Creating Metabolic Network Models using Text Mining and Expert Knowledge

This paper describes the initial development of a tool that helps find and visualize metabolic networks. The tool is written in Java™ and consists of two parts. The first part is a text-mining tool that pulls out potential metabolic relationships from the existing database PubMed. These relationships are then reviewed by a domain expert and added to an existing network model. The result is visualized using a graph display module. The basic metabolic or regulatory flow is illustrated using a binary network. An example from the regulatory network for the plant hormone gibberellin shows how this tool operates.