Knowledge Discovery on Chemical Reactivity from Experimental Reaction Information

A knowledge discovery approach from chemical information with focusing on negative information in positive data is described. Reported experimental chemical reactions are classified into some reaction groups according to similarities in physicochemical features with a self-organizing mapping (SOM) method. In one of the reaction groups, functional groups of reactants are divided into two categories according to the experimental results whether they reacted or not. The classes of the functional groups are used for derivation of knowledge on chemical reactivity and condition intensity. The approach is demonstrated with a model dataset.

[1]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[2]  J. Gasteiger,et al.  Automated derivation of reaction rules for the EROS 6.0 system for reaction prediction , 1990 .

[3]  Kimito Funatsu,et al.  SOPHIA, a Knowledge Base-Guided Reaction Prediction System - Utilization of a Knowledge Base Derived from a Reaction Database , 1995, J. Chem. Inf. Comput. Sci..

[4]  J. Gasteiger,et al.  Organic Reactions Classified by Neural Networks: Michael Additions, Friedel–Crafts Alkylations by Alkenes, and Related Reactions† , 1996 .

[5]  Kimito Funatsu,et al.  Further Development of a Reaction Generator in the SOPHIA System for Organic Reaction Prediction. Knowledge-Guided Addition of Suitable Atoms and/or Atomic Groups to Product Skeleton , 1996, J. Chem. Inf. Comput. Sci..

[6]  Johann Gasteiger,et al.  Classification of Organic Reactions: Similarity of Reactions Based on Changes in the Electronic Features of Oxygen Atoms at the Reaction Sites1 , 1998, J. Chem. Inf. Comput. Sci..

[7]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[8]  J. Gasteiger,et al.  Organische Reaktionen mit Hilfe neuronaler Netze klassifiziert: Michael‐Additionen, Friedel‐Crafts‐Alkylierungen durch Alkene und verwandte Reaktionen , 1996 .

[9]  H. Koshino,et al.  Extended CAST Coding Method for Exact Search of Stereochemical Structures , 2002 .

[10]  Kimito Funatsu,et al.  Novel Canonical Coding Method for Representation of Three-Dimensional Structures , 2000, J. Chem. Inf. Comput. Sci..

[11]  Kimito Funatsu,et al.  A Novel Method for Characterization of Three-Dimensional Reaction Fields Based on Electrostatic and Steric Interactions toward the Goal of Quantitative Analysis and Understanding of Organic Reactions , 1999, J. Chem. Inf. Comput. Sci..

[12]  S. Sasaki,et al.  Computer-assisted organic synthesis design and reaction prediction system, “AIPHOS” , 1988 .

[13]  K. Funatsu,et al.  Classification and Prediction of Reagents' Roles by FRAU System with Self-Organizing Neural Network Model , 2000 .

[14]  Kimito Funatsu,et al.  Representation of Molecular Configurations by CAST Coding Method , 2001, J. Chem. Inf. Comput. Sci..