相关实验视频

Updated: Jul 15, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

使用具有大规模引用的多个对手域适应网络进行单细胞赋值

Pengfei Ren¹, Xiaoying Shi², Zhiguang Yu³

¹Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration of Ministry of Education, Department of Orthopedics, Tongji Hospital, School of Life Science and Technology, Tongji University, Shanghai 200092, China; Frontier Science Center for Stem Cells, School of Life Sciences and Technology, Tongji University, Shanghai 200092, China; Center for Quantitative Biology, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, 100084, China; Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, 100084, China.

Cell reports methods

|September 26, 2023

概括

SELINA是一个新的框架,用于从单细胞RNA测序数据中准确地对人类细胞类型进行注释. 它克服了批量效应和罕见细胞类型等挑战,提供了一个强大而全面的参考地图.

科学领域:

基因组学就是基因组学.
生物信息学是一种生物信息学.
计算生物学计算生物学

背景情况:

单细胞RNA测序 (scRNA-seq) 产生了用于细胞群体表征的大量数据集.
准确的细胞类型注释受到不一致的公开引用,批量效应和罕见细胞类型的识别的阻碍.

研究的目的:

开发一个集成和自动的框架,SELINA (单细胞身份导航器),用于强大的人类细胞类型注释.
为scRNA-seq数据创建一个全面和统一的参考地图.

主要方法:

塞琳娜利用一个预先整理的参考地图,包含230种人类细胞类型的170万个细胞.
采用多个对手域调整网络来缓解批量效应.
包含用于罕见细胞类型注释的合成少数超采样和用于数据拟合的自动编码器.

主要成果:

塞琳娜在各种各样的人体组织中表现出强大而卓越的性能.
在各种疾病背景下实现了细胞类型的准确注释.
该框架成功地整合和协调了一个大规模的参考地图.

结论:

塞琳娜为人类scRNA-seq数据注释提供了一个全面的解决方案.
该框架可作为Python和R包提供,以促进更广泛的采用.
在复杂的生物数据集中,SELINA提高了细胞类型识别的可靠性和准确性.

关键词:

CP:系统生物学系统生物学细胞类型预测预测深度学习是一种深度学习.域名适应域名适应预先训练的模型模型.参考地图是参考地图.一个单细胞RNA测序.

更多相关视频

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关概念视频

Cell Adhesion Molecules - Types and Functions

Cell Adhesion Molecules - Types and Functions

Cell adhesion molecules (CAMs) are pivotal to multicellularity and the coordinated functioning of tissues and organ systems. They enable physical interactions between cells and provide mechanical strength to tissues. They also function as receptors for signal transmission across the plasma membrane. The CAMs are broadly classified into four families - integrins, cadherins, selectins, and immunoglobulin-like CAMs (IgCAMs).
CAM Families
The Integrin family of proteins is primarily involved...

Cell Adhesion in Plants

Cell Adhesion in Plants

Plants have rigid cell walls that are made up of cell wall polysaccharides that mediate cell-cell adhesion. The primary cell walls of plants consist of two independent and interacting polysaccharide networks: a pectin matrix that embeds the second network comprising cellulose and hemicelluloses.
Pectins are complex heteropolymers mainly composed of negatively-charged α-D-glucopyranosyl uronic acid and some neutral glycosyl residues such as α-L-rhamnopyranose, α-L-arabinofuranose,...