Incorporating Neural Networks into the AMOEBA Polarizable Force Field

14 December 2023, Version 3
This content is a preprint and has not undergone peer review at the time of posting.


Neural network potentials (NNPs) offer significant promise to bridge the gap be- tween the accuracy of quantum mechanics and the efficiency of molecular mechanics in molecular simulation. Most NNPs rely on the locality assumption that ensures the model’s transferability and scalability and thus lack the treatment of long-range inter- actions, which are essential for molecular systems in condensed phase. Here we present an integrated hybrid model, AMOEBA+NN, which combines the AMOEBA potential for the short- and long-range non-covalent atomic interactions and an NNP to capture the remaining local covalent contributions. The AMOEBA+NN model was trained on the conformational energy of ANI-1x dataset and tested on several external datasets ranging from small molecules to tetrapeptides.The hybrid model demonstrated sub- stantial improvements over the baseline models in term of accuracy as the molecule size increased, suggesting its potential as a next-generation approach for chemically accurate molecular simulations.


Neural Network Potentials
Polarizable Force Fields
Machine Learning
Deep Learning


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.