Utilizing Machine Learning to Greatly Expand the Range and Accuracy of Bottom-Up Coarse-Grained Models Through Virtual Particles

TL;DR

This paper introduces a machine learning-enhanced method for improving coarse-grained models of biomolecules by incorporating virtual particles, significantly increasing their accuracy and ability to capture complex behaviors.

Contribution

The paper presents VD-REM, a novel approach that integrates virtual particles into CG models using machine learning and relative entropy minimization, enhancing model fidelity.

Findings

Virtual particles improve solvent behavior modeling.

VD-REM captures higher-order correlations.

Enhanced accuracy over standard CG models.

Abstract

Coarse-grained (CG) models parameterized using atomistic reference data, i.e., 'bottom up' CG models, have proven useful in the study of biomolecules and other soft matter. However, the construction of highly accurate, low resolution CG models of biomolecules remains challenging. We demonstrate in this work how virtual particles, CG sites with no atomistic correspondence, can be incorporated into CG models within the context of relative entropy minimization (REM) as latent variables. The methodology presented, variational derivative relative entropy minimization (VD-REM), enables optimization of virtual particle interactions through a gradient descent algorithm aided by machine learning. We apply this methodology to the challenging case of a solvent-free CG model of a 1,2-dioleoyl-sn-glycero-3-phosphocholine (DOPC) lipid bilayer and demonstrate that introduction of virtual particles captures solvent-mediated behavior and higher-order correlations which REM alone cannot capture in a more standard CG model based only on the mapping of collections of atoms to the CG sites.