A Semiparametric Bayesian Method of Clustering Genes Using Time-Series of Expression Profiles
An increasing number of microarray experiments look at expression levels of genes over the course of several points in time. In this article, we present two models for clustering such time series of expression profiles. We use nonparametric Bayesian methods which make the models robust to misspecifications and provide a natural framework for clustering of the genes through the use of Dirichlet process priors. Unlike other clustering techniques, the resulting number of clusters is completely data driven. We demonstrate the effectiveness of our methodology using simulation studies with artificial data as well as through an application to a real data set.
KeywordsDirichlet Process Heteroscedastic Model Markov Chain Monte Carlo Procedure Dirichlet Process Mixture Model Time Series Gene Expression
Unable to display preview. Download preview PDF.
- 3.Dahl D (2006) Model-based clustering for expression data via a Dirichlet process mixture model. In: Bayesian inference for gene expression and proteomics. Cambridge University Press, Cambridge, pp 201–218Google Scholar
- 13.Singh R, Palmer N, Gifford D, Berger B, Bar-Joseph Z (2005) Active learning for sampling in time-series experiments with application to gene expression analysis. In: ICML ’05: proceedings of the 22nd international conference on Machine learning. ACM, New York, pp 832–839Google Scholar
- 14.Spellman PT, Sherlock G, Zhang MQ, Iyer VR, Anders K, Eisen MB, Botstein D, Futcher B (1998) Comprehensive identification of cell cycle-regulated genes of the yeast saccharomyces cervisiae by microarray hybridization. Mol Biol Cell 9(12):3273–3297Google Scholar