DNA Microarray Data Clustering by Hidden Markov Models and Bayesian Information Criterion
In this study, the microarray data under diauxic shift condition of Saccharomyces Cerevisiae was considered. The objective of this study is to propose another strategy of cluster analysis for gene expression levels under time-series conditions. The continuous hidden markov model was newly proposed to select genes which significantly expressed. Then, new approach of hidden markov model clustering was proposed to include Bayesian information criterion technique which helped to determine the size of model. The result of this technique provided a good quality of clustering from gene expression patterns.
KeywordsHide Markov Model Bayesian Information Criterion Mixture Gaussian Model Hide Markov Model Model Observation Probability
Unable to display preview. Download preview PDF.
- 1.Rabiner, L.B.: A tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE 77(2) (1986)Google Scholar
- 2.Schliep, A.: Using hidden Markov models to analyze gene expression time course data. Bioinformatics 19(suppl. 1), i255–i263 (2003)Google Scholar
- 3.Schliep, A.: Robust inference of groups in gene expression time-courses using mixtures of HMMs. Bioinformatics 20(suppl. 1), i283–i289 (2004)Google Scholar
- 4.Li, C.: A Bayesian Approach to Temporal Data Clustering using Hidden Markov Models. In: International Conference on Machine Learning (ICML 2000), Stanford, California, pp. 543–550 (2000)Google Scholar
- 5.Eisen Lab.: Public microarray expression data for yeast Saccharomyces cerevisiae [Online], available http://rana.lbl.gov/EisenData.htm