Accurate global machine learning force fields for molecules with hundreds of atoms

S Chmiela, V Vassilev-Galindo, OT Unke… - Science …, 2023 - science.org
Global machine learning force fields, with the capacity to capture collective interactions in
molecular systems, now scale up to a few dozen atoms due to considerable growth of model …

Exploring the mechanism of catalysis with the unified reaction valley approach (URVA)—A review

E Kraka, W Zou, Y Tao, M Freindorf - Catalysts, 2020 - mdpi.com
The unified reaction valley approach (URVA) differs from mainstream mechanistic studies,
as it describes a chemical reaction via the reaction path and the surrounding reaction valley …

Reaction mechanism–explored with the unified reaction valley approach

E Kraka, JJ Antonio, M Freindorf - Chemical Communications, 2023 - pubs.rsc.org
One of the ultimate goals of chemistry is to understand and manipulate chemical reactions,
which implies the ability to monitor the reaction and its underlying mechanism at an atomic …

Molecular force fields with gradient-domain machine learning (GDML): Comparison and synergies with classical force fields

HE Sauceda, M Gastegger, S Chmiela… - The Journal of …, 2020 - pubs.aip.org
Modern machine learning force fields (ML-FF) are able to yield energy and force predictions
at the accuracy of high-level ab initio methods, but at a much lower computational cost. On …

Dynamical strengthening of covalent and non-covalent molecular interactions by nuclear quantum effects at finite temperature

HE Sauceda, V Vassilev-Galindo, S Chmiela… - Nature …, 2021 - nature.com
Nuclear quantum effects (NQE) tend to generate delocalized molecular dynamics due to the
inclusion of the zero point energy and its coupling with the anharmonicities in interatomic …

Dual-level training of Gaussian processes with physically inspired priors for geometry optimizations

C Teng, Y Wang, D Huang, K Martin… - Journal of Chemical …, 2022 - ACS Publications
Gaussian process (GP) regression has been recently developed as an effective method in
molecular geometry optimization. The prior mean function is one of the crucial parts of the …

Electrostatic embedding machine learning for ground and excited state molecular dynamics of solvated molecules

P Mazzeo, E Cignoni, A Arcidiacono, L Cupellini… - Digital …, 2024 - pubs.rsc.org
The application of quantum mechanics (QM)/molecular mechanics (MM) models for studying
dynamics in complex systems is nowadays well established. However, their significant …

Learning to decouple complex systems

Z Zhou, T Yu - International Conference on Machine …, 2023 - proceedings.mlr.press
A complex system with cluttered observations may be a coupled mixture of multiple simple
sub-systems corresponding to latent entities. Such sub-systems may hold distinct dynamics …

Electronic and Nuclear Quantum Effects on Proton Transfer Reactions of Guanine–Thymine (GT) Mispairs Using Combined Quantum Mechanical/Molecular …

Y Tao, TJ Giese, DM York - Molecules, 2024 - mdpi.com
Rare tautomeric forms of nucleobases can lead to Watson–Crick-like (WC-like) mispairs in
DNA, but the process of proton transfer is fast and difficult to detect experimentally. NMR …

Error bounds of the invariant statistics in machine learning of ergodic Itô diffusions

H Zhang, J Harlim, X Li - Physica D: Nonlinear Phenomena, 2021 - Elsevier
This paper studies the theoretical underpinnings of machine learning of ergodic Itô
diffusions. The objective is to understand the convergence properties of the invariant …