Using Text Mining for Understanding Insulin Signalling

In this paper we describe our efforts and experience in using a mix of e-Science and text mining technologies in the context of large scale integrative biology studies. Using insulin signaling as an application framework, we describe the service-based text mining infrastructure used for the project and present a number of text mining workflows for performing a number of common tasks encountered in integrative biology studies, including document categorization, and literature-based methods for the identification of gene-tissue interactions, for performing automated gene differentiation and scoring, and for automatically labeling gene groups.