Defining the Possible Molecular Structure of the Drug to Be Penetrated through Skin Layers Using Genetic Algorithm

Abstract

The scientists in the past when they were trying to solve the problem of relationship between parameters by using trial and errors method, due to increase of the number of parameters problem of deadlock or non-evaluation of the solution has occurred.  They tried to find new techniques in order to solve the problems of parameters and positive results were taken from genetic algorithms of artificial intelligence. Genetic algorithm which has an optimization technique has been identified as a non-traditional type of research techniques. The implementation of genetic algorithm have been realized in the identification of quotients of penetration of chemicals through skin and Delphi 7.0 and MOLGA (MOLecule and Genetic Algorithm) program was set up in this work. Genetic algorithm method was used in solving the problems of multi parameters optimization problems. 11 parameters were taken as the basis of the molecular structure of the chemicals, and random method has chosen in the optimization of the genetic algorithm. As the coherence function for the implementation of genetic algorithm regression equation of penetration through skin quotients based on the parameters have been used. It was seen that, when the quotients identified according to the MOLGA program results and molecular structure were compared there was very little margin of error. At the same time, molecular structure of the chemicals within MOLGA program has to be changed and developed.

Key words: Quotients of penetration, Genetic algorithms, Molga.

Keywords

• Quotients of penetration, Genetic algorithms, Molga

Algorithm

Abstract

References

1. Degim, I. T. “Understanding skin penetration: Computer aided modeling and data interpretation”, Current Computer-Aided Drug Design, 1, 11-20, (2005).
2. Pugh, W. J., Degim, I. T. and Hadgraft, J., “Epidermal relationships: 4, QSAR of permeant diffusion across human stratum corneum in terms of molecular weight, H-bonding and electronic charge”, Int. J. Pharm., 197, 203–211, (2000). structure
3. Kustrin A. R. Beresford and Yusof, A. P. “ANN modeling polydimethylsiloxane membrane from theoretically derived molecular descriptors”, J. Pharm. Biomed. Anal., 26, 241–254, (2001). across a
4. Addicks, W. J., Flynn, G.L., Weiner, N. and Chiang, C. M. “Drug transport from thin applications of topical dosage forms: development of methodology”, Pharm. Res. 5, 377– 382, (1988).
5. Jetzer, W. E., Huq, A. S., Ho, N. F, Flynn, G. L., Duraiswamy, N. and Condie L. Jr. “Permeation of mouse skin and silicone rubber membranes by phenols: relationship to in vitro partitioning”, J. Pharm. Sci. 75, 1098–1103, (1986).
6. Chen, Y., Vayuhasuwan, P. and Matheson, L. E. “Prediction of flux through polydimethylsiloxane membranes using atomic charge calculations: application to an extended data set”, Int. J. Pharm. 137, 149–158, (1996).
7. Chen, Y., Yang, W. L. and Matheson L.E. “Prediction of flux through polydimethylsiloxane membranes using atomic charge calculations”, Int. J. Pharm. 94 81–88, (1993).
8. Cronin, M. T., Dearden, J. C. Gupta, R. and Moss, G. P. “An investigation of the mechanism of uxacrosspolydi-methylsiloxane membranes by use of quantitative structure-permeability relationships”, J. Pharm. Pharmacol. 50, 143–152, (1998).

9. Degim T., Hadgraft J., Ilbasmis S. and Ozkan Y. “Prediction of skin penetration using artificial neural network (ANN) modeling”, J. Pharm. Sci. 92, 656– 664, (2003).
10. Murty, K. G. Operations Research Deterministic Optimal Models, Prentice Hall, N.J., , p 581, (1995).
11. Karaboga, D., Yapay Zeka Optimizasyon Algoritmaları, Atlas Yayınevi, Yayın No: 38, Istanbul, 79p, (2004).
12. Mitchell, M. An Introduction to Genetic Algorithms, MIT Press, Massachusetts, p 205, (1996).
13. Pugh W. J. and Hadgraft J., “Ab initio prediction of human skin permeability coefficients”, Int. J. Pharm., 103: 163-178, (1994).
14. Degim I. Pugh, W.J. Hadgraft, J. “Skin permeability: Anomalous results”, Int. J. Pharm. 170:129 – 133, (1998).