Spectral clustering gene ontology terms to group genes by function

With the invention of biotechnological high throughput methods like DNA microarrays, biologists are capable of producing huge amounts of data. During the analysis of such data the need for a grouping of the genes according to their biological function arises. In this paper, we propose a method that provides such a grouping. As functional information, we use Gene Ontology terms. Our method clusters all GO terms present in a data set using a Spectral Clustering method. Then, mapping the genes back to their annotation, genes can be associated to one or more clusters of defined biological processes. We show that our Spectral Clustering method is capable of finding clusters with high inner cluster similarity.