An application of kernel methods to gene cluster temporal meta-analysis

The application of various clustering techniques for large-scale gene-expression measurement experiments is a well-established method in bioinformatics. Clustering is also usually accompanied by functional characterization of gene sets by assessing statistical enrichments of structured vocabularies, such as the gene ontology (GO) (2006). If different clusters are generated for correlated experiments, a machine learning step termed cluster meta-analysis may be performed, in order to discover relations among the components of such sets. Several approaches have been proposed: in particular, kernel methods may be used to exploit the graphical structure of typical ontologies such as GO. Following up the formulation of such approach by Merico, Zoppis, et al (2007), in this paper we discuss, from an information-theoretic point of view, further results about its applicability and its performance.