Abstract

Lars Juhl Jensen
European Molecular Biology Laboratory (EMBL), Heidelberg, Germany

Biomedical literature mining (and why we really need Open Access)

The vast amount of biomedical abstracts available from a single source, Medline, has become an important breeding ground for the development of new methods for mining the scientific literature. Although, to most biologists, hands-on literature mining currently means a keyword search in PubMed, methods for extracting biomedical facts from the scientific literature have improved considerably, and the associated tools will likely soon be used in many laboratories to interpret large-scale experimental data sets. Owing to the increasing body of text, literature mining is also becoming useful for automatic hypothesis generation and thus for driving biological discovery. To realize the full potential of such methods, however, they will need access to full-text papers, rather than just the abstracts, for which reason open-access publishing will play an important role for the future of literature mining.