PROJECT TITLE :

A Class-Information-Based Sparse Component Analysis Method to Identify Differentially Expressed Genes on RNA-Seq Data

ABSTRACT:

With the development of deep sequencing technologies, many RNA-Seq information have been generated. Researchers have proposed many strategies based mostly on the sparse theory to identify the differentially expressed genes from these data. In order to improve the performance of sparse principal element analysis, in this paper, we have a tendency to propose a novel class-data-based sparse part analysis (CISCA) method which introduces the category information via a complete scatter matrix. Initial, CISCA normalizes the RNA-Seq information by employing a Poisson model to obtain their differential sections. Second, the whole scatter matrix is gotten by combining the between-class and at intervals-category scatter matrices. Third, we tend to decompose the whole scatter matrix by using singular price decomposition and construct a new knowledge matrix by using singular values and left singular vectors. Then, aiming at obtaining sparse elements, CISCA decomposes the constructed information matrix by solving an optimization downside with sparse constraints on loading vectors. Finally, the differentially expressed genes are identified by using the sparse loading vectors. The results on simulation and real RNA-Seq information demonstrate that our technique is effective and appropriate for analyzing these knowledge.