article Machine Learning Potentials Reactions & Reactivity Experiment Automation Materials Informatics

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

Dylan Anstine, Roman Zubatyuk, Liliana Gallegos, Robert Paton, Olaf Wiest, Benjamin Nebgen, Travis Jones, Gabe Gomes, Sergei Tretiak, Olexandr Isayev

2025 3 citations

Highlight

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.

Abstract

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. We report AIMNet2-Pd, a machine learned interatomic potential that enables rapid, accurate computational studies of palladium-catalyzed cross-coupling reactions. AIMNet2-Pd replaces computationally expensive electronic structure calculations with a neural network-based model that performs geometry optimization, transition state searches, and energy calculations in seconds while maintaining accuracy within 1-2 kcal mol⁻¹ and ~0.1 Å compared to the reference QM calculations. AIMNet2-Pd makes computational high-throughput catalyst screening and mechanistic studies of realistic systems feasible by providing on-demand thermodynamic and kinetic predictions for each step of a catalytic cycle. Importantly, the applicability of the systems extends beyond the monophosphine ligands in Pd(0)/Pd(II) cycles for which it has been trained on to chemically diverse Pd complexes. This demonstrates AIMNet2-Pd's utility to serve as a general-purpose and high-throughput tool for studying catalytic reactions.

Keywords

Cite This Paper

@article{Anstine2025a,
  author = {Anstine, Dylan and Zubatyuk, Roman and Gallegos, Liliana and Paton, Robert and Wiest, Olaf and Nebgen, Benjamin and Jones, Travis and Gomes, Gabe and Tretiak, Sergei and Isayev, Olexandr},
  title = {Transferable Machine Learning Interatomic Potential for Pd-Catalyzed Cross-Coupling Reactions},
  year = {2025},
  doi = {10.26434/chemrxiv-2025-n36r6},
  url = {http://dx.doi.org/10.26434/chemrxiv-2025-n36r6},
  publisher = {American Chemical Society (ACS)},
  keywords = {neural network, machine learning, transition state, high-throughput},
  researchAreas = {ml-potentials, reactions-reactivity, experiment-automation, materials-informatics},
  highlight = {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.},
  citations = {3}
}

Related Research Areas

Related Publications

2024
cited2

Accurate Ring Strain Energy Predictions with Machine Learning and Application in Strain-Promoted Reactions

Liu Z., Vinskus J., Fu Y., Liu P., Noonan K., Isayev O.

(2024)

Ml Potentials
Experiment Automation
Reactions Reactivity

Ring strain energy (RSE) is crucial for understanding molecular reactivity.

DOI
2025

Discovery of Novel Celecoxib Polymorphs Using AIMNet2 Machine Learning Interatomic Potential

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

(2025)

Ml 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
2024
cited85

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

Zhang S., Makoś M. Z., Jadrich R. B., Kraka E., Barros K., Nebgen B. T., Tretiak S., Isayev O., Lubbers N., Messerly R. A., Smith J. S.

Nature Chemistry, 16, 727–734 (2024)

Ml Potentials
Experiment Automation

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

DOI
2023

The Challenge of Balancing Model Sensitivity and Robustness in Predicting Yields: A Benchmarking Study of Amide Coupling Reactions

Liu Z., Moroz Y. S., Isayev O.

(2023)

Reactions Reactivity
Experiment Automation

Accurate prediction of reaction yield is the holy grail for computer-assisted synthesis, but current models have failed to generalize to large literature datasets.

DOI
2023

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

Messerly R., Zhang S., Makoś M., Jadrich R., Kraka E., Barros K., Nebgen B., Tretiak S., Isayev O., Lubbers N., Smith J.

(2023)

Ml Potentials
Experiment Automation
Reactions Reactivity

Abstract Reactive chemistry atomistic simulation has a broad range of applications from drug design to energy to materials discovery.

DOI