Abstract
Data mining techniques are becoming increasingly important in chemistry as databases become too large to examine manually. Data mining methods from the field of Inductive Logic Programming (ILP) have potential advantages for structural chemical data. In this paper we present Warmr, the first ILP data mining algorithm to be applied to chemoinformatic data. We illustrate the value of Warmr by applying it to a well studied database of chemical compounds tested for carcinogenicity in rodents. Data mining was used to find all frequent substructures in the database, and knowledge of these frequent substructures is shown to add value to the database. One use of the frequent substructures was to convert them into probabilistic prediction rules relating compound description to carcinogenesis. These rules were found to be accurate on test data, and to give some insight into the relationship between structure and activity in carcinogenesis. The substructures were also used to prove that there existed no accurate rule, based purely on atom-bond substructure with less than seven conditions, that could predict carcinogenicity. This results put a lower bound on the complexity of the relationship between chemical structure and carcinogenicity. Only by using a data mining algorithm, and by doing a complete search, is it possible to prove such a result. Finally the frequent substructures were shown to add value by increasing the accuracy of statistical and machine learning programs that were trained to predict chemical carcinogenicity. We conclude that Warmr, and ILP data mining methods generally, are an important new tool for analysing chemical databases.
Similar content being viewed by others
References
Fayyad, U., Piatetsky-Shapiro, G., Smyth, P., and Uthurusamy (Eds) Advances in Knowledge Discovery and Data Mining, MIT Press, Cambridge, MA, 1996.
Communications of the ACM. Special issue on data mining 39, 11 (1996).
Agrawal, R., Imielinski, T. and Swami, A., in Buneman, P. and Jajodia, S. (Eds), Proceedings of the ACM SIGMOD Conference on Management of Data (1993) 207–216.
Mitchell, T.M. Machine Learning. McGraw-Hill, New York, NY, 1997.
Hansch, C., Malony, P.P., Fujiya, T. and Muir, R.M., Nature 194, (1962) 178.
Martin, Y.C. Quantitative Drug Design: A Critical Introduction, Marcel Dekker, New York, NY, 1978.
Klopman, G., J. Am. Chem. Soc., 106 (1984) 7315.
Cramer, R.D., Patterson, D.E. and Bunce, J.D., J. Am. Chem. Soc., 110 (1988) 5959.
Chen, X., Rusinko, A. and Young, S.S., J. Chem. Inf. Comput. Sci., 38 (1998) 1054.
Rusinko, A., Farmen, M.W., Lambert, C.G., Brown, P.L. and Young, S.S., J. Chem. Inf. Comput. Sci., 39 (1999) 1017.
Muggleton, S. (Ed.) Inductive Logic Programming. Academic Press, London, 1992.
Lavrac, N. and Dzeroski, S., Inductive Logic Programming: Techniques and Applications. Ellis Horwood, Chichester, 1994.
King, R.D., Muggleton, S., Lewis R.A. and Sternberg, M.J.E., Proc. Natl. Acad. Sci. USA, 89 (1992) 11322.
Hirst, J.D., King, R.D. and Sternberg, M.J.E., J. Comp. Aid. Mol. Des., 8 (1994) 405.
Hirst, J.D., King, R.D. and Sternberg, M.J.E., J. Comp. Aid. Mol. Des., 8 (1994) 421.
King, R.D., Muggleton, S.H., Srinivasan, A. and Sternberg, M.J.E., Proc. Natl. Acad. Sci. USA, 93 (1996) 438.
King, R.D. & Srinivasan, A., Env. Health Perspect., 104 (supplement 5) (1996) 1031.
King, R.D. and Srinivasan, A., J. Comp. Aid. Mol. Des., 11 (1998) 571.
Finn, P., Muggleton S., Page, D. and Srinivasan, A., Machine Learning J., 30 (1998) 241.
Dehaspe, L. and De Raedt, L., Lecture Notes in Artificial Intelligence, vol. 1297. Springer-Verlag, New York, NY, 1997.
Dehaspe, L. and Toivonen. H., Data Mining Knowledge Discovery, 3 (1999) 7.
Huff, J. and Hasernan, J., Env. Health Perspect., 96 (1991) 23.
Ashby, J. and Tennant, R.W., Mutation Res., 257 (1991) 229.
Tennant, R.W., Spalding, J., Stasiewicz, S. and Ashby, J., Mutagenesis, 5 (1990) 3.
Bahler, D.R. and Bristol, D.W., in Hunter, L., Searls, D. and Shavlik, D. (Eds), Proceedings of the First International Conference on Intelligent Systems for Molecular Biology MIT Press, Menlo Park, 1993, pp. 29–37.
Bristol, D.W., Wachsman, J.T. and Greenwall, A., Env. Health Perspect., 104 (supplement 5) (1996) 1001.
Srinivasan, A., King, R.D., Bristol, D.W., in Dzeroski, S and Flach, P.A. (Eds), Proceedings of the Ninth International Workshop on Inductive Logic programming LNAI. Springer-Verlag Berlin, 1999, pp. 291–302.
Srinivasan, A., King, R.D., Muggleton, S.H. and Sternberg, M.J.E., Fifteenth International Joint Conference on Artificial Intelligence. Morgan Kaufmann, San Francisco, 1997, pp. 4–9.
Srinivasan, A., King, R.D., Bristol, D.W., Sixteenth International Joint Conference on Artificial Intelligence. Morgan Kaufmann, San Francisco, 1999, pp. 270–275.
Ullman, J.D., Principles of Database and Knowledge-Base Systems. MD Computer Science Press, Rockville, 1988.
Agrawal, R., Mannila, H., Srikant, R., Toivonen, H. and Verkamo, A.I., in Fayyad, U.M, Piatetsky-Shapiro, G., Smyth and Uthurusamy, R. (Eds), Advances in Knowledge Discovery and Data mining AAAI Press, Menlo Park, CA, 1996, pp. 307–328.
Mannila, H. and Toivonen, H., Data Mining and Knowledge Discovery, 1 (1997) 241.
Muggleton, S., New Gen. Comput., 13 (1995) 245.
Blockeel, H. and De Raedt, L. Artif. Intell., 101 (1998) 285.
Bahler, D. and Bristol, D., Predictive Toxicology of Chemicals: Experience and Impact of AI tools (AAAI Spring Symposium Technical Report SS–99-01) AAAI Press Menlo Park CA, 1999, pp. 74-77.
Quinlan, J.R., C4.5: Programs for Empirical Learning, Morgan Kaufmann, San Fancisco, CA, 1993.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
King, R.D., Srinivasan, A. & Dehaspe, L. Warmr: a data mining tool for chemical data. J Comput Aided Mol Des 15, 173–181 (2001). https://doi.org/10.1023/A:1008171016861
Issue Date:
DOI: https://doi.org/10.1023/A:1008171016861