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

Xu, Ming; Zhu, Tong; Zhang, John ZH

doi:10.26434/chemrxiv.14370527.v1

Cited by 2 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To automatically train the NN potential and NN charge model, we employed the ESOINN-DP method developed in our previous work. (Xu et al, 2021) Its framework is shown in Figure 2.…”

Section: Theory and Methods The Nn Potentialmentioning

confidence: 99%

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

Zhu

2021

Front. Chem.

Self Cite

View full text Add to dashboard Cite

The development of accurate and efficient potential energy functions for the molecular dynamics simulation of metalloproteins has long been a great challenge for the theoretical chemistry community. An artificial neural network provides the possibility to develop potential energy functions with both the efficiency of the classical force fields and the accuracy of the quantum chemical methods. In this work, neural network potentials were automatically constructed by using the ESOINN-DP method for typical zinc proteins. For the four most common zinc coordination modes in proteins, the potential energy, atomic forces, and atomic charges predicted by neural network models show great agreement with quantum mechanics calculations and the neural network potential can maintain the coordination geometry correctly. In addition, MD simulation and energy optimization with the neural network potential can be readily used for structural refinement. The neural network potential is not limited by the function form and complex parameterization process, and important quantum effects such as polarization and charge transfer can be accurately considered. The algorithm proposed in this work can also be directly applied to proteins containing other metal ions.

show abstract

“…To automatically train the NN potential and NN charge model, we employed the ESOINN-DP method developed in our previous work. (Xu et al, 2021) Its framework is shown in Figure 2.…”

Section: Theory and Methods The Nn Potentialmentioning

confidence: 99%

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

Zhu

2021

Front. Chem.

Self Cite

View full text Add to dashboard Cite

show abstract

“…To identify an optimal set of nonredundant training datasets, recently, Behler and Paleico 13 have proposed a computationally efficient bin and hash method. Xu et al 14 have adopted a different approach of the enhanced self-organizing incremental neural network (ESOINN) to construct a training dataset with minimum redundancy. Zhang et al 15 used the generalized Euclidean distance between positions of atoms and atomic forces to eliminate redundant configurations.…”

Section: Introductionmentioning

confidence: 99%

Systematic Identification of Atom-Centered Symmetry Functions for the Development of Neural Network Potentials

et al. 2022

View full text Add to dashboard Cite

Neural network potentials are emerging as promising classical force fields that can enable long-time and large-length scale simulations at close to ab initio accuracies. They learn the underlying potential energy surface by mapping the Cartesian coordinates of atoms to system energies using elemental neural networks. To ensure invariance with respect to system translation, rotation, and atom index permutations, in the Behler−Parrinnello type of neural network potential (BP-NNP), the Cartesian coordinates of atoms are transformed into "structural fingerprints" using atom-centered symmetry functions (ACSFs). Development of an accurate BP-NNP for any chemical system critically relies on the choice of these ACSFs. In this work, we have proposed a systematic framework for the identification of an optimal set of ACSFs for any target system, which not only considers the diverse atomic environments present in the training dataset but also inter-ACSF correlations. Our method is applicable to different kinds of ACSFs and across diverse chemical systems. We demonstrate this by building accurate BP-NNPs for water and Cu 2 S systems.

show abstract

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

Cited by 2 publications

References 30 publications

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

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

Systematic Identification of Atom-Centered Symmetry Functions for the Development of Neural Network Potentials

Contact Info

Product

Resources

About