Many researchers have attempted to find relations in the Biomedical domain using strategies for recognizing protein and gene names, for example. By contrast, our strategy is to combine statistical and lexical techniques to find major noun and verb phrases of all types and compute relations by recurring proximity. We then can apply biomedical term recognition as a filter against the relations we discover. We report here on our work in discovering protein interactions using a standard collection of yeast protein abstracts. After adjusting our recognition algorithms to include complexes and resolve apparent false positives, we obtained a precision of 0.92 and a recall of 0.84. We also examined these relations using our graphical display of the computed relations. In this case it also helps us discover additional relations indirectly and indicates a fruitful avenue for further inquiry.
By: James W. Cooper
Published in: RC23060 in 2004
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .