Gene Ontology-Based Annotation Analysis and Categorization of Metabolic Pathways

Functional characterizations of pathways provide new opportunities in defining, understanding, and comparing existing biological pathways, and in helping discover new ones in different organisms. In this paper, we present and evaluate computational techniques for categorizing pathways, based upon the Gene Ontology (GO) annotations of enzymes within metabolic pathways. Our approach is to use the notion of functionality templates, GO-functional graphs of pathways. Pathway categorization is then achieved through learning models built on different characteristics of functionality templates. We have experimentally evaluated the accuracy of automated pathway categorization with respect to different learning models and their parameters. Using KEGG metabolic pathways, the pathway categorization tool reaches to 90% and higher accuracy.