Cartesian message passing neural networks for directional properties: Fast and transferable atomic multipoles
Autor: | Daniel L. Cheney, Zachary L. Glick, Alexios Koutsoukas, C. David Sherrill |
---|---|
Rok vydání: | 2021 |
Předmět: |
Physics
010304 chemical physics Artificial neural network Message passing Ab initio General Physics and Astronomy Electronic structure 010402 general chemistry 01 natural sciences 0104 chemical sciences Computational physics law.invention Dipole Cartesian tensor law Component (UML) 0103 physical sciences Cartesian coordinate system Physics::Atomic Physics Physical and Theoretical Chemistry |
Zdroj: | The Journal of chemical physics. 154(22) |
ISSN: | 1089-7690 |
Popis: | The message passing neural network (MPNN) framework is a promising tool for modeling atomic properties but is, until recently, incompatible with directional properties, such as Cartesian tensors. We propose a modified Cartesian MPNN (CMPNN) suitable for predicting atom-centered multipoles, an essential component of ab initio force fields. The efficacy of this model is demonstrated on a newly developed dataset consisting of 46 623 chemical structures and corresponding high-quality atomic multipoles, which was deposited into the publicly available Molecular Sciences Software Institute QCArchive server. We show that the CMPNN accurately predicts atom-centered charges, dipoles, and quadrupoles and that errors in the predicted atomic multipoles have a negligible effect on multipole–multipole electrostatic energies. The CMPNN is accurate enough to model conformational dependencies of a molecule’s electronic structure. This opens up the possibility of recomputing atomic multipoles on the fly throughout a simulation in which they might exhibit strong conformational dependence. |
Databáze: | OpenAIRE |
Externí odkaz: |