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

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

Intranasal delivery of a polymeric nanoparticle subunit vaccine for the induction of protective immunity against respiratory syncytial virus.

Frontiers in immunology·2026
Same author

SMART (Shuimu Automated Reconstruction Technology): An Integrated Computational Platform for Streamlining Cryo-Electron Microscopy Workflow.

Journal of visualized experiments : JoVE·2026
Same author

Complementary nonlinear optics for polarimetric computing in tellurium.

Nature communications·2026
Same author

Challenging pacemaker implantation in a child with aggressive atrial standstill caused by compound heterozygous <i>SCN5A</i> variants.

Cardiology in the young·2026
Same author

Topical application of low-concentration IL-2 enhances Treg's function and plays anti-inflammatory roles in experimental dry eye disease.

The ocular surface·2026
Same author

Karyopherin Subunit Alpha 3 Drives Temozolomide Resistance in Glioblastoma by Upregulating MGMT and Activating STAT3 to Sustain Glioma Stem Cells.

Cell biology international·2026

相关实验视频

Updated: May 10, 2025

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

434

scRSSL:剩余的半监督学习与深度生成模型自动识别细胞类型.

Yanru Gao1, Hongyu Duan2, Fanhao Meng1

  • 1School of Computer Science, Qufu Normal University, Rizhao, China.

IET systems biology
|April 22, 2025
PubMed
概括

这项研究引入了一种新的半监督深度学习模型,scRSSL,用于在单细胞转录学中准确识别细胞类型. 它有效地处理不平衡和稀疏性等数据挑战,提高细胞分类准确度.

关键词:
生物信息学是一种生物信息学.深度生成模型深度生成模型深度学习是一种深度学习.半监督学习 半监督学习一个单细胞的单细胞.

更多相关视频

Single-cell RNA-Seq of Defined Subsets of Retinal Ganglion Cells
11:26

Single-cell RNA-Seq of Defined Subsets of Retinal Ganglion Cells

Published on: May 22, 2017

13.7K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.2K

相关实验视频

Last Updated: May 10, 2025

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

434
Single-cell RNA-Seq of Defined Subsets of Retinal Ganglion Cells
11:26

Single-cell RNA-Seq of Defined Subsets of Retinal Ganglion Cells

Published on: May 22, 2017

13.7K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.2K

科学领域:

  • 计算生物学 计算生物学
  • 基因组学就是基因组学.
  • 生物信息学是一种生物信息学.

背景情况:

  • 单细胞测序 (scRNA-seq) 可进行细胞异质性研究.
  • 细胞类型识别在单细胞转录组学中至关重要.
  • 现有的方法在scRNA-seq数据中的高维度,稀疏性和样本不平衡方面存在困难.

研究的目的:

  • 在具有挑战性的单细胞数据集中开发一种可靠的细胞类型识别方法.
  • 为了解决传统细胞类型识别方法的局限性.
  • 为了利用半监督式学习来准确的细胞分类,使用有限的标签.

主要方法:

  • 提出了基于半监督学习 (scRSSL) 的深度残留生成模型.
  • 在半监督生成模型中集成剩余网络.
  • 利用剩余神经网络进行细胞类型推断和局部特征提取.
  • 使用半监督学习来管理样本不平衡并利用有限的细胞标签.

主要成果:

  • scRSSL模型展示了高维度,稀疏性和样本不平衡的有效处理.
  • 实现了单个细胞类型的自动和准确预测,即使使用最小的标记数据.
  • 实验结果显示,与现有的细胞类型识别方法相比,其性能优越.

结论:

  • scRSSL为单细胞转录学中的细胞类型识别提供了先进的解决方案.
  • 该模型的半监督方法提高了复杂数据集的准确性和稳定性.
  • 这种方法为分析细胞异质性提供了有价值的工具.