Journal of Computer-Aided Molecular Design

, Volume 19, Issue 3, pp 189–201 | Cite as

A support vector machine approach to classify human cytochrome P450 3A4 inhibitors

  • Jan M. Kriegl
  • Thomas Arnhold
  • Bernd Beck
  • Thomas Fox
Article

Summary

The cytochrome P450 (CYP) enzyme superfamily plays a major role in the metabolism of commercially available drugs. Inhibition of these enzymes by a drug may result in a plasma level increase of another drug, thus leading to unwanted drug–drug interactions when two or more drugs are coadministered. Therefore, fast and reliable in silico methods predicting CYP inhibition from calculated molecular properties are an important tool which can be applied to assess both already synthesized as well as virtual compounds. We have studied the performance of support vector machines (SVMs) to classify compounds according to their potency to inhibit CYP3A4. The data set for model generation consists of more than 1300 structural diverse drug-like research molecules which were divided into training and test sets. The predictive power of SVMs crucially depends on a careful selection of parameters specifying the kernel function and the penalty for misclassifications. In this study we have investigated a procedure to identify a valid set of SVM parameters which is based on a sampling of the parameter space on a regular grid. From this set of parameters, either single SVMs or SVM committees were trained to distinguish between strong and weak inhibitors or to achieve a more realistic three-class assignment, with one class representing medium inhibitors. This workflow was studied for several kernel functions and descriptor sets. All SVM models performed significantly better than PLS-DA models which were generated from the corresponding descriptor sets. As a very promising result, simple two-dimensional (2D) descriptors yield a three-class model which correctly classifies more than 70% of the test set. Our work illustrates that SVMs used in combination with simple 2D descriptors provide a very effective and reliable tool which allows a fast assessment of CYP3A4 inhibition potency in an early in silico filtering process.

Keywords

ADME cytochrome P450 in silico filter molecular descriptor QSAR support vector machine 

Abbreviations

ADME

absorption, distribution, metabolism and excretion

CYP

cytochrome P450

PLS

partial least squares

DA

discriminant analysis

SVM(s)

support vector machine(s)

3D

three-dimensional

2D

two-dimensional

QM

quantum-mechanical

RBF

radial basis function.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lewis, D.F. 2003Curr. Med. Chem.101955CrossRefPubMedGoogle Scholar
  2. 2.
    Danielson, P.B. 2002Curr. Drug Metab.3561CrossRefPubMedGoogle Scholar
  3. 3.
    Rendic, S., Di Carlo, F.J. 1997Drug Metab. Rev.29413PubMedGoogle Scholar
  4. 4.
    Wrighton, S.A., Schuetz, E.G., Thummel, K.E., Shen, D.D., Korzekwa, K.R., Watkins, P.B. 2000Drug Metab. Rev.32339CrossRefPubMedGoogle Scholar
  5. 5.
    Miller, V.P., Stresser, D.M., Blanchard, A.P., Turner, S., Crespi, C.L. 2000Ann. NewYork Acad. Sci.91926Google Scholar
  6. 6.
    Jenkins, K.M., Angeles, R., Quintos, M.T., Xu, R., Kassel, D.B., Rourick, R.A. 2004J. Pharm. Biomed. Anal.34989CrossRefPubMedGoogle Scholar
  7. 7.
    Böhm, H.-J., Schneider, G. 2000Virtual Screening for Bioactive MoleculesWiley-VCHNew YorkGoogle Scholar
  8. 8.
    Schoch, G.A., Yano, J.K., Wester, M.R., Griffin, K.J., Stout, C.D., Johnson, E.F. 2004J. Biol. Chem.2799497CrossRefPubMedGoogle Scholar
  9. 9.
    Szklarz, G.D., Halpert, J.R. 1998Drug Metab Dispos.261179PubMedGoogle Scholar
  10. 10.
    Wester, M.R., Johnson, E.F., Marques-Soares, C., Dansette, P.M., Mansuy, D., Stout, C.D. 2003Biochemistry426370CrossRefPubMedGoogle Scholar
  11. 11.
    Williams, P.A., Cosme, J., Ward, A., Angove, H.C., Vinković, D.M., Jhoti, H. 2003Nature424464CrossRefPubMedGoogle Scholar
  12. 12.
    Williams, P.A., Cosme, J., Vinković, D.M., Ward, A., Angove, H.C., Day, P.J., Vonrhein, C., Tickle, I.J., Jhoti, H. 2004Science305683CrossRefPubMedGoogle Scholar
  13. 13.
    Wester, M.R., Yano, J.K., Schoch, G.A., Yang, C., Griffin, K.J., Stout, C.D., Johnson, E.F. 2004J. Biol. Chem.27935630CrossRefPubMedGoogle Scholar
  14. 14.
    Yano, J.K., Wester, M.R., Schoch, G.A., Griffin, K.J., Stout, C.D., Johnson, E.F. 2004J. Biol. Chem.27938091CrossRefPubMedGoogle Scholar
  15. 15.
    Ekins, S., Bravi, G., Wikel, J.H., Wrighton, S.A. 1999J.␣Pharmacol. Exp. Ther.291424PubMedGoogle Scholar
  16. 16.
    Ekins, S., Stresser, D.M., Williams, J.A. 2003Trends Pharmacol. Sci.24161CrossRefPubMedGoogle Scholar
  17. 17.
    Ekins, S., Bravi, G., Binkley, S., Gillespie, J.S., Ring, B.J., Wikel, J.H., Wrighton, S.A. 1999J. Pharmacol. Exp. Ther.290429PubMedGoogle Scholar
  18. 18.
    Kumar, G.N., Surapaneni,  2001Med. Res. Rev.21397CrossRefPubMedGoogle Scholar
  19. 19.
    Szklarz, G.D., Halpert, J.R. 1997J. Comput.-Aided Mol. Des.11265CrossRefPubMedGoogle Scholar
  20. 20.
    Schrag, M.L., Wienkers, L.C. 2001Arch. Biochem. Biophys.39149CrossRefPubMedGoogle Scholar
  21. 21.
    Zuegge, J., Fechner, U., Roche, O., Parrott, N.J., Engkvist, O., Schneider, G. 2002Quant. Struct. Act. Relat.21249CrossRefGoogle Scholar
  22. 22.
    Molnár, L., Keseru, G.M. 2002Bioorg. Med. Chem. Lett.12419CrossRefPubMedGoogle Scholar
  23. 23.
    Ekins, S., Berbaum, J., Harrison, R.K. 2003Drug Metab. Dispos.311077CrossRefPubMedGoogle Scholar
  24. 24.
    Merkwirth, C., Mauser, H., Schulz-Gasch, T., Roche, O., Stahl, M., Lengauer, T. 2004J. Chem. Inf. Comput. Sci.441971CrossRefPubMedGoogle Scholar
  25. 25.
    Vapnik, V. 1995The Nature of Statistical Learning TheorySpringerNew YorkGoogle Scholar
  26. 26.
    Lee, Y., Lee, C.K. 2003Bioinformatics191132CrossRefPubMedGoogle Scholar
  27. 27.
    Byvatov, E., Fechner, U., Sadowski, J., Schneider, G. 2003J. Chem. Inf. Comput. Sci.431882CrossRefPubMedGoogle Scholar
  28. 28.
    Warmuth, M.K., Liao, J., Rätsch, G., Mathieson, M., Putta, S., Lemmen, C. 2003J. Chem. Inf. Comput. Sci.43667CrossRefPubMedGoogle Scholar
  29. 29.
    Trotter, M.W.B., Holden, S.B. 2003Quant. Struct. Act. Relat.22533Google Scholar
  30. 30.
    Zernov, V.V., Balakin, K.V., Ivaschenko, A.A., Savchuk, N.P., Pletnev, I.V. 2003J. Chem. Inf. Comput. Sci.432048CrossRefPubMedGoogle Scholar
  31. 31.
    Lind, P., Maltseva, T. 2003J. Chem. Inf. Comput. Sci.431855CrossRefPubMedGoogle Scholar
  32. 32.
    Sorich, M.J., Miners, J.O., McKinnon, R.A., Winkler, D.A., Burden, F.R., Smith, P.A. 2003J. Chem. Inf. Comput. Sci.432019CrossRefPubMedGoogle Scholar
  33. 33.
    Cortes, C., Vapnik, V. 1995Mach. Learn.20273Google Scholar
  34. 34.
    Hsu, C.-W., Lin, C.-J. 2002IEEE Transactions on Neural Networks13415CrossRefGoogle Scholar
  35. 35.
    Moody, G.C., Griffin, S.J., Mather, A.N., McGinnity, D.F., Riley, R.J. 1999Xenobiotica2953CrossRefPubMedGoogle Scholar
  36. 36.
    These descriptors are calculated by a Boehringer Ingelheim in-house software package (propty, developed by K.M. Hasselbach)Google Scholar
  37. 37.
    Molecular Operating Environment Release 2003.2, Chemical Computing Group, Montreal, Canada, 2003Google Scholar
  38. 38.
    VolSurf 3.0.11, Molecular Discovery Ltd., London, UK, 2004Google Scholar
  39. 39.
    Cruciani, G., Pastor, M., Guba, W. 2000Eur. J. Pharm. Sci.11 S29CrossRefPubMedGoogle Scholar
  40. 40.
    CORINA 3.1, Molecular Networks GmbH, Erlangen, Germany, 2004Google Scholar
  41. 41.
    Dewar, M.J.S., Zoebisch, E.G., Healy, E.F., Stewart, J.J.P. 1985J. Am. Chem. Soc.1073902CrossRefGoogle Scholar
  42. 42.
    VAMP 8.1, University of Erlangen, Erlangen, Germany (This version is provided as part of Materials Studio 2.2.1 by Accelrys, Inc.), 2003Google Scholar
  43. 43.
    Golbraikh, A., Shen, M., Xiao, Z., Xiao, Y.D., Lee, K.H., Tropsha, A. 2003J. Comput.-Aided Mol. Des.17241CrossRefPubMedGoogle Scholar
  44. 44.
    Kennard, R.W., Stone, L.A. 1969Technometrics11137Google Scholar
  45. 45.
    Eriksson, L., Johansson, E., Lindgren, F., Sjøstrøm, M., Wold, S. 2002J. Comput.-Aided Mol. Des.16711CrossRefPubMedGoogle Scholar
  46. 46.
    Eriksson, L., Arnhold, T., Beck, B., Fox, T., Johansson, E., Kriegl, J.M. 2004J. Chemometrics18188CrossRefGoogle Scholar
  47. 47.
    SIMCA-P+ 10, Umetrics AB, Umeå, Sweden, 2004Google Scholar
  48. 48.
    Wold, S. 1978Technometrics20397Google Scholar
  49. 49.
    LIBSVM 2.5 National Taiwan University, 2003; http://www.csie.ntu.edu.tw/∼ ∼cjlin/libsvm/index.htmlGoogle Scholar
  50. 50.
    Keerthi, S.S., Lin, C.-J. 2003Neural Comput.151667CrossRefPubMedGoogle Scholar
  51. 51.
    Baldi, P., Brunak, S., Chauvin, Y., Andersen, C.A., Nielsen, H. 2000Bioinformatics16412CrossRefPubMedGoogle Scholar
  52. 52.
    Matthews, B.W. 1975Biochim. Biophys. Acta405442PubMedGoogle Scholar
  53. 53.
    Bishop, C. M. 2004Br. J. Clin. Pharmacol.57473CrossRefPubMedGoogle Scholar
  54. 54.
    Byvatov, E., Schneider, G. 2004J. Chem. Inf. Comput. Sci.44993CrossRefPubMedGoogle Scholar

Copyright information

© Springer 2005

Authors and Affiliations

  • Jan M. Kriegl
    • 1
  • Thomas Arnhold
    • 2
  • Bernd Beck
    • 1
  • Thomas Fox
    • 1
  1. 1.Computational Chemistry, Department of Lead DiscoveryBoehringer Ingelheim Pharma GmbH & Co. KGBiberachGermany
  2. 2.DDS-DMPK, Department of Drug Discovery Support Boehringer Ingelheim Pharma GmbH & Co. KGBiberachGermany

Personalised recommendations