Qsar Analysis of the Estrogen Activities of Bisphenol a Analogs using Multiple Linear Regression and Artificial Neural Network

Abstract

Abstract. This study gives a quantitative structure-activity relationship (QSAR) analysis of the estrogen activities of bisphenol A and analogs. The chemical structures of 23 Bisphenol A analogs have been characterized by quantum-electronic descriptors. The present study was performed using multiple regression analysis (MLR) and artificial neural network (ANN). The quantitative model was accordingly proposed and the toxicity of the compounds was interpreted based on the multivariate statistical analysis. This study shows that the results obtained by MLR were suitable and have served to predict estrogen activities, but compared to the results of the ANN model, we conclude that the prediction achieved by the latter is more effective and better than MLR model. Following to the obtained results, our proposed model may be useful to predict of Estrogen activities and risk assessment of chemicals. Keywords QSAR, Bisphenol A, multiple linear regression, artificial neural network References [1] Rezg R, El-Fazaa S, Gharbi N, Mornagui B (March 2014). "Bisphenol A and human chronic diseases: Current evidences, possible mechanisms, and future perspectives".Environment International 2014, 64, 83–90. [2] Melzer D, Rice NE, Lewis C, Henley WE, Galloway TS (2010). Zhang, Baohong, ed."Association of Urinary Bisphenol a Concentration with Heart Disease: Evidence from NHANES 2003/06". PLoS ONE 5 (1). [3] Manikkam, M.; Tracey, R.; Guerrero-Bosagna, C.; Skinner, M. K. (January 24, 2013). "Plastics derived endocrine disruptors (BPA, DEHP and DBP) induce epigenetic transgenerational inheritance of obesity, reproductive disease and sperm epimutations".PLoS ONE 8 (1). 1–16. [4] D.R. Doerge, N.C. Twaddle, M. Vanlandingham, R.P. Brown, J.W. Fisher, Toxicol. Appl. Pharmacol. 2011, 255, 261.[5] Ho SM, Tang WY, Belmonte de Frausto J, Prins GS (2006). "Developmental exposure to estradiol and bisphenol A increases susceptibility to prostate carcinogenesis and epigenetically regulates phosphodiesterase type 4 variant 4". Cancer Res. 66 (11): 5624–32. [6] Johanna R. Rochester and Ashley L. Bolden (2015 Jul) “Bisphenol S and F: A Systematic Review and Comparison of the Hormonal Activity of Bisphenol A Substitutes”. Environ Health Perspect123(7):643-50.[7] Kelly, P. C., William, A. T., Thomas, E. W., QSAR models of thein vitro estrogen activity of bisphenol A analogs, QSAR Comb.Sci., 2003, 22: 78―88.[8]. Frisch, M. J. T., G. W. et al , Gaussian 09, Revision D.01. Gaussian, Inc., Wallingford CT, 2009.[9]. Zhao, Y.; Truhlar, D., The M06 suite of density functionals for main group thermochemistry, thermochemical kinetics, noncovalent interactions, excited states, and transition elements: two new functionals and systematic testing of four M06-class functionals and 12 other functionals. Theor Chem[10] J. Devillers (1996), Strengths and Weaknesses of the Backpropagation Neural Network in QSAR and QSPR Studies, in: J. Devillers (Ed.) Neural Networks in QSAR and Drug Design, Academic Press, London, pp.1-46.[11] K. Hornik (1991), AppSroximation capabilities of multilayer feedforward networks, Neural Networks, 4 251-257.[12] A. Adad, M. Larif, R. Hmamouchi, M. Bouachrine, T. Lakhlifi, J. Comp. Meth. Mol. Des. 4(3) (2014) 72-83.[13] A. Golbraikh, A. Tropsha, Beware of q2. J. Mol. Graphics Model. 20 (2002) 269–276.