Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Molecular Models02:00

Molecular Models

37.8K
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.
37.8K

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

The genetic control of growth rate: a systems biology study in yeast.

BMC systems biology·2012
Same author

Presence of somatic mutations in most early-stage pancreatic intraepithelial neoplasia.

Gastroenterology·2012
Same author

Terpenoids from root bark of Celastrus orbiculatus.

Phytochemistry·2011
Same author

Zero-order noise suppression with various space-shifting manipulations of reconstructed images in digital holography.

Applied optics·2011
Same author

Design, synthesis and insecticidal activities of novel pyrazole amides containing hydrazone substructures.

Pest management science·2011
Same author

Imbricate scales as a design construct for microsystem technologies.

Small (Weinheim an der Bergstrasse, Germany)·2011

相关实验视频

Updated: Jun 4, 2025

Obtaining 3D Chemical Maps by Energy Filtered Transmission Electron Microscopy Tomography
08:15

Obtaining 3D Chemical Maps by Energy Filtered Transmission Electron Microscopy Tomography

Published on: June 9, 2018

6.4K

D3-ImgNet:基于数据驱动的电子密度图像进行分子性质预测的框架.

Junfeng Zhao1,2, Lixin Tang1, Jiyin Liu3

  • 1National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Northeastern University, Shenyang 110819, China.

The journal of physical chemistry. A
|January 3, 2025
PubMed
概括

我们开发了D3-ImgNet,这是一种使用电子密度图像来预测分子性质的深度学习框架. 这种人工智能方法整合了物理,实现了原子化能量,双极时刻和化学反应路径的高精度.

更多相关视频

Investigating Protein Sequence-structure-dynamics Relationships with Bio3D-web
09:51

Investigating Protein Sequence-structure-dynamics Relationships with Bio3D-web

Published on: July 16, 2017

15.4K
Author Spotlight: Exploring Cellular Processes by Modeling Ligands in Cryo-EM Maps
09:30

Author Spotlight: Exploring Cellular Processes by Modeling Ligands in Cryo-EM Maps

Published on: July 19, 2024

1.2K

相关实验视频

Last Updated: Jun 4, 2025

Obtaining 3D Chemical Maps by Energy Filtered Transmission Electron Microscopy Tomography
08:15

Obtaining 3D Chemical Maps by Energy Filtered Transmission Electron Microscopy Tomography

Published on: June 9, 2018

6.4K
Investigating Protein Sequence-structure-dynamics Relationships with Bio3D-web
09:51

Investigating Protein Sequence-structure-dynamics Relationships with Bio3D-web

Published on: July 16, 2017

15.4K
Author Spotlight: Exploring Cellular Processes by Modeling Ligands in Cryo-EM Maps
09:30

Author Spotlight: Exploring Cellular Processes by Modeling Ligands in Cryo-EM Maps

Published on: July 19, 2024

1.2K

科学领域:

  • 量子化学 是一个量子化学.
  • 材料科学 材料科学 材料科学
  • 人工智能的人工智能

背景情况:

  • 机器学习越来越多地用于预测分子性质.
  • 现有的模型往往缺乏与物理机制的整合.

研究的目的:

  • 提出D3-ImgNet,这是一个用于分子性质预测的新型深度学习框架.
  • 整合数据驱动的电子密度图像与物理原理.

主要方法:

  • 开发了D3-ImgNet框架,结合了群理论,DFT机制,深度学习和多目标优化.
  • 利用QM9和QM9X数据集进行属性预测 (原子化能量,二极点时刻,力).
  • 适用于SN2反应数据集的应用框架,用于最小能量路径预测.

主要成果:

  • 在使用QM9数据集预测分子原子化能量方面取得了高准确性.
  • 在QM9X数据集上证明了对双极时刻和力具有令人满意的预测能力.
  • 成功预测了SN2反应的最小能量路径,显示了框架的适应性.

结论:

  • D3-ImgNet框架有效地预测了分子特性和反应途径.
  • 可视化证实了电子密度转移的准确复制.
  • 该框架显示了加速材料发现和高通量选的潜力.