Implicit Solvent Approach Based on Generalised Born and Transferable Graph Neural Networks for Molecular Dynamics Simulations

TL;DR

This paper introduces a GNN-based implicit solvent model for molecular dynamics that accurately captures explicit solvent effects across diverse peptide conformations, improving efficiency without sacrificing accuracy.

Contribution

It presents a transferable GNN-based implicit solvent approach that generalizes to peptides outside the training set, addressing limitations of prior ML-based solvent models.

Findings

Accurately models explicit solvent effects in peptides.

Generalizes to unseen peptide compositions.

Enhances efficiency of molecular dynamics simulations.

Abstract

Molecular dynamics (MD) simulations enable the study of the motion of small and large (bio)molecules and the estimation of their conformational ensembles. The description of the environment (solvent) has thereby a large impact. Implicit solvent representations are efficient but in many cases not accurate enough (especially for polar solvents such as water). More accurate but also computationally more expensive is the explicit treatment of the solvent molecules. Recently, machine learning (ML) has been proposed to bridge the gap and simulate in an implicit manner explicit solvation effects. However, the current approaches rely on prior knowledge of the entire conformational space, limiting their application in practice. Here, we introduce a graph neural network (GNN) based implicit solvent that is capable of describing explicit solvent effects for peptides with different composition than contained in the training set.