QSAR Study of Artemisinin Analogues as Antimalarial Drugs by Neural Network and Replacement Method

Abstract

Quantitative structure–activity relationship (QSAR) models were derived for 179 analogues of artemisinin, a potent antimalarial agent. Molecular descriptors derived solely from molecular structure were used to represent molecular structure. Utilizing replacement method, a subset of 11 descriptors was selected. General regression neural network (GRNN) was used to construct the nonlinear QSAR models in all stages of study. The relative standard error percent in antimalarial activity predictions for the training set by the application of cross-validation (RMSE-CV) was 0.43, and for test set (RMSE_test) was 0.51. GRNN analysis yielded predicted activities in the excellent agreement with the experimentally obtained values (R2training = 0.967 and R2test = 0.918). The mean absolute error for the test set was computed as 0.4115.

Key words

quantitative-structure-activity relationship - generalized regression neural network - artemisinin - antimalarial activity - replacement method

• References

• 1 Araújo JQ, Carneiro JWdM, Araujo MTd. et al. Interaction between artemisinin and heme. A density functional theory study of structures and interaction energies. Biorg Med Chem 2008; 16: 5021-5029
• 2 Dhingra V, Vishweshwar Rao K, Lakshmi Narasu M. Artemisinin: Present status and perspectives. Biochemical Education 1999; 27: 105-109
• 3 Mockenhaupt FP. Mefloquine resistance in Plasmodium falciparum. Parasitol. Today 1995; 11: 248-253
• 4 Olliarol PL, Trigg PL. Status of antimalarial drugs under development. Bull. World Health Organ 1995; 73: 565-571
• 5 Kaur K, Jain M, Kaur T. et al. Antimalarials from nature. Bioorg Med Chem 2009; 17: 3229-3256
• 6 Robert A, Meunier B. Is alkylation the main mechanism of action of the antimalarial drug artemisinin? Chem. Soc Rev 1998; 27: 273-274
• 7 Meshnick SR. Artemisinin: Mechanisms of action, resistance and toxicity. Int J Parasitol 2002; 32: 1655-1660
• 8 Dearden JC. The history and development of quantitative structure-activity relationships (QSARs). IJQSPR 2016; 1: 1-44
• 9 Roy K, Kar S, Das RN. Understanding the basics of QSAR for applications in pharmaceutical sciences and risk assessment. Ed. Boston: Academic Press; 2015
• 10 Zare-Shahabadi V. Quantitative structure–activity relationships of dihydrofolatereductase inhibitors. Med Chem Res 2016; 25: 2787-2797
• 11 Zare-Shahabadi V, Abbasitabar F. Application of ant colony optimization in development of models for prediction of anti-HIV-1 activity of HEPT derivatives. J Comput Chem 2010; 31: 2354-2362
• 12 Abbasitabar F, Zare-Shahabadi V. In silico prediction of toxicity of phenols to Tetrahymena pyriformis by using genetic algorithm and decision tree-based modeling approach. Chemosphere 2017; 172: 249-259
• 13 Akhlaghi Y, Kompany-Zareh M. Application of radial basis function networks and successive projections algorithm in a QSAR study of anti-HIV activity for a large group of HEPT derivatives. J Chemom 2006; 20: 1-12
• 14 Jalali-Heravi M, Parastar F. Use of artificial neural networks in a QSAR study of anti-HIV activity for a large group of HEPT derivatives. J Chem Inf Comput Sci 2000; 40: 147-154
• 15 Zhu J, Chen D, Wu P. Exploration of artificial neural system for simulation of the halogen-exchange fluorination reaction. Comput Chem 1999; 23: 97-100
• 16 Yan A, Jiao G, Hu Z. et al. Use of artificial neural networks to predict the gas chromatographic retention index data of alkylbenzenes on carbowax-20m. Comput Chem 2000; 24: 171-179
• 17 Zare-Shahabadi V. Prediction of toxicity of aliphatic carboxylic acids using adaptive neuro-fuzzy inference system. J Iranian Chem Res 2012; 5: 177-185
• 18 Shahbazikhah P, Asadollahi-Baboli M, Khaksar R. et al. Predicting partition coefficients of migrants in food simulant/polymer systems using adaptive neuro-fuzzy inference system. J Braz Chem. Soc 2011; 22: 1446-1451
• 19 Yao XJ, Panaye A, Doucet JP. et al. Comparative study of QSAR/QSPR correlations using support vector machines, radial basis function neural networks, and multiple linear regression. J Chem Inf Comput Sci 2004; 44: 1257-1266
• 20 Szczurek A, Maciejewska M. Recognition of benzene, toluene and xylene using TGS array integrated with linear and non-linear classifier. Talanta 2004; 64: 609-617
• 21 Pompe M, Razinger M, Novič M. et al. Modelling of gas chromatographic retention indices using counterpropagation neural networks. Anal Chim Acta 1997; 348: 215-221
• 22 Niwa T. Using general regression and probabilistic neural networks to predict human intestinal absorption with topological descriptors derived from two-dimensional chemical structures. J Chem Inf Comput Sci 2003; 43: 113-119
• 23 Mosier PD, Jurs PC. QSAR/QSPR studies using probabilistic neural networks and generalized regression neural networks. J Chem Inf Comput Sci 2002; 42: 1460-1470
• 24 Guha R, Jurs PC. Development of QSAR models to predict and interpret the biological activity of artemisinin analogues. J Chem Inf Comput Sci 2004; 44: 1440-1449
• 25 Abbasitabar F, Zare-Shahabadi V. Development predictive QSAR models for artemisinin analogues by various feature selection methods: A comparative study. SAR QSAR Environ Res 2012; 23: 1-15
• 26 Tonmunphean S, Kokpol S, Parasuk V. et al. Comparative molecular field analysis of artemisinin derivatives: Ab initio versus semiempirical optimized structures. J Comput Aided Mol Des 1998; 12: 397-409
• 27 Avery MA, Alvim-Gaston M, Vroman JA. et al. Structure−activity relationships of the antimalarial agent artemisinin. 7. Direct modification of (+)-artemisinin and in vivo antimalarial screening of new, potential preclinical antimalarial candidates. J Med Chem 2002; 45: 4321-4335
• 28 Avery MA, Gao F, Chong WKM. et al. Structure-activity relationships of the antimalarial agent artemisinin. 1. Synthesis and comparative molecular field analysis of c-9 analogs of artemisinin and 10-deoxoartemisinin. J Med Chem 1993; 36: 4264-4275
• 29 Cramer RD, Patterson DE, Bunce JD. Comparative molecular field analysis (CoMFA). 1. Effect of shape on binding of steroids to carrier proteins. J Am Chem Soc 1988; 110: 5959-5967
• 30 Shamsipur M, Zare-Shahabadi V, Hemmateenejad B. et al. Ant colony optimisation: A powerful tool for wavelength selection. J Chemom 2006; 20: 146-157
• 31 Shamsipur M, Zare-Shahabadi V, Hemmateenejad B. et al. An efficient variable selection method based on the use of external memory in ant colony optimization. Application to QSAR/QSPR studies. Anal Chim Acta 2009; 646: 39-46
• 32 Shamsipur M, Zare-Shahabadi V, Hemmateenejad B. et al. Combination of ant colony optimization with various local search strategies. A novel method for variable selection in multivariate calibration and QSPR study. QSAR Comb Sci 2009; 28: 1263-1275
• 33 Hemmateenejad B, Shamsipur M, Zare-Shahabadi V. et al. Building optimal regression tree by ant colony system–genetic algorithm: Application to modeling of melting points. Anal Chim Acta 2011; 704: 57-62
• 34 Zare-Shahabadi V, Lotfizadeh M, Gandomani ARA. et al. Determination of boiling points of azeotropic mixtures using quantitative structure–property relationship (QSPR) strategy. J Mol Liq 2013; 188: 222-229
• 35 Avery MA, Alvim-Gaston M, Rodrigues CR. et al. Structure−activity relationships of the antimalarial agent artemisinin. 6. The development of predictive in vitro potency models using CoMFA and HQSAR methodologies. J Med Chem 2002; 45: 292-303
• 36 Chemdraw ultra 6.0 and chem3d ultra, cambrige soft corporation, cambridge, USA
• 37 Specht DF. A general regression neural network. IEEE Trans Neural Netw 1991; 2: 568-576
• 38 Parzen E. On estimation of a probability density function and mode. Ann Math Statist 1962; 33: 1065-1076
• 39 Duchowicz PR, Garro JCM, Castro EA. QSPR study of the henry's law constant for hydrocarbons. Chemometrics Intellig Lab Syst 2008; 91: 133-140
• 40 Duchowicz PR, González MP, Helguera AM. et al. Application of the replacement method as novel variable selection in QSPR. 2. Soil sorption coefficients. Chemometrics Intellig Lab Syst 2007; 88: 197-203
• 41 Mercader AG, Duchowicz PR, Fernández FM. et al. Advances in the replacement and enhanced replacement method in QSAR and QSPR theories. J Chem Inf Model 2011; 51: 1575-1581
• 42 Saaidpour S. Quantitative modeling for prediction of critical temperature of refrigerant compounds. Phys Chem Res 2016; 4: 61-71
• 43 Chirico N, Gramatica P. Real external predictivity of QSAR models: How to evaluate it? Comparison of different validation criteria and proposal of using the concordance correlation coefficient. J Chem Inf Model 2011; 51: 2320-2335
• 44 Pratim Roy P, Paul S, Mitra I. et al. On two novel parameters for validation of predictive QSAR models. Molecules 2009; 14: 1660
• 45 Nekoeinia M, Yousefinejad S, Abdollahi-Dezaki A. Prediction of ETN polarity scale of ionic liquids using a QSPR approach. Ind Eng Chem Res 2015; 54: 12682-12689
• 46 Roy K, Kar S, Ambure P. On a simple approach for determining applicability domain of QSAR models. Chemometrics Intellig Lab Syst 2015; 145: 22-29
• 47 Massart DL, Vandeginste BGM, Buydens LMC. et al. Handbook of chemometrics and qualimetrics part a. Ed. Amsterdam: Elsevier; 1997
• 48 Roy K, Das RN, Ambure P. et al. Be aware of error measures. Further studies on validation of predictive QSAR models. Chemometrics Intellig Lab Syst 2016; 152: 18-33
• 49 Baumann D, Baumann K. Reliable estimation of prediction errors for QSAR models under model uncertainty using double cross-validation. J. Cheminform 2014; 6: 47
• 50 Practical guide to chemometrics. 2 ed Gemperline P. Ed. Boca Raton: Taylor & Francis Group; 2006
• 51 Yousefinejad S, Honarasa F, Montaseri H. Linear solvent structure-polymer solubility and solvation energy relationships to study conductive polymer/carbon nanotube composite solutions. RSC Advances 2015; 5: 42266-42275
• 52 Todeschini R, Consonni V, Gramatica P. Chemometrics in QSAR, in Comprehensive chemometrics: Chemical and biochemical data analysis. Tauler R, Walczak B, Brown SD. (eds.) Amsterdam: Elsevier B.V.; 2009
• 53 Pasha FA, Srivastava HK, Singh PP. Comparative QSAR study of phenol derivatives with the help of density functional theory. Bioorganic & Medicinal Chemistry 2005; 13: 6823-6829
• 54 Ferreira JEV, Figueiredo AF, Barbosa JP. et al. A study of new antimalarial artemisinins through molecular modeling and multivariate analysis. J Serb Chem Soc 2010; 75: 1533-1548
• 55 Kumar Yadav D, Dhawan S, Chauhan A. et al. QSAR and docking based semi-synthesis and in vivo evaluation of artemisinin derivatives for antimalarial activity. Curr Drug Targets 2014; 15: 753-761
• 56 Rajkhowa S, Hussain I, Hazarika KK. et al. Quantitative structure-activity relationships of the antimalarial agent artemisinin and some of its derivatives–a DFT approach. Comb Chem High Throughput Screen 2013; 16: 590-602
• 57 Cardoso FJB, de Figueiredo AF, da Silva Lobato M. et al. A study on antimalarial artemisinin derivatives using MEP maps and multivariate QSAR. J Mol Model 2008; 14: 39-48
• 58 Guha R, Stanton DT, Jurs PC. Interpreting computational neural network quantitative structure-activity relationship models: A detailed interpretation of the weights and biases. J Chem Inf Model 2005; 45: 1109-1121
• 59 Guha R, Jurs PC. Interpreting computational neural network QSAR models: A measure of descriptor importance. J Chem Inf Model 2005; 45: 800-806
• 60 Burden FR. Molecular identification number for substructure searches. J Chem Inf Comput Sci 1989; 29: 225-227
• 61 Stanton DT. Evaluation and use of bcut descriptors in QSAR and QSPR studies. J Chem Inf Comput Sci 1998; 39: 11-20
• 62 Todeschini R, Consonni V. Handbook of molecular descriptors. Ed. 2000. Weinheim: Wiley-VCH;
• 63 Gasteiger J, Sadowski J, Schuur J. et al. Chemical information in 3D space. J Chem Inf Comput Sci 1996; 36: 1030-1037
• 64 Schuur JH, Selzer P, Gasteiger J. The coding of the three-dimensional structure of molecules by molecular transforms and its application to structure-spectra correlations and studies of biological activity. J Chem Inf Comput Sci 1996; 36: 334-344