QSPR Studies on n-Octanol/Water Partition Coefficient of Polychlorinated Biphenyls by Using Artificial Neural Network

Abstract:

Quantitative structure property relationship (QSPR) model for predicting the n-octanol/water partition coefficient, Kow, of 21 polychlorinated biphenyls (PCBs) was investigated. The structure of the investigated PCBs is mathematically characterized by using molecular distance-edge vector (MDEV) index, a topological index which is developed based on the topological method. The calibration model of Kow was developed by using radial basis function artificial neural network (RBF ANN). Leave one out cross validation was carried out to assess the predictive ability of the developed QSPR model. The R2 between the predicted and experimental logKow is 0.9793. The prediction RMS%RE for the 21 PCBs is 1.92. It is demonstrated that there is a quantitative relationship between the MDEV index and the Kow of the 21 PCBs. RBF ANN is shown to practicable for developing the QSPR model for Kow of PCBs.

• Periodical: Advanced Materials Research (Volumes 455-456)
• Pages: 925-929
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.455-456.925
• Online since: January 2012
• Authors: Long Jiao
• Keywords: Artificial Neural Network (ANN), Molecular Distance-Edge Vector Index, n-Octanol/Water Partition Coefficient, PCB, QSPR

References

[1] European Commission, http: /ec. europa. eu/environment/pops/index _en. htm, updated on Jan. 15th (2011).

[2] X.Y. Han, Z.Y. Wang, Z.C. Zhai, and L.S. Wang, Estimation of n-octanol/water partition coefficients (Kow) of all PCB congeners by ab initio and a Cl substitution position method, QSAR Comb. Sci., vol. 25, p.333 – 341, (2006).

DOI: 10.1002/qsar.200530141

[3] M.S. Petersen, J. Halling, P. Damkier, F. Nielsen ,P. Grandjean, P. Weihe, et al., Polychlorinated biphenyl (PCB) induction of CYP3A4 enzyme activity in healthy Faroese adults, Toxicol. Appl. Pharma., vol. 224, p.202–206, (2007).

DOI: 10.1016/j.taap.2007.07.002

[4] P. Rulle, The n-octanol and n-hexane/water partition coefficient of environmentally relevant chemicals predicted from the mobile order and disorder (MOD) thermodynamics, Chemosphere, vol. 40, pp.457-512, (2000).

DOI: 10.1016/s0045-6535(99)00268-4

[5] J. Padmanabhan, R. Parthasarathi, V. Subramaniana, and P.K. Chattaraj, QSPR models for polychlorinated biphenyls: n-octanol/water partition coefficient, Bioorg. Med. Chem., vol. 14, p.1021–1028, (2006).

DOI: 10.1016/j.bmc.2005.09.017

[6] D.R. Zhang, QSPR studies of PCBs by the combination of genetic algorithms and PLS analysis, Comput. Chem., vol. 25, pp.197-204, (2001).

DOI: 10.1016/s0097-8485(00)00081-4

[7] P. Ruiza, O. Faroona, C.J. Moudgal, H. Hansena, C.T. De Rosa, and M. Mumtaz, Prediction of the health effects of polychlorinated biphenyls (PCBs) and their metabolites using quantitative structure–activity relationship (QSAR), , Toxicol. Lett., p.181, 53–65, (2008).

DOI: 10.1016/j.toxlet.2008.06.870

[8] E.S. Heimstada, and P.L. Andersson, Docking and QSAR studies of an indirect estrogenic effect of hydroxylated PCBs, Quant. Struct. -Act. Relat., vol. 21, pp.257-266, (2002).

DOI: 10.1002/1521-3838(200208)21:3<257::aid-qsar257>3.0.co;2-w

[9] H.H. Liu , X. Xiao, J. Qin, and Y.M. Liu, Study on structural characteristics and QSPR of polychlorinated biphenyls isomers (PCBs), J. Chongqing Institute of Technology, vol. 19, No. 5., pp.67-70, May, (2005).

[10] S.S. Liu, H.L. Liu, Z.N. Xia, C.Z. Cao, and Z.L. Li, Molecular distance-edge vector (μ): an extension from alkanes to alcohols, J. Chem. Inf. Comput. Sci., vol. 39. no. 6, pp.951-957, (1999).

DOI: 10.1021/ci990011f

[11] H.A. Martens, and P. Dardenne, Validation and verification of regression in small data sets., Chemometr. Intell. Lab. Syst., vol. 44, 99–121, (1998).

[12] L. Jiao, Gao S.Y., Z.H. Jia, and H. Li, Quantification of Benzoic Acid and Salicylic Acid by Capillary Zone Electrophoresis Combined with Artificial Neural Network, Comput. Appl. Chem., vol. 24, pp.1595-1599, (2007).

[13] Y. X Zhang, H. Li, A.X. Hou, and J. Havel, Artificial neural networks based on principal component analysis input selection for quantification in overlapped capillary electrophoresis peaks,. Chemometr. Intell. Lab. Sys., vol. 82, pp.165-175, (2006).

DOI: 10.1016/j.chemolab.2005.08.012

[14] V. David, and A. Sanchez, Searching for a solution to the automatic RBF network design problem, Neurocomputing, vol. 42, pp.147-153, (2002).

DOI: 10.1016/s0925-2312(01)00600-2

[15] X.P. Guo, and Z.J. Wang, An Algorithm for Selecting RBF-ANN Centers of Species Mass in Engine, Computer Science and Information Engineering, 2009 WRI World Congress on, vol. 3, pp.40-42, (2009).

DOI: 10.1109/csie.2009.374