Ontologies pp 777-822 | Cite as

Engineering a Development Platform for Ontology-Enhanced Knowledge Applications

  • Gary H. Merrill
Chapter
Part of the Integrated Series in Information Systems book series (ISIS, volume 14)

Abstract

Babylon Knowledge Explorer (BKE) is an integrated suite of tools and information sources being developed in GlaxoSmithKline’s A 2 RT to support the prototyping and implementation of ontology-driven information systems and ontology-enhanced knowledge applications. In this paper we describe the current state of BKE development and focus on some of its distinctive or novel approaches, highlighting

  • How BKE makes use of multiple large pre-existing ontologies in support of text and data mining.

  • The methodology employed for importing an ontology and making it immediately accessible to BKE’s tools, interfaces, and API.

  • A formal description of BKE’s ontology-based fact model and how this is employed in implementing information retrieval and data mining capabilities.

  • A sample application built on BKE that illustrates an ontology-enhanced machine learning tool.

Key words

Data mining machine learning ontology-driven ontology-enhanced biomedical ontologies knowledge discovery XML Topic Maps 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Berkeley DB embedded database library. See http://www.sleepycat.com/ and (for the Python bsddb module) http://pybsddb.sourceforge.net/.Google Scholar
  2. [2]
    BioWisdom ontologies page, http://www.biowisdom.com/products/content.htm.Google Scholar
  3. [3]
    Canada’s Adverse Drug Event Database, CBC online version, http://www.cbc.ca/news/adr/database/.Google Scholar
  4. [4]
    Celi home page: http://www.celi.it.Google Scholar
  5. [5]
    Cycorp home page: http://www.cyc.com.Google Scholar
  6. [6]
    Bernhard Ganter and Rudolf Wille, Formal Concept Analysis: Mathematical Foundations, Springer, Berlin, 1999.MATHGoogle Scholar
  7. [7]
    The Gene Ontology Consortium, http://www.geneontology.org.Google Scholar
  8. [8]
    B. A. Davey and H. A. Priestley, Introduction to Lattices and Order, Cambridge University Press, Second, Cambridge, 2002.Google Scholar
  9. [9]
    J. Demsar and B. Zupin, Orange: From Experimental Machine Learning to Interactive Data Mining, Faculty of Computer and Information Science, University of Ljubljana, 2004, http://magix.fri.uni-lj.si/orange/doc/wp/orange.pdf.Google Scholar
  10. [10]
    J. Liu, W. Wang, and J. Yang, A Framework for Ontology-Driven Subspace Clustering, In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 623–628, August, 2004, Seattle, WashingtonGoogle Scholar
  11. [11]
    MedDRA home page, http://www.meddramsso.com/NewWeb2003/index.htm.Google Scholar
  12. [12]
    G. H. Merrill, The Babylon Project: Toward an Extensible Text-Mining Platform, IT Professional, IEEE Computer Society, pp. 23–30, March/April, 2003.Google Scholar
  13. [13]
    G. H. Merrill, A Practical Multi-Ontology Approach to Knowledge Exploration. In: Proceedings of Technology for Life (NC Symposium on Biotechnology & Bioinformatics), Raleigh, NC, 2004.Google Scholar
  14. [14]
    Metakit embedded database library, http://www.equi4.com/metakit.html.Google Scholar
  15. [15]
    National Center for Health Statistics, Classifications of Diseases and Functioning & Disability, http://www.cdc.gov/nchs/icd9.htm.Google Scholar
  16. [16]
    Open Biological Ontologies, http://obo.sourceforge.net.Google Scholar
  17. [17]
    OWL Web Ontology Language: http://www.w3.org/TR/owl-ref/.Google Scholar
  18. [18]
    W. Paik, E. D. Liddy, E. Allen, E. Brown, A. Farris, R. Irwin, J. H. Liddy, I. Niles, Applying Link Analysis to Automatically Extracted Information from Texts Using KNOW-IT, Proceedings of the AAAI Symposium on Artificial Intelligence on Link Analysis, October, 1998, pp. 520–529.Google Scholar
  19. [19]
    Greg Ewing’s Plex lexical analysis module for Python. http://www.cosc.canterbury.ac.nz/\~greg/python/Plex/.Google Scholar
  20. [20]
    Porter stemming algorithm home page: http://www.tartarus.org/~martin/PorterStemmer/.Google Scholar
  21. [21]
    SourceForge home page for the Psyco Python optimizer: http://sourceforge.net/projects/psyco.Google Scholar
  22. [22]
    The PyQt bindings for the Qt toolkit: http://www.riverbankcomputing.co.uk/pyqt/.Google Scholar
  23. [23]
    Python home page: http://python.org.Google Scholar
  24. [24]
    The Qt application development framework: http://www.trolltech.com/products/qt/.Google Scholar
  25. [25]
    W. V. O. Quine, Mathematical Logic, Harvard University Press, Revised Edition, 1979.Google Scholar
  26. [26]
    Barry Smith, Jacob Köhler, and Anand Kumar, On the Application of Formal Principles to Life Science Data: A Case Study in the Gene Ontology, forthcoming in E. Rahm (ed.), Database Integration in the Life Sciences (DILS 2004), Springer, Berlin, 2004.Google Scholar
  27. [27]
    Merwyn G. Taylor, Killian Stoffel, and James A. Hendler, Ontology-based Induction of High Level Classification Rules, Proceedings of the SIGMOD Data Mining and Knowledge Discovery workshop, Tuscon, Arizona, 1997.Google Scholar
  28. [28]
    Temis-Group home page: http://www.temis-group.com.Google Scholar
  29. [29]
    The Unified Medical Language System (UMLS), U.S. National Library of Medicine: http://www.nlm.nih.gov/research/umls.Google Scholar
  30. [30]
    Jack Park and Sam Hunting, Editors, XML Topic Maps: Creating and Using Topic Maps for the Web, Addison-Wesley, Boston, 2003.Google Scholar
  31. [31]
    Therese Vachon, Nicolas Grandjean and Pierre Parisot, Interactive Exploration< of Patent Data for Competitive Intelligence: Applications in Ulix (Novartis Knowledge Miner). In: Proceedings of the International Chemical Informatics Conference. Nimes, France, 2001.Google Scholar
  32. [32]
    Verity Inc., Verity K2 Enterprise Intelligent Classification Guide V4.5, Sunnyvale, 2002.Google Scholar
  33. [33]
    The World Health Organization Drug Dictionary (WHO DD), http://www.who-umc.org/faqs/faqdd.html.Google Scholar
  34. [34]
    The Wing IDE (integrated development environment) for Python, http://www.wingide.com.Google Scholar
  35. [35]
    The wxDesigner GUI design tool, http://www.roebling.de.Google Scholar
  36. [36]
    WxPython Python wrapper for the wxWidgets C++ GUI library. http://wxpython.org/Google Scholar
  37. [37]
    The XML Topics Maps specification, http://www.topicmaps.org/xtm/index.html.Google Scholar
  38. [38]
    Jun Zhang, Adrian Silvescu, and Vasant Honavar, Ontology-Driven Induction of Decision Trees at Multiple Levels of Abstraction. In: Proceedings of the Symposium on Abstraction, Reformulation, and Approximation (SARA-2002). Kananaskis, Alberta, Canada pp. 316–323.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  • Gary H. Merrill
    • 1
  1. 1.Analysis Applications, Research, and Technologies (A2RT)GlaxoSmithKline Inc., Research and DevelopmentResearch Triangle Park

Personalised recommendations