Quantitative Structure Activity Relationship Prediction of Oral Bioavailabilities Using Support Vector Machine

  • Fatemi, Mohammad Hossein ;
  • Fadaei, Fatemeh
  • Received : 2014.07.16
  • Accepted : 2014.09.18
  • Published : 2014.12.20


A quantitative structure activity relationship (QSAR) study is performed for modeling and prediction of oral bioavailabilities of 216 diverse set of drugs. After calculation and screening of molecular descriptors, linear and nonlinear models were developed by using multiple linear regression (MLR), artificial neural network (ANN), support vector machine (SVM) and random forest (RF) techniques. Comparison between statistical parameters of these models indicates the suitability of SVM over other models. The root mean square errors of SVM model were 5.933 and 4.934 for training and test sets, respectively. Robustness and reliability of the developed SVM model was evaluated by performing of leave many out cross validation test, which produces the statistic of $Q^2_{SVM}=0.603$ and SPRESS = 7.902. Moreover, the chemical applicability domains of model were determined via leverage approach. The results of this study revealed the applicability of QSAR approach by using SVM in prediction of oral bioavailability of drugs.


Quantitative structure activity relationship;Support vector machine;Multiple linear regressions;Oral bioavailability;Molecular descriptors


  1. Moda, T. L.; Montanari, C. A.; Andricopulo, A. D. J. Bioorg. Med. Chem. 2007, 15, 7738.
  2. Andrews, C. W.; Bennett, L.; Lawrence, X. Y. J. Pharm. Res. 2000, 17, 639.
  3. Yasri, A.; Hartsough, D. J. Chem. Inf. Comput. Sci. 2001, 41, 1218.
  4. Turner, J. V.; Maddalena, D. J.; Agatonovic-Kustrin, S. J. Pharm. Res. 2004, 21, 68.
  5. Todeschini, R.; Consonni, V. Handbook of Molecular Descriptors; WILEY-VCH Verlag GmbH: 2000, Vol. 11, p 516.
  6. The Dragon Website.
  7. Hyper Chem Release 7.0 for windows; Hypercube, Inc., 2002.
  8. Stewart, J. P. P. MOPAC 6.0, Quantum Chemistry Program Exchange, vol. 455; India University: Bloomington, 1989.
  9. Cortes, C.; Vapnik, V. J. M. l. R. 1995, 20, 273.
  10. Bennett, K. P.; Campbell, C. J. ACM. SIGKDD. 2000, 2, 1.
  11. Fatemi, M. H.; Gharaghani, S.; Mohammadkhani, S.; Rezaie, Z. J. Electrochim. Acta. 2008, 53, 4276.
  12. Fatemi, M. H.; Dorostkar, F.; Ghorbannezhad, Z. J. Monatsh. Chem. Chem. Mon. 2011, 142, 1061.
  13. Yang, S. Y.; Huang, Q.; Li, L. L.; Ma, C. Y.; Zhang, H.; Bai, R.; Teng, Q. Z.; Xiang, M. L.; Wei, Y. Q. J. Artif. Intell. Med. 2009, 46, 155.
  14. Golmohammadi, H.; Dashtbozorgi, Z.; Acree Jr., W. E. J. Pharm. Sci. 2012, 47, 421.
  15. Kermani, B.; Kozlov, I.; Melnyk, P.; Zhao, C.; Hachmann, J.; Barker, D.; Lebl, M. J. Sens. Actuators, B. 2007, 125, 149.
  16. Consonni, V.; Todeschini, R.; Pavan, M. J. Chem. Inf. Comput. Sci. 2002, 42, 682.
  17. Balaban, A. T, 1983. J. Pure & Appl. Chem. 1983, 55, 199.
  18. Broto, P.; Moreau, G.; Vandycke, C. J. Med. Chem. 1984, 19, 66.
  19. Gramatica, P. J. QSAR. Comb. Sci. 2007, 26, 694.
  20. Tropsha, A.; Gramatica, P.; Gombar, V. K. J. QSAR. Comb. Sci. 2003, 22, 69.
  21. Maldonado, A. G.; Doucet, J.; Petitjean, M.; Fan, B.T. J. Mol. Diversity. 2006, 10, 39.
  22. Zhu, J., Wang, J.; Yu, H.; Li, Y.; Hou, T. Chem. High Throughput Screening. 2011, 14, 362.
  23. Turner, J. V.; Glass, B. D.; Agatonovic Kustrin, S. J. Anal. Chim. Acta. 2003, 485, 89.
  24. Wang, J.; Krudy, G.; Xie, X. Q.; Wu, C.; Holland, G. J. Chem. Inf. Model. 2006, 46, 2674.
  25. Kumar, R.; Sharma, A.; Varadwaj, P. K. J. Nat. Sci. Bio. Med. 2011, 2, 168.

Cited by

  1. Computational approaches to find the active binding sites of biological targets against busulfan vol.22, pp.6, 2016,


Supported by : the Korean Chemical Society