高维神经网络潜力的长距离相互作用:小型有机分子的基准研究.
Nguyen Thien Phuc Tu1, Alexander L M Knoll2,3, Jörg Behler2,3
1Department of Chemistry, Carleton University, Ottawa, Ontario K1S 5B6, Canada.
The journal of physical chemistry. B
|November 21, 2025
概括
机器学习潜力 (MLP) 在长距离交互方面扎. 将静电和分散校正与高维神经网络潜力 (HDNNP) 结合起来,可显著提高分子相互作用的准确性.
科学领域:
- 计算化学的计算化学
- 材料科学 材料科学 材料科学
- 机器学习 机器学习
背景情况:
- 机器学习潜力 (MLP) 通常使用局部原子环境,限制它们对远程分子间力量的准确性.
- 准确建模远程静电和分散相互作用对于预测分子行为至关重要.
研究的目的:
- 研究将静电和分散校正纳入高维神经网络潜能 (HDNNP) 的影响.
- 开发和评估一种新的模型,CombineNet,用于预测气相分子间相互作用.
主要方法:
- 通过基于机器学习的电静电电荷平衡 (QEq) 方案来增强HDNNP.
- 使用机器学习交换孔双极矩 (MLXDM) 模型进行分散校正.
- 在密度函数理论 (DFT) 数据上训练模型,并与CCSD (T) /CBS基准进行比较.
主要成果:
- 在DES370K数据集上,CombineNet实现了0.59 kcal/mol的低平均绝对误差 (MAE) 和3.38 meV/原子的根平均平方误差 (RMSE).
- 与希尔什菲尔德收费相比,最小基础代股东 (MBIS) 收费提供了更准确的长期互动趋势.
- 培训组的组成是至关重要的,需要涵盖分离极限和接近切线区域的数据.
结论:
- 明确包括远程静电和分散校正,可以提高MLP对分子间相互作用的准确性.
- 电荷模型的选择显著影响了对静电贡献的预测.
- 仔细考虑训练数据对于开发可靠的分子二次体MLP至关重要.
更多相关视频
09:17Structure-Based Simulation and Sampling of Transcription Factor Protein Movements along DNA from Atomic-Scale Stepping to Coarse-Grained Diffusion
Published on: March 1, 2022
3.5K
10:21Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
Published on: February 23, 2024
3.6K
相关概念视频
¹H NMR: Long-Range Coupling
2.6K
The coupling interactions of nuclei across four or more bonds are usually weak, with J values less than 1 Hz. While these are usually not observed in spectra, the presence of multiple bonds along the coupling pathway can result in observable long-range coupling.
In alkenes, spin information is communicated via σ–π overlap, as seen in allylic (four-bond) and homoallylic (five-bond) couplings. These coupling interactions are stronger when the σ bond is parallel to the alkene...
In alkenes, spin information is communicated via σ–π overlap, as seen in allylic (four-bond) and homoallylic (five-bond) couplings. These coupling interactions are stronger when the σ bond is parallel to the alkene...
2.6K
Noncovalent Attractions in Biomolecules
19.2K
19.2K
Noncovalent Attractions in Biomolecules
63.0K
Noncovalent attractions are associations within and between molecules that influence the shape and structural stability of complexes. These interactions differ from covalent bonding in that they do not involve sharing of electrons.
Four types of noncovalent interactions are hydrogen bonds, van der Waals forces, ionic bonds, and hydrophobic interactions.
Hydrogen bonding results from the electrostatic attraction of a hydrogen atom covalently bonded to a strong-electronegative atom like oxygen,...
Four types of noncovalent interactions are hydrogen bonds, van der Waals forces, ionic bonds, and hydrophobic interactions.
Hydrogen bonding results from the electrostatic attraction of a hydrogen atom covalently bonded to a strong-electronegative atom like oxygen,...
63.0K
Van der Waals Interactions
70.0K
Atoms and molecules interact with each other through intermolecular forces. These electrostatic forces arise from attractive or repulsive interactions between particles with permanent, partial, or temporary charges. The intermolecular forces between neutral atoms and molecules are ion–dipole, dipole–dipole, and dispersion forces, collectively known as van der Waals forces.
70.0K
Predicting Molecular Geometry
44.5K
VSEPR Theory for Determination of Electron Pair Geometries
44.5K
Molecular Geometry and Dipole Moments
17.9K
The VSEPR theory can be used to determine the electron pair geometries and molecular structures as follows:
17.9K
