Text mining from biological literature is emerging as one of the main issues in bioinformatics research. In the past 25 years, a tremendous effort by the biomedical research community has led to more than 10 million publications available in the PubMed database. Half a million new articles get published every year, that is about 1000 articles a day. An essential task of Information Extraction is therefore to retrieve and process this huge amount of information.

Moreover, combining the complete scientific literature opens up new perspectives, hidden to the single researcher. A clear example offers the interaction between proteins. A single article may report the interaction of protein A with protein B, and another article the interaction of protein B with C. By combining this kind of information from all articles, a complete network of protein interaction emerges. For these reasons, Information Extraction has become a powerful tool to make new discoveries in the molecular and biomedical area.

Hoffmann, R., Valencia, A. A gene network for navigating the literature. Nature Genetics 36, 664 (2004).
Hoffmann, R., Valencia, A. Implementing the iHOP concept for navigation of biomedical literature. Bioinformatics 21(suppl. 2), ii252-ii258 (2005).
Hoffmann, R., Krallinger, M., Andres, E, Tamames, J., Blaschke, C., Valencia, A. Text mining for metabolic pathways, signaling cascades, and protein networks. A. Sci STKE 283, 21 (2005) 16204114