Incorporating Neural Networks into the AMOEBA Polarizable Force Field - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Physical Chemistry B Année : 2024

Incorporating Neural Networks into the AMOEBA Polarizable Force Field

Résumé

Neural network potentials (NNPs) have great potential to bridge the gap between the accuracy of quantum mechanics and the efficiency of molecular mechanics in molecular simulation. However, most of the NNPs remain restricted by the locality assumption that ensures the model's transferability and scalability but misses out the long-range interactions. Here we present an integrated non-reactive hybrid model, AMOEBA+NN, which employs the AMOEBA potential for the short- and long-range non-bonded interactions and an NNP to capture the remaining local (covalent) contributions. A first 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. It was encouraging to see that the hybrid model becomes significantly advantageous over the baseline models in term of accuracy as the molecules get larger, offering perspectives for the development of a generalized and improved approach.
Fichier non déposé

Dates et versions

hal-04288412 , version 1 (16-11-2023)

Identifiants

Citer

X. Wang, T. Jaffrelot Inizan, C. Liu, Jean-Philip Piquemal, P. Ren. Incorporating Neural Networks into the AMOEBA Polarizable Force Field. Journal of Physical Chemistry B, 2024, ⟨10.1021/acs.jpcb.3c08166⟩. ⟨hal-04288412⟩
37 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More