Summary
Rule-based ensemble modelling has been used to develop a model with high accuracy and predictive capabilities for distinguishing between four different modes of toxic action for a set of 220 phenols. The model not only predicts the majority class (polar narcotics) well but also the other three classes (weak acid respiratory uncouplers, pro-electrophiles and soft electrophiles) of toxic action despite the severely skewed distribution among the four investigated classes. Furthermore, the investigation also highlights the merits of using ensemble (or consensus) modelling as an alternative to the more traditional development of a single model in order to promote robustness and accuracy with respect to the predictive capability for the derived model.
Similar content being viewed by others
Abbreviations
- RDS:
-
Rule Discovery System
- QSAR:
-
quantitative structure-activity relationship
- LDA:
-
linear discriminant analysis
- PSA:
-
polar surface area
- HMO:
-
Hückel molecular orbital
- HOMO:
-
highest occupied molecular orbital
- LUMO:
-
lowest unoccupied molecular orbital
- E_HOMO:
-
energy of highest occupied molecular orbital
- E_LUMO:
-
energy of lowest unoccupied molecular orbital
- No_Hdon:
-
number of hydrogen bond donor centres
- pKa:
-
negative decadic logarithm of the acidity constant
- logKow:
-
decadic logarithm of the octanol/water partition coefficient
- min dist DD:
-
minimum topological distance between two H-bond donors
- max eV #3:
-
third highest eigen-value from BCUT (Burden-Chemical Abstracts-University of Texas) parameter matrix
- nonpolar count/M:
-
number of non-polar atoms divided by molecular weight.
References
Garg, R., Kurup, A. and Hansch, C., Comparative QSAR: On the toxicology of the phenolic OH moiety, Crit. Rev. Toxicol., 31 (2001) 223–245.
Aptula, A.O., Netzeva, T.I., Valkova, I.V., Cronin, M.T.D., Schultz, T.W., Kühne, R. and Schüürmann, G., Multivariate Discrimination between Modes of Toxic Action of Phenols, Quant. Struct.-Act. Relat., 21 (2002) 12–22.
Ren, S., Ecotoxicity prediction using mechanism- and non-mechanism-based QSARs: A preliminary study, Chemosphere, 53 (2003) 1053–1065.
Schultz, T.W., Cronin, M.T.D., Walker, J.D. and Aptula, A.O., Quantitative structure-activity relationships (QSARs) in toxicology: A historical perspective, J. Mol. Struct. (Theochem), 622 (2003) 1–22.
Schultz, T.W., Lin, D.T., Wilke, T.S. and Arnold, L.M., Quantitative structure-activity relationships for the Tetrahymena pyriformis population growth endpoint: A mechanism of toxic action approach. In: Karcher, W., Devillers, J. (Eds.), Practical Applications of Quantitative Structure-Activity Relationships (QSAR) in Environmental Chemistry and Toxicology. Kluwer Academic, Dordrecht, Netherlands, 1990, pp. 241–262.
Cronin, M.T.D. and Dearden, J.C., Review: QSAR in toxicology. 1. Prediction of aquatic toxicity, Quant. Struct.-Act. Relat., 14 (1995) 1–7.
Michie, D., Spiegelhalter, D.J., Taylor, C.C. and Campbell, J., Machine Learning, Neural and Statistical Classification, Ellis Horwood, Upper Saddle River, USA, 1995.
Zmuidinavicius, D., Japertas, P., Petrauskas, A. and Didziapetris, D., Progress in Toxinformatics: The Challenge of Predicting Acute Toxicity, Curr. Top. Med. Chem., 3 (2003) 1301–1314.
Dearden, J.C., In silico prediction of drug toxicity, J. Comput.-Aid. Mol. Des., 17 (2003) 119–127.
Pudenz, S., Brüggemann, R. and Bartel, H.-G., QSAR of Ecotoxicological Data on the Basis of Data-Driven If-Then-Rules, Ecotox., 11 (2002) 337–342.
Greene, N., Computer systems for the prediction of toxicity: an update, Adv. Drug Deliv. Rev., 54 (2002) 417–431.
Karabunarlieva, S., Nikolovac, N., Nikolovd, N. and Mekenyana, O., Rule interpreter: A chemical language for structure-based screening, Journal of Molecular Structure (Theochem), 622 (2003) 53–62.
Breiman, L., Bagging Predictors, Machine Learning, 24 (1996) 123–140.
Breiman, L., Random Forests, Machine Learning, 45 (2001) 5–32.
Dietterich, T.G., Ensemble Methods in Machine Learning, Lecture Notes in Computer Science 1857 (2000) 1–15.
Olsson, T., Sherbukhin, V. SELMA, Synthesis and Structure Administration (SaSA), AstraZeneca R&D Mölndal, Sweden.
Compumine® Rule Discovery System™ (RDS™) version 2.1, Compumine AB, Uppsala Science Park, SE-751 83 Uppsala, Sweden, www.compumine.com
Quinlan, J. R., Induction of decision trees, Machine Learning, 1 (1986) 81–106.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Norinder, U., Lidén, P. & Boström, H. Discrimination between modes of toxic action of phenols using rule based methods. Mol Divers 10, 207–212 (2006). https://doi.org/10.1007/s11030-006-9019-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11030-006-9019-3