A convex multi-view low-rank sparse regression for feature selection and clustering

Many real-world problems involve multi-view high-dimension-small-sample-size data analysis, such as multi-omics data. The combination of multi-view databases is supposed to provide a better biological significance. However, the multi-view data always contain noise and outlying entries that result in inaccurate and unreliable. It has become an urgent need how to effectively analyze these data. We proposed a novel convex multi-view low-rank sparse regression (CMLSR) algorithm to do cluster and feature selection. The model was constructed by imposing L_2,1-norm and trace norm constraints on the regularization functions. It can diminish the impact of noises and outliers and produce more precise results. Clustering quality was determined by both sparse constraint and low-rank constraint. Finally, we selected characteristic genes based on the projection matrix. The method was used in TCGA multi-view genes expression data sets, annotated according to Gene Ontology (GO). In this paper, we demonstrated the effectiveness of the proposed algorithm through comparing it with the existing methods.