scRECL:用于scRNA-seq数据聚类分析的对比学习的代表集合.
Yixiang Huang1, Hao Jiang1, Wai-Ki Ching2
1Department of Information and Computing Sciences, School of Mathematics, Renmin University of China, No. 59 Zhongguancun Street, Haidian District, Beijing 100872, China.
我们介绍了scRECL,这是一个新的对比集体学习方法,用于强大的单细胞RNA测序 (scRNA-seq) 数据集群. 这种方法通过提高深度学习模型中的算法稳定性来增强细胞异质性的分析.
科学领域:
- 计算生物学 计算生物学
- 基因组学就是基因组学.
- 机器学习 机器学习
背景情况:
- 单细胞转录组学提供了高分辨率的基因表达数据.
- 细胞聚类对于识别单细胞数据中的细胞异质性至关重要.
- 现有的scRNA-seq集群的深度学习方法对参数设置敏感.
研究的目的:
- 为单细胞RNA测序 (scRNA-seq) 数据集群开发一种强大的深度学习方法.
- 解决深度学习模型对参数设置的敏感性.
- 改进细胞异质性的分析.
主要方法:
- 提出了scRECL,一种对比集体学习方法.
- 利用在k-最近邻居分区上训练的语神经网络进行低维嵌入.
- 采用多重图表来进行代表性元素选择,以过噪音细胞.
主要成果:
- 实现了scRNA-seq数据的高效和有效的潜伏嵌入.
- 证明了细胞异质性的可靠分析.
- 成功地利用了复杂的scRNA-seq数据结构的深度学习.
结论:
- scRECL为scRNA-seq数据集群提供了一个强大的和有效的方法.
- 该方法增强了细胞异质性的识别.
- scRECL为单细胞数据分析提供了可靠的深度学习解决方案.
更多相关视频
10:41Leveraging CyVerse Resources for De Novo Comparative Transcriptomics of Underserved Non-model Organisms
Published on: May 9, 2017
07:35Author Spotlight: A Computational Pipeline for Analyzing Chimeric Noncoding RNA-Target RNA Interactions in High-Throughput Sequencing Data
Published on: December 1, 2023
相关概念视频
RNA-seq
Before the discovery of RNA-seq, microarray-based methods and Sanger sequencing were used for transcriptome analysis. However, while...
Sanger Sequencing
Multi-species Conserved Sequences
Although the genome of each species varies greatly from each other, a few sequences are highly conserved. Such conserved...
Cluster Sampling Method
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
Next-generation Sequencing
Next-Generation Sequencing Methods
Although all next-generation methods use different technologies, they all share a set of standard features....
Signal Sequences and Sorting Receptors
