Hidden markov of factor analyzers for biclustering of microarray time course data in multiple conditions.

A challenging task in time course microarray data is to discover groups of genes that show homogeneous temporal expression patterns when time course experiments are collected in multiple biological conditions. In such case, an appealing goal would be related to discover local structures composed by sets of genes that show homogeneous expression patterns across subsets of biological conditions which also capture the history of the gene's and condition's dynamic behavior across time. To address this, at each time point one could apply any of biclustering methods for identifying differentially expressed genes across biological conditions. However, a consideration of each time point in isolation can be inefficient, because it does not use the information contained in the dependence structure of the time course data. Our proposal is an extension of the Hidden Markov of factor analyzers model allowing for simultaneous clustering of genes and biological conditions. The proposed model is rathe