Mixture Model Analysis of DNA Microarray Images.pdfVIP

IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. ??, NO. ??, ?? 2005 1 Mixture Model Analysis of DNA Microarray Images K. Blekas, N. P. Galatsanos, A. Likas and I. E. Lagaris Abstract— In this paper we propose a new methodology for analysis of microarray images. First a new gridding algorithm is proposed for determining the individual spots and their borders. Then, a Gaussian Mixture Model (GMM) approach is presented for the analysis of the individual spot images. The main advantages of the proposed methodology are modeling flexibility and adaptability to the data, which are well known strengths of GMM. The maximum likelihood (ML) and maximum a posteriori (MAP) approaches are used to estimate the GMM parameters via the Expectation Maximization (EM) algorithm. The proposed approach has the ability to detect and compensate for artifacts that might occur in microarray images. This is accomplished by a model-based criterion that selects the number of the mixture components. We present numerical experiments with artificial and real data where we compare the proposed approach with previous ones and existing software tools for microarray image analysis and demonstrate its advantages. Keywords: DNA microarray image analysis, microarray gridding, Gaussian mixture models, maximum likelihood, maximum a posteriori, Markov random fields, Expectation- Maximization algorithm, cross-validated likelihood I. INTRODUCTION DNA microarrays [1] are used to measure the expression levels of thousands of genes simultaneously over different time points and different experiments. In microarray exper- iments, the two mRNA samples to be compared are reverse transcripted into cDNA and then hybridized simultaneously to a glass slide. The end product of a comparative hybridization experiment is a scanned array image, where the measured intensities from the two fluorescent reporters have been col- ored red (R) and green (G) and overlaid. This array image is structured with intensity spots located on a gr