Spectral clustering of single cells using Siamese nerual network combined with improved affinity matrix

doi:10.1093/bib/bbac113

CORC > 自动化研究所 > 中国科学院自动化研究所 > 国家专用集成电路设计工程技术研究中心 > 新型计算技术

	Spectral clustering of single cells using Siamese nerual network combined with improved affinity matrix
	Jiang, Hanjing 2; Huang, Yabing 3; Li, Qianpeng 1
刊名	BRIEFINGS IN BIOINFORMATICS
	2022-04-13
页码	12
关键词	scRNA-seq Sigmoid kernel Siamese CNN improved spectral clustering
ISSN号	1467-5463
DOI	10.1093/bib/bbac113
通讯作者	Huang, Yabing(ybhuangwhu@163.com)
英文摘要	Limitations of bulk sequencing techniques on cell heterogeneity and diversity analysis have been pushed with the development of single-cell RNA-sequencing (scRNA-seq). To detect clusters of cells is a key step in the analysis of scRNA-seq. However, the high-dimensionality of scRNA-seq data and the imbalances in the number of different subcellular types are ubiquitous in real scRNA-seq data sets, which poses a huge challenge to the single-cell-type detection.We propose a meta-learning-based model, SiaClust, which is the combination of Siamese Convolutional Neural Network (CNN) and improved spectral clustering, to achieve scRNA-seq cell type detection. To be specific, with the help of the constrained Sigmoid kernel, the raw high-dimensionality data is mapped to a low-dimensional space, and the Siamese CNN learns the differences between the cell types in the low-dimensional feature space. The similarity matrix learned by Siamese CNN is used in combination with improved spectral clustering and t-distribution Stochastic Neighbor Embedding (t-SNE) for visualization. SiaClust highlights the differences between cell types by comparing the similarity of the samples, whereas blurring the differences within the cell types is better in processing high-dimensional and imbalanced data. SiaClust significantly improves clustering accuracy by using data generated by nine different species and tissues through different scNA-seq protocols for extensive evaluation, as well as analogies to state-of-the-art single-cell clustering models. More importantly, SiaClust accurately locates the exact site of dropout gene, and is more flexible with data size and cell type.
资助项目	National Natural Science Foundation of China[62172171]
WOS关键词	CELLULAR HETEROGENEITY ; GENE-EXPRESSION ; EMBRYOS ; FATE
WOS研究方向	Biochemistry & Molecular Biology ; Mathematical & Computational Biology
语种	英语
出版者	OXFORD UNIV PRESS
WOS记录号	WOS:000785718100001
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48304]
专题	国家专用集成电路设计工程技术研究中心_新型计算技术
通讯作者	Huang, Yabing
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Huazhong Univ Sci & Technol, Inst Artificial Intelligence, Key Lab Image Informat Proc & Intelligent Control, Sch Artificial Intelligence & Automat,Educ Minist, Wuhan 430074, Peoples R China 3.Wuhan Univ, Dept Pathol, Renmin Hosp, Wuhan 430060, Peoples R China
推荐引用方式 GB/T 7714	Jiang, Hanjing,Huang, Yabing,Li, Qianpeng. Spectral clustering of single cells using Siamese nerual network combined with improved affinity matrix[J]. BRIEFINGS IN BIOINFORMATICS,2022:12.
APA	Jiang, Hanjing,Huang, Yabing,&Li, Qianpeng.(2022).Spectral clustering of single cells using Siamese nerual network combined with improved affinity matrix.BRIEFINGS IN BIOINFORMATICS,12.
MLA	Jiang, Hanjing,et al."Spectral clustering of single cells using Siamese nerual network combined with improved affinity matrix".BRIEFINGS IN BIOINFORMATICS (2022):12.