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

Conserved Binding Sites01:49

Conserved Binding Sites

4.2K
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
4.2K
Ligand Binding Sites02:40

Ligand Binding Sites

12.8K
Proteins are dynamic macromolecules that carry out a wide variety of essential processes; however, the activities of most proteins depend on their interactions with other molecules or ions, known as ligands.
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
12.8K

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

Ligand Conformational Variability Enhances Machine Learning Prediction of Protein-Ligand Binding Affinity.

The journal of physical chemistry. B·2026
Same author

Cr(I)-Cr(I) Terphenyl Bridged Complexes: A Broken-Symmetry DFT and Multideterminant CASSCF/NEVPT2 Handshake.

ACS omega·2025
Same author

Is it possible to obtain a plausible experimental electronic structure without collecting high-order diffraction data?

Acta crystallographica Section B, Structural science, crystal engineering and materials·2025
Same author

DFT Modeling of Polyethylene Chains Cross-linked by Selected <i>n</i>s<sup>1</sup> and <i>n</i>s<sup>2</sup> Metal Atoms.

The journal of physical chemistry. A·2024
Same author

Thermodynamics of the gas-phase dimerization of formic acid: Fully anharmonic finite temperature calculations at the CCSD(T) and many DFT levels.

The Journal of chemical physics·2024
Same author

Chemical and Redox Noninnocence of Pentane-2,4-dione Bis(<i>S</i>-methylisothiosemicarbazone) in Cobalt Complexes and Their Application in Wacker-Type Oxidation.

JACS Au·2024

相关实验视频

Updated: Jun 26, 2025

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
10:21

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA

Published on: February 23, 2024

2.5K

为了更可靠的顶部对接得分预测,SchNetPack超参数优化.

Ján Matúška1, Lukas Bucinsky1, Marián Gall2,3

  • 1Institute of Physical Chemistry and Chemical Physics, Faculty of Chemical and Food Technology, Slovak University of Technology in Bratislava, Radlinského 9, SK-81237 Bratislava, Slovak Republic.

The journal of physical chemistry. B
|May 11, 2024
PubMed
概括

SchNetPack模型的超参数调整,特别是切断距离,显著提高了顶部对接分数的预测. 这种方法优于数据采样技术,如过量采样和不足采样,以提高机器学习模型的准确性.

更多相关视频

Author Spotlight: Network Pharmacology and Molecular Docking to Decipher the Action of Jiawei Shengjiang San Against Diabetic Kidney Disease
08:15

Author Spotlight: Network Pharmacology and Molecular Docking to Decipher the Action of Jiawei Shengjiang San Against Diabetic Kidney Disease

Published on: May 10, 2024

558
Network Pharmacology Prediction and Metabolomics Validation of the Mechanism of Fructus Phyllanthi against Hyperlipidemia
11:06

Network Pharmacology Prediction and Metabolomics Validation of the Mechanism of Fructus Phyllanthi against Hyperlipidemia

Published on: April 7, 2023

2.0K

相关实验视频

Last Updated: Jun 26, 2025

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
10:21

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA

Published on: February 23, 2024

2.5K
Author Spotlight: Network Pharmacology and Molecular Docking to Decipher the Action of Jiawei Shengjiang San Against Diabetic Kidney Disease
08:15

Author Spotlight: Network Pharmacology and Molecular Docking to Decipher the Action of Jiawei Shengjiang San Against Diabetic Kidney Disease

Published on: May 10, 2024

558
Network Pharmacology Prediction and Metabolomics Validation of the Mechanism of Fructus Phyllanthi against Hyperlipidemia
11:06

Network Pharmacology Prediction and Metabolomics Validation of the Mechanism of Fructus Phyllanthi against Hyperlipidemia

Published on: April 7, 2023

2.0K

科学领域:

  • 计算化学是一种计算化学.
  • 机器学习在药物发现中的作用

背景情况:

  • 预测顶级对接分数对于识别有力的药物候选人至关重要.
  • 机器学习模型,如使用SchNetPack的机器学习模型,往往难以推断到罕见的,高得分的化合物.

研究的目的:

  • 增强SchNetPack神经网络的推断能力,用于预测顶级对接分数.
  • 确定提高高得分化合物的预测准确度的关键超参数.

主要方法:

  • 对SchNetPack原子模型表示的超参数调整.
  • 使用平均平方误差 (MSE) 和损失景观来评估预测稳定性.
  • 截止距离,辐射基函数,网络层和特征向量大小的比较.
  • 对训练数据的超采样和不足采样技术的分析.

主要成果:

  • 优化截止超参数 (在5 Å) 显著改善了顶部对接得分的预测 (MSE从3.5降低到0.9 kcal/mol).
  • 其他超参数对预测最高得分的化合物与截止值相比的影响很小.
  • 截止优化比数据采样方法 (低采样>高采样) 更能提高最高分数的准确性.
  • 当专注于最高得分的化合物时,总体预测准确性略有下降.

结论:

  • 切断距离是改善SchNetPack对顶部对接分数的预测最重要的超参数.
  • 超参数调整提供了一个比数据采样更有效的策略,用于提高机器学习模型中稀有,高价值化合物的预测.
  • 仔细调整可以通过更准确的对接分数预测来改善有前途的候选药物的识别.