Scalable Learning Method to Extract Biological Relationships from Medline Abstracts

X. Hu (USA)


biomedical literature mining, biologicalrelationships, protein-protein interaction, information extraction


In this paper we present a scalable learning method to automatically extract biological relationships from biomedical literature. Our method integrates information extraction and data mining together, automatically learns the patterns based on a few user seed instances, and then extract new instances from the biomedical literatures based on the discovered patterns. A novel framework Biological Relationship EXtract (BRExtract) is implemented and tested on the PuBMed to find the chromatin proteinprotein interaction and the experimental results indicate our approach is very effective in extracting biological relationships from large collection of online biomedical literature.

Important Links:

Go Back