E (3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials

S Batzner, A Musaelian, L Sun, M Geiger… - Nature …, 2022 - nature.com
Abstract This work presents Neural Equivariant Interatomic Potentials (NequIP), an E (3)-
equivariant neural network approach for learning interatomic potentials from ab-initio …

Incorporating long-range physics in atomic-scale machine learning

A Grisafi, M Ceriotti - The Journal of chemical physics, 2019 - pubs.aip.org
The most successful and popular machine learning models of atomic-scale properties derive
their transferability from a locality ansatz. The properties of a large molecule or a bulk …

Raman spectrum and polarizability of liquid water from deep neural networks

GM Sommers, MFC Andrade, L Zhang… - Physical Chemistry …, 2020 - pubs.rsc.org
We introduce a scheme based on machine learning and deep neural networks to model the
environmental dependence of the electronic polarizability in insulating materials. Application …

Machine learning Hubbard parameters with equivariant neural networks

M Uhrin, A Zadoks, L Binci, N Marzari… - npj Computational …, 2025 - nature.com
Density-functional theory with extended Hubbard functionals (DFT+ U+ V) provides a robust
framework to accurately describe complex materials containing transition-metal or rare-earth …

Regression clustering for improved accuracy and training costs with molecular-orbital-based machine learning

L Cheng, NB Kovachki, M Welborn… - Journal of Chemical …, 2019 - ACS Publications
Machine learning (ML) in the representation of molecular-orbital-based (MOB) features has
been shown to be an accurate and transferable approach to the prediction of post-Hartree …

An overview of recent advances and challenges in predicting compound-protein interaction (CPI)

Y Li, Z Fan, J Rao, Z Chen, Q Chu, M Zheng, X Li - Medical Review, 2023 - degruyter.com
Compound-protein interactions (CPIs) are critical in drug discovery for identifying
therapeutic targets, drug side effects, and repurposing existing drugs. Machine learning (ML) …

General atomic neighborhood fingerprint for machine learning-based methods

R Batra, HD Tran, C Kim, J Chapman… - The Journal of …, 2019 - ACS Publications
To facilitate chemical space exploration for material screening or to accelerate
computationally expensive first-principles simulations, inexpensive surrogate models that …

Tensor improve equivariant graph neural network for molecular dynamics prediction

C Jiang, Y Zhang, Y Liu, J Peng - Computational Biology and Chemistry, 2024 - Elsevier
Molecular dynamics (MD) simulations are essential for molecular structure optimization,
drug-drug interactions, and other fields of drug discovery by simulating the motion of …

Neural Network Potential with Multi-Resolution Approach Enables Accurate Prediction of Reaction Free Energies in Solution

F Pultar, M Thuerlemann, I Gordiy, E Doloszeski… - arxiv preprint arxiv …, 2024 - arxiv.org
We present design and implementation of a novel neural network potential (NNP) and its
combination with an electrostatic embedding scheme, commonly used within the context of …

Predicting Energetic material properties and investigating the effect of pore morphology on shock sensitivity via machine learning

AD Casey - 2020 - search.proquest.com
An improved understanding of energy localization (“hot spots”) is needed to improve the
safety and performance of explosives. In this work I establish a variety of experimental and …