Shape-output gene clustering for time series microarrays

Abstract

The identification of coexpressed genes is a challenging problem in microarray data analysis due to a very high number of genes and low number of samples normally available. This paper presents a shape-output clustering method which is engaged in the analysis of a real-world time series microarray data from the industrial microbiology area. The proposed approach uses the changes in gene expression levels to group genes based on their shape measured over time in several samples. Furthermore, these coexpression patterns are correlated with the measured outputs of production and growth available for each sample. Experiments are performed for time series microarray of a bacteria and an analysis from a biological perspective is carried out. The obtained results confirm the existence of relationships between output variables and gene expressions.