Improved non-negative factorization in the analysis of gene expression data

In recent years, non-negative matrix factorization (NMF) has been widely used in the analysis of gene expression data. However the NMF algorithm has its limitations of little dithering during the iteration process when the initial values are chosen randomly. In this paper, data smoothing is introduced in the iteration to resolve the dithering problem. Both the traditional and the improved NMF algorithm are applied in the analysis of leukaemia microarray data. Experiment results show that both the accuracy and the stability can be significantly improved with the proposed algorithm.