Abstract
One approach to deal with real complex systems is to use two or more techniques in order to combine their different strengths and overcome each other’s weakness to generate hybrid solutions. In this project we pointed out the needs of an improved system in toxicology prediction. An architecture able to satisfy these needs has been developed. The main tools we integrated are rules and ANN. We defined chemical structures of fragments responsible for carcinogenicity according to human experts. After them we developed specialized rules to recognize these fragments into a given chemical and to assess their toxicity. In practice the rule-based expert associates a category to each fragment found, then a category to the molecule. Furthermore, we developed an ANN-based expert that uses molecular descriptors in input and predicts carcinogenicity as a numerical value. Finally we added a classifier program to combine the results obtained from the two previous experts into a single predictive class of carcinogenicity to man.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Benfenati, E., and Gini, G.:Computational predictive programs (expert systems) in toxicology, Toxicology, vol.119 (1997).213–225,.
HazardExpert, version 3.0. Compudrug Chemistry Ltd, Budapest, Hungary.
Benigni R. and Richard, A.M.: QSARS of mutagens and carcinogens: two case studies illustrating problems in the construction of models for noncongeneric chemicals, Mutation Res., vol.371 (1996).29–46.
Lee, Y., Buchanan, B. G., Mattison, D. M., Klopman, G., and Rosenkranz, H. S.: Learning rules to predict rodent carcinogenicity of non-genotoxic chemicals. Mutation Res., vol. 328 (1995) 127–149.
Ashby, J., and Paton, D.: The influence of chemical structure on the extent and sites of carcinogenesis for 522 rodent carcinogens and 55 different human carcinogens exposures. Mutation Res. 286 (1993) 3–74.
Darvas, F., Papp, A., Allerdyce, A., Benfenati, E., Tichy, M., Sobb, N., Citti, A., Gini, G.: Overview of Different Artificial Intelligence Approaches Combined with a Deductive Logic-based Expert System for Predicting Chemical Toxicity. In Gini and Katritzky (eds) AAAI Spring Symposium on Predictive Toxicology, SS-99-01, AAAI Press, Menlo Park, California (1999) 94–99.
Sanderson, D.M., and Earnshaw, C.G.: Computer prediction of possible toxic action from chemical structure; the DEREK system. Human and Experimental Toxicology 10 (1991) 261–273.
Ullmann, J. R.: An algorithm for subgraph isomorphisms. Journal of ACM, Vol. 23-1 (1976) 31–42.
Anguita, D.: Matrix Back Propagation v. 1.1 User Manual, Genova, Italy (1993).
Gini, G., Benfenati, E., Lorenzini, M., Bruschi, M., Grasso, P.: Predictive Carcinogenicity: a Model for Aromatic Compounds, with Nitrogen-containing Substituents, Based on Molecular Descriptors Using an Artificial Neural Network. J of Chem Inf and Comp Sciences, 39 (1999) 1076–1080.
Quinlan, J.R.: C4.5 Programs for Machine Learning. Morgan Kaufmann Publishers Inc.: San Mateo, CA (1993).
Breiman, L., Friedman, J.H., Olshen, R.A., and Stone, C.J.: Classification and regression trees. Wadsworth: Belmont, CA (1984).
Murthy, S. K., Kasif, S. and Salzberg, S.: A system for induction of obliques decision trees. J. of Artificial Intelligence Research, vol.2 (1994).
Omenn, G.S.: Assessing the risk assessment paradigm. Toxicology 102 (1995) 23–28.
Srinivasan, A., King, R. D., Bristol, D. W.: An assessment of submissions made to the predictive toxicology evaluation challenge. Proc.IJCAI 1999 (1999) 270–275.
Gini, G., Benfenati, E., Testaguzza, V., Todeschini, R.: Hytex (Hybrid Toxicology Expert System): Architecture and implementation of a multi-domain hybrid expert system for toxicology. Chemometrics and intelligent laboratory systems 43 (1998) 135–145.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gini, G., Lorenzini, M., Benfenati, E., Brambilla, R., Malvé, L. (2001). Mixing a Symbolic and a Subsymbolic Expert to Improve Carcinogenicity Prediction of Aromatic Compounds. In: Kittler, J., Roli, F. (eds) Multiple Classifier Systems. MCS 2001. Lecture Notes in Computer Science, vol 2096. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48219-9_13
Download citation
DOI: https://doi.org/10.1007/3-540-48219-9_13
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42284-6
Online ISBN: 978-3-540-48219-2
eBook Packages: Springer Book Archive