Linear and nonlinear modeling of antifungal activity of some heterocyclic ring derivatives using multiple linear regression and Bayesian-regularized neural networks


Antifungal activity was modeled for a set of 96 heterocyclic ring derivatives (2,5,6-trisubstituted benzoxazoles, 2,5-disubstituted benzimidazoles, 2-substituted benzothiazoles and 2-substituted oxazolo(4,5-b)pyridines) using multiple linear regression (MLR) and Bayesian-regularized artificial neural network (BRANN) techniques. Inhibitory activity against Candida albicans (log(1/C)) was correlated with 3D descriptors encoding the chemical structures of the heterocyclic compounds. Training and test sets were chosen by means of k-Means Clustering. The most appropriate variables for linear and nonlinear modeling were selected using a genetic algorithm (GA) approach. In addition to the MLR equation (MLR–GA), two nonlinear models were built, model BRANN employing the linear variable subset and an optimum model BRANN–GA obtained by a hybrid method that combined BRANN and GA approaches (BRANN–GA). The linear model fit the training set (n=80) with r 2=0.746, while BRANN and BRANN–GA gave higher values of r 2=0.889 and r 2=0.937, respectively. Beyond the improvement of training set fitting, the BRANN-GA model was superior to the others by being able to describe 87% of test set (n=16) variance in comparison with 78 and 81% the MLR–GA and BRANN models, respectively. Our quantitative structure–activity relationship study suggests that the distributions of atomic mass, volume and polarizability have relevant relationships with the antifungal potency of the compounds studied. Furthermore, the ability of the six variables selected nonlinearly to differentiate the data was demonstrated when the total data set was well distributed in a Kohonen self-organizing neural network (KNN).

General structure of heterocyclic ring derivatives

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6


  1. 1.

    Georgopapadakou NH (1998) Curr Opin Microbiol 1:547–557

    Article  CAS  Google Scholar 

  2. 2.

    St-Georgiev V (2000) Curr Drug Targets 1:261–284

    Article  CAS  Google Scholar 

  3. 3.

    Rex JH, Walsh TJ, Sobel JD, Filler SG, Pappas PG, Dismukes WE, Edwards JE (2000) Clin Infect Dis 30:662–678

    Article  CAS  Google Scholar 

  4. 4.

    Meyers FH, Jawetz E, Goldfien A (1976) Review of medical pharmacology. Lange Medical Pub, California

    Google Scholar 

  5. 5.

    Tafi A, Costi R, Botta M, Di Santo R, Corelli F, Massa S, Ciacci A, Manetti F, Artico M (2002) J Med Chem 45:2720–2732

    Article  CAS  Google Scholar 

  6. 6.

    Chan JH., Hong, JS, Kuyper LF, Baccanari DP, Joyner SS, Tansik RL, Boytos CM, Rudolph SK (1995) J Med Chem 38:3608–3616

    Article  CAS  Google Scholar 

  7. 7.

    Elnima EI, Zubair MU, Al-Badr AA (1981) Antimicrob Agents Chemother 19:29–32

    CAS  Google Scholar 

  8. 8.

    Göker H, Kus C, Boykin DW, Yildizc S, Altanlarc N (2002) Bioorg Med Chem 10:2589–2596

    Article  Google Scholar 

  9. 9.

    Yildiz-Oren I, Yalcin I, Aki-Sener E, Ucarturk N (2004) Eur J Med Chem 39:291–298

    Article  CAS  Google Scholar 

  10. 10.

    Yalcin I, Sener E, Ozden T, Ozden S, Akin A (1990) Eur J Med Chem 25:705–708

    Article  CAS  Google Scholar 

  11. 11.

    Hansch C, Leo A (1995) Exploring QSAR. Fundamentals and applications in chemistry and biology, ACS professional reference book. American chemical society, Washington DC

    Google Scholar 

  12. 12.

    Yalcin I, Oren I, Temiz O, Sener EA (2000) Acta Biochim Pol 47:481–486

    CAS  Google Scholar 

  13. 13.

    García-Domenech R, Ríos-Santamarina I, Catalá A, Calabuig C, del Castillo L, Gálvez J (2003) J Mol Struct (THEOCHEM) 624:97–107

    Article  CAS  Google Scholar 

  14. 14.

    Hasegawa K, Deushi T, Yaegashi O, Miyashita Y, Sasaki S (1995) Eur J Med Chem 30:569–574

    Article  CAS  Google Scholar 

  15. 15.

    Mghazli S, Jaouad A, Mansour M, Villemin D, Cherqaoui D (2001) Chemosphere 43:385–390

    Article  CAS  Google Scholar 

  16. 16.

    Mackay DJC (1992) Neural Comput 4:415–447

    Article  Google Scholar 

  17. 17.

    Stewart JJP (1989) J Comp Chem 10:210–220

    Google Scholar 

  18. 18.

    MOPAC 6.0 (1993) Frank J Seiler Research Laboratory, US Air Force academy, Colorado Springs, CO

  19. 19.

    Todeschini R, Consonni V, Pavan M (2002) Dragon software version 2.1

  20. 20.

    Todeschini R, Consonni V (2000) Handbook of molecular descriptors. Wiley-VCH, Weinheim

    Google Scholar 

  21. 21.

    Kruszewski J, Krygowski TM (1972) Tetrahedron Lett 36:3839–3842

    Article  Google Scholar 

  22. 22.

    Jug K (1983) J Org Chem 48:1344–1348

    Article  CAS  Google Scholar 

  23. 23.

    Randic M (1995) J Chem Inf Comput Sci 35:372–382

    Google Scholar 

  24. 24.

    Hemmer MC, Steinhauer V, Gasteiger J (1999) Vibrat Spect 19:151–154

    Article  CAS  Google Scholar 

  25. 25.

    Schuur J, Selzer P, Gasteiger J (1996) J Chem Inf Comput Sci 36:334–344

    Article  CAS  Google Scholar 

  26. 26.

    Todeschini R, Lansagni M, Marengo E (1994) J Chemom 8:263–272

    Article  CAS  Google Scholar 

  27. 27.

    Consonni V, Todeschini R, Pavan M (2002) J Chem Inf Comput Sci 42:682–692

    Article  CAS  Google Scholar 

  28. 28.

    Mc Farland JW, Gans DJ (1995) Cluster significance analysis. In: Manhnhold R, Krogsgaard-Larsen P, Timmerman H (eds) Method and principles in medicinal chemistry, vol 2. Chemometric methods in molecular design. van Waterbeemd H (ed) VCH Weinheim, pp 295–307

  29. 29.

    Gao H, Lajiness MS, Van Drie J (2002) J Mol Graph Model 20:259–268

    Article  CAS  Google Scholar 

  30. 30.

    So SS, Karplus M (1996) J Med Chem 39:1521–1530

    Article  CAS  Google Scholar 

  31. 31.

    Matlab 7.0 (2004) The Math Works Inc

  32. 32.

    The MathWorks Inc (2004) Genetic algorithm and direct search toolbox user’s guide for use with MATLAB. The Mathworks Inc, Massachusetts

  33. 33.

    Hemmateenejad B, Safarpour MA, Miri R, Nesari N (2005) J Chem Inf Model 45:190–199

    Article  CAS  Google Scholar 

  34. 34.

    Zupan J, Gasteiger J (1991) Anal Chim Acta 248:1–30

    Article  CAS  Google Scholar 

  35. 35.

    Burden FR, Winkler D (2000) Chem Res Toxicol 13:436–440

    Article  CAS  Google Scholar 

  36. 36.

    Kohonen T (1987) Self-organization and associative memory, 2nd edn. Springer-Verlag, Berlin

    Google Scholar 

  37. 37.

    Wold S (1991) Quant Struct–Act Relat 10:191–193

    Article  CAS  Google Scholar 

  38. 38.

    Moreau G, Broto P (1980) Nouv J Chim 4:757–764

    CAS  Google Scholar 

  39. 39.

    Foresee FD, Hagan MT (1997) Gauss-Newton approximation to Bayesian regularization. Proceedings of the 1997 International joint conference on neural networks 1930–1935

  40. 40.

    Bazoui H, Zahouily M, Sebti S, Boulajaaj S, Zakarya D (2002) J Mol Model 8:1–7

    Article  CAS  Google Scholar 

  41. 41.

    Fernández M, Caballero J, Helguera AM, Castro EA, González MP (2005) Bioorg Med Chem 13:3269–3277

    Article  CAS  Google Scholar 

  42. 42.

    Golbraikh A, Tropsha A (2002) J Comp Aided Mol Design 16:357–369

    Article  CAS  Google Scholar 

  43. 43.

    González MP, Helguera AM (2003) J Comp Aided Mol Design 17:665–672

    Article  Google Scholar 

Download references


Authors would like to acknowledge the anonymous referee for his useful comments that helped to improve the quality of the manuscript.

Author information



Corresponding author

Correspondence to Michael Fernández.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Caballero, J., Fernández, M. Linear and nonlinear modeling of antifungal activity of some heterocyclic ring derivatives using multiple linear regression and Bayesian-regularized neural networks. J Mol Model 12, 168–181 (2006).

Download citation


  • QSAR analysis
  • Neural network
  • Bayesian regularization
  • Heterocyclic ring derivatives
  • Antifungal activity