NepoIP/MM: Towards Accurate Biomolecular Simulation with a Machine Learning/Molecular Mechanics Model Incorporating Polarization Effects

TL;DR

This paper introduces NepoIP, a polarizable machine learning/molecular mechanics model that accurately simulates biomolecules by incorporating polarization effects, achieving stability and transferability across different environments.

Contribution

The authors adapt NequIP into NepoIP, enabling polarization modeling in ML/MM frameworks, and demonstrate its stability, accuracy, and transferability in biomolecular simulations.

Findings

NepoIP/MM simulations are stable for solvated dipeptides.

NepoIP shows excellent agreement with QM/MM reference data.

A single NepoIP model transfers across different MM force fields and environments.

Abstract

Machine learning force fields offer the ability to simulate biomolecules with quantum mechanical accuracy while significantly reducing computational costs, attracting growing attention in biophysics. Meanwhile, leveraging the efficiency of molecular mechanics in modeling solvent molecules and long-range interactions, a hybrid machine learning/molecular mechanics (ML/MM) model offers a more realistic approach to describing complex biomolecular systems in solution. However, multiscale models with electrostatic embedding require accounting for the polarization of the ML region induced by the MM environment. To address this, we adapt the state-of-the-art NequIP architecture into a polarizable machine learning force field, NepoIP, enabling the modeling of polarization effects based on the external electrostatic potential. We found that the nanosecond MD simulations based on NepoIP/MM are stable for the periodic solvated dipeptide system and the converged sampling shows excellent agreement with the reference QM/MM level. Moreover, we show that a single NepoIP model can be transferable across different MM force fields, as well as extremely different MM environment of water and proteins, laying the foundation for developing a general machine learning biomolecular force field to be used in ML/MM with electrostatic embedding.