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

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models01:06

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

333
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
333

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

Genetic continuity and dietary change during the emergence of millet farming in northern China.

Current biology : CB·2026
Same author

Genome-wide variation landscape reveals temperature adaptation in Chinese indigenous cattle.

Journal of animal science and biotechnology·2026
Same author

CORO1A links inflammatory chondrocyte subpopulations to immune microenvironment alterations in osteoarthritis: an integrative multi-omics and single-cell study.

Frontiers in immunology·2026
Same author

Se-Fe Hydrogel with Switchable Hyperthermia for Osteosarcoma Therapy.

International journal of nanomedicine·2026
Same author

Ultrasound-driven microbubble motors for targeted myocardial ischemia-reperfusion injury treatment.

Materials today. Bio·2026
Same author

A multifunctional Cu@g-C<sub>3</sub>N<sub>4</sub> interfacial coating with synergistic desolvation promotion and interfacial pH stabilization for aqueous zinc-ion batteries.

Chemical communications (Cambridge, England)·2026

相关实验视频

Updated: May 3, 2026

Functional Evaluation of Biological Neurotoxins in Networked Cultures of Stem Cell-derived Central Nervous System Neurons
15:05

Functional Evaluation of Biological Neurotoxins in Networked Cultures of Stem Cell-derived Central Nervous System Neurons

Published on: February 5, 2015

9.4K

ToxMPNN:用于小分子毒性预测的深度学习模型.

Yini Zhou1,2,3, Chao Ning1,2,3, Yijun Tan4

  • 1The National and Local Joint Engineering Laboratory of Animal Peptide Drug Development, College of Life Sciences, Hunan Normal University, Changsha, China.

Journal of applied toxicology : JAT
|February 27, 2024
PubMed
概括

一个新的机器学习模型,ToxMPNN,使用基于图形的深度学习准确预测小分子毒性. 添加已销售的药物作为负样本可以提高药物开发的预测准确性和模型稳定性.

关键词:
MPNN MPNN 在线观看深度学习是一种深度学习.机器学习是机器学习.分子毒性分子毒性

更多相关视频

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
Small Molecule Screening and Toxicity Testing in Early-stage Zebrafish Larvae
02:52

Small Molecule Screening and Toxicity Testing in Early-stage Zebrafish Larvae

Published on: March 7, 2025

1.2K

相关实验视频

Last Updated: May 3, 2026

Functional Evaluation of Biological Neurotoxins in Networked Cultures of Stem Cell-derived Central Nervous System Neurons
15:05

Functional Evaluation of Biological Neurotoxins in Networked Cultures of Stem Cell-derived Central Nervous System Neurons

Published on: February 5, 2015

9.4K
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
Small Molecule Screening and Toxicity Testing in Early-stage Zebrafish Larvae
02:52

Small Molecule Screening and Toxicity Testing in Early-stage Zebrafish Larvae

Published on: March 7, 2025

1.2K

科学领域:

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

背景情况:

  • 机器学习 (ML) 在预测小分子毒性方面表现有前途,但数据限制阻碍了性能.
  • 在单个毒性终点上训练的模型往往产生不满意的结果.
  • 编制了一套全面的数据集,包含7个类别的27个毒性终点.

研究的目的:

  • 为小分子开发一个准确的毒性预测模型.
  • 提高毒性预测模型的性能和稳定性.
  • 评估基于图表的深度学习对毒性评估的有用性.

主要方法:

  • 开发了ToxMPNN,一种利用消息传递神经网络 (MPNN) 架构的毒性预测模型.
  • 整合了一组具有多个终点的有毒小分子数据集,并添加已销售的药物作为负样本.
  • 采用基于图形的深度学习 (DL) 算法进行毒性预测.

主要成果:

  • 在捕获有毒分子特征方面,ToxMPNN表现出卓越的性能,在毒性药物数据集上获得ROC_AUC得分为0.886.
  • 将已销售的药物作为负样本纳入,提高了共同毒性任务的预测性能和模型稳定性.
  • 基于图形的DL算法在毒性预测中被证明是有效的.

结论:

  • ToxMPNN是评估小分子毒性的可靠和有效工具.
  • 开发的模型可以帮助有效开发新药.
  • 综合数据集和先进的DL架构提高了毒性预测的准确性.