article Machine Learning Potentials Experiment Automation

Exploring the frontiers of condensed-phase chemistry with a general reactive machine learning potential

Shuhao Zhang, Małgorzata Z. Makoś, Ryan B. Jadrich, Elfi Kraka, Kipton Barros, Benjamin T. Nebgen, Sergei Tretiak, Olexandr Isayev, Nicholas Lubbers, Richard A. Messerly, +1 more

Nature Chemistry Vol. 16(5) pp. 727–734 2024 85 citations

Highlight

Abstract Atomistic simulation has a broad range of applications from drug design to materials discovery.

Abstract

Abstract Atomistic simulation has a broad range of applications from drug design to materials discovery. Machine learning interatomic potentials (MLIPs) have become an efficient alternative to computationally expensive ab initio simulations. For this reason, chemistry and materials science would greatly benefit from a general reactive MLIP, that is, an MLIP that is applicable to a broad range of reactive chemistry without the need for refitting. Here we develop a general reactive MLIP (ANI-1xnr) through automated sampling of condensed-phase reactions. ANI-1xnr is then applied to study five distinct systems: carbon solid-phase nucleation, graphene ring formation from acetylene, biofuel additives, combustion of methane and the spontaneous formation of glycine from early earth small molecules. In all studies, ANI-1xnr closely matches experiment (when available) and/or previous studies using traditional model chemistry methods. As such, ANI-1xnr proves to be a highly general reactive MLIP for C, H, N and O elements in the condensed phase, enabling high-throughput in silico reactive chemistry experimentation.

Keywords

Cite This Paper

@article{Zhang2024,
  author = {Zhang, Shuhao and Makoś, Małgorzata Z. and Jadrich, Ryan B. and Kraka, Elfi and Barros, Kipton and Nebgen, Benjamin T. and Tretiak, Sergei and Isayev, Olexandr and Lubbers, Nicholas and Messerly, Richard A. and Smith, Justin S.},
  title = {Exploring the frontiers of condensed-phase chemistry with a general reactive machine learning potential},
  year = {2024},
  journal = {Nature Chemistry},
  volume = {16},
  number = {5},
  pages = {727--734},
  doi = {10.1038/s41557-023-01427-3},
  url = {http://dx.doi.org/10.1038/s41557-023-01427-3},
  publisher = {Springer Science and Business Media LLC},
  keywords = {machine learning, ab initio, high-throughput},
  researchAreas = {ml-potentials, experiment-automation},
  highlight = {Abstract Atomistic simulation has a broad range of applications from drug design to materials discovery.},
  citations = {85}
}

Related Research Areas

Related Publications

2025
cited 3

Transferable Machine Learning Interatomic Potential for Pd-Catalyzed Cross-Coupling Reactions

Anstine D., Zubatyuk R., Gallegos L., Paton R., Wiest O., Nebgen B., Jones T., Gomes G., Tretiak S., Isayev O.

Machine Learning Potentials Reactions & Reactivity Experiment Automation Materials Informatics

Finding efficient substrate-catalyst combinations for palladium-catalyzed cross-coupling reactions remains a critical challenge in synthetic chemistry, with broad implications for pharmaceutical and materials manufacturing.

DOI
2020
cited 212

The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for molecules

Smith J. S., Zubatyuk R., Nebgen B., Lubbers N., Barros K., Roitberg A. E., Isayev O., Tretiak S.

Scientific Data 7

Machine Learning Potentials Quantum Chemistry Experiment Automation

Abstract Maximum diversification of data is a central theme in building generalized and accurate machine learning (ML) models.

DOI
2025

Discovery of Novel Celecoxib Polymorphs Using AIMNet2 Machine Learning Interatomic Potential

Zheng P., Abramov Y., Sun C. C., Isayev O.

Machine Learning Potentials Experiment Automation Drug Discovery Materials Informatics

Polymorphism plays a pivotal role in defining the solid-state properties of pharmaceutical compounds, yet the discovery and accurate energy ranking of polymorphs remain a challenge.

DOI
2017
cited 269

ANI-1, A data set of 20 million calculated off-equilibrium conformations for organic molecules

Smith J. S., Isayev O., Roitberg A. E.

Scientific Data 4

Machine Learning Potentials Quantum Chemistry

AbstractOne of the grand challenges in modern theoretical chemistry is designing and implementing approximations that expedite ab initio methods without loss of accuracy.

DOI
2023
cited 143

Machine Learning Interatomic Potentials and Long-Range Physics

Anstine D. M., Isayev O.

J. Phys. Chem. A 127 , 2417–2431

Machine Learning Potentials

Machine Learning Interatomic Potentials and Long-Range Physics.

DOI