Important Note
The following application may not be bug-free because it is an
emerging technology prototype or proof of concept currently under
development in IBM research and development labs. |
What is Anatomy Lens?
Anatomy Lens is a search engine that helps scientists hone in on PubMed articles most relevant to their research. Users enter anatomy terms, MeSH terms, and biological processes as search keywords. Anatomy Lens is more precise and has better recall than text search. For example, for the query Alzheimer's, brain, neuron development, Anatomy Lens will match Alzheimer's articles that discuss dendrite development in the hippocampus, whereas a standard text search will only find articles containing the queried keywords explicitly and might also find articles that are unrelated (such as articles about neuron development in the spine).
How does it work?
Anatomy Lens uses ontologies as knowledge bases to improve the recall of a search. Through inferencing, it is able to determine that if a user is interested in the brain, the user is also interested in the hippocampus and not the spine. To improve precision, Anatomy Lens searches over annotations on articles added by experts instead of keywords. In the above example query, an article that centrally talks about the spine but also happens to mention the keyword "brain" will be returned by a standard text search but not by Anatomy Lens. In the spirit of the semantic web, we have integrated multiple data sets and ontologies: Foundational Model of Anatomy (FMA), Gene Ontology (GO), Gene Ontology Annotations (GOA), MeSH, and PubMed. The power of Anatomy Lens's search and inferencing comes from this integration.
Please see sources and acknowledgements (PDF).
Your suggestions for Anatomy Lens are most welcome. Please send feedback by e-mail.
| About the technology authors |
| Julian Dolby, Ph.D., is a researcher at IBM's T. J. Watson Research Center. His research has three foci: scripting languages and virtual machines; applications of program analysis to software quality and understanding for a variety of languages; and semantic Web technology.
Achille Fokoue, a researcher at IBM Watson Research Lab, works on problems related to knowledge representation and reasoning, data management, and information integration.
Aditya Kalyanpur, Ph.D, joined IBM Watson as a research staff member in 2006. His research interests lie in knowledge representation and reasoning (especially in the context of the semantic Web), ontology engineering, and in applying semantics to software modeling and design.
Li Ma, Ph.D, joined IBM China Research Lab as a research staff member in 2003. He is interested in semantic Web data management, pattern recognition, and the application of semantic technologies to enterprise information integration and search.
Edith Schonberg, Ph.D., a manager at Watson Research Center, is interested in broadening the use of the semantic Web by creating better tools and inventing new applications. She also manages a project on diagnosing and eliminating run-time bloat in Java applications.
Kavitha Srinivas, Ph.D., started the SHER project in 2005 in order to build a scalable ontology reasoning engine for OWL ontologies. She is interested in the application of semantic technologies such as RDF and OWL to different domains and in harnessing the power of linked, open data for improving search and information retrieval.
|
Java and all Java-based trademarks are trademarks of Sun Microsystems, Inc. in the United States, other countries, or both.
Microsoft, Windows, Windows NT, and the Windows logo are trademarks of Microsoft Corporation in the United States, other countries, or both.
Linux is a registered trademark of Linus Torvalds in the United States, other countries, or both.
IBM, WebSphere, System i, and iSeries are trademarks of IBM Corporation in the United States, other countries, or both.
Other company, product, or service names may be trademarks or service marks of others.
|
Date Posted: April 10, 2008
|
