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

Waste print paper generated cellulose-chitosan composite film for cell attachment application.

International journal of biological macromolecules·2026

Same author

OMNI: Optimized Multiview Network Integration with Heterogeneous Graph Attention for Biomedical Interaction Prediction.

Journal of chemical information and modeling·2026

Same author

Hormonal crosstalk in endophyte-mediated biotic stress resilience: from colonization to defence for sustainable agriculture.

Plant physiology and biochemistry : PPB·2026

Same author

M-Tune: imbalanced data handling in machine learning by tuning the decision threshold.

Molecular diversity·2026

Same author

Insights on Hetero-Nanostructured CuO-Cu<sub>x</sub>Ce<sub>y</sub>O<sub>z</sub>/C Catalyzed Oxygen Reduction Reaction.

Chemistry, an Asian journal·2026

Same author

Multi-representation machine learning approaches for screening aurora kinases A & B inhibitors and insights from structural alerts.

Journal of molecular graphics & modelling·2026

Search research articles

相关实验视频

Updated: Sep 16, 2025

Studying Triple Negative Breast Cancer Using Orthotopic Breast Cancer Model

Studying Triple Negative Breast Cancer Using Orthotopic Breast Cancer Model

Published on: March 20, 2020

探索基于图形的模型,用于预测抗三阴性乳腺癌的活性化合物.

Hridoy Jyoti Mahanta^1,2, Amarjeet Boruah³, Bikram Phukan⁴

¹Advanced Computation and Data Sciences Division, CSIR-North East Institute of Science and Technology, Jorhat, 785006, Assam, India. hridoy@neist.res.in.

Molecular diversity

|July 9, 2025

概括

研究人员开发了人工智能模型来预测新的三阴性乳腺癌 (TNBC) 候选药物. 最好的模型确定了有前途的化合物,在FDA批准的药物上实现了高精度,加速了TNBC治疗发现.

关键词:

人工智能的人工智能是人工智能.可以解释的可解释性.基于图形的建模.自然产品是天然产品.三阴性乳腺癌是三阴性乳腺癌.

更多相关视频

Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases

Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases

Published on: May 17, 2019

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

相关实验视频

Last Updated: Sep 16, 2025

Studying Triple Negative Breast Cancer Using Orthotopic Breast Cancer Model

Studying Triple Negative Breast Cancer Using Orthotopic Breast Cancer Model

Published on: March 20, 2020

Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases

Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases

Published on: May 17, 2019

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

科学领域:

在瘤学瘤学.
计算生物学计算生物学
药物发现药物发现药物发现

背景情况:

三阴性乳腺癌 (TNBC) 是一种具有有限治疗选择的侵袭性亚型.
在TNBC中缺少HER2,孕激素和雌激素受体,需要新的治疗策略.
人工智能 (AI) 和机器学习 (ML) 加快生物数据分析和治疗结果预测.

研究的目的:

开发和验证人工智能驱动的计算模型,用于对TNBC预测活性化合物.
确定关键的结构碎片,负责化合物对TNBC细胞的抑制活性.
评估模型在识别潜在的TNBC候选药物的稳定性.

主要方法:

策划了来自三个细胞系的756种突变型化合物的数据集.
开发了四个基于图形的AI/ML模型,用于预测TNBC活性化合物.
采用了分层嵌套十倍交叉验证和Optuna模型优化和验证框架.
利用可解释性技术来解释模型预测和识别关键结构特征.

主要成果:

实现了预测准确度,AUC值从0.65到0.82不等,消息传递神经网络 (MPNN) 模型表现出卓越的性能.
确定了与细胞抑制和模型预测相关的关键结构碎片.
使用FDA批准的药物的外部验证表明预测准确度从66%到97%.

结论:

开发的AI模型有效地预测了对TNBC细胞具有潜在抑制活性的化合物.
该MPNN模型显示显著的希望加速新型TNBC候选药物的发现.
可解释性技术为化合物活性的结构基础提供了洞察力,有助于药物设计.