Drug Resistance in Leukemia and Lymphoma III pp 95-105 | Cite as
Artificial Neural Networks as Versatile Tools for Prediction of MDR-Modulatory Activity
Chapter
Abstract
Following our ongoing studies on structure-activity relationship studies of propafenone-type modulators of multidrug resistance, we performed both a Free-Wilson analysis and a combined Hansch/Free-Wilson analysis on a set of 48 compounds using artificial neural networks (ANN). In comparison to classical multiple linear regression (MLR) analysis, the ANN showed equal or even slightly better predictive power in leave one out cross validation procedures and was remarkably superior when performing a leave 8 out cross validation. Additionally, it was possible to train a network using only 14 compounds and to properly predict the MDR-modulating activity of the remaining 34 compounds. In this case, the MLR analysis completely failed due to insufficient number of cases.
Attempts to extract informations on which input descriptors are important using a genetic input selection algorithm failed. Best results were obtained using those descriptors which showed highest statistical significance in MLR analyses.
Keywords
Modulators of Multidrug resistance propafenone structure-activity relationship artificial neural networks Free-Wilson analysisPreview
Unable to display preview. Download preview PDF.
References
- 1.Kane, S.E. Multidrug resistance of cancer cells. Adv. Drug Res. 1996, 28, 182–238.Google Scholar
- 2.Broxterman, H.L., Schuurhuis, G.J. Transport proteins in drug resistance: detection and prognostic significance in acute myeloid leukemia. J. Intern. Med. Suppl. 1997, 740, 147–151.PubMedGoogle Scholar
- 3.Sonneveld, P., Lokhorst, H.M., Vossebeld, P. Drug resistance in multiple myeloma. Semin. Hematol 1997, 34, 34–39.PubMedGoogle Scholar
- 4.Raderer, M., Scheithauer, W. Clinical trials of agents that reverse multidrug resistance. Cancer 1993, 72, 3553–3563.PubMedCrossRefGoogle Scholar
- 5.Ecker, G., Chiba, P. Structure-activity-relationship studies on modulators of the multidrug transporter P-glycoprotein — an overview. Wien. Klin. Wochenschr. 1995, 107, 681–686.PubMedGoogle Scholar
- 6.Andrea, T.A., Kalayeh, H. Applications of neural networks in quantitative structure-activity relationships of dihydrofolate reductase inhibitors. J. Med. Chem. 1991, 34, 2824–2836.PubMedCrossRefGoogle Scholar
- 7.Schaper, K.J., Samitier, M.L.R. Calculation of Octanol/Water Partition Coefficients (logP) using artificial neural networks and connection matices. Quant. Struct. Act. Relat. 1997, 16, 224–230.CrossRefGoogle Scholar
- 8.Tmej, C., Chiba, P., Huber, M., Richter, E., Hitzler, M., Schaper, K.J., Ecker, G. A combined Hansch/Free-Wilson approach as predictive tool in QSAR studies on propafenone-type modulators of multidrug resistance. Archiv. der Pharmazie 1998, 331, 233–240.PubMedCrossRefGoogle Scholar
- 9.Ghose, A.K., Pritchett, A., Crippen, G.M. Atomic physicochemical parameters for three dimensional structure directed quantitative structure-activity relationships III: Modeling hydrophobic interactions. J. Comput. Chem. 1988, 9, 80–90CrossRefGoogle Scholar
- 10.Baricic, P., Mackov, M.; distributed by Hudecek, M., P. Horova 18, 841 07 Bratislava, SlowakiaGoogle Scholar
- 11.Prets, S., Jungreithmair, A., Chiba, P., Ecker, G. Comparison of different methods for estimation of lipophilicity of propafenone-type modulators of multidrug resistance. Sci. Pharm. 1996, 64, 627–636.Google Scholar
- 12.Gekeler, V., Frese, G., Noller, A., Handgretinger, R., Wilisch, A., Schmidt, H., Muller, C., Dopfer, R., Klingebiel, T., Diddens, H., Probst, H., Niethammer, D. Mdr1/P-glycoprotein, topoisomerase and glutathione-S-transferase gene expression in primary and relapsed state adult and childhood leukemias. Br. J. Cancer 1992, 66, 507–517.PubMedCrossRefGoogle Scholar
- 13.TRAJAN V 3.0, Trajan Software Ltd., Trajan House, Durham, England.Google Scholar
- 14.Kama, K.N., Breen, D.M. An artificial neural networks tutorial: Part1 — basics. Neural Networks 1989, 1, 4–22.Google Scholar
- 15.So, S.-S., Richards, G. Application of neural networks: Quantitative structure-activity relationships of the derivatives of 2,4-diamino-5-(substituted-benzyl)pyrimidines as DHFR inhibitors. J. Med. Chem. 1992, 35, 3201–3207.PubMedCrossRefGoogle Scholar
- 16.Aoyama, T., Ichikawa, H. Obtaining the correlation indices between drug activity and strucutral parameters using a neural network. Chem. Pharm. Bull. 1991, 39, 372–378.CrossRefGoogle Scholar
- 17.Holland, J.H. Adaption in natural and artificial systems; The Univeristy of Michigan Press, An Arbor, MI, 1975Google Scholar
- 18.Cramer, R.D. III, Patterson, D.E., Bunce, J.D. Comparative molacular field analysis (CoMFA). 1. Effect of shape on binding of steroids to carrier proteins. J. Am. Chem. Soc. 1988, 110, 5959–5967.PubMedCrossRefGoogle Scholar
- 19.Fujita, T., Ban, T. Structure-activity study of phenylethylamines as substrates of biosynthetic enzymes of sympathetic transmitters. J. Med. Chem. 1971, 14, 148–152.PubMedCrossRefGoogle Scholar
- 20.Ecker, G., Chiba, P., Hitzler, M., Schmid, D., Visser, K., Cordes, H.P., Csöllei, J., Seydel, J.K., Schaper, K.-J. Structure-activity relationship studies on benzofurane analogs of propafenone-type modulators of tumor cell multidrug resistance. J. Med. Chem. 1996, 39, 4767–4774.PubMedCrossRefGoogle Scholar
- 21.Chiba, P., Ecker, G., Schmid, D., Drach, J., Tell, B., Goldenberg, S., Gekeler, V. Structural requirements for activity of propafenone type modulators in PGP-mediated multidrug resistance. Mol. Pharmacol. 1996, 49, 1122–1130.PubMedGoogle Scholar
- 22.Chiba, P., Holzer, W., Landau, M., Bechmann, G., Lorenz, K., Plagens, B., Hitzler, M., Richter, E., Ecker, G. Substituted 4-acylpyrazoles and-pyrazolones: Synthesis and MDR-modulating activity. J. Medicinal Chem. 1998, 41, 4001–4011.CrossRefGoogle Scholar
Copyright information
© Springer Science+Business Media New York 1999