Co-clustering of single-cell RNA-seq data based on weighted non-negative matrix tri-factorization combined with consensus clustering

Single-cell RNA sequencing (scRNA-seq) has the ability to accurately identify cell types contained in tissues at single-cell resolution. However, the research of identifying imbalanced cell types using scRNA-seq data is still challenging. In this article, we propose scCO2, a method based on weighted non-negative matrix tri-factorization (NMTF) combined with Kmeans-based consensus clustering for the co-clustering of scRNA-seq data. Compared with several popular methods on six real scRNA-seq data with known cell types, scCO2 can achieve comparable or superior cell clustering performance to selected clustering methods. Through the case study on a real scRNA-seq dataset of the human pancreas, scCO2 could obtain good correspondence between gene clusters and cell clusters. Additionally, scCO2 also shows the ability to identify rare cell types. Moreover, by comparing the gene sets from gene clusters to existing known marker genes, we demonstrate that scCO2 has the potential to identify more underlying cell-type-specific genes, and the weights of genes learned by scCO2 could be used as the indicator of gene importance.