TOXICITY MODELLING OF SOME ACTIVE COMPOUNDS AGAINST K562 CANCER CELL LINE USING GENETIC ALGORITHM-MULTIPLE LINEAR REGRESSIONS

Abstract

This research entails the modelling of the toxicity of anticancer compounds on K562 cell line, where 112 compounds that make up the data set were divided into training and test set to be used for developing and validating the model respectively. The internal and external validation parameter R² for the training and test set given as 0.845 and 0.5316 respectively justifies the robustness and the ability of the model to predict toxicity of the compounds. WPSA-3 and minHBint7 molecular descriptor is responsible for about 50% of the overall effect on the model.

Keywords

• QSAR,Model,External Validation,Molecular descriptors,Genetic algorithm

References

1. Speck-Planche, A., et al., Rational drug design for anti-cancer chemotherapy: Multi-target QSAR models for the in silico discovery of anti-colorectal cancer agents. Bioorganic & Medicinal Chemistry, 2012. 20(15): p. 4848-4855.
2. Dunnington, B.D. and J.R. Schmidt, Molecular bonding-based descriptors for surface adsorption and reactivity. Journal of Catalysis, 2015. 324: p. 50-58.
3. Andrada, M.F., et al., Application of k-means clustering, linear discriminant analysis and multivariate linear regression for the development of a predictive QSAR model on 5-lipoxygenase inhibitors. Chemometrics and Intelligent Laboratory Systems, 2015. 143: p. 122-129.
4. Alanazi, A.M., et al., Design, synthesis and biological evaluation of some novel substituted quinazolines as antitumor agents. European Journal of Medicinal Chemistry, 2014. 79: p. 446-454.
5. Gagic, Z., et al., QSAR studies and design of new analogs of vitamin E with enhanced antiproliferative activity on MCF-7 breast cancer cells. Journal of the Taiwan Institute of Chemical Engineers.
6. Chen, B., et al., Development of quantitative structure activity relationship (QSAR) model for disinfection byproduct (DBP) research: A review of methods and resources. Journal of Hazardous Materials, 2015. 299: p. 260-279.
7. Speck-Planche, A., et al., Chemoinformatics in anti-cancer chemotherapy: Multi-target QSAR model for the in silico discovery of anti-breast cancer agents. European Journal of Pharmaceutical Sciences, 2012. 47(1): p. 273-279.
8. Zhao, L., et al., A novel two-step QSAR modeling work flow to predict selectivity and activity of HDAC inhibitors. Bioorganic & Medicinal Chemistry Letters, 2013. 23(4): p. 929-933.

9. Benarous, N., et al., Synthesis, characterization, crystal structure and DFT study of two new polymorphs of a Schiff base (E)-2-((2,6-dichlorobenzylidene)amino)benzonitrile. Journal of Molecular Structure, 2016. 1105: p. 186-193.
10. Bauernschmitt, R. and R. Ahlrichs, Treatment of electronic excitations within the adiabatic approximation of time dependent density functional theory. Chemical Physics Letters, 1996. 256(4): p. 454-464.
11. Kennard, R.W. and L.A. Stone, Computer aided design of experiments. Technometrics, 1969. 11(1): p. 137-148.
12. Deb, K., et al., A fast and elitist multiobjective genetic algorithm: NSGA-II. Evolutionary Computation, IEEE Transactions on, 2002. 6(2): p. 182-197.
13. Leardi, R., R. Boggia, and M. Terrile, Genetic algorithms as a strategy for feature selection. J. Chemom, 1992. 6(5): p. 267-281.
14. Tropsha, A., Best practices for QSAR model development, validation, and exploitation. Molecular Informatics, 2010. 29(6‐7): p. 476-488.
15. Hehre, W.J. and W.W. Huang, Chemistry with Computation: An introduction to SPARTAN. 1995: Wavefunction, Inc.
16. Yap, C.W., PaDEL‐descriptor: An open source software to calculate molecular descriptors and fingerprints. J. Comput. Chem, 2011. 32(7): p. 1466-1474.
17. Panagos, P., et al., Soil erodibility in Europe: A high-resolution dataset based on LUCAS. Science of the total environment, 2014. 479: p. 189-200.
18. Roy, K., S. Kar, and P. Ambure, On a simple approach for determining applicability domain of QSAR models. Chemometr Intell Lab Syst, 2015. 145: p. 22-29.
19. Barretina, J., et al., The Cancer Cell Line Encyclopedia enables predictive modelling of anticancer drug sensitivity. Nature, 2012. 483(7391): p. 603-607.
20. Abdel-Atty, M.M., et al., Design, synthesis, 3D pharmacophore, QSAR, and docking studies of carboxylic acid derivatives as Histone Deacetylase inhibitors and cytotoxic agents. Bioorganic Chemistry, 2014. 57: p. 65-82.
21. Carlberg, C., Statistical Analysis: Microsoft Excel 2013. 2014: Que Publishing.