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

Structure-Activity Relationships and Drug Design01:28

Structure-Activity Relationships and Drug Design

1.6K
Drug design is a dynamic field that involves discovering and developing new medications based on specific biological targets. This process heavily relies on structure-activity relationships (SAR) and quantitative structure-activity relationships (QSAR) to guide the design and optimization of efficient drugs.
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence...
1.6K

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

Recent advances in protein engineering and synthetic applications of amino acid oxidases.

Bioresource technology·2026
Same author

Aggregation Issues in Radioactive Copper-Labeled Antibodies.

Nuclear medicine and molecular imaging·2026
Same author

A robust multi-criteria supplier selection framework based on linguistic cubic interval-valued intuitionistic fuzzy aggregation operators.

Scientific reports·2026
Same author

Defect Diamond-Like d<sup>10</sup> Metal Indium Selenium With Strong Second-Harmonic Generation and Enhanced Laser-Induced Damage Threshold.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Cerium-coated Fe<sub>3</sub>O<sub>4</sub> nanocomposite enhances salt stress tolerance in maize by modulating photosynthetic efficiency, antioxidant defense, and cellular ultrastructure.

Frontiers in plant science·2026
Same author

Role of UAVs in precision pesticide spraying and environmental safety by combating pesticide resistance and safety of natural enemies.

Pest management science·2026

相关实验视频

Updated: Jan 8, 2026

A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

69.6K

关注点:基于结构的虚拟选的特定目标,偏差感知评分函数:METTL3的案例研究

Muhammad Junaid1,2, Muhammad Zeeshan3, Wenjin Li1

  • 1Institute for Advanced Study, Shenzhen University, Shenzhen 518060, China.

Journal of chemical information and modeling
|December 23, 2025
PubMed
概括

一个新的深度学习工具AttentionScore通过整合配体和蛋白质数据来增强基于结构的METTL3虚拟选. 这种针对特定目标的方法优于通用方法,为药物发现提供了强大的框架.

更多相关视频

Achieving Efficient Fragment Screening at XChem Facility at Diamond Light Source
08:35

Achieving Efficient Fragment Screening at XChem Facility at Diamond Light Source

Published on: May 29, 2021

6.8K
Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins
05:08

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins

Published on: July 8, 2025

888

相关实验视频

Last Updated: Jan 8, 2026

A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

69.6K
Achieving Efficient Fragment Screening at XChem Facility at Diamond Light Source
08:35

Achieving Efficient Fragment Screening at XChem Facility at Diamond Light Source

Published on: May 29, 2021

6.8K
Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins
05:08

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins

Published on: July 8, 2025

888

科学领域:

  • 计算化学是一种计算化学.
  • 结构生物学是结构生物学.
  • 机器学习在药物发现中的作用

背景情况:

  • 虚拟选中的通用评分功能可能会有偏见,容易出现错误.
  • 需要针对特定目标的评分功能来提高基于结构的虚拟选的准确性和可靠性.
  • METTL3是各种疾病的关键标,使其抑制剂成为药物发现的焦点.

研究的目的:

  • 为METTL3.3引入基于深度学习的评分功能AttentionScore.
  • 为了改善查,整合仅合体和蛋白质-合体相互作用信息.
  • 为虚拟选方法提供一个有偏见的评估框架.

主要方法:

  • 开发了一个端到端的深度学习架构 (AttentionScore),使用多头注意力编码器和联合潜伏表示.
  • 综合蛋白质 - 配体相互作用 (PLEC) 指纹与配体化学型指纹 (Avalon/ECFP4).
  • 构建了一个相似性受约束 (SC) 分割和一个推断测试集 (Set 2) 进行严格的,有偏见的评估.

主要成果:

  • 在SC测试组 (组1) 中,AttentionScore在PR-AUC = 0.9609.9的SC测试组 (组1) 中取得了高性能.
  • 该模型在更严格的Set 2上表现出强的表现,超过了通用评分功能和机器学习基线.
  • 统计分析证实了观察到的业绩增长的稳定性和可靠性.

结论:

  • 注意Score在针对METTL3.3的特定目标的虚拟选方面取得了重大进展.
  • 开发的偏见感知评估框架最大限度地减少了模拟泄漏,并确保了可靠的性能评估.
  • 公开可用的数据,代码和用户友好的界面促进了研究人员的透明度和可访问性.