Abstract
In this work, two logistic regression (LR) and artificial neural networks (ANNs) were applied for seeking quantitative structure–activity relationships (QSARs) that correlate structural descriptors and inhibition activity of tyrosinase inhibitors. This study was devoted to extraction of the most effective structural features of these inhibitors from a large number of quantitative descriptors. Many quantitative descriptors were generated to express the physicochemical properties of 35 compounds with optimized structures. After filtration of these descriptors, 39 of them remained and selected for QSAR study. Logistic regression was used to non-linearly select different subsets of descriptors and develop for prediction of IC50. The best subset then fed to artificial neural network as non-linear procedure. The best prediction model was found to be a 3–11–1 artificial neural network. The evaluating indices (FC, FAR and POD) of this prediction model were found 84.75, 13.48 and 93.15 %, respectively. The conformability of results by the network model and logistic regression ensured the effectiveness of the selected structural features (descriptors).
Similar content being viewed by others
References
A.A. Saboury, J. Iran. Chem. Soc. 6, 219 (2009)
S.Y. Seo, V.K. Sharma, N. Sharma, J. Agric. Food Chem. 51, 2837 (2003)
K.M. Khan, G.M. Maharvi, M.T.H. Khan, Bioorg. Med. Chem. 14, 344 (2006)
M. Shiino, Y. Watanabe, K. Umezawa, Bioorg. Med. Chem. 9, 1233 (2001)
K.T. Yasunobu, M. Gordon, Pigment Cell Biology (Academic Press, New York, 1959), p. 583
F. Artes, M. Castaner, M.I. Gil, J. Agric. Food Chem. 4, 377 (1998)
N. Yokochi, T. Morita, T. Yagi, J. Agric. Food Chem. 51, 2733 (2003)
O. Nerya, R. Musa, S. Khatib, S. Tamir, J. Vaya, J. Phytochem. 65, 1389 (2004)
K. Maeda, M. Fukuda, J. Soc. Cosmet. Chem. 42, 361 (1991)
K. Maeda, M. Fukuda, J. Pharm. Exp. Ther. 276, 765 (1996)
Q.X. Chen, I. Kubo, J. Agric. Food Chem. 50, 4108 (2002)
S. Khatib, O. Nerya, R. Musa, S. Tamir, T. Pete, J. Vaya, J. Med. Chem. 50, 2676 (2007)
S. Goll, P. Jurs, J. Chem. Inf. Comput. Sci. 39, 1081 (1999)
J. Tetteh, T. Suzuki, E. Metcalfe, S. Howells, J. Chem. Inf. Comput. Sci. 39, 491 (1999)
J. Zupan, J. Gasteiger, Neural Networks for Chemists: An Introduction (VCH, Weinheim, 1993), p. 213
J.A. Burns, G. Whitesides, Chem. Rev. 93, 2583 (1993)
D. Svozil, V. Kvasnicka, Pospichal, J. Chem. Intell. Lab. Sys. 39, 43 (1997)
S. Agatonovic Kustrin, H. L. Ling, S. Y. Tham, R. G. Alany, J. Pharm. Biomed. Anal. 29, 103 (2002)
J. Liu, W. Yi, Y. Wan, L. Ma, H. Song, J. Bioorg. Med. Chem. 16, 1096 (2008)
W. Yi, R. Cao, Z. Chen, L. Yu, L. Ma, H. Song, J. Chem. Pharm. Bull. 57(11), 1273 (2009)
Hyperchem v. 7.5. Hypercube Inc., Gainesville
M.J.S. Dewar, E.G. Zoebisch, E.F. Healy, J.J.P. Stewart, J. Am. Chem. Soc. 107, 3902 (1985)
D.Z. Chen, Y.Q. Chen, S.X. Hu, Comput. Chem. 21(2), 109–113 (1997)
K.J. Hunt, D. Sbarbaro et al., Automatica. 28(9), 1083–1112 (1992)
G. Kateman, Chemom. Intell. Lab. Syst. 19, 135–142 (1993)
I.A. Basheer, M. Hajmeer, J. Microbiol. Methods 43, 23–31 (2000)
M.R. Sohrabi, P. Abdolmaleki et al., Indian J. Chem. 43A, 2582 (2004)
M. Hajmeer, I. Basheer, J. Food Microbiol. 20, 43 (2003)
I. Kanellopoula, G.G. Wilkinson, Int. J. Remote Sens. 18, 711–725 (1997)
I. Kaastra, M. Boyd, Neurocomputing. 10, 215–236 (1996)
C. Alderich, M.A. Reuter, J.S.J. Deventer, Miner. Eng. 7, 789–809 (1994)
R. Todeschini, V. Consonni, Handbook of Molecular Descriptors (Wiley, Weinheim, 2000)
V. Consonni, R. Todeschini, M. Pavan, J. Chem. Inf. Comput. Sci. 42, 682 (2002)
V. Consonni, R. Todeschini, M. Pavan, J. Chem. Inf. Comput. Sci. 42, 693 (2002)
Y. Matoba, T. Kumagai, A. Yamamoto, H. Yoshitsu, M. Sugiyama, J. Biol. Chem. 281, 8981 (2006)
T. Klabunde, C. Eicken, Nat. Struct. Biol. 5, 1084 (1998)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mahmood Janlou, M.A., Abdolmaleki, P., Tajbakhsh, M. et al. Quantitative structure–activity relationships study of tyrosinase inhibitors using logistic regression and artificial neural networks. J IRAN CHEM SOC 9, 643–653 (2012). https://doi.org/10.1007/s13738-012-0083-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13738-012-0083-6