Artificial Neural Networks Analysis Used to Evaluate the Molecular Interactions between Selected Drugs and Human Cyclooxygenase2 Receptor

Tayarani, Ali; Baratian, Ali; Bagher Naghibi Sistani, Mohammad; Saberi, Mohammad Reza; Tehranizadeh, Zeinab

doi:10.22038/ijbms.2013.1938

Artificial Neural Networks Analysis Used to Evaluate the Molecular Interactions between Selected Drugs and Human Cyclooxygenase2 Receptor

Document Type : Original Article

Authors

¹ Department of Electrical Engineering, Ferdosi University of Mashad, Mashad, Iran

² School of Pharmacy, Mashhad University of Medical Sciences, Mashad, Iran

10.22038/ijbms.2013.1938

Abstract

Objective(s):
A fast and reliable evaluation of the binding energy from a single conformation of a molecular complex is an important practical task. Artificial neural networks (ANNs) are strong tools for predicting nonlinear functions which are used in this paper to predict binding energy. We proposed a structure that obtains binding energy using physicochemical molecular descriptions of the selected drugs.

Material and Methods:
The set of 33 drugs with their binding energy to cyclooxygenase enzyme (COX2) in hand, from different structure groups, were considered. 27 physicochemical property descriptors were calculated by standard molecular modeling. Binding energy was calculated for each compound through docking and also ANN. A multi-layer perceptron neural network was used.
Results:
The proposed ANN model based on selected molecular descriptors showed a high degree of correlation between binding energy observed and calculated. The final model possessed a 27-4-1 architecture and correlation coefficients for learning, validating and testing sets equaled 0.973, 0.956 and 0.950, respectively.
Conclusion:
Results show that docking results and ANN data have a high correlation. It was shown that ANN is a strong tool for prediction of the binding energy and thus inhibition constants for different drugs in very short periods of time.

Keywords

Artificial Neural Networks Binding Energy Cyclooxygenase 2 COX2 Docking

References

1. Lengauer T, Rarey M. Computational methods for biomolecular docking. Curr Opin Struct Biol 1996; 6:402-046.

2. Kitchen DB, Decornez H, Furr JR, Bajorath J. Docking and scoring in virtual screening for drug discovery: methods and applications. Nat Rev Drug Discov 2004; 3:935-949.

3. Goldman BB, Wipke WT. QSD quadratic shape descriptors. 2. Molecular docking using quadratic shape descriptors (QSDock). Proteins 2000; 38:79-94.

4. Feig M, Onufriev A, Lee MS, Im W, Case DA, Brooks CL, 3rd. Performance comparison of generalized born and Poisson methods in the calculation of electrostatic solvation energies for protein structures. J Comput Chem 2004; 25:265-284.

5. Cai W, Shao X, Maigret B. Protein-ligand recognition using spherical harmonic molecular surfaces: towards a fast and efficient filter for large virtual throughput screening. J Mol Graph Model 2002; 20:313-328.

6. Morris RJ, Najmanovich RJ, Kahraman A, Thornton JM. Real spherical harmonic expansion coefficients as 3D shape descriptors for protein binding pocket and ligand comparisons. Bioinformatics 2005; 21:2347-2355.

7. Bucinski A, Wnuk M, Gorynski K, Giza A, Kochanczyk J, Nowaczyk A,

et al. Artificial neural networks analysis used to evaluate the molecular interactions between selected drugs and human alpha1-acid glycoprotein. J Pharm Biomed Anal 2009; 50:591-996.

8. Yamamura S. Clinical application of artificial neural network (ANN) modeling to predict pharmacokinetic parameters of severely ill patients. Adv Drug Deliv Rev 2003; 55:1233-2251.

9. Temurtas H, Yumusak N, Temurtas F. A comparative study on diabetes disease diagnosis using neural networks. Expert Sys Appl 2009; 36:8610-1625.

10. Park J, Edington DW. A sequential neural network model for diabetes prediction. Artif Intell Med 2001;23:277-293.

11. Ergün U, Serhatlıo

ǧlu S, Hardalaç F, Güler İ. Classification of carotid artery stenosis of patients with diabetes by neural network and logistic regression. Compu Biol Med 2004; 34:389-405.

12. Jouyban A, Majidi MR, Jalilzadeh H, Asadpour-Zeynali K. Modeling drug solubility in water-cosolvent mixtures using an artificial neural network. Farmaco 2004; 59:505-912.

13. Agatonovic-Kustrin S, Beresford R. Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. J Pharm Biomed Anal 2000; 22:717-727.

14. Huuskonen J. Estimation of aqueous solubility for a diverse set of organic compounds based on molecular topology. J Chem Inf Comput Sci 2000; 40:773-777.

15. Hu L, Chen G, Chau RM-W. A neural networks-based drug discovery approach and its application for designing aldose reductase inhibitors. J Mol Graph Modell 2006; 24:244-253.

16. Turner JV, Maddalena DJ, Cutler DJ. Pharmacokinetic parameter prediction from drug structure using artificial neural networks. Int J Pharm 2004; 270:209-219.

17. Jamshed A, Iqbal M, Chaudhary M, Yasin T, Massey S. A QSPR study of drug release from an arabinoxylan using

ab initio optimization and neural networks. Carbohydr Polym 2012; 88 2:2 348-1357.

18. Erić S, Kalinić M, Popović A, Zloh M, Kuzmanovski l. Prediction of aqueous solubility of drug-like molecules using a novel algorithm for automatic adjustment of relative importance of descriptors implemented in counter-propagation artificial neural networks. Int J Pharm 2012; 437

:232-241.

19. Menhaj MB. Computational intelligence: Fundamental of neural networks, Tehran: Amirkabir university of technology publication, Second Edition (2005).

20. Bowen WR, Jones MG, Yousef HNS. Dynamic ultrafiltration of proteins – A neural network approach. J Membrane Sci 1998; 146:225-235.