Application of Artificial Neural Networks for Optimization of Preparation of Insulin Nanoparticles Composed of Quaternized Aromatic Derivatives of Chitosan

Abstract

The aim of this research was to develop an artificial neural network (ANN) in order to design a nanoparticulate oral drug delivery system for insulin. The pH of polymer solution (X₁), concentration ratio of polymer/insulin (X₂) and polymer type (X₃) in 3 level including methylated N-(4-N,N- dimethyl aminobenzyl) chitosan, methylated N-(4-pyridinyl) chitosan, and methylated N-(benzyl) chitosan are considered as the input values and the particle size, zeta potential, PdI, and entrapment efficiency (EE %) as output data. ANNs are employed to generate the best model to determining the relationships between input and response values. In this research, a multi-layer percepteron with different topologies has been tested in order to define the one with the best accuracy and performance. The optimization was used by minimizing the error between the predicted and observed values. Three training algorithms (Levenberg-Marquardt (LM), Bayesian-Regularization (BR), and Gradient Descent (GD)) were employed to train ANNs with various numbers of nodes, hidden layers and transfer functions by random selection. The accuracy of prediction data were assayed by the mean squared error (MSE).The ability of all algorithms was in the order: BR>LM>GD. Thus, BR was selected as the best algorithm.

Key words

artifical neural network (ANN) - Pharmaceutius - nanoparticles - Levenberg-Marquadt algorithm - Bayesian-Regulation (BR) algorithm - Gardient-Descent algorithm

• References

• 1 Gwinup G, Elias AN, Vaziri ND. A case for oral insulin therapy in the prevention of diabetic micro- and macroangiopathy. Int J Artif Organs 1990; 13: 393-395
• 2 Kowapradit J, Opanasopit P, Ngawhiranpat T et al. Methylated N-(4-N,Ndimethylaminobenzyl) chitosan, a novel chitosan derivative, enhances paracellular permeability across intestinal epithelial cells(Caco-2). AAPS PharmSci Tech 2008; 9: 1143-1152
• 3 Mahjub R, Dorkoosh FA, Amini M et al. Preparation, Statistical Optimization, and In vitro Characterization of Insulin Nanoparticles Composed of Quaternized Aromatic Derivatives of Chitosan. AAPS PharmSciTech 2011; 12: 1407-1419
• 4 Peh KK, Lim CP, Quek SS et al. Use of artificial neural network to predict drug dissolution profiles and evaluation of network performance using similarity factor. Pharm Res 2000; 17: 1384-1388
• 5 Barmplexis P, Kanaze FI, Kachrimanis K et al. Artificial neural networks in the optimization of a nimodipine controlled release tablet formulation. Eur J Pharm Biopharm 2010; 74: 316-323
• 6 Pham DT. An introduction to artificialcial neural networks. In: Bulsari AB. (ed.) Neural Networks for Chemical Engineering. Amsterdam: Elsevier; 1995. Chapter 1
• 7 Plumb AP, Rowe RC, York P et al. The effect of experimental design on the modeling of a tablet coating formulation using artificial neural networks. Eur J Pharm Sci 2002; 16: 281-288
• 8 Hecht-Nielsen R. Kolmogorov’s mapping neural network existence theorem. in: Proc First IEEE Int Joint Conf Neural Networks. San Diego: 1987: 11-14
• 9 Levenberg KA. Method for the Solution of Certain Non-linear Problems in Least Squares. Quarterly of Applied Mathematics 1994; 2: 164-168
• 10 Marquardt DW. An Algorithm for the Least-Squares Estimation of Nonlinear Parameters. SIAM Journal of Applied Mathematics 1963; 11: 431-441
• 11 De Freitas JFG. Bayesian Methods for Neural Networks. Cambridge University, Engineering Department; 1. 1999
• 12 Leighton RR. The Aspirin/MIGRAINES Software Tools. User’s Manual, Release V5.0. Technical Report MP-91W00050, MITRE Corporation, 1991
• 13 Nazari J, Ersoy OK. Implementation of back-propagation neural networks with Matlab. Purdue University School of Electrical Engineering, 9-1-1992
• 14 Ramasamy S, Desphande PB, Paxton GE et al. Consider neural networks for process identification. Hydrocarbon Processing 1995; 74: 59-62
• 15 Rumelhart DE, Hinton GE, Williams RJ. Leaning Internal Representations by Ewvr Propagation. In Rumelhart DE, McClelland JL. Pamllel Distributed Processing: Explorations in the Microstructure of Cognition. MIT Press; Cambridge Massachusette: 1986
• 16 Sakamoto H, Matsumoto K, Kuwahara A et al. Acceleration and stabilization techniques for the Levenberg-Marquardt method. IEICE Trans Fund 2005; E88-A 1971-1978
• 17 MacKay DJC. A Practical Bayesian Framework for Back propagation Network. Neural Computation 1992; 4: 448-472
• 18 Burden F, Winkler D. Bayesian regularization of neural networks. Methods Mol Biol 2008; 458: 25-44
• 19 Zhang L. Parallel training algorithms for analogue hardware neural nets. Ph.D thesis. School of software engineering and Data communication. Queensland University of Technology; Australia: 2007