Machine-Learned Molecular Surface and Its Application to Implicit Solvent Simulation

TL;DR

This paper introduces a machine learning approach to accurately compute the solvent-excluded surface (SES) for biomolecular simulations, enabling efficient and derivative-friendly surface calculations suitable for parallel computing.

Contribution

The authors develop a novel machine learning-based level-set method for SES computation, achieving high agreement with classical algorithms and facilitating improved molecular simulations.

Findings

Over 95% agreement with classical SES

High consistency in reaction field energy calculations

Potential for efficient parallel implementation

Abstract

Implicit solvent models, such as Poisson-Boltzmann models, play important roles in computational studies of biomolecules. A vital step in almost all implicit solvent models is to determine the solvent-solute interface, and the solvent excluded surface (SES) is the most widely used interface definition in these models. However, classical algorithms used for computing SES are geometry-based, thus neither suitable for parallel implementations nor convenient for obtaining surface derivatives. To address the limitations, we explored a machine learning strategy to obtain a level-set formulation for the SES. The training process was conducted in three steps, eventually leading to a model with over 95% agreement with the classical SES. Visualization of tested molecular surfaces shows that the machine-learned SES overlaps with the classical SES on almost all situations. We also implemented the machine-learned SES into the Amber/PBSA program to study its performance on reaction field energy calculation. The analysis shows that the two sets of reaction field energies are highly consistent with 1% deviation on average. Given its level-set formulation, we expect the machine-learned SES to be applied in molecular simulations that require either surface derivatives or high efficiency on parallel computing platforms.