Automated Construction of Neural Network Potential Energy Surface: The Enhanced Self-Organizing Incremental Neural Network Deep Potential Method

Abstract

In recent years, the use of deep learning (neural network) potential energy surface (NNPES) in molecular dynamics simulation has experienced explosive growth as it can be as accurate as quantum chemistry methods while being as efficient as classical mechanic methods. However, the development of NNPES is highly non-trivial. In particular, it has been troubling to construct a dataset that is as small as possible yet can cover the target chemical space. In this work, an ESOINN-DP method is developed, which has the enhanced self-organizing incremental neural-network (ESOINN) and a newly proposed error indicator at its core. With ESOINN-DP, One can construct the NNPES with little human intervention, and this method ensures that the constructed reference dataset covers the target chemical space with minimum redundancy. The performance of the ESOINN-DP method has been well validated by developing neural network potential energy surfaces for water clusters and by de-redundancy of a sub-data set of the ANI-1 database. We believe that the ESOINN-DP method provides a novelty idea for the construction of NNPES and especially, the reference datasets, and it can be used for MD simulations of various gas-phase and condensed-phase chemical systems.

Automatically Constructed Neural Network Potentials for Molecular Dynamics Simulation of Zinc Proteins

“…The RSESs are used as input by ESOINN to automatically construct the reference dataset, and ESOINN can ensure that the dataset has minimal redundancy while covering the target chemical space (Furao et al, 2007;Mingyuan et al, 2021). In addition, the final dataset will be divided into several subsets according to the similarity between the MBG structure after passing through the ESOINN layer.…”

“…This model describes the interactions between Zn 2+ and water accurately and can reproduce the hydration structure of Zn 2+ well in MD simulations. Recently, we proposed an ESOINN-DP (enhanced self-organizing incremental high dimensional neural network-deep potential) method that can construct a reference dataset and NN potentials for molecular systems automatically (Mingyuan et al, 2021). In this study, on the basis of these two works, we developed NN potentials specifically for zinc-containing proteins, and systematically benchmarked them, demonstrating their accuracy and efficiency.…”