从MM转移知识到QM:一个基于图形神经网络的隐性溶剂模型,用于小型有机分子
Paul Katzberger1, Felix Pultar1, Sereina Riniker1
1Department of Chemistry and Applied Biosciences, ETH Zürich, Vladimir-Prelog-Weg 2, Zürich 8093, Switzerland.
Journal of chemical theory and computation
|July 28, 2025
概括
本研究引入了一种新的机器学习隐性溶剂模型,用于量子力学 (QM) 计算. 这种模型有效地从经典模拟中转移知识,使得各种溶剂中分子行为的准确预测成为可能,而不需要实验数据.
科学领域:
- 计算化学计算化学
- 分子建模分子建模
- 机器学习 机器学习
背景情况:
- 分子环境显著影响着形状组合.
- 准确的环境建模对于计算研究至关重要.
- 机器学习 (ML) 对模拟分子相互作用,特别是在古典分子动力学方面,显示出前景.
研究的目的:
- 开发一个通用的机器学习隐性溶剂模型用于量子力学 (QM) 计算.
- 克服QM现有的ML隐性溶剂模型的计算成本限制.
- 创建一个可以跨不同QM函数和基础集转移的模型.
主要方法:
- 通过将知识从经典交互转移到QM,开发了一种新的方法.
- 模拟了一个QM/MM (量子力学/分子力学) 设置,其中包含静电嵌入和一个非极化MM溶剂.
- 使用图形神经网络 (GNN) 来创建隐性溶剂模型 (QM-GNNIS).
主要成果:
- QM-GNNIS模型不需要QM/MM参考计算,也不需要实验数据进行培训.
- 基于GNN的模型与任何QM功能和基础集兼容.
- QM-GNNIS准确地描述了小型有机分子的39种有机溶剂,并重现了实验趋势.
结论:
- 开发的QM-GNNIS模型为QM计算中的隐性溶剂建模提供了一个计算效率高且广泛适用的解决方案.
- 这种方法成功地弥合了经典和量子力学模拟溶剂效应之间的差距.
- 与现有的最先进的方法相比,该模型在复制实验观测时表现出更高的性能.
相关概念视频
Molecular Models
40.5K
Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.
40.5K
Chemical Shift: Internal References and Solvent Effects
772
In an NMR sample, precise measurement of the absolute absorption frequencies of nuclei is difficult. A standard internal reference compound is added, and the frequency difference between the reference signal and sample signals is measured.
The internal reference compound generally used in NMR spectroscopy is tetramethylsilane (TMS). TMS is preferred because it is chemically inert, soluble in NMR solvents, and easily removable. Also, the highly shielded methyl protons in TMS yield an intense...
The internal reference compound generally used in NMR spectroscopy is tetramethylsilane (TMS). TMS is preferred because it is chemically inert, soluble in NMR solvents, and easily removable. Also, the highly shielded methyl protons in TMS yield an intense...
772
Predicting Molecular Geometry
36.1K
VSEPR Theory for Determination of Electron Pair Geometries
36.1K
Entropy and Solvation
7.2K
The process of surrounding a solute with solvent is called solvation. It involves evenly distributing the solute within the solvent. The rule of thumb for determining a solvent for a given compound is that like dissolves like. A good solvent has molecular characteristics similar to those of the compound to be dissolved. For example, polar solutions dissolve polar solutes, and apolar solvents dissolve apolar solutes. A polar solvent is a solvent that has a high dielectric constant (ϵ...
7.2K
Newman Projections
17.7K
Different notations are used to represent the three-dimensional structure of molecules on two-dimensional surfaces. One of the most commonly used representations is the dash-wedge formula. The dashed wedges, solid wedges, and the plane lines indicate the groups situated behind the plane, coming out of the plane, and in the plane, respectively.
The organic molecules rotate across the single bonds leading to numerous temporary three-dimensional structures of varying energy known as...
The organic molecules rotate across the single bonds leading to numerous temporary three-dimensional structures of varying energy known as...
17.7K
Fischer Projections
13.9K
Learning to draw Fischer projections of molecules and understanding their relevance plays a crucial role in the visual depiction of organic molecules. A Fischer projection is a two-dimensional projection on a planar surface to simplify the three-dimensional wedge–dash representation of molecules. This is especially helpful in the case of molecules with multiple chiral centers that can be difficult to draw. Here, all the bonds of interest are represented as horizontal or vertical lines.
13.9K


