Does a Machine-Learned Potential Perform Better Than an Optimally Tuned Traditional Force Field? A Case Study on Fluorohydrins

We present a comparative study that evaluates the performance of a machine learning potential (ANI-2x), a conventional force field (GAFF), and an optimally tuned GAFF-like force field in the modeling of a set of 10 gamma-fluorohydrins that exhibit a complex interplay between intra-and intermolecular interactions in determining conformer stabi l i t y . To benchmark the performance of each molecular model, we evaluated their energetic, geometric, and sampling accuracies relative to quantum-mechanical data. This benchmark involved conforma-tional analysis both in the gas phase and chloroform solution. We also assessed the performance of the aforementioned molecular models in estimating nuclear spin-spin coupling constants by comparing their predictions to experimental data available in chloroform. The results and discussion presented in this study demonstrate that ANI-2x tends to predict stronger-than-expected hydrogen bonding and overstabilize global minima and shows problems related to inadequate description of dispersion interactions. Furthermore, while ANI-2x is a viable model for modeling in the gas phase, conventional force fields sti l l play an important role, especially for condensed-phase simulations. Overall, this study highlights the strengths and weaknesses of each model , providing guidelines for the use and future development of force fields and machine learning potentials.

Automated summary

We present a comparative study on the performance of different molecular models in simulating the stability and properties of 10 gamma-fluorohydrins. The results show that the ANI-2x model tends to predict stronger hydrogen bonding and overstabilize global minima, while conventional force fields still play an important role in condensed-phase simulations. This study provides guidelines for the future development and application of force fields and machine learning potentials.