules, combining physics-based and data-driven methods, achieving high accuracy and transferability from small fragments to large polymers.

Contribution

It presents a new approach integrating nonbonding potentials with a subgraph neural network model, enabling accurate, scalable force field development at correlated wavefunction level.

Findings

High accuracy and robustness demonstrated on polyethylene glycol chains

Force field developed from small fragments can be transferred to large polymers

Enables ab initio level force fields for large organic molecules

Abstract

An accurate force field is the key to the success of all molecular mechanics simulations on organic polymers and biomolecules. Accuracy beyond density functional theory is often needed to describe the intermolecular interactions, while most correlated wavefunction (CW) methods are prohibitively expensive for large molecules. Therefore, it posts a great challenge to develop an extendible ab initio force field for large flexible organic molecules at CW level of accuracy. In this work, we face this challenge by combining the physics-driven nonbonding potential with a data-driven subgraph neural network bonding model (named sGNN). Tests on polyethylene glycol polymer chains show that our strategy is highly accurate and robust for molecules of different sizes. Therefore, we can develop the force field from small molecular fragments (with sizes easily accessible to CW methods) and safely transfer it to large polymers, thus opening a new path to the next-generation organic force fields.