Summary
Recently, methods have been developed in the field of Artificial Intelligence (AI), specifically in the expert systems area using rule-induction, designed to extract rules from data. We have applied these methods to the analysis of molecular series with the objective of generating rules which are predictive and reliable.
The input to rule-induction consists of a number of examples with known outcomes (a training set) and the output is a tree-structured series of rules. Unlike most other analysis methods, the results of the analysis are in the form of simple statements which can be easily interpreted. These are readily applied to new data giving both a classification and a probability of correctness.
Rule-induction has been applied to in-house generated and published QSAR datasets and the methodology, application and results of these analyses are discussed.
The results imply that in some cases it would be advantageous to use rule-induction as a complementary technique in addition to conventional statistical and pattern-recognition methods.
Similar content being viewed by others
References
Hyde, R.M. and Livingstone, D.J., J. Comput.-Aided Mol. Design, 2 (1988) 145.
Chatfield, C. and Collins, A.J., Introduction to Multivariate Analysis, 3rd Ed., Chapman and Hall, 1986.
Hayes-Roth, F., Waterman, D.A. and Lenat, D.B. (Eds), Building Expert Systems, Addison-Wesley, London, 1984.
Winston, P.H., Artificial Intelligence, Addison-Wesley, London, 1984.
Gunhold, R. and Zettel, J., ‘DIAESS: An expert system for diagnosis of faults in electronic circuit boards’, In Proceedings of the Artificial Intelligence and Advanced Computer Technology Conference, 23–25 September 1986, Rhein-Main-Halle, Wiesbaden, 1987.
Austin, D.J., Blake, P.S., Fletcher, D.A. and Garrett, C.M.E., Chemometrics, 5 (1988) 53.
Modessitt, K., Experience with commercial tools involving induction on large databases for space shuttle main engine testing, 4th International Expert Systems Conference, London, June 1988.
A-Razzak, M., Hassan, T. and Ahmad, A., EXTRAN 7 User Manual, Infolink Decision Services Ltd., 9–11 Grosvenor Gardens, London SW1 W0BD, U.K.
Quinlan, J.R., Machine Learning, Kluwer, Boston, U.S.A., 1 (1986) 81–106.
Krogsgaard-Larsen, P., Jacobsen, P. and Falch, E. In S.J.Enna (Ed.) The GABA Receptors, The Humana Press, Clifton, NJ, U.S.A., 1983, pp. 149–176.
SYBYL molecular modelling package, Tripos Associates, St. Louis, MO, 1990.
MOPAC, Version 5.0, Quantum Chemical Program Exchange, Department of Chemistry, University of Indiana, Bloomington, IN.
CNDO/2. QCPE 91, Quantum Chemical Program Exchange, Department of Chemistry, University of Indiana, Bloomington, IN.
Glen, R.C. and Rose, V.S., J. Mol. Graph., 5 (1987) 79.
Barraclough, P., Beams, R.M., Black, J.W., Cambridge, D., Collard, D., Demaine, D.A., Firmin, D., Gerskowitch, V.P., Glen, R.C., Giles, H., Hill, A.P., Hull, R.A.D., Iyer, R., King, W.R., Livingstone, D.J. and Nobbs, M., Eur. J. Med. Chem., 25 (1990) 467.
Barraclough, P., Black, J.W., Cambridge, D., Collard, D., Firmin, D., Gerskowitch, V.P., Glen, R.C., Giles, H., Hill, A.P., Hull, R.A.D., Iyer, R., King, W.R., Kneen, C.O., Lindon, J.C., Nobbs, M.S., Randall, P., Shah, G., Smith, S., Vine, S.J., Whiting, M.V. and Williams, J., J. Med. Chem., 33 (1990) 2231.
Weise, M., Seydel, J.K., Pieper, H., Kruger, G., Noll, K.R. and Keck, J., Quant. Struct.-Act. Relat., 6 (1987) 164.
Lien, E.J., Liao, C.H. and Shinouda, H.G., J. Pharm. Sci., 68 (1979) 463.
Hassan, T. and A-Razzak, M., Exception programming: A new approach to defining specification examples, Proceedings of the International Conference on Expert Systems, London, 1988, pp. 181–197.
Gomez-Jeria, J., Pharm. Sci., 71 (1982) 1423. (N.B. In this version of the calculation of superdelocalizability, the calculation as originally defined by Fukui et al. [21] is modified, as the Hückel parameter Lambda is replaced by the orbital energy E. E may tend to zero and is not scaled between molecules, however this parameter appears to act as a useful variable correlating well with biological activity in some cases.)
Fukui, K., Yonezawa, T. and Nagata, C., Bull. Chem. Soc. Jpn., 27 (1954) 423.
Edward, J.T., J. Chem. Ed., 47 (1970) 261.
Pearlman, R.S., SAREA, QCPE Bull., 1 (1981) 16.
Margenaux, H. and Murphy, G.M., The Mathematics of Physics and Chemistry, 2nd Ed., D. Van Nostrand Co. Inc., New York, NY, 1956.
CLOGP, Medchem software version 3.52. Pomona College Medicinal Chemistry Project, Claremont, CA, 1987.
Weast, R.C. and Astle, M.J. (Eds), CRC Handbook of Chemistry and Physics, 60th Ed., 1980.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
A-Razzak, M., Glen, R.C. Applications of rule-induction in the derivation of quantitative structure-activity relationships. J Computer-Aided Mol Des 6, 349–383 (1992). https://doi.org/10.1007/BF00125944
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00125944