SinNLRR: a robust subspace clustering method for cell type detection by nonnegative and low rank representation

• Published in: Bioinformatics (Oxford, England) England), 2019-03
• Main Authors: Zheng, Ruiqing, Li, Min, Liang, Zhenlan, Wu, Fang-Xiang, Pan, Yi, Wang, Jianxin
• Format: Article
• Language: English
• ISSN: 1367-4811

The development of single-cell RNA-sequencing (scRNA-seq) provides a new perspective to study biological problems at the single-cell level. One of the key issues in scRNA-seq analysis is to resolve the heterogeneity and diversity of cells, which is to cluster the cells into several groups. However, many existing clustering methods are designed to analyze bulk RNA-seq data, it is urgent to develop the new scRNA-seq clustering methods. Moreover, the high noise in scRNA-seq data also brings a lot of challenges to computational methods. In this study, we propose a novel scRNA-seq cell type detection method based on similarity learning, called SinNLRR. The method is motivated by the self-expression of the cells with the same group. Specifically, we impose the nonnegative and low rank structure on the similarity matrix. We apply ADMM to solve the optimization problem and propose an adaptive penalty selection method to avoid the sensitivity to the parameters. The learned similarity matrix could be incorporated with spectral clustering, t-SNE for visualization and Laplace score for prioritizing gene markers. In contrast to other scRNA-seq clustering methods, our method achieves more robust and accurate results on different datasets. Our Matlab implementation of SinNLRR is available at https://github.com/zrq0123/SinNLRR. Supplementary data are available at Bioinformatics online.