期刊
JOURNAL OF CHEMICAL PHYSICS
卷 154, 期 22, 页码 -出版社
AIP Publishing
DOI: 10.1063/5.0050444
关键词
-
资金
- Bristol Myers Squibb
- U.S. National Science Foundation [CHE-1955940, MRI-1828187]
- U.S. Department of Energy (DOE) Office of Science, Office of Basic Energy Sciences, Computational Chemical Sciences (CCS) Research Program [AL-18-380-057]
The study introduces a modified Cartesian MPNN framework for predicting atomic multipoles, demonstrating its accuracy and effectiveness on a large-scale dataset. The model accurately predicts atom-centered charges, dipoles, and quadrupoles, with minimal impact on multipole-multipole electrostatic energies, and is able to model the conformational dependencies of a molecule.
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. Published under an exclusive license by AIP Publishing.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据