A major challenge of microarray data analysis is to discover local structures composed by sets of genes that show coherent expression patterns across subsets of conditions. In this work, we present an extension of the finite mixture of factor analyzers model (MFA) for simultaneous clustering of genes and conditions. The proposed model is rather flexible since it models the density of high-dimensional data assuming a mixture of Gaussian distributions with a particular component-specific covariance structure. Specifically, a binary and row stochastic matrix representing tissue membership is used in the component-specific covariance matrix, while the traditional mixture approach is used to allow the gene clustering. An AECM algorithm is proposed for parameter estimation, and the performance of the proposed model is discussed through the analysis of a benchmark data set.
Scheda prodotto non validato
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo
|Titolo:||Biclustering of microarray data|
|Data di pubblicazione:||2007|
|Appartiene alla tipologia:||02a Capitolo o Articolo|