Machine learning force fields

OT Unke, S Chmiela, HE Sauceda… - Chemical …, 2021 - ACS Publications
In recent years, the use of machine learning (ML) in computational chemistry has enabled
numerous advances previously out of reach due to the computational complexity of …

Combining machine learning and computational chemistry for predictive insights into chemical systems

JA Keith, V Vassilev-Galindo, B Cheng… - Chemical …, 2021 - ACS Publications
Machine learning models are poised to make a transformative impact on chemical sciences
by dramatically accelerating computational algorithms and amplifying insights available from …

Equivariant message passing for the prediction of tensorial properties and molecular spectra

K Schütt, O Unke, M Gastegger - … Conference on Machine …, 2021 - proceedings.mlr.press
Message passing neural networks have become a method of choice for learning on graphs,
in particular the prediction of chemical properties and the acceleration of molecular …

A molecular descriptor of intramolecular noncovalent interaction for regulating optoelectronic properties of organic semiconductors

M Liu, X Han, H Chen, Q Peng, H Huang - Nature Communications, 2023 - nature.com
In recent years, intramolecular noncovalent interaction has become an important means to
modulate the optoelectronic performances of organic/polymeric semiconductors. However, it …

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 …

Shining light on porous liquids: from fundamentals to syntheses, applications and future challenges

D Wang, Y ** kinetics explored with machine learning potentials and path integral molecular dynamics
M Bocus, R Goeminne, A Lamaire… - Nature …, 2023 - nature.com
Proton hop** is a key reactive process within zeolite catalysis. However, the accurate
determination of its kinetics poses major challenges both for theoreticians and …

Biomolecular dynamics with machine-learned quantum-mechanical force fields trained on diverse chemical fragments

OT Unke, M Stöhr, S Ganscha, T Unterthiner… - Science …, 2024 - science.org
Molecular dynamics (MD) simulations allow insights into complex processes, but accurate
MD simulations require costly quantum-mechanical calculations. For larger systems, efficient …

Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting

S Thaler, J Zavadlav - Nature communications, 2021 - nature.com
In molecular dynamics (MD), neural network (NN) potentials trained bottom-up on quantum
mechanical data have seen tremendous success recently. Top-down approaches that learn …