Notice: Users may be experiencing issues with displaying some pages on stanfordhealthcare.org. We are working closely with our technical teams to resolve the issue as quickly as possible. Thank you for your patience.
 

Learn about the flu shot, COVID-19 vaccine, and our masking policy »

Stanford Health Care

Combining Force Fields and Neural Networks for an Accurate Representation of Bonded Interactions. The journal of physical chemistry. A Kamath, G., Illarionov, A., Sakipov, S., Pereyaslavets, L., Kurnikov, I. V., Butin, O., Voronina, E., Ivahnenko, I., Leontyev, I., Nawrocki, G., Darkhovskiy, M., Olevanov, M., Cherniavskyi, Y. K., Lock, C., Greenslade, S., Chen, Y., Kornberg, R. D., Levitt, M., Fain, B. 2024

Abstract

We present a formalism of a neural network encoding bonded interactions in molecules. This intramolecular encoding is consistent with the models of intermolecular interactions previously designed by this group. Variants of the encoding fed into a corresponding neural network may be used to economically improve the representation of torsional degrees of freedom in any force field. We test the accuracy of the reproduction of the ab initio potential energy surface on a set of conformations of two dipeptides, methyl-capped ALA and ASP, in several scenarios. The encoding, either alone or in conjunction with an analytical potential, improves agreement with ab initio energies that are on par with those of other neural network-based potentials. Using the encoding and neural nets in tandem with an analytical model places the agreements firmly within "chemical accuracy" of ±0.5 kcal/mol.

View details for DOI 10.1021/acs.jpca.3c07598

View details for PubMedID 38232765