18 March 2010
Bridging the Gap: from Dependency Parse Trees to Biomedical Networks
Meeting Room 10, 2nd Floor, JLB
12:30pm - 13:45pm
Dr Goran Nenadic - University of Manchester
Biomedical literature contains over 17 million bibliographic units, presenting various experiments, results, tool implementations, discussions and interpretations. Extracting information from this repository is challenging not only because of the huge volume, but also because of complex expressions used to present biomedical findings and methods. One of the ultimate aims of biomedical text mining is reverse-engineering of the biomedical knowledge space from text. In this talk I will present our recent investigations to bridge the gap between textual and biomedical spaces, where the textual space is modelled through deeper syntactic processing (such as dependency parsing) and the biomedical domain is represented through networks. Three case studies will be discussed: one concerned with building networks of protein-protein interactions from the literature; one related to generating semantic networks of biomedical resources (tools, algorithms, databases), and finally one focused on disease-specific risk factors.
Bio: Dr Goran Nenadic is a Senior Lecturer in the School of Computer Science, University of Manchester and a group leader in the Manchester Interdisciplinary BioCenter (MIB). His main research interests are in the area of text mining in the domains of biomedicine and health-care, including terminology identification and structuring, and relationship extraction and modelling. His most recent research activities are focused on the extraction of contextualised information from the literature to support customised text mining and hypothesis generation.
Save to your Calendar