Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Mutagenicity and Carcinogenicity

Mutagenicity and Carcinogenicity

Mutagenicity and carcinogenicity refer to the ability of drugs to cause genetic defects and induce cancer, respectively. The International Agency for Research on Cancer (IARC) classifies agents into four groups based on their carcinogenic potential. Group 1 agents are known human carcinogens; group 2A agents are probably carcinogenic to humans; group 3 agents lack data to support their role in carcinogenesis; and group 4 includes agents for which data support that they are not likely to be...

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

Brain endothelial Gα<sub>q/11</sub> signalling in cerebrovascular function and cognition of aged mice.

EBioMedicine·2026

Same author

Thyrotropin-releasing hormone neurons of different hypothalamic nuclei increase energy expenditure.

Nature communications·2026

Same author

Nitrosamine Ames Data Review and Method Development: proceedings of a US FDA/HESI workshop.

Mutagenesis·2026

Same author

Ames concordance with the in vivo transgenic rodent (TGR) gene mutation assay for NDSRIs and relative in vivo TGR potency with nitrosamines with robust dose-response carcinogenicity data.

Regulatory toxicology and pharmacology : RTP·2026

Same author

HyperSBINN: A Hypernetwork-Enhanced Systems Biology-Informed Neural Network for Efficient Drug Cardiosafety Assessment.

Journal of computational biology : a journal of computational molecular cell biology·2026

Same author

A Simple Framework for Collaborative Development of Predictive Models Trained on Proprietary Data.

Journal of chemical information and modeling·2025

Search research articles

相关实验视频

Updated: Jun 4, 2025

Advanced 3D Liver Models for In vitro Genotoxicity Testing Following Long-Term Nanomaterial Exposure

Advanced 3D Liver Models for In vitro Genotoxicity Testing Following Long-Term Nanomaterial Exposure

Published on: June 5, 2020

机器学习增强了使用MultiFlow® DNA损伤试验的基因毒性评估.

Panuwat Trairatphisan¹, Lena Dorsheimer¹, Peter Monecke¹

¹Research and Development, Preclinical Safety, Sanofi, Industriepark Hoechst, Frankfurt am Main, Germany.

Environmental and molecular mutagenesis

|December 31, 2024

概括

机器学习模型使用MultiFlow® DNA损伤测定 (MFA) 数据准确预测基因毒性的作用模式. 这种方法通过提高基因毒性测试的精度来提高药物安全性评估.

关键词:

它是DNA损伤生物标志物.遗传毒性遗传毒性遗传毒性遗传毒性图形化用户界面图形化用户界面机器学习是机器学习.模型的部署部署.模型开发模型的发展.视觉化的可视化

更多相关视频

Cell Cycle-specific Measurement of γH2AX and Apoptosis After Genotoxic Stress by Flow Cytometry

Cell Cycle-specific Measurement of γH2AX and Apoptosis After Genotoxic Stress by Flow Cytometry

Published on: September 1, 2019

The Lambda Select cII Mutation Detection System

The Lambda Select cII Mutation Detection System

Published on: April 26, 2018

相关实验视频

Last Updated: Jun 4, 2025

Advanced 3D Liver Models for In vitro Genotoxicity Testing Following Long-Term Nanomaterial Exposure

Advanced 3D Liver Models for In vitro Genotoxicity Testing Following Long-Term Nanomaterial Exposure

Published on: June 5, 2020

Cell Cycle-specific Measurement of γH2AX and Apoptosis After Genotoxic Stress by Flow Cytometry

Cell Cycle-specific Measurement of γH2AX and Apoptosis After Genotoxic Stress by Flow Cytometry

Published on: September 1, 2019

The Lambda Select cII Mutation Detection System

The Lambda Select cII Mutation Detection System

Published on: April 26, 2018

科学领域:

药理学和毒理学药理学和毒理学
计算化学计算化学
生物技术是生物技术.

背景情况:

基因毒性测试对于药物安全性评估至关重要.
诸如MultiFlow® DNA损伤测试 (MFA) 等机械测试可以提供对DNA损伤途径的见解.
机器学习 (ML) 在提高基因毒剂作用模式 (MoA) 的分类方面显示出潜力.

研究的目的:

开发和验证ML模型以使用MFA数据预测基因毒性的MOA.
提高药品基因毒性风险评估的准确性和可靠性.
创建一个用户友好的工具来分析MFA数据和MoA预测.

主要方法:

将R包"caret"中的最先进的ML算法应用于MFA数据.
从in silico模型中整合分子描述符,以提高模型性能.
使用R包"shiny"开发图形用户界面,用于数据可视化和分析.
对培训,内部测试和外部测试数据集的模型的验证.

主要成果:

最好的ML模型在训练数据集上达到95%的准确性,并在测试数据集中的17个案例中16个案例中正确预测了基因毒性.
整合分子描述符提高了性能,特别是在复杂的药物病例中.
对49种化合物的外部验证表明,模型准确度高达92%.
开发了一个用户友好的图形界面,以促进广泛的实验室使用.

结论:

ML模型,当量身定制时,可以显著提高基因毒性测试中MoA确定精度.
开发的方法为基因毒性评估提供了可靠的方法,有助于制药安全评估.
整合MoA预测可以作为监管性基因毒性评估工作流程中宝贵的证据.