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

Spatially Separated Activation-Conversion Nitride Catalysts for Accelerated Ammonia Synthesis.

ACS applied materials & interfaces·2026

Same author

Direct Assembly of Magnetically Tunable Nanoallotropes as Photonic Inks.

ACS nano·2026

Same author

Light-Driven Coupled Upcycling of Polyethylene and CO<sub>2</sub> to Aromatics over Zeolite-Ni/CeO<sub>2</sub> Composite Catalysts.

ChemSusChem·2026

Same author

Aging transforms marine microplastics into reactive interfaces with environmental consequences.

iScience·2026

Same author

A Liposomal Delivery System of Blueberry Anthocyanins Ameliorates Corneal Laser Injury.

Biomolecules·2026

Same author

New hybrid iridoid glycoside oligomers from Scabiosa comosa with anti-cholestasis potential.

Bioorganic chemistry·2026

Search research articles

相关实验视频

Updated: Jun 28, 2025

Detection of Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology

Detection of Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology

Published on: March 24, 2015

ACP-DRL:一种基于深度表示学习的抗癌识别方法.

Xiaofang Xu¹, Chaoran Li¹, Xinpu Yuan²

¹State Key Laboratory of Medical Proteomics, Beijing Proteome Research Center, National Center for Protein Sciences(Beijing), Beijing Institute of Lifeomics, Beijing, China.

Frontiers in genetics

|April 24, 2024

概括

此摘要是机器生成的。

研究人员开发了ACP-DRL,这是一种用于识别抗癌 (ACP) 的新型深度学习方法. 这种方法通过提高发现潜在抗癌疗法的效率和降低成本来增强癌症研究.

关键词:

贝尔特 (BERT) 公司抗癌是一种抗癌.深度表示学习学习 (deep representation learning) 是一种学习方式.语言模型语言模型预先培训的培训前培训自主监督的自我监督

更多相关视频

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Peptide Scanning-assisted Identification of a Monoclonal Antibody-recognized Linear B-cell Epitope

Peptide Scanning-assisted Identification of a Monoclonal Antibody-recognized Linear B-cell Epitope

Published on: March 24, 2017

相关实验视频

Last Updated: Jun 28, 2025

Detection of Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology

Detection of Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology

Published on: March 24, 2015

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Peptide Scanning-assisted Identification of a Monoclonal Antibody-recognized Linear B-cell Epitope

Peptide Scanning-assisted Identification of a Monoclonal Antibody-recognized Linear B-cell Epitope

Published on: March 24, 2017

科学领域:

生物化学生物化学
计算生物学计算生物学
在瘤学瘤学.

背景情况:

癌症是全球死亡的主要原因,需要新的治疗策略.
抗癌 (ACP) 在抑制瘤生长方面表现有前途,副作用比传统治疗更少.
目前通过湿实验室实验来识别非洲和中东的方法是低效和昂贵的.

研究的目的:

引入ACP-DRL,一种基于深度表示学习的方法,用于准确有效地识别抗癌.
克服传统湿实验室识别方法的局限性.
借助先进的计算技术,加速发现新型的非洲国家和地区.

主要方法:

蛋白质语言模型与域内进一步预培训的整合,以增强代表性学习.
利用双向长短期记忆 (BiLSTM) 网络来提取基于序列的氨基酸特征.
开发一个深度学习框架 (ACP-DRL) 用于ACP认可,独立于序列长度和手动特征工程.

主要成果:

与现有的非洲国家/地区识别方法相比,ACP-DRL表现优越.
该模型有效地从氨基酸序列中提取相关特征,无需人工干预.
在识别潜在的抗癌上获得了高精度,减少了实验成本和时间.

结论:

在计算上,ACP-DRL为识别抗癌提供了一种高效且具有成本效益的替代方案.
蛋白质语言模型和深度学习的整合代表了癌症计算药物发现的重大进步.
这种方法有助于加速发现和开发新的基于的癌症治疗方法.