Developing Machine-Learned Potentials for Coarse-Grained Molecular Simulations: Challenges and Pitfalls

TL;DR

This paper explores the use of graph neural networks, specifically SchNet, to develop coarse-grained force fields for molecular simulations, highlighting challenges and potential improvements.

Contribution

It applies SchNet to coarse-grained modeling of liquids, analyzing how architecture and hyperparameters affect simulation accuracy and discussing associated challenges.

Findings

SchNet can learn CG potentials for liquid benzene.

Model architecture impacts thermodynamic and structural accuracy.

Challenges include hyperparameter tuning and environment representation.

Abstract

Coarse graining (CG) enables the investigation of molecular properties for larger systems and at longer timescales than the ones attainable at the atomistic resolution. Machine learning techniques have been recently proposed to learn CG particle interactions, i.e. develop CG force fields. Graph representations of molecules and supervised training of a graph convolutional neural network architecture are used to learn the potential of mean force through a force matching scheme. In this work, the force acting on each CG particle is correlated to a learned representation of its local environment that goes under the name of SchNet, constructed via continuous filter convolutions. We explore the application of SchNet models to obtain a CG potential for liquid benzene, investigating the effect of model architecture and hyperparameters on the thermodynamic, dynamical, and structural properties of the simulated CG systems, reporting and discussing challenges encountered and future directions envisioned.