With the increasing availability of text information related to biology, including Medline abstracts and full-text journal articles, the field of biomedical text mining has been rapidly maturing. It is concerned with using techniques from natural language processing, information extraction and information retrieval to automate knowledge discovery from biomedical text.

  The BioLINK SIG meeting has been regularly held in association with the ISMB conference since 2001, focusing on the development and application of resources and tools for biomedical text mining. The SIG is interdisciplinary in nature, and brings together researchers applying natural language processing, text mining, information extraction and retrieval in the biomedical domain, with scientists from bioinformatics and biology.

  This year the SIG will go beyond text to take into account the analysis of images and figures in scientific publications because of their critical information content. Furthermore, we will include a session about the future of scientific publishing, and the impact of information extraction methods (be they based on text or on images) on producers and consumers of scientific information. The SIG will feature a special session (on Monday), including presentations and discussions by representatives from scientific journals and community members. This session is jointly organized with PLoS, and is open to all ISMB attendees.

  The meeting includes invited talks, presentations of peer-reviewed contributed papers, reports from recent evaluations and workshops, as well as a poster session. The SIG solicits papers that discuss current biological image- and text-related needs, the challenges of meeting them, and the tools that may help address them. Specific topics include: biological image analysis and its relationship to biomedical text mining, application of text-mining tools to biomedical research, automated indexing of the biomedical literature, generation of structured digital abstracts, new evaluation measures to measure utility and usability of text mining tools integrated into the biologists. workflow, as well as new tools and applications, and future directions in biomedical text mining.

  We anticipate a productive workshop that will facilitate discussion and exchange of ideas by bringing together multiple communities: the users of text mining tools, including curators of biological databases, bench scientists and bioinformaticians; and the researchers applying natural language processing, ontologies, text mining, image analysis, information extraction and retrieval to problems in the biomedical domain.

 Information about last year's meeting,can be found on the BioLINK08 web site.

Page last updated by Andrew Wong