Anticipating the Selectivity of Intramolecular Cyclization Reaction Pathways with Neural Network Potentials

Reactive potentials serve as essential tools for investigating chemical reactions with moderate computational costs. However, traditional reactive potentials often depend on fixed, semiempirical parameters, which limits their accuracy and transferability. Overcoming these limitations can significantly expand the applicability of reactive potentials, enabling the simulation of a broader range of reactions under diverse conditions and the prediction of reaction properties, such as barrier heights. This work introduces ANI-1xBB, a novel ANI-based reactive ML potential trained on off-equilibrium molecular conformers generated through an automated bond-breaking workflow. ANI-1xBB significantly enhances the prediction of reaction energetics, barrier heights, and bond dissociation energies, surpassing those of conventional ANI models. Our results show that ANI-1xBB improves transition state modeling and reaction pathway prediction while generalizing effectively to pericyclic reactions and radical-driven processes. Furthermore, the automated data generation strategy supports the efficient construction of large-scale, high-quality reactive data sets, reducing reliance on expensive QM calculations. This work highlights ANI-1xBB as a practical model for accelerating the development of reactive machine learning potentials, offering new opportunities for modeling reaction phenomena.

As quantum mechanics marks its centennial in 2025, machine learning interatomic potentials have emerged as transformative tools in molecular modeling, bridging quantum mechanical accuracy with classical efficiency. Here we examine their development through four defining challenges-achieving chemical accuracy, maintaining computational efficiency, ensuring interpretability and reaching universal generalizability. We highlight architectural innovations, physics-informed approaches, and foundation models trained on extensive data. Together, these developments chart a path toward predictive, transferable and physically grounded machine learning frameworks for next-generation computational chemistry.

Machine learning interatomic potentials (MLIPs) have emerged as powerful tools for investigating atomistic systems with high accuracy and a relatively low computational cost. However, a common and unaddressed challenge with many current neural network (NN) MLIP models is their limited ability to accurately predict the relative energies of systems containing isolated or nearly isolated atoms, which appear in various reactive processes. To address this limitation, we present a mathematical technique for modifying any existing atom-centered NN architecture to account for the energies of isolated atoms. The result produces a consistent prediction of the atomization energy (AE) of a system using minimal constraints on the model. Using this technique, we build a model architecture that we call hierarchically interacting particle neural network (HIP-NN)-AE, an AE-constrained version of the HIP-NN, as well as ANI-AE, the AE-constrained version of the accurate NN engine for molecular energies (ANI). Our results demonstrate AE consistency of AE-constrained models, which drastically improves the AE predictions for the models. We compare the AE-constrained approach to unconstrained models as well as models from the literature in other scenarios, such as bond dissociation energies, bond dissociation pathways, and extensibility tests. These results show that the constraints improve the model performance in some of these tasks and do not negatively affect the performance on any tasks. The AE constraint approach thus offers a robust solution to the challenges posed by isolated atoms in energy prediction tasks.

Ring strain energy (RSE) is crucial for understanding molecular reactivity, with broad implications in polymerization, click chemistry, drug discovery and beyond. However, quantitatively determining RSE through experiments or quantum mechanics (QM) is resource-intensive, limiting its application on a large scale. We present a machine learning (ML)-based workflow that enables the reliable and efficient prediction of RSE, entirely bypassing traditional QM calculations. Our workflow employs AIMNet2 machine learning interatomic potentials and Auto3D for the identification of low-energy conformers and RSE computation. Remarkably, it achieves an R 2 of 0.997 and a mean absolute error (MAE) of 0.896 kcal/mol when benchmarked against the ωB97M-D4/Def2-TZVPP method, while running orders of magnitude faster than DFT calculations. To demonstrate the utility of our workflow, we successfully differentiated reactive from nonreactive molecules in copper-free click chemistry, [3 + 2] cycloaddition reaction and ring-opening metathesis polymerization, underscoring its transferability to diverse molecular systems. Additionally, we compiled the RSE Atlas, a computational database encompassing 16,905 single-ring molecules, offering a valuable resource for investigating factors influencing RSE. Our approach transforms RSE into a readily computable property, facilitating its integration into reaction designs.