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

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 impact of physical-mental mixed fatigue on landing biomechanics inter-joint coordination and injury risk in elite American football players.

Frontiers in psychology·2026
Same author

Lipidomic and Transcriptomic Insights into Hepatic Lipid Remodeling Induced by Peony Seed Oil.

Journal of agricultural and food chemistry·2026
Same author

Glyphosate Induces Liver Macrophage Pyroptosis via Mitochondrial Damage-Mediated cGAS-STING Activation.

Toxics·2026
Same author

IL-2 mutein promotes antigen-specific transplant acceptance in mice through expansion of ST2<sup>+</sup> regulatory T cells.

Nature communications·2026
Same author

Identification of Immune-Related Genes in Predicting the Progression of Colitis-Associated Colorectal Cancer: An Integrated Bioinformatics and Experimental Validation Study.

Journal of inflammation research·2026
Same author

Mitigation of transient beam loading in a compact high duty cycle injector via hardware upgrade and multi-objective optimization.

Scientific reports·2026

相关实验视频

Updated: Jan 17, 2026

Technical Applications of Microelectrode Array and Patch Clamp Recordings on Human Induced Pluripotent Stem Cell-Derived Cardiomyocytes
10:30

Technical Applications of Microelectrode Array and Patch Clamp Recordings on Human Induced Pluripotent Stem Cell-Derived Cardiomyocytes

Published on: August 4, 2022

3.4K

在药物开发中预测心脏毒性:一种深度学习方法

Kaifeng Liu1, Huizi Cui1, Xiangyu Yu1

  • 1Key Laboratory for Molecular Enzymology and Engineering of Ministry of Education, Edmond H. Fischer Signal Transduction Laboratory, School of Life Sciences, Jilin University, Changchun, 130012, China.

Journal of pharmaceutical analysis
|September 22, 2025
PubMed
概括

计算模型使用机器学习准确预测药物心脏毒性,改善药物安全性评估. 这些方法提高了药物开发的效率并降低了药物开发成本.

关键词:
心脏毒性 有关心脏的毒性.深度学习是一种深度学习.药物开发 药物开发人类以太基因相关的基因通道分子指纹的分子指纹.

更多相关视频

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K
Measurement of Heart Contractility in Isolated Adult Human Primary Cardiomyocytes
09:17

Measurement of Heart Contractility in Isolated Adult Human Primary Cardiomyocytes

Published on: August 9, 2022

2.5K

相关实验视频

Last Updated: Jan 17, 2026

Technical Applications of Microelectrode Array and Patch Clamp Recordings on Human Induced Pluripotent Stem Cell-Derived Cardiomyocytes
10:30

Technical Applications of Microelectrode Array and Patch Clamp Recordings on Human Induced Pluripotent Stem Cell-Derived Cardiomyocytes

Published on: August 4, 2022

3.4K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K
Measurement of Heart Contractility in Isolated Adult Human Primary Cardiomyocytes
09:17

Measurement of Heart Contractility in Isolated Adult Human Primary Cardiomyocytes

Published on: August 9, 2022

2.5K

科学领域:

  • 计算化学是一种计算化学.
  • 药物发现 药物发现
  • 毒理学 毒理学 毒理学

背景情况:

  • 心脏毒性是药物开发中的重大风险,通常与hERG通道有关.
  • 传统的心脏毒性检测是昂贵和耗时的.
  • 计算式虚拟选提供了一个更有效的替代方案.

研究的目的:

  • 开发准确和高效的计算模型来预测复合性心脏毒性.
  • 通过机器学习和深度学习技术改进药物安全性评估.

主要方法:

  • 使用分子指纹和描述符与机器学习 (高斯 NB,RF,SVM,KNN,XGBoost) 和深度学习 (变压器) 算法.
  • 使用精度 (ACC) 和曲线下的面积 (AUC) 评估模型性能.
  • 为了特征解释性,使用了夏普利添加式解释 (SHAP).

主要成果:

  • 最好的机器学习模型 (XGBoost Morgan) 实现了0.84.8的ACC.
  • 最好的深度学习模型 (Transformer_Morgan) 实现了0.85.5的ACC.
  • 转换器_摩根模型在独立验证集上获得了0.93的AUC,超过了现有的工具.
  • SHAP分析确定了与心脏毒性相关的关键化学特征,例如环和含的组.

结论:

  • 机器学习和深度学习模型为心脏毒性提供了高度准确的预测.
  • 这些计算方法为药物安全性评估提供了可靠和可解释的方法.
  • 该研究促进了高效的药物开发,降低了成本,并提高了新药候选药物的安全性.