SSRE: Cell Type Detection Based on Sparse Subspace Representation and Similarity Enhancement

Zhenlan Liang, Min Li, Ruiqing Zheng, Yu Tian, Xuhua Yan, Jin Chen, Fang Xiang Wu, Jianxin Wang

Research output: Contribution to journalArticlepeer-review

22 Scopus citations


Accurate identification of cell types from single-cell RNA sequencing (scRNA-seq) data plays a critical role in a variety of scRNA-seq analysis studies. This task corresponds to solving an unsupervised clustering problem, in which the similarity measurement between cells affects the result significantly. Although many approaches for cell type identification have been proposed, the accuracy still needs to be improved. In this study, we proposed a novel single-cell clustering framework based on similarity learning, called SSRE. SSRE models the relationships between cells based on subspace assumption, and generates a sparse representation of the cell-to-cell similarity. The sparse representation retains the most similar neighbors for each cell. Besides, three classical pairwise similarities are incorporated with a gene selection and enhancement strategy to further improve the effectiveness of SSRE. Tested on ten real scRNA-seq datasets and five simulated datasets, SSRE achieved the superior performance in most cases compared to several state-of-the-art single-cell clustering methods. In addition, SSRE can be extended to visualization of scRNA-seq data and identification of differentially expressed genes. The matlab and python implementations of SSRE are available at

Original languageEnglish
Pages (from-to)282-291
Number of pages10
JournalGenomics, Proteomics and Bioinformatics
Issue number2
StatePublished - Apr 2021

Bibliographical note

Publisher Copyright:
© 2021 Beijing Institute of Genomics


  • Cell type
  • Clustering
  • Enhancement
  • Similarity learning
  • Single-cell RNA sequencing

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Genetics
  • Computational Mathematics


Dive into the research topics of 'SSRE: Cell Type Detection Based on Sparse Subspace Representation and Similarity Enhancement'. Together they form a unique fingerprint.

Cite this