Analogical reasoning of organic reactions based on the structurized compound-reaction diagram

  • Hironobu Gotoda
  • Jianghong An
  • Yuzuru Fujiwara
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1085)


As the number of chemical compounds identified increases as well as the amount of the associated knowledge of their properties and reactions, the necessity for developing intelligent database or expert systems is correspondingly expanding. Such systems are often required to analogically reason new reactions by recognizing the similarities of compounds and reactions.

This paper presents a novel method to analogically reason new reactions based on the structural similarities of compounds and reactions, which are represented by a kind of semantic network, termed the compound-reaction diagram. The diagram integrates the abstraction hierarchies of compounds and reaction types, and also the parametric properties of compounds and reaction conditions. An efficient and usercustomizable scheme is developed for retrieving and evaluating analogs, which is the combination of the structure-based reasoning with the statistical, numerical processing of physical and chemical parameters.


analogical reasoning similarity of concepts conceptual structures semantic network organic compounds organic reactions 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    J. M. Barnard. Structure searching methods: old and new. J. Chem. Inf. Comput. Sci., 33(4):532–538, 1993.CrossRefGoogle Scholar
  2. 2.
    J. Gasteiger, W. Ihelenfeld, R. Fick, and J. R. Rose. Similarity concepts for the planning of organic reactions and syntheses. J. Chem. Inf. Comput. Sci., 32(6):700–712, 1992.CrossRefGoogle Scholar
  3. 3.
    R. P. Hall. Computational approaches to analogical reasoning: A comparative analysis. Artificial Intelligence, 39:39–120, 1989.CrossRefMathSciNetGoogle Scholar
  4. 4.
    M. A. Johnson and G. M. Maggiora. Concepts and Applications of Molecular Similarity. Wiley, New York, 1990.Google Scholar
  5. 5.
    J. J. Lai, H. X. Chen, and Y. Fujiwara. Extraction of semantic relationships among terms—SS-KWIC. In Proc. 47th FID Conference and Congress, pages 155–159, 1994.Google Scholar
  6. 6.
    J. F. Sowa. Conceptual Structures. Addison-Wesley, 1984.Google Scholar
  7. 7.
    S. L. Tanimoto. The Elements of Artificial Intelligence. Computer Science Press, 1987.Google Scholar
  8. 8.
    Z. Q. Wang and Y. Fujiwara. Learning and reasoning in the information-base systems for organic synthesis research. J. Japan Soc. Information and Knowledge, 2(1):71–82, 1991.Google Scholar
  9. 9.
    P. H. Winston. Learning and reasoning by analogy. Comm. ACM, 23(12):689–703, 1980.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Hironobu Gotoda
    • 1
  • Jianghong An
    • 2
  • Yuzuru Fujiwara
    • 2
  1. 1.Research and Development DepartmentNational Center for Science Information SystemsTokyoJapan
  2. 2.Institute of Information Sciences and ElectronicsUniversity of TsukubaIbarakiJapan

Personalised recommendations