Clustering of microarray data using finite mixture models

The study of the molecular variation among diseases is rapidly growing thanks to the development of microarray-based technologies. In fact, such technologies allow us to simultaneously measure thousands of gene expression levels from biological tissue samples. A major task in this context is the classification of samples to improve the diagnoses of patients and, therefore, the quality of treatments. We discuss a model-based approach which allows both to reduce the dimension of genes and to cluster the tissue samples, simultaneously. We adopt statistical techniques formulated by Ghahramani and Hinton (1996) and Rocci and Vichi (2002). The performance of the proposed models is illustrated on a well known data set in microarray literature: the leukaemia data, containing classes that are well known to be easy separable (Golub et al., 1999).