Prediction of Aromatic Hydroxylation Sites for Human CYP1A2 Substrates Using Condensed Graph of Reactions
In this paper, support vector machine and condensed graph of reaction (CGR) approaches have been used to predict the regioselectivity of aromatic hydroxylation for human CYP1A2 substrates. Experimental data on aromatic hydroxylation for human cytochrome CYP1A2 (observed molecular or “real” transformations) used in the modeling were extracted from the Metabolite database and the XenoSite database. In addition, all potential but unobserved (“unreal”) transformations were generated. The dataset containing “real” and “unreal” transformations was converted into an ensemble of CGRs representing pseudomolecules with conventional (single, double, aromatic, etc.) bonds and dynamic bonds characterizing chemical transformations. ISIDA fragment descriptors generated for CGRs were used for the modeling. The models have been validated in three times repeated fivefold cross-validation on the training set and then on an external set. The final model was constructed by consensus over models built on different descriptors sets. Predictive performance of our model on the external test set was similar to that of XenoSite and Way2Drug tools. Unlike previously used atom labeling-based approaches, the proposed CGR-based representation of metabolic transformations could be applied to different types of reactions catalyzed by the same enzyme and therefore, it is more suitable for automatized handling of metabolic data.
KeywordsCYP1A2 Aromatic hydroxylation Support vector machine (SVM) Condensed graph of reaction (CGR)
We thank Prof. Vladimir Poroikov for providing us with the experimental data set and useful discussion. ChemAxon is acknowledged for the software tools used in this study for data storage and standardization. The study was supported by Russian Science Foundation (Contract 14-43-00024).
- 7.de Groot, M. J., Ackland, M. J., Horne, V. A., Alex, A. A., & Jones, B. C. (1999). A novel approach to predicting P450 mediated drug metabolism. CYP2D6 catalyzed N-dealkylation reactions and qualitative metabolite predictions using a combined protein and pharmacophore model for CYP2D6. Journal of Medicinal Chemistry, 42(20), 4062–4070.CrossRefGoogle Scholar
- 8.de Groot, M. J., Ackland, M. J., Horne, V. A., Alex, A. A., & Jones, B. C. (1999). Novel approach to predicting P450-mediated drug metabolism: development of a combined protein and pharmacophore model for CYP2D6. Journal of Medicinal Chemistry, 42(9), 1515–1524. https://doi.org/10.1021/jm981118h.CrossRefGoogle Scholar
- 9.Borodina, Y., Rudik, A., Filimonov, D., Kharchevnikova, N., Dmitriev, A., Blinova, V., & Poroikov, V. (2004). A new statistical approach to predicting aromatic hydroxylation sites. Comparison with model-based approaches. Journal of Chemical Information and Computer Sciences, 44(6), 1998–2009. https://doi.org/10.1021/ci049834h9.CrossRefGoogle Scholar
- 13.Hennemann, M., Friedl, A., Lobell, M., Keldenich, J., Hillisch, A., Clark, T., & Göller, A. H. (2009). CypScore: Quantitative prediction of reactivity toward cytochromes P450 based on semiempirical molecular orbital theory. ChemMedChem, 4(4), 657–669. https://doi.org/10.1002/cmdc.200800384.CrossRefGoogle Scholar
- 21.Rudik, A. V., Dmitriev, A. V., Lagunin, A. A., Filimonov, D. A., & Poroikov, V. V. (2014). Metabolism site prediction based on xenobiotic structural formulas and PASS prediction algorithm. Journal of Chemical Information and Modeling, 54(2), 498–507. https://doi.org/10.1021/ci400472j.CrossRefGoogle Scholar
- 23.Accelrys, Inc. (2009) Accelrys Metabolite, San Diego. http://accelrys.com .
- 24.JChem 16.4.18, 2016, ChemAxon. http://www.chemaxon.com.
- 25.Varnek, A., Fourches, D., Hoonakker, F., & Solov’ev, V. P. (2005). Substructural fragments: an universal language to encode reactions, molecular and supramolecular structures. Journal of Computer-Aided Molecular Design, 19(9–10), 693–703. https://doi.org/10.1007/s10822-005-9008-0.CrossRefGoogle Scholar
- 26.Nugmanov, R. I., Madzhidov, T. I., Khaliullina, G. R., Baskin, I. I., Antipin, I. S., & Varnek, A. A. (2014). Development of “structure-property” models in nucleophilic substitution reactions involving azides. Journal of Structural Chemistry, 55, 1026–1032. https://doi.org/10.1134/S0022476614060043.CrossRefGoogle Scholar
- 27.Madzhidov, T. I., Bodrov, A. V., Gimadiev, T. R., Nugmanov, R. I., Antipin, I. S., & Varnek, A. A. (2015). Structure–reactivity relationship in bimolecular elimination reactions based on the condensed graph of a reaction. Journal of Structural Chemistry, 56, 1227–1234. https://doi.org/10.1134/S002247661507001X.CrossRefGoogle Scholar
- 28.Madzhidov, T. I., Polishchuk, P. G., Nugmanov, R. I., Bodrov, A. V., Lin, A. I., Baskin, I. I., Varnek, A. A., & Antipin, I. S. (2014). Structure-reactivity relationships in terms of the condensed graphs of reactions. Russian Journal of Organic Chemistry, 50, 459–463. https://doi.org/10.1134/S1070428014040010.CrossRefGoogle Scholar
- 29.Polishchuk, P., Madzhidov, T., Gimadiev, T., Bodrov, A., Nugmanov, R., & Varnek, A. (2017). Structure–reactivity modeling using mixture-based representation of chemical reactions. Journal of Computer-Aided Molecular Design, 31(9), 829–839. https://doi.org/10.1007/s10822-017-0044-3.CrossRefGoogle Scholar
- 31.Marcou, G., de Sousa, J. A., Latino, D. A. R. S., de Luca, A., Horvath, D., Rietsch, V., & Varnek, A. (2015). Expert system for predicting reaction conditions: the Michael reaction case. Journal of Chemical Information and Modeling, 55(2), 239–250. https://doi.org/10.1021/ci500698a.CrossRefGoogle Scholar
- 32.Lin, A. I., Madzhidov, T. I., Klimchuk, O., Nugmanov, R. I., Antipin, I. S., & Varnek, A. (2016). Automatized assessment of protective group reactivity: a step toward big reaction data analysis. Journal of Chemical Information and Modeling, 56, 2140–2148. https://doi.org/10.1021/acs.jcim.6b00319.CrossRefGoogle Scholar
- 34.Horvath, D., Marcou, G., Varnek, A., Kayastha, S., de la Vega de León, A., & Bajorath, J. (2016). Prediction of activity cliffs using condensed graphs of reaction representations, descriptor recombination, support vector machine classification, and support vector regression. Journal of Chemical Information and Modeling, 56(9), 1631–1640. https://doi.org/10.1021/acs.jcim.6b00359.CrossRefGoogle Scholar
- 35.Muller, C., Marcou, G., Horvath, D., Aires-de-Sousa, J., & Varnek, A. (2012). Models for identification of erroneous atom-to-atom mapping of reactions performed by automated algorithms. Journal of Chemical Information and Modeling, 52(12), 3116–3122. https://doi.org/10.1021/ci300418q.CrossRefGoogle Scholar
- 38.Chang CC, Lin CJ (2001) LIBSVM: a library for support vector machines. https://www.csie.ntu.edu.tw/~cjlin/papers/libsvm Accessed 19 October 2017