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 data-sets,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 https://github.com/CSUBioGroup/SSRE.

Objective To explore the effects of outpatient and inpatient self-management education in patients with type 2 diabetes and analyze the weak spot of diabetes mellitus health education. Methods We selected in a 1∶1 rate 110 newly diagnosed patients with diabetes mellitus in outpatient and endocrine ward from March 2013 to October 2013. Out-patients selectively received systematic outpatient education related to diabetes as one-to-one guidance by outpatient education nurses. Inpatients received diabetes self-management education as alternate one-to-one guidance and lectures undertaken by primary nurses and education nurses. Results One month after interventions, the compliance of diet, exercise, medications, and blood glucose monitoring in out-patients were all lower than that in inpatients (P <0. 01). Conclusions The effects of inpatient′s self-management education are better than outpatient education. Managers should analyze the weak spot of outpatient diabetes mellitus health education, and explore the effective methods of blood glucose monitoring education to improve patients′blood glucose monitoring compliance.