Pharmaceutical Research

, Volume 22, Issue 9, pp 1454–1460 | Cite as

Prediction of pKa for Neutral and Basic Drugs Based on Radial Basis Function Neural Networks and the Heuristic Method

  • Feng Luan
  • Weiping Ma
  • Haixia Zhang
  • Xiaoyun Zhang
  • Mancang Liu
  • Zhide Hu
  • Botao Fan
Research Paper


Quantitative structure–property relationships (QSPR) were developed to predict the pKa values of a set of neutral and basic drugs via linear and nonlinear methods. The ability of the models to predict pKa was assessed and compared.


The descriptors of 74 neutral and basic drugs in this study were calculated by the software CODESSA, which can calculate constitutional, topological, geometrical, electrostatic, and quantum chemical descriptors. Linear and nonlinear QSPR models were developed based on the heuristic method (HM) and radial basis function neural networks (RBFNN), respectively. The heuristic method was also used for the preselection of appropriate molecular descriptors.


The obtained linear model had a correlation coefficient of r = 0.884, F = 37.72 with a root-mean-squared (RMS) error of 0.482 for the training set, and r = 0.693, F = 11.99, and RMS = 0.987 for the test set. The RMS in predicting the overall data set is 0.619. The nonlinear model gave better results; for the training set, r = 0.886, F = 202.314, and RMS = 0.458, and for the test set r = 0.737, F = 15.41, and RMS = 0.613. The RMS error in prediction for overall data set is 0.493. Prediction results from nonlinear model are in good agreement with experimental values.


In present study, we developed a QSPR model to predict the important parameter (pKa) of neutral and basic drugs. The model is useful in predicting pKa during the discovery of new drugs when experimental data are unknown.

Key Words

neutral and basic drugs quantitative structure–property relationship radial basis function neural networks the heuristic method 



The authors thank the National Natural Science Foundation of China (NSFC) Fund (NO.20305008) for supporting this project.


  1. 1.
    Perrin, D. D., Dempsey, B., Serjeant, E. P. 1981pKa prediction for organic acids and basesChapman and HallNew YorkGoogle Scholar
  2. 2.
    Santili-Kakoulidou, A. T., Panderi, I., Sizmadia, F. C., Darvas, F. 1997Prediction of distribution coefficient from structure 2. Validation of Prolog D, an expert systemJ. Pharm. Sci.8611731179CrossRefPubMedGoogle Scholar
  3. 3.
    Silva, C. O., Silva, E. C., Nascimento, M. A. C. 1999Ab Initio calculations of absolute pKa values in aqueous solution I. carboxylic acidsJ. Phys. Chem. A1031119411199CrossRefGoogle Scholar
  4. 4.
    Citra, M. J. 1999Estimating the pKa of phenols, carboxylic acids and alcohols from semiempirical quantum chemical methodsChemosphere38191206CrossRefPubMedGoogle Scholar
  5. 5.
    Oberoi, H., Allewell, N. M. 1993Multigrid solution of the nonlinear Poisson–Boltzmann equation and calculation of titration curvesBiophys. J.654855PubMedGoogle Scholar
  6. 6.
    Antosiewicz, J., McCammon, J. A., Gilson, M. K. 1994Prediction of pH dependent properties of proteinsJ. Mol. Biol.238415436CrossRefPubMedGoogle Scholar
  7. 7.
    Sham, Y. Y., Chu, Z. T., Warshel, A. 1997Consistent calculations of pKa’s of ionizable residues in proteins: semi-microscopic andmicroscopic approachesJ. Phys. Chem. B10144584472CrossRefGoogle Scholar
  8. 8.
    Warwicker, J. 1999Simplified methods for pKa and acid pH-dependent stability estimation in proteins: removing dielectric and counterion boundariesProtein Sci.8418425PubMedGoogle Scholar
  9. 9.
    Li, X., Robert, C. G. 2002Novel methods for the prediction of logP, pKa, and logDJ. Chem. Inf. Comput. Sci.42796805CrossRefPubMedGoogle Scholar
  10. 10.
    Li, X., Robert, C. G., Robert, D. C. 2003Predicting pKa by molecular tree structured fingerprints and PLSJ. Chem. Inf. Comput. Sci.43870879CrossRefPubMedGoogle Scholar
  11. 11.
    Gargallo, R., Sotriffer, C. A., Klaus, R. L., Bernd, M. R. 1999Application of multivariate data analysis methods to Comparative Molecular Field Analysis (CoMFA) data: Proton affinities and pKa prediction for nucleic acids componentsJ. Comput.-Aided Mol. Des.13611623CrossRefPubMedGoogle Scholar
  12. 12.
    Polański, J., Gieleciak, R., Bark, A. 2002The Comparative Molecular Surface Analysis (COMSA)—a nongrid 3D QSAR method by a coupled neural network and PLS system: predicting pKa values of benzoic and alkanoic acidsJ. Chem. Inf. Comput. Sci.42184191CrossRefPubMedGoogle Scholar
  13. 13.
    Polanski, J., Bak, A. 2003Modeling steric and electronic effects in 3D- and 4D-QSAR schemes: predicting benzoic pKa values and steroid CBG binding affinitiesJ. Chem. Inf. Comput. Sci.4320812092CrossRefPubMedGoogle Scholar
  14. 14.
    Lombardo, F., Scott Obach, R., Shalaeva, M. Y., Gao, F. 2004Prediction of human volume of distribution values for neutral and basic drugs. 2. Extended data set and leave-class-out statisticsJ. Med. Chem.4712421250CrossRefPubMedGoogle Scholar
  15. 15.
    ISIS Draw2.3, MDL Information Systems, Inc., 1990–2000Google Scholar
  16. 16.
    HyperChem 4.0, Hypercube, Inc., 2000Google Scholar
  17. 17.
    MOPAC, v.6.0 Quantum Chemistry Program Exchange, Program 455, Indiana University, Bloomington, INGoogle Scholar
  18. 18.
    Katritzky, A. R., Lobanov, V. S., Karelson, M. 1995CODESSA: Training ManualUniversity of FloridaGainesville, FLGoogle Scholar
  19. 19.
    Katritzky, A. R., Lobanov, V. S., Karelson, M. 1994CODESSA: Reference ManualUniversity of FloridaGainesville, FLGoogle Scholar
  20. 20.
    Oblak, M. R. M., Solmajer, T. 2000Quantitative structure–activity relationship of flavonoid analogues. 3. Inhibition of p56lck protein tyrosine kinaseJ. Chem. Inf. Comput. Sci.409941001CrossRefPubMedGoogle Scholar
  21. 21.
    F. Luan, C. X. Xue, R. S. Zhang, C. Y. Zhao, M. C. Liu, Z. D. Hu, B. T. Fan. Prediction of retention time of a variety of volatile organic compounds based on the heuristic method andsupport vector machine. Anal. Chim. Acta. 537:101–110 (2005).Google Scholar
  22. 22.
    Yao, X. J., Panaye, A., Doucet, P., Zhang, R. S., Chen, H. F., Liu, M. C., Hu, Z. D., Fan, B. T. 2004Comparative study of QSAR/QSPR correlations using support vector machines, radial basis function neural networks, and multiple linear regressionJ. Chem. Inf. Comput. Sci.4412571266CrossRefPubMedGoogle Scholar
  23. 23.
    Xiang, Y. H., Liu, M. C., Zhang, X. Y., Zhang, R. S., Hu, Z. D., Fan, B. T., Doucet, J. P., Panaye, A. 2002Quantitative prediction of liquid chromatography retention of N-benzylideneanilines based on quantum chemical parameters and radial basis function neural networkJ. Chem. Inf. Comput. Sci.42592597CrossRefPubMedGoogle Scholar
  24. 24.
    M. J. L. Orr. Introduction to Radial basis function networks, Centre for Cognitive Science, Edinburgh University, 1996.Google Scholar
  25. 25.
    M. J. L Orr. MATLAB routines for subset selection and ridge regression in linear neural networks, Centre for Cognitive Science, Edinburgh University, 1996.Google Scholar

Copyright information

© Springer Science + Business Media, Inc. 2005

Authors and Affiliations

  • Feng Luan
    • 1
  • Weiping Ma
    • 1
  • Haixia Zhang
    • 1
  • Xiaoyun Zhang
    • 1
  • Mancang Liu
    • 1
  • Zhide Hu
    • 1
  • Botao Fan
    • 2
  1. 1.Department of ChemistryLanzhou UniversityLanzhouChina
  2. 2.Université Paris 7-Denis Diderot, ITODYS 1ParisFrance

Personalised recommendations