Machine learning force fields: Recent advances and remaining challenges
I Poltavsky, A Tkatchenko - The journal of physical chemistry …, 2021 - ACS Publications
In chemistry and physics, machine learning (ML) methods promise transformative impacts by
advancing modeling and improving our understanding of complex molecules and materials …
advancing modeling and improving our understanding of complex molecules and materials …
Materials by design at high pressures
M Xu, Y Li, Y Ma - Chemical Science, 2022 - pubs.rsc.org
Pressure, a fundamental thermodynamic variable, can generate two essential effects on
materials. First, pressure can create new high-pressure phases via modification of the …
materials. First, pressure can create new high-pressure phases via modification of the …
Linear atomic cluster expansion force fields for organic molecules: beyond rmse
We demonstrate that fast and accurate linear force fields can be built for molecules using the
atomic cluster expansion (ACE) framework. The ACE models parametrize the potential …
atomic cluster expansion (ACE) framework. The ACE models parametrize the potential …
The rise of neural networks for materials and chemical dynamics
Machine learning (ML) is quickly becoming a premier tool for modeling chemical processes
and materials. ML-based force fields, trained on large data sets of high-quality electron …
and materials. ML-based force fields, trained on large data sets of high-quality electron …
Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks
D Schwalbe-Koda, AR Tan… - Nature …, 2021 - nature.com
Neural network (NN) interatomic potentials provide fast prediction of potential energy
surfaces, closely matching the accuracy of the electronic structure methods used to produce …
surfaces, closely matching the accuracy of the electronic structure methods used to produce …
A general tensor prediction framework based on graph neural networks
Graph neural networks (GNNs) have been shown to be extremely flexible and accurate in
predicting the physical properties of molecules and crystals. However, traditional invariant …
predicting the physical properties of molecules and crystals. However, traditional invariant …
[HTML][HTML] The MD17 datasets from the perspective of datasets for gas-phase “small” molecule potentials
There has been great progress in developing methods for machine-learned potential energy
surfaces. There have also been important assessments of these methods by comparing so …
surfaces. There have also been important assessments of these methods by comparing so …
Accurate, affordable, and generalizable machine learning simulations of transition metal x-ray absorption spectra using the XANESNET deep neural network
CD Rankine, TJ Penfold - The Journal of Chemical Physics, 2022 - pubs.aip.org
The affordable, accurate, and generalizable prediction of spectroscopic observables plays a
key role in the analysis of increasingly complex experiments. In this article, we develop and …
key role in the analysis of increasingly complex experiments. In this article, we develop and …
PhyNEO: A Neural-Network-Enhanced Physics-Driven Force Field Development Workflow for Bulk Organic Molecule and Polymer Simulations
J Chen, K Yu - Journal of Chemical Theory and Computation, 2023 - ACS Publications
An accurate, generalizable, and transferable force field plays a crucial role in the molecular
dynamics simulations of organic polymers and biomolecules. Conventional empirical force …
dynamics simulations of organic polymers and biomolecules. Conventional empirical force …
Along the road to crystal structure prediction (CSP) of pharmaceutical-like molecules
MK Dudek, K Drużbicki - CrystEngComm, 2022 - pubs.rsc.org
Computational methods used for predicting the crystal structures of organic compounds are
mature enough to be routinely used with many rigid and semi-rigid organic molecules. The …
mature enough to be routinely used with many rigid and semi-rigid organic molecules. The …