article Reactions & Reactivity Machine Learning Potentials Quantum Chemistry

AIMNet2-rxn: A Machine Learned Potential for Generalized Reaction Modeling on a Millions-of-Pathways Scale

Dylan M. Anstine, Qiyuan Zhao, Roman Zubatiuk, Shuhao Zhang, Veerupaksh Singla, Filipp Nikitin, Brett M. Savoie, Olexandr Isayev

2025 5 citations

View on Publisher

Highlight

AIMNet2-rxn is a machine-learned interatomic potential trained on 4.7 10^6 range-separated DFT calculations that accelerates reaction modeling by about six orders of magnitude while retaining approximately 1–2 kcal/mol accuracy along reaction coordinates. By leveraging three‑dimensional chemical information and a batched nudged elastic band (BNEB) method, the model searches millions of reaction pathways and enables high‑throughput mechanistic analysis for complex transformations such as glucose pyrolysis.

Abstract

Mechanistic modeling of chemical transformations offers a compelling basis for understanding reactivity and allows for prediction of reaction outcomes before attempting experiments. Despite progress in machine learned interatomic potentials (MLIPs), we demonstrate that available models lack the accuracy for diverse reaction modeling. With this motivation, we developed a general MLIP for mechanistic modeling of organics, AIMNet2-rxn, using a dataset of ~4.7 x 106 range-separated DFT calculations. AIMNet2-rxn enables reaction modeling ~106 faster than the reference quantum mechanical (QM) methods while significantly outperforming graph-based ML, reaffirming the value using 3D chemical information for training. On a test suite of well-known reaction mechanisms—such as amide formation, proton transfers, and pericyclics—AIMNet2-rxn yields 1-2 kcal mol-1 accuracy across reaction coordinates without retraining or system-specific fine-tuning. To exploit GPU parallelism and AIMNet2-rxn efficiency, we introduce a batched nudged elastic band (BNEB) method that readily achieves minimum energy pathway search on a millions-of-reactions scale. To demonstrate complex reaction characterization, the thermodynamics of an 11-step pathway producing hydroxymethylfurfural, the experimentally observed major product of glucose pyrolysis, is evaluated. Overall, the accuracy and efficiency afforded by AIMNet2-rxn creates opportunities in high-throughput reaction discovery and deep reaction network analysis that would be infeasible with QM methods.

Keywords

reaction mechanism high-throughput

Cite This Paper

@article{Anstine2025,
  author = {Anstine, Dylan M. and Zhao, Qiyuan and Zubatiuk, Roman and Zhang, Shuhao and Singla, Veerupaksh and Nikitin, Filipp and Savoie, Brett M. and Isayev, Olexandr},
  title = {AIMNet2-rxn: A Machine Learned Potential for Generalized Reaction Modeling on a Millions-of-Pathways Scale},
  year = {2025},
  doi = {10.26434/chemrxiv-2025-hpdmg},
  url = {http://dx.doi.org/10.26434/chemrxiv-2025-hpdmg},
  publisher = {American Chemical Society (ACS)},
  keywords = {reaction mechanism, high-throughput},
  researchAreas = {reactions-reactivity, ml-potentials, quantum-chemistry},
  highlight = {AIMNet2-rxn is a machine-learned interatomic potential trained on 4.7 10^6 range-separated DFT calculations that accelerates reaction modeling by about six orders of magnitude while retaining approximately 1–2 kcal/mol accuracy along reaction coordinates. By leveraging three‑dimensional chemical information and a batched nudged elastic band (BNEB) method, the model searches millions of reaction pathways and enables high‑throughput mechanistic analysis for complex transformations such as glucose pyrolysis.},
  citations = {5}
}

Related Research Areas

Reactions & Reactivity Machine Learning Potentials Quantum Chemistry

Related Publications

2021

cited94

Teaching a neural network to attach and detach electrons from molecules

Zubatyuk R., Smith J. S., Nebgen B. T., Tretiak S., Isayev O.

Nature Communications, 12 (2021)

Ml Potentials

Reactions Reactivity

Drug Discovery

Quantum Chemistry

Abstract Interatomic potentials derived with Machine Learning algorithms such as Deep-Neural Networks (DNNs), achieve the accuracy of high-fidelity quantum mechanical (QM) methods in areas traditionally dominated by empirical force fields and allow performing massive simulations.

DOI

2025

cited1

AIMNet2‐NSE: A Transferable Reactive Neural Network Potential for Open‐Shell Chemistry

Kalita B., Zubatyuk R., Anstine D. M., Bergeler M., Settels V., Stork C., Spicher S., Isayev O.

Angewandte Chemie International Edition (2025)

Ml Potentials

Quantum Chemistry

Reactions Reactivity

Abstract Open‐shell systems such as radical intermediates are central to radical polymerization (RP), combustion, catalysis, and many other chemical and industrial processes, yet their accurate modeling presents significant computational challenges.

DOI

2025