Pharmaceutical Research

, 25:1902 | Cite as

QSAR Modeling of the Blood–Brain Barrier Permeability for Diverse Organic Compounds

  • Liying Zhang
  • Hao Zhu
  • Tudor I. Oprea
  • Alexander Golbraikh
  • Alexander TropshaEmail author
Research Paper



Development of externally predictive Quantitative Structure–Activity Relationship (QSAR) models for Blood–Brain Barrier (BBB) permeability.


Combinatorial QSAR analysis was carried out for a set of 159 compounds with known BBB permeability data. All six possible combinations of three collections of descriptors derived from two-dimensional representations of molecules as chemical graphs and two QSAR methodologies have been explored. Descriptors were calculated by MolconnZ, MOE, and Dragon software. QSAR methodologies included k-Nearest Neighbors and Support Vector Machine approaches. All models have been rigorously validated using both internal and external validation methods.


The consensus prediction for the external evaluation set afforded high predictive power (R 2 = 0.80 for 10 compounds within the applicability domain after excluding one activity outlier). Classification accuracies for two additional external datasets, including 99 drugs and 267 organic compounds, classified as permeable (BBB+) or non-permeable (BBB−) were 82.5% and 59.0%, respectively. The use of a fairly conservative model applicability domain increased the prediction accuracy to 100% and 83%, respectively (while naturally reducing the dataset coverage to 60% and 43%, respectively). Important descriptors that affect BBB permeability are discussed.


Models developed in these studies can be used to estimate the BBB permeability of drug candidates at early stages of drug development.


combinatorial QSAR k-nearest neighbors model validation predictors of BBB permeability support vector machines 



applicability domain


blood–brain barrier


combinatorial QSAR


k-nearest neighbors


mean absolute error


National Institutes of Health


Organization for Economic Co-operation and Development


quantitative structure–activity relationship


support vector machines



We are grateful to Dr. Scott Oloff for his implementation of the SVM approach that was used in this study. We also thank Dr. J. Grier for his critical comments and his help with editing this manuscript. The studies reported in this paper have been supported by the NIH RoadMap grant GM076059.

Supplementary material

11095_2008_9609_MOESM1_ESM.doc (860 kb)
Supplemental Materials (DOC 743 KB)


  1. 1.
    P. L. Golden, and G. M. Pollack. Blood–brain barrier efflux transport. J. Pharm. Sci. 92:1739–1753 (2003).PubMedCrossRefGoogle Scholar
  2. 2.
    U. Bickel, T. Yoshikawa, and W. M. Pardridge. Delivery of peptides and proteins through the blood–brain barrier. Adv. Drug Deliv. Rev. 46:247–279 (2001).PubMedCrossRefGoogle Scholar
  3. 3.
    C. L. Graff, and G. M. Pollack. Drug transport at the blood–brain barrier and the choroid plexus. Curr. Drug Metab. 5:95–108 (2004).PubMedCrossRefGoogle Scholar
  4. 4.
    R. C. Young, R. C. Mitchell, T. H. Brown, C. R. Ganellin, R. Griffiths, M. Jones, K. K. Rana, D. Saunders, I. R. Smith, N. E. Sore, and T. J. Wilks. Development of a new physicochemical model for brain penetration and its application to the design of centrally acting H2 receptor histamine antagonists. J. Med. Chem. 31:656–671 (1988).PubMedCrossRefGoogle Scholar
  5. 5.
    M. H. Abraham, H. S. Chadha, and R. C. Mitchell. Hydrogen bonding. 33. Factors that influence the distribution of solutes between blood and brain. J. Pharm. Sci. 83:1257–1268 (1994).PubMedCrossRefGoogle Scholar
  6. 6.
    M. H. Abraham, H. S. Chadha, and R. C. Mitchell. Hydrogen-bonding. Part 36. Determination of blood brain distribution using octanol–water partition coefficients. Drug Des. Discov. 13:123–131 (1995).PubMedGoogle Scholar
  7. 7.
    F. Lombardo, J. F. Blake, and W. J. Curatolo. Computation of brain–blood partitioning of organic solutes via free energy calculations. J. Med. Chem. 39:4750–4755 (1996).PubMedCrossRefGoogle Scholar
  8. 8.
    G. Subramanian, and D. B. Kitchen. Computational models to predict blood–brain barrier permeation and CNS activity. J. Comput. Aided Mol. Des. 17:643–664 (2003).PubMedCrossRefGoogle Scholar
  9. 9.
    D. E. Clark. Rapid calculation of polar molecular surface area and its application to the prediction of transport phenomena. 2. Prediction of blood–brain barrier penetration. J. Pharm. Sci. 88:815–821 (1999).PubMedCrossRefGoogle Scholar
  10. 10.
    J. M. Luco. Prediction of the brain–blood distribution of a large set of drugs from structurally derived descriptors using partial least-squares (PLS) modeling. J. Chem. Inf. Comput. Sci. 39:396–404 (1999).PubMedGoogle Scholar
  11. 11.
    M. Feher, E. Sourial, and J. M. Schmidt. A simple model for the prediction of blood–brain partitioning. Int. J. Pharm. 201:239–247 (2000).PubMedCrossRefGoogle Scholar
  12. 12.
    J. Kelder, P. D. Grootenhuis, D. M. Bayada, L. P. Delbressine, and J. P. Ploemen. Polar molecular surface as a dominating determinant for oral absorption and brain penetration of drugs. Pharm. Res. 16:1514–1519 (1999).PubMedCrossRefGoogle Scholar
  13. 13.
    M. E. Brewster, E. Pop, M. J. Huang, and N. Bodor. AM1-based model system for estimation of brain/blood concentration ratios. Int. J. Quantum Chem. 60:51–63 (1996).CrossRefGoogle Scholar
  14. 14.
    U. Norinder, P. Sjoberg, and T. Osterberg. Theoretical calculation and prediction of brain–blood partitioning of organic solutes using MolSurf parametrization and PLS statistics. J. Pharm. Sci. 87:952–959 (1998).PubMedCrossRefGoogle Scholar
  15. 15.
    A. Tropsha, P. Gramatica, and V. K. Gombar. The importance of being earnest: Validation is the absolute essential for successful application and interpretation of QSPR Models. QSAR Comb. Sci. 22:69–77 (2003).CrossRefGoogle Scholar
  16. 16.
    H. Kubinyi, F. A. Hamprecht, and T. Mietzner. Three-dimensional quantitative similarity–activity relationships (3D QSiAR) from SEAL similarity matrices. J. Med. Chem. 41:2553–2564 (1998).PubMedCrossRefGoogle Scholar
  17. 17.
    A. Golbraikh, and A. Tropsha. Beware of q2!. J. Mol. Graph. Model. 20:269–276 (2002).PubMedCrossRefGoogle Scholar
  18. 18.
    M. Vracko, V. Bandelj, P. Barbieri, E. Benfenati, Q. Chaudhry, M. Cronin, J. Devillers, A. Gallegos, G. Gini, P. Gramatica, C. Helma, P. Mazzatorta, D. Neagu, T. Netzeva, M. Pavan, G. Patlewicz, M. Randic, I. Tsakovska, and A. Worth. Validation of counter propagation neural network models for predictive toxicology according to the OECD principles: A case study. SAR QSAR Environ. Res. 17:265–284 (2006).PubMedCrossRefGoogle Scholar
  19. 19.
    L. P. de Cerqueira, A. Golbraikh, S. Oloff, Y. Xiao, and A. Tropsha. Combinatorial QSAR modeling of P-glycoprotein substrates. J. Chem. Inf. Model. 46:1245–1254 (2006).CrossRefGoogle Scholar
  20. 20.
    A. Kovatcheva, A. Golbraikh, S. Oloff, Y. D. Xiao, W. Zheng, P. Wolschann, G. Buchbauer, and A. Tropsha. Combinatorial QSAR of ambergris fragrance compounds. J. Chem. Inf. Comput. Sci. 44:582–595 (2004).PubMedCrossRefGoogle Scholar
  21. 21.
    A. Kovatcheva, A. Golbraikh, S. Oloff, J. Feng, W. Zheng, and A. Tropsha. QSAR modeling of datasets with enantioselective compounds using chirality sensitive molecular descriptors. SAR QSAR Environ. Res. 16:93–102 (2005).PubMedCrossRefGoogle Scholar
  22. 22.
    B. Hemmateenejad, R. Miri, M. A. Safarpour, and A. R. Mehdipour. Accurate prediction of the blood–brain partitioning of a large set of solutes using ab initio calculations and genetic neural network modeling. J. Comput. Chem. 27:1125–1135 (2006).PubMedCrossRefGoogle Scholar
  23. 23.
    U. Norinder, and M. Haeberlein. Computational approaches to the prediction of the blood–brain distribution. Adv. Drug Deliv. Rev. 54:291–313 (2002).PubMedCrossRefGoogle Scholar
  24. 24.
    J. A. Platts, M. H. Abraham, Y. H. Zhao, A. Hersey, L. Ijaz, and D. Butina. Correlation and prediction of a large blood–brain distribution data set—an LFER study. Eur. J. Med. Chem. 36:719–730 (2001).PubMedCrossRefGoogle Scholar
  25. 25.
    A. Golbraikh, M. Shen, Z. Xiao, Y. D. Xiao, K. H. Lee, and A. Tropsha. Rational selection of training and test sets for the development of validated QSAR models. J. Comput. Aided Mol. Des. 17:241–253 (2003).PubMedCrossRefGoogle Scholar
  26. 26.
    M. Olah, M. Mracec, L. Ostopovici, R. Rad, A. Bora, N. Hadaruga, I. Olah, M. Banda, Z. Simon, M. Mracec, and Y. I. Oprea. WOMBAT: World of Molecular Bioactivity, in chemoinformatics in drug discovery. Wiley-VCH, New York, 2004.Google Scholar
  27. 27.
    H. Li, C. W. Yap, C. Y. Ung, Y. Xue, Z. W. Cao, and Y. Z. Chen. Effect of selection of molecular descriptors on the prediction of blood–brain barrier penetrating and nonpenetrating agents by statistical learning methods. J. Chem. Inf. Model. 45:1376–1384 (2005).PubMedCrossRefGoogle Scholar
  28. 28.
    L. B. Kier, and L. H. Hall. Molecular connectivity in structure–activity analysis. Wiley, New York, 1986.Google Scholar
  29. 29.
    L. B. Kier, and L. H. Hall. Molecular connectivity in chemistry and drug research. Academic Press, New York, 1976.Google Scholar
  30. 30.
    M. Randic. Characterization of molecular branching. J. Am. Chem. Soc. 97:6609–6615 (1975).CrossRefGoogle Scholar
  31. 31.
    L. B. Kier. A Shape index from molecular graphs. Quant. Struct.—Act. Relat. 4:109–116 (1985).CrossRefGoogle Scholar
  32. 32.
    L. B. Kier. Inclusion of symmetry as a shape attribute in Kappa-Index analysis. Quant. Struct.—Act. Relatsh. 6:8–12 (1987).CrossRefGoogle Scholar
  33. 33.
    L. H. Hall, and L. B. Kier. Determination of topological equivalence in molecular graphs from the topological state. Quant. Struct.—Act. Relat. 9:115–131 (1990).CrossRefGoogle Scholar
  34. 34.
    L. H. Hall, B. K. Mohney, and L. B. Kier. The electrotopological state: An atom index for QSAR. Quant. Struct.—Act. Relat. 10:43–51 (1991).CrossRefGoogle Scholar
  35. 35.
    L. H. Hall, B. K. Mohney, and L. B. Kier. The electrotopological state: Structure information at the atomic level for molecular graphs. J. Chem. Inf. Comput. Sci. 31:76–82 (1991).Google Scholar
  36. 36.
    G. E. Kellogg, L. B. Kier, P. Gaillard, and L. H. Hall. E-state fields: Applications to 3D QSAR. J. Comput. Aided Mol. Des. 10:513–520 (1996).PubMedCrossRefGoogle Scholar
  37. 37.
    L. B. Kier, and L. H. Hall. Molecular structure description: The electrotopological state. Academic Press, New York, 1999.Google Scholar
  38. 38.
    L. B. Kier, and L. H. Hall. A differential molecular connectivity index. Quant. Struct.—Act. Relat. 10:134–140 (1991).CrossRefGoogle Scholar
  39. 39.
    M. Petitjean. Applications of the radius–diameter diagram to the classification of topological and geometrical shapes of chemical compounds. J. Chem. Inf. Comput. Sci. 32:331–337 (1992).Google Scholar
  40. 40.
    H. J. Wiener. Structural determination of paraffin boiling points. J. Am. Chem. Soc. 69:17–20 (1947).CrossRefGoogle Scholar
  41. 41.
    J. R. Platt. Influence of neighbor bonds on additive bond properties in paraffins. J. Chem. Phys. 15:419–420 (1947).CrossRefGoogle Scholar
  42. 42.
    C. Shannon, and W. Weaver. In mathematical theory of communication. University of Illinois, Urbana, Illinois, 1949.Google Scholar
  43. 43.
    D. Bonchev, O. Mekenyan, and N. Trinajstic. Isomer discrimination by topological information approach. J. Comput. Chem. 2:127–148 (1981).CrossRefGoogle Scholar
  44. 44.
    A. T. Balaban. Five new topological indices for the branching of tree-like graphs. Theor. Chim. Acta. 53:355–375 (1979).CrossRefGoogle Scholar
  45. 45.
    A. T. Balaban. Highly discriminating distance-based topological index. Chem. Phys. Lett. 89:399–404 (1982).CrossRefGoogle Scholar
  46. 46.
    Talete s.r.l. Dragon. [5.4.2006]. 2007. Milan (Italy).Google Scholar
  47. 47.
    R. Todeschini, and V. Consonni. Handbook of molecular descriptors. Wiley, Weinheim (Germany), 2000.Google Scholar
  48. 48.
    W. Zheng, and A. Tropsha. Novel variable selection quantitative structure–property relationship approach based on the k-nearest-neighbor principle. J. Chem. Inf. Comput. Sci. 40:185–194 (2000).PubMedCrossRefGoogle Scholar
  49. 49.
    V. N. Vapnik. In the nature of statistical learning theory. Springer, New York, 2000.Google Scholar
  50. 50.
    J. R. Votano, M. Parham, L. M. Hall, L. H. Hall, L. B. Kier, S. Oloff, and A. Tropsha. QSAR modeling of human serum protein binding with several modeling techniques utilizing structure-information representation. J. Med. Chem. 49:7169–7181 (2006).PubMedCrossRefGoogle Scholar
  51. 51.
    A. Tropsha, and A. Golbraikh. Predictive QSAR modeling workflow, model applicability domains, and virtual screening. Curr. Pharm. Des. 13:3494–3504 (2007).PubMedCrossRefGoogle Scholar
  52. 52.
    M. Shen, C. Beguin, A. Golbraikh, J. P. Stables, H. Kohn, and A. Tropsha. Application of predictive QSAR models to database mining: Identification and experimental validation of novel anticonvulsant compounds. J. Med. Chem. 47:2356–2364 (2004).PubMedCrossRefGoogle Scholar
  53. 53.
    L. Sachs. Applied statistics: A handbook of techniques. Springer, New York, 1984.Google Scholar
  54. 54.
    K. M. Mahar Doan, J. E. Humphreys, L. O. Webster, S. A. Wring, L. J. Shampine, C. J. Serabjit-Singh, K. K. Adkison, and J. W. Polli. Passive permeability and P-glycoprotein-mediated efflux differentiate central nervous system (CNS) and non-CNS marketed drugs. J. Pharmacol. Exp. Ther. 303:1029–1037 (2002).PubMedCrossRefGoogle Scholar
  55. 55.
    G. J. Durant, J. M. Loynes, and H. B. Wright. Potential histamine H2-receptor autagonists. 1. Aminoethylimidayo(1,2-a)pyridines and -imidayo(1,5-a)pyridines. J. Med. Chem. 16:1272–1276 (1973).PubMedCrossRefGoogle Scholar
  56. 56.
    P. D. Hansten, and R. H. Levy. Role of P-glycoprotein and organic anion transporting polypeptides in drug absorption and distribution—Focus on H-1-receptor antagonists. Clin. Drug Investig. 21:587–596 (2001).CrossRefGoogle Scholar
  57. 57.
    H. Zhu, A. Tropsha, D. Fourches, A. Varnek, E. Papa, P. Gramatica, T. Oberg, P. Dao, A. Cherkasov, and I. V. Tetko. Combinatorial QSAR modeling of chemical toxicants tested against tetrahymena pyriformis. J. Chem. Inf. Model. in press (2008).Google Scholar
  58. 58.
    M. Iyer, R. Mishru, Y. Han, and A. J. Hopfinger. Predicting blood–brain barrier partitioning of organic molecules using membrane-interaction QSAR analysis. Pharm. Res. 19:1611–1621 (2002).PubMedCrossRefGoogle Scholar
  59. 59.
    W. H. van de, G. Camenisch, G. Folkers, J. R. Chretien, and O. A. Raevsky. Estimation of blood–brain barrier crossing of drugs using molecular size and shape, and H-bonding descriptors. J. Drug Target. 6:151–165 (1998).CrossRefGoogle Scholar
  60. 60.
    K. Rose, L. H. Hall, and L. B. Kier. Modeling blood–brain barrier partitioning using the electrotopological state. J. Chem. Inf. Comput. Sci. 42:651–666 (2002).PubMedCrossRefGoogle Scholar
  61. 61.
    J. R. Votano, M. Parham, L. H. Hall, L. B. Kier, S. Oloff, A. Tropsha, Q. Xie, and W. Tong. Three new consensus QSAR models for the prediction of Ames genotoxicity. Mutagenesis. 19:365–377 (2004).PubMedCrossRefGoogle Scholar
  62. 62.
    L. H. Hall, and L. B. Kier. MDL QSAR modeling blood–brain barrier partitioning. 2002.
  63. 63.
    T. R. Stouch, and O. Gudmundsson. Progress in understanding the structure–activity relationships of P-glycoprotein. Adv. Drug Deliv. Rev. 54:315–328 (2002).PubMedCrossRefGoogle Scholar
  64. 64.
    P. Labute. A widely applicable set of descriptors. J. Mol. Graphics Modell. 18:464–477 (2000).CrossRefGoogle Scholar
  65. 65.
    T. Litman, T. Zeuthen, T. Skovsgaard, and W. D. Stein. Structure–activity relationships of P-glycoprotein interacting drugs: Kinetic characterization of their effects on ATPase activity. Biochim. Biophys. Acta. 1361:159–168 (1997).PubMedGoogle Scholar
  66. 66.
    T. Suzuki, N. Fukazawa, K. San nohe, W. Sato, O. Yano, and T. Tsuruo. Structure–activity relationship of newly synthesized quinoline derivatives for reversal of multidrug resistance in cancer. J. Med. Chem. 40:2047–2052 (1997).PubMedCrossRefGoogle Scholar
  67. 67.
    G. M. Keseru, and L. Molnar. High-throughput prediction of blood–brain partitioning: a thermodynamic approach. J. Chem. Inf. Comput. Sci. 41:120–128 (2001).PubMedCrossRefGoogle Scholar
  68. 68.
    T. Salminen, A. Pulli, and J. Taskinen. Relationship between immobilised artificial membrane chromatographic retention and the brain penetration of structurally diverse drugs. J. Pharm. Biomed. Anal. 15:469–477 (1997).PubMedCrossRefGoogle Scholar
  69. 69.
    X. L. Ma, C. Chen, and J. Yang. Predictive model of blood–brain barrier penetration of organic compounds. Acta Pharmacol. Sin. 26:500–512 (2005).PubMedCrossRefGoogle Scholar
  70. 70.
    A. R. Katritzky, M. Kuanar, S. Slavov, D. A. Dobchev, D. C. Fara, M. Karelson, W. E. Acree Jr., V. P. Solov’ev, and A. Varnek. Correlation of blood–brain penetration using structural descriptors. Bioorg. Med. Chem. 14:4888–4917 (2006).PubMedCrossRefGoogle Scholar
  71. 71.
    T. J. Hou, and X. J. Xu. ADME evaluation in drug discovery. 3. Modeling blood–brain barrier partitioning using simple molecular descriptors. J. Chem. Inf. Comput. Sci. 43:2137–2152 (2003).PubMedCrossRefGoogle Scholar
  72. 72.
    D. Pan, M. Iyer, J. Liu, Y. Li, and A. J. Hopfinger. Constructing optimum blood brain barrier QSAR models using a combination of 4D-molecular similarity measures and cluster analysis. J. Chem. Inf. Comput. Sci. 44:2083–2098 (2004).PubMedCrossRefGoogle Scholar
  73. 73.
    D. A. Winkler, and F. R. Burden. Modelling blood–brain barrier partitioning using Bayesian neural nets. J. Mol. Graph. Model. 22:499–505 (2004).PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Liying Zhang
    • 1
  • Hao Zhu
    • 1
  • Tudor I. Oprea
    • 2
  • Alexander Golbraikh
    • 1
  • Alexander Tropsha
    • 1
    Email author
  1. 1.The Laboratory for Molecular Modeling, School of PharmacyUniversity of North Carolina at Chapel HillChapel HillUSA
  2. 2.Division of Biocomputing, MSC11 6145University of New Mexico School of Medicine, University of New MexicoAlbuquerqueUSA

Personalised recommendations