预测溶解自由能量使用电子阴性-平衡原子电荷和密集的神经网络:一种普遍的方法
1Institut de Química Computacional i Catàlisi and Departament de Química, Universitat de Girona, Carrer Maria Aurèlia Capmany 69, 17003 Girona, Spain.
Journal of chemical theory and computation
|November 14, 2023
概括
一个新的密集神经网络,ESE-GB-DNN,准确地预测了分子和离子的溶解自由能量. 这种方法提供了高效率和精度,与各种溶剂的标准DFT方法相竞争.
科学领域:
- 计算化学计算化学
- 物理化学 物理化学
- 机器学习在化学中的应用
背景情况:
- 准确预测溶解自由能量 (ΔG°solv) 对于理解化学过程至关重要.
- 像DFT这样的标准方法可以是计算密集的.
- 开发高效,准确的模拟溶解自由能量是一个持续的挑战.
研究的目的:
- 引入ESE-GB-DNN,一个新的密集神经网络,用于评估无溶解能.
- 评估ESE-GB-DNN在不同类型的溶剂和溶解物中所具有的准确性和效率.
- 为了比较ESE-GB-DNN与已建立的基于DFT的方法的性能.
主要方法:
- 使用密集的神经网络 (ESE-GB-DNN),将一般化Born术语,原子表面积和分子体积作为输入特征.
- 采用修改后的电子阴性等分方法来计算原子电荷.
- 在各种溶剂类别 (水,非水性) 和溶解物类型 (中性分子,离子) 中使用根平均平方误差 (RMSE) 评估性能.
主要成果:
- 对于中性溶液,ESE-GB-DNN可以达到高精度,RMSE在0.7到1.3kcal/mol之间,取决于溶剂.
- 该模型对非水性离子溶液表现出色,产生RMSE约为0.7kcal/mol.
- 对于水中的离子,ESE-GB-DNN显示较大的RMSE为2.9 kcal/mol,表明需要进一步精炼的区域.
结论:
- ESE-GB-DNN提供了一种简单,高效和高度准确的方法来预测溶解自由能量.
- 该模型的性能挑战了基于DFT的标准方法的性能,特别是对于中性溶液和非水性离子溶液.
- ESE-GB-DNN代表了计算化学在溶解自由能计算中的重大进步.
更多相关视频
11:14A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
Published on: October 4, 2015
11.0K
12:11Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry
Published on: April 8, 2020
8.2K
相关概念视频
Entropy and Solvation
7.1K
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...
7.1K
Chemical and Solubility Equilibria
4.1K
The free energy change associated with dissolving a solute in a liter of solvent is called the free energy of a solution, ΔGsolution. The overall ΔGsolution is expressed as the balance of ΔGinteraction against the always-favorable free-energy of mixing, ΔGmixing. Solution formation is favorable if ΔGsolution is less than zero, whereas it is unfavorable if ΔGsolution is greater than zero. In short, for a solution to form and complete dissolution to take place,...
4.1K
The Born-Haber Cycle
21.9K
Lattice Energy
21.9K
Solvating Effects
7.5K
An understanding of the solvating effect helps rationalize the relation between solvation and acidity of the compound. In addition, this also explains the relative stability of conjugate bases for compounds with different pKa values. This lesson details, in-depth, the principle of solvating effects. The strength of an acid and the stability of its corresponding conjugate base are determined using pKa values. This observed relationship is a consequence of solvation, which is the interaction...
7.5K
Energetics of Solution Formation
6.8K
The formation of a solution is an example of a spontaneous process, which is a process that occurs under specified conditions without energy from some external source.
When the strengths of the intermolecular forces of attraction between solute and solvent species in a solution are no different than those present in the separated components, the solution is formed with no accompanying energy change. Formation of the solution requires the solute–solute and solvent–solvent...
When the strengths of the intermolecular forces of attraction between solute and solvent species in a solution are no different than those present in the separated components, the solution is formed with no accompanying energy change. Formation of the solution requires the solute–solute and solvent–solvent...
6.8K
Predicting Molecular Geometry
34.4K
VSEPR Theory for Determination of Electron Pair Geometries
34.4K
