Hybrid classical/machine-learning force fields for the accurate description of molecular condensed-phase systems

Thürlemann, Moritz; Riniker, Sereina

doi:10.1039/d3sc04317g

Cited by 2 publications

(1 citation statement)

References 125 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, the rapid development of neural network potentials (NNPs) has shown great promise to improve the accuracy of molecular simulations with reasonable computational efficiency. − Without the explicit functional forms, as seen in classical mechanics, NNPs are able to learn the potential energy surface from quantum mechanics (QM) reference data. The transferability and scalability of NNPs are usually ensured by the locality assumption, wherein the total energy of a system can be expressed as the sum of its atomic energies that depend on a local atomic descriptor representing the local environment of the atom within a certain cutoff radius (e.g 5–6 Å).…”

Section: Introductionmentioning

confidence: 99%

Incorporating Neural Networks into the AMOEBA Polarizable Force Field

Wang,

Inizan,

Liu

et al. 2024

J. Phys. Chem. B

View full text Add to dashboard Cite

Neural network potentials (NNPs) offer significant promise to bridge the gap between 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 interactions, which are essential for molecular systems in the condensed phase. Here we present an integrated hybrid model, AMOEBA+NN, which combines the AMOEBA potential for the short- and long-range noncovalent atomic interactions and an NNP to capture the remaining local covalent contributions. The AMOEBA+NN model was trained on the conformational energy of the ANI-1x data set and tested on several external data sets ranging from small molecules to tetrapeptides. The hybrid model demonstrated substantial 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.

show abstract