LFE

Lehre

Forschung

Kontakt

Intern

Webservices
English version


Forschungs-
projekte


ExpressionLab@LMU

NetworkLab@LMU

Proteinstrukturen

Protein Interaktionen

Textmining

Algorithmische Bioinformatik


Publikationen

Arbeitsgebiet "Textmining"

Textmining spielt in der Bioinformatik eine wichtige Rolle, da ein Grossteil des biologischen Wissens nur in Form von Text zugänglich ist. Um dieses Wissen zu extrahieren, ist es wesentlich, biologische Objekte in Texten zu erkennen, dies gilt insbesondere für Gene und Proteine.

Unsere Arbeit zielt darauf ab:
  • Informationen aus Texten zu extrahieren
  • Aus Texten Netzwerke zur weiteren Analyse zu generieren
  • Text-Informationen zusammen mit Daten aus anderen Quellen (z.B. Genexpressionsdaten) zu analysieren

Projekte

  • ProThesaurus-Wiki: A thesaurus for gene and protein names.
  • Allows for:
    • manual querying and editing of the entries of curated synonym dictionaries
    • searching all Synonyms for a given gene/protein via PubMed and Google
    • contains dictionaries for human, mouse, rat, fly and yeast

  • ProThesaurus: A biological name and markup web service for automated querying via custom software.
  • ProTag - Web Servicing the Biological Office: Integration of the ProThesaurus web services into Microsoft Office applications for retrieval and markup of gene and protein names.

Publikationen

Human Gene Normalization by an Integrated Approach including Abbreviation Resolution and Disambiguation. Katrin Fundel, Ralf Zimmer. Second BioCreative Challenge Evaluation Workshop, Madrid, Spain, 2007.

RelEx - relation extraction using dependency parse trees. Katrin Fundel, Robert Küffner, Ralf Zimmer. Bioinformatics 2007 23(3):365-371; doi:10.1093/bioinformatics/btl616 (HTML).

Gene and protein nomenclature in public databases. Katrin Fundel, Ralf Zimmer. BMC Bioinformatics 2006, 7:372 (HTML)

Expert knowledge without the expert: integrated analysis of gene expression and literature to derive active functional contexts. Robert Küffner, Katrin Fundel, Ralf Zimmer. Bioinformatics. 2005; 21(Suppl. 2):ii259-ii267

Web Servicing the Biological Office. Martin Szugat, Daniel Güttler, Katrin Fundel, Florian Sohler, Ralf Zimmer. Bioinformatics. 2005; 21(Suppl. 2):ii268-ii269

A simple approach for protein name identification: prospects and limits. Katrin Fundel, Daniel Güttler, Ralf Zimmer, Joannis Apostolakis. BMC Bioinformatics 2005, 6(Suppl 1):S15 (24 May 2005)

ProMiner: rule-based protein and gene entity recognition. Daniel Hanisch, Katrin Fundel, Heinz-Theodor Mevissen, Ralf Zimmer, Juliane Fluck. BMC Bioinformatics 2005, 6(Suppl 1):S14 (24 May 2005)

Exact versus approximate string matching for protein name identification. Fundel, K., D. Guettler, R. Zimmer, J. Apostolakis. BioCreative Challenge Evaluation Workshop, Granada, Spain, 2004.

ProMiner: Organism-specific protein name detection using approximate string matching. Hanisch, D., K. Fundel, H.-T. Mevissen, R. Zimmer, J. Fluck. BioCreative Challenge Evaluation Workshop, Granada, Spain, 2004.

Playing biology's name game: identifying protein names in scientific text. Hanisch, D., J. Fluck, H. T. Mevissen, R. Zimmer. Pac Symp Biocomput: 403-14, 2003.

Mitarbeiter der LFE Bioinformatik im Bereich Text-Mining

Joannis Apostolakis
Katrin Fundel
Robert Küffner

Mitwirkende Studenten

Martin Szugat