Simulating enzyme catalysis with electrostatically embedded machine learning potentials

TL;DR

This paper introduces a new method to simulate enzyme reactions efficiently by combining machine learning with electrostatic embedding.

Contribution

The novel EMLE method enables accurate enzyme catalysis simulations using gas-phase-trained machine learning potentials.

Findings

EMLE correctly differentiates catalytic actions in enzyme-substrate conformations for Diels–Alderase AbyU.

EMLE accurately captures the catalytic effects of the chorismate to prephenate conversion.

EMLE outperforms mechanical embedding in predicting enzyme catalysis with high accuracy and efficiency.

Abstract

To simulate enzyme reactions, multiscale quantum mechanics/molecular mechanics (QM/MM) approaches are well established and popular. However, accurately and efficiently estimating enzyme activity is a challenge, because in general, precise methods are too computationally expensive. Here, we demonstrate that enzyme catalysis can be captured by coupling efficient, reactive machine-learned potentials (MLPs) trained on gas phase data to the wider enzyme environment using electrostatic machine learning embedding (EMLE). The EMLE scheme is first applied to the natural Diels–Alderase AbyU, showing that it correctly differentiates the catalytic action on different enzyme–substrate conformations. Then, we show that training a reaction-specific EMLE model allows us to accurately capture the enzyme catalytic effects of the conversion of chorismate to prephenate, a reaction with a highly polarizable and charged transition state. In both cases, in contrast to mechanical embedding approaches, the EMLE scheme allows accurate and efficient predictions of enzyme catalysis, agreeing with high-level QM/MM reference calculations. This approach facilitates the use of gas phase-trained MLPs in MLP/molecular mechanics (ML/MM) simulations and should thus be highly beneficial for computational activity screening of enzyme biocatalysts.

Enzyme catalysis can be simulated accurately and efficiently by coupling machine-learned potentials trained on gas-phase data to the environment (ML/MM) using electrostatic machine-learning embedding (EMLE).

Figures