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

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

Comparative associations of the TyG index and HOMA2-IR with 6-month outcomes after moderate-to-severe traumatic brain injury: a single-center retrospective cohort study.

Frontiers in molecular neuroscience·2026

Same author

A machine learning model for diabetic retinopathy risk stratification using routine blood and urine parameters: insights into kidney-eye crosstalk.

Frontiers in endocrinology·2026

Same author

Ablation of idiopathic fascicular ventricular tachycardia in a patient with congenitally corrected transposition of the great arteries: A case report.

HeartRhythm case reports·2026

Same author

Nitroxyl relieves acute kidney injury by suppressing SLC31A1-mediated cuproptosis in renal tubular epithelial cells.

Life sciences·2026

Same author

A Plasmonic "Lid-Off" Nanoplatform for Spatiotemporally Controlled PA/NIR-II Dual-Modal Imaging and Cuproptosis-Based Synergistic Photothermal and Chemodynamic Therapy.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same author

Ti@ZnO Mediated Sonodynamic Disruption of Deep Implant Biofilms with Concomitant Immune Tracestream Remodeling.

Advanced healthcare materials·2026

Search research articles

相关实验视频

Updated: Jan 9, 2026

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

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

Published on: October 10, 2018

基于投影的分子特征地图用于CNN驱动的毒性预测.

Muhammad Zafar Irshad Khan¹, Jia-Nan Ren¹, Hong-Yu-Xiang Ye¹

¹College of Pharmaceutical Sciences, Zhejiang University, 866 Yuhangtang Rd., Hangzhou, 310058, Zhejiang, China.

Archives of toxicology

|December 8, 2025

概括

这项研究引入了一种新的投影方法,用于预测药物对脏的毒性. 这种方法将3D分子结构转换为2D地图,提高药物安全性预测模型的准确性.

关键词:

深度学习是一种深度学习.静电电位的电位可能是静电电位.毒性毒性毒性基于投影的模型.范德瓦尔斯相互作用

更多相关视频

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

相关实验视频

Last Updated: Jan 9, 2026

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

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

Published on: October 10, 2018

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

科学领域:

计算化学是一种计算化学.
毒理学毒理学毒理学
药物开发药物开发

背景情况:

预测毒剂对于药物开发至关重要,因为毒性风险.
传统的分子描述器往往缺乏用于准确预测毒性的空间和电子细节.

研究的目的:

开发一种新的基于投影的方法,用于增强毒性预测.
通过3D到2D分子结构转换来改善特征表示和深度学习模型性能.

主要方法:

利用Mollweide和等直角投影将3D分子几何形状转换为2D地图.
包含基于原子,静电和范德瓦尔斯 (vdW) 的投影来表示分子性质.
开发了一个卷积神经网络 (CNN) 模型用于预测.

主要成果:

莫尔韦德预测实现了83%的预测准确度和0.86的AUC,优于其他方法.
基于投影的地图通过可视化原子位置,电荷分布和固态潜力来增强分子模式识别.
该模型的可靠性通过独立测试,交叉验证和与传统描述模型的比较来证实.

结论:

基于投影的分子表示显示了有效的毒性查的巨大潜力.
这种方法在毒理学预测方面取得了进展,并有助于提高药物安全性.