Evaluating Graph Kernel Methods for Relation Discovery in GO-annotated Clusters

The application of various clustering techniques for largescale gene-expression measurement experiments is an 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) [1]. If different cluster sets 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 for this step: 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 [2], in this paper we present and discuss further results about its applicability and its performance, always in the context of the well known Spellman's Yeast Cell Cycle dataset [3].