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

Understanding the determinants of public trust in the health care system in China: an analysis of a cross-sectional survey.

Journal of health services research & policy·2018
Same author

Adverse Childhood Experiences, Epigenetic Measures, and Obesity in Youth.

The Journal of pediatrics·2018
Same author

LncRNA UCA1 sponges miR-204-5p to promote migration, invasion and epithelial-mesenchymal transition of glioma cells via upregulation of ZEB1.

Pathology, research and practice·2018
Same author

International variations in trust in health care systems.

The International journal of health planning and management·2018
Same author

Toll-like receptor 9 negatively regulates pancreatic islet beta cell growth and function in a mouse model of type 1 diabetes.

Diabetologia·2018
Same author

Methylation in OTX2 and related genes, maltreatment, and depression in children.

Neuropsychopharmacology : official publication of the American College of Neuropsychopharmacology·2018

相关实验视频

Updated: Feb 24, 2026

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

755

来自语言模型的嵌入是单细胞数据分析的良好学习者.

Tianyu Liu1,2, Tianqi Chen2, Wangjie Zheng2

  • 1Interdepartmental Program in Computational Biology & Bioinformatics, Yale University, New Haven, CT 06511, USA.

Patterns (New York, N.Y.)
|February 23, 2026
PubMed
概括

scELMo利用大型语言模型 (LLM) 来分析单细胞数据,使细胞聚类,注释和扰动分析无需新模型训练. 这种方法为单细胞数据解释提供了一种资源高效的方法.

关键词:
基础模型的基础模型.在化处理分析分析.大型语言模型扰动分析是一种干扰分析.单细胞数据分析的数据分析.

更多相关视频

Single-cell RNA Sequencing of Fluorescently Labeled Mouse Neurons Using Manual Sorting and Double In Vitro Transcription with Absolute Counts Sequencing DIVA-Seq
07:49

Single-cell RNA Sequencing of Fluorescently Labeled Mouse Neurons Using Manual Sorting and Double In Vitro Transcription with Absolute Counts Sequencing DIVA-Seq

Published on: October 26, 2018

9.9K
Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

5.9K

相关实验视频

Last Updated: Feb 24, 2026

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

755
Single-cell RNA Sequencing of Fluorescently Labeled Mouse Neurons Using Manual Sorting and Double In Vitro Transcription with Absolute Counts Sequencing DIVA-Seq
07:49

Single-cell RNA Sequencing of Fluorescently Labeled Mouse Neurons Using Manual Sorting and Double In Vitro Transcription with Absolute Counts Sequencing DIVA-Seq

Published on: October 26, 2018

9.9K
Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

5.9K

科学领域:

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

背景情况:

  • 基础模型 (FMs) 对单细胞数据分析有希望,但它们的应用有所不同.
  • 分析复杂的单细胞数据需要先进的计算方法.

研究的目的:

  • 介绍 scELMo,一种使用大型语言模型 (LLM) 进行单细胞数据分析的新方法.
  • 在不需要新模型培训的情况下,展示scELMo在各种单细胞数据分析任务中的能力.

主要方法:

  • scELMo将LLM生成的元数据描述中的嵌入内容与原始单细胞数据集成在一起.
  • 采用零射击学习框架进行初始分析和微调框架进行高级任务.
  • 利用LLM生成元数据描述及其相应嵌入.

主要成果:

  • scELMo有效地执行细胞聚类,批量效应校正和细胞类型注释.
  • 微调框架可以分析复杂的任务,如处理和扰动建模.
  • 在不需要培训新模型的情况下实现这些结果.

结论:

  • scELMo通过使用LLMs提供了一种多功能和高效的工具,用于单细胞数据分析.
  • 该方法提供了一个更轻的结构,更低的资源需求,为未来的研究提供了一个有希望的方向.
  • 促进高级分析,如扰动建模和治疗效果预测.