相关实验视频

Updated: Mar 10, 2026

Rapid in-silico Battery Electrolyte Electrochemical Reaction Generation using 3T-VASP Multi-Scale Energy Minimization

Rapid in-silico Battery Electrolyte Electrochemical Reaction Generation using 3T-VASP Multi-Scale Energy Minimization

Published on: August 22, 2025

超越切线:用于神经网络潜力的混合ML/MM静电学

Shahed Haghiri¹, Andres S Urbina¹, Lyudmila V Slipchenko¹

¹Department of Chemistry, Purdue University, West Lafayette, Indiana 47907, USA.

The Journal of chemical physics

|March 9, 2026

概括

混合机器学习/分子力学 (ML/MM) 神经网络准确预测蛋白质-连接体复合体中的结合能. 这种方法提高了各种应用中复杂分子建模的可扩展性和准确性.

科学领域:

计算化学计算化学
机器学习在化学中的应用
生物物理学的生物物理.

背景情况:

原子神经网络潜力 (NNP) 提供了可扩展的,低成本的分子性质预测,但与长距离相互作用作斗争.
现有的NNP是局部的,这限制了它们在生物,工程和制药领域至关重要的缩相系统的可靠性.
之前的工作是将远程静电信息集成到NNP中 (ANI/MM),与量子力学/分子力学 (QM/MM) 相似.

研究的目的:

开发和训练一个ANI/MM神经网络,用于预测蛋白质-连接体复合体中的结合能.
评估ANI/MM网络在预测力方面的准确性及其对分子动力学模拟的潜力.
为了比较开发的ANI/MM NNP与已建立的经典力场的性能.

主要方法:

重新训练 ANI NNP 来纳入来自分子环境的静电潜力,创建嵌入式 ANI/MM 模型.
训练ANI/MM网络,专门针对两个蛋白质-连接体复合体进行训练,以预测结合能.
评估力预测的准确性,并将性能与初始装备的经典力场Q-Force进行比较.

主要成果:

该ANI/MM网络准确地预测力量的误差低于1kcal/mol/Å,使得几何优化和分子动力学.
开发的ANI/MM NNP超越了研究复合体的Q-Force场的性能.
当训练数据包括相关的结构碎片时,该模型证明了对新溶液的良好可转移性.

结论:

混合ML/MM神经架构为复杂的分子系统的化学精确和可扩展的建模提供了一个有希望的途径.
ANI/MM NNP为模拟生物,工程和制药应用提供了重大进展.
这项工作突出了将远程交互信息集成到神经网络潜力中,用于增强分子建模的潜力.

更多相关视频

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Published on: June 21, 2022

Author Spotlight: Advancing Cell Membrane Biophysics - Exploring Interactions and Challenges Through Experimental and Computational Approaches

Author Spotlight: Advancing Cell Membrane Biophysics - Exploring Interactions and Challenges Through Experimental and Computational Approaches

Published on: September 1, 2023

相关概念视频

Hybridization of Atomic Orbitals I

Hybridization of Atomic Orbitals I

The mathematical expression known as the wave function, ψ, contains information about each orbital and the wavelike properties of electrons in an isolated atom. When atoms are bound together in a molecule, the wave functions combine to produce new mathematical descriptions that have different shapes. This process of combining the wave functions for atomic orbitals is called hybridization and is mathematically accomplished by the linear combination of atomic orbitals. The new orbitals that...

Predicting Molecular Geometry

Predicting Molecular Geometry

VSEPR Theory for Determination of Electron Pair Geometries

Molecular Models

Molecular Models

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.

Molecular Geometry and Dipole Moments

Molecular Geometry and Dipole Moments

The VSEPR theory can be used to determine the electron pair geometries and molecular structures as follows:

Molecular Orbital Theory I

Molecular Orbital Theory I

Overview of Molecular Orbital Theory

Molecular Orbital Theory II

Molecular Orbital Theory II

Molecular Orbital Energy Diagrams