Tumor Classification Using Non-negative Matrix Factorization

With the advent of DNA microarrys, it is now possible to use the microarry data for tumor classification. Yet previous works have not use the non-negative information of gene expression data for classification. In this paper, we propose a new method for tumor classification using gene expression data. In this method, we first extract new features of the gene expression data by virtue of non-negative matrix factorization (NMF) and its extension, i.e. sparse NMF (SNMF) then apply support vector machines (SVM) to classify the tumor samples using the extracted features. To better fit for classification aim, a new SNMF algorithm is also proposed.