An Adaptive Sparse Subspace Clustering for Cell Type Identification.

Ruiqing Zheng,Chen Cao,Xiang Chen,Yu Tian,Zhenlan Liang,Min Li

doi:10.3389/fgene.2020.00407

Abstract

The rapid development of single-cell transcriptome sequencing technology has provided us with a cell-level perspective to study biological problems. Identification of cell types is one of the fundamental issues in computational analysis of single-cell data. Due to the large amount of noise from single-cell technologies and high dimension of expression profiles, traditional clustering methods are not so applicable to solve it. To address the problem, we have designed an adaptive sparse subspace clustering method, called AdaptiveSSC, to identify cell types. AdaptiveSSC is based on the assumption that the expression of cells with the same type lies in the same subspace; one cell can be expressed as a linear combination of the other cells. Moreover, it uses a data-driven adaptive sparse constraint to construct the similarity matrix. The comparison results of 10 scRNA-seq datasets show that AdaptiveSSC outperforms original subspace clustering and other state-of-art methods in most cases. Moreover, the learned similarity matrix can also be integrated with a modified t-SNE to obtain an improved visualization result.

Highlights

Cells are the basic functional unit all organisms are made of and play significant roles in the different stages of life
We proposed a subspace clustering with an adaptive sparse constraint, called AdaptiveSSC
A data-driven adaptive sparse strategy is applied to keep the locality of cells in the original dimension and decrease the sensitivity to the penalty factor

Summary

Introduction

Cells are the basic functional unit all organisms are made of and play significant roles in the different stages of life. Through various DNA and RNA sequencing data, researchers have a comprehensive and deep understanding of cell biology. Traditional sequencing data is obtained from bulks of cells, and these are composed of the mixed effect of numerous cells and ignore cell heterogeneity. These bulk-seq data will lead to deviations in downstream analysis if a specific type of cell is expected. Single-cell sequencing techniques have developed rapidly and make up the defect of bulk sequencing data. The single-cell sequencing technique cannot capture all cell information, it provides a great opportunity to reveal the characteristics of an individual cell

Methods

Results

Conclusion