Current approaches for choosing feature selection and learning algorithms in quantitative structure–activity relationships (QSAR)

References

• Hansch C, Muir RM, Fujita T, et al. The correlation of biological activity of plant growth regulators and chloromycetin derivatives with Hammett constants and partition coefficients. J Am Chem Soc. 1963;85(18):2817–2824.
   Web of Science ®Google Scholar
• Hansch C, Fujita T. p-σ-π analysis. A method for the correlation of biological activity and chemical structure. J Am Chem Soc. 1964;86(8):1616–1626.
   Web of Science ®Google Scholar
• Hansch C, Hoekman D, Gao H. Comparative QSAR: toward a deeper understanding of chemicobiological interactions. Chem Rev. 1996;96(3):1045–1076.
   PubMed Web of Science ®Google Scholar
• Yasri A, Hartsough D. Toward an optimal procedure for variable selection and QSAR model building. J Chem Inf Comput Sci. 2001;41(5):1218–1227.
   PubMedGoogle Scholar
• Katritzky AR, Lobanov VS, Karelson M. QSPR: the correlation and quantitative prediction of chemical and physical properties from structure. Chem Soc Rev. 1995;24(4):279–287.
   Web of Science ®Google Scholar
• Siraki A, Chevaldina T, Moridani M, et al. Quantitative structure-toxicity relationships by accelerated cytotoxicity mechanism screening. Curr Opin Drug Discov Devel. 2004;7(1):118–125.
   PubMedGoogle Scholar
• Nigam A, Klein MT. A mechanism-oriented lumping strategy for heavy hydrocarbon pyrolysis: imposition of quantitative structure-reactivity relationships for pure components. Ind Eng Chem Res. 1993;32(7):1297–1303.
   Web of Science ®Google Scholar
• Driebergen R, Moret E, Janssen L, et al. Electrochemistry of potentially bioreductive alkylating quinones: part 3. Quantitative structure-electrochemistry relationships of aziridinylquinones. Anal Chim Acta. 1992;257(2):257–273.
   Web of Science ®Google Scholar
• Tömpe P, Clementis G, Petnehazy I, et al. Quantitative structure-electrochemistry relationships of α, β-unsaturated ketones. Anal Chim Acta. 1995;305(1–3):295–303.
   Web of Science ®Google Scholar
• Hemmateenejad B, Yazdani M. QSPR models for half-wave reduction potential of steroids: A comparative study between feature selection and feature extraction from subsets of or entire set of descriptors. Anal Chim Acta. 2009;634(1):27–35.
   PubMed Web of Science ®Google Scholar
• Mozrzymas A, Rozycka-Roszak B. Prediction of critical micelle concentration of nonionic surfactants by a quantitative structure–property relationship. Comb Chem High Throughput Screen. 2010;13(1):39–44.
   PubMed Web of Science ®Google Scholar
• Fourches D, Pu D, Tassa C, et al. Quantitative nanostructure−activity relationship modeling. ACS Nano. 2010;4(10):5703–5712.
   PubMed Web of Science ®Google Scholar
• Mauri A, Consonni V, Pavan M, et al. Dragon software: an easy approach to molecular descriptor calculations. Match. 2006;56(2):237–248.
   Google Scholar
• Yap CW. PaDEL‐descriptor: an open source software to calculate molecular descriptors and fingerprints. J Comput Chem. 2011;32(7):1466–1474.
   PubMed Web of Science ®Google Scholar
• Shahlaei M. Descriptor selection methods in quantitative structure–activity relationship studies: a review study. Chem Rev. 2013;113(10):8093–8103.
   PubMed Web of Science ®Google Scholar
• Kohavi R, John GH. Wrappers for feature subset selection. Artif Intell. 1997;97(1–2):273–324.
   Web of Science ®Google Scholar
• Kohavi R, John GH. The wrapper approach. Feature extraction, construction and selection. Springer: New York; 1998. p. 33–50.
   Google Scholar
• Dutta D, Guha R, Wild D, et al. Ensemble feature selection: consistent descriptor subsets for multiple QSAR models. J Chem Inf Model. 2007;47(3):989–997.
   PubMed Web of Science ®Google Scholar
• Blanchet FG, Legendre P, Borcard D. Forward selection of explanatory variables. Ecology. 2008;89(9):2623–2632.
   PubMed Web of Science ®Google Scholar
• Unger SH. Consequences of the Hansch paradigm for the pharmaceutical industry. Med Chem. 1980;9:47–119. Elsevier.
   Google Scholar
• Merkwirth C, Mauser H, Schulz-Gasch T, et al. Ensemble methods for classification in cheminformatics. J Chem Inform Comput Sci. 2004;44(6):1971–1978.
   PubMedGoogle Scholar
• Guyon I, Weston J, Barnhill S, et al. Gene selection for cancer classification using support vector machines. Mach Learn. 2002;46(1–3):389–422.
   Web of Science ®Google Scholar
• Wegner J, Fröhlich H, Zell A. Feature selection for descriptor based classification models. 1. Theory and GA-SEC algorithm. J Chem Inform Comput Sci. 2004;44(3):921–930.
   PubMedGoogle Scholar
• Santos V. Uma perspectiva da modelagem QSPR para triagem/desenho de catalisadores para a síntese de carbonatos oleoquímicos Porto Alegre: Pontifícia Universidade Católica do Rio Grande do Sul; 2018
   Google Scholar
• Seierstad M, Agrafiotis DK. A QSAR model of hERG binding using a large, diverse, and internally consistent training set. Chem Biol Drug Des. 2006;67(4):284–296.
   PubMed Web of Science ®Google Scholar
• Derksen S, Keselman HJ. Backward, forward and stepwise automated subset selection algorithms: frequency of obtaining authentic and noise variables. Br J Math Stat Psychol. 1992;45(2):265–282.
   Web of Science ®Google Scholar
• Yang S-P, Song S-T, Tang Z-M, et al. Optimization of antisense drug design against conservative local motif in simulant secondary structures of HER-2 mRNA and QSAR analysis. Acta Pharmacol Sin. 2003;24(9):897–902.
   PubMed Web of Science ®Google Scholar
• Szaleniec M, Tadeusiewicz R, Witko M. How to select an optimal neural model of chemical reactivity? Neurocomputing. 2008;72(1–3):241–256.
   Web of Science ®Google Scholar
• Darlington RB. Regression and linear models. New York: McGraw-Hill; 1990.
   Google Scholar
• Yousefinejad S, Hemmateenejad B. Chemometrics tools in QSAR/QSPR studies: A historical perspective. Chemom Intell Lab Syst.2015; 149:177–204.
   Web of Science ®Google Scholar
• Liu -S-S, Liu H-L, Yin C-S, et al. VSMP: a novel variable selection and modeling method based on the prediction. J Chem Inform Comput Sci. 2003;43(3):964–969.
   PubMedGoogle Scholar
• Furnival GM, Wilson RW. Regressions by leaps and bounds. Technometrics. 1974;16(4):499–511.
   Web of Science ®Google Scholar
• Chen B-K, Horvath C, Bertino JR. Multivariate analysis and quantitative structure-activity relationships. Inhibition of dihydrofolate reductase and thymidylate synthetase by quinazolines. J med chem. 1979;22(5):483–491.
   PubMed Web of Science ®Google Scholar
• Zhou Y-X, Xu L, Wu Y-P, et al. A QSAR study of the antiallergic activities of substituted benzamides and their structures. Chemom Intell Lab Syst. 1999;45(1–2):95–100.
   Web of Science ®Google Scholar
• Goldberg DE. Genetic algorithms in search, optimization machine learning. Adison-Wesley, Publishing Co. Reading MA; ; 1989.
   Google Scholar
• Rogers D, Hopfinger AJ. Application of genetic function approximation to quantitative structure-activity relationships and quantitative structure-property relationships. J Chem Inform Comput Sci. 1994;34(4):854–866.
   Google Scholar
• Holland JH. Adaption in natural and artificial systems. Ann Arbor MI: The University of Michigan Press; 1975.
   Google Scholar
• Lucasius CB, Kateman G. Understanding and using genetic algorithms Part 1. Concepts, properties and context. Chemom Intell Lab Syst. 1993;19(1):1–33.
   Web of Science ®Google Scholar
• Aoyama T, Suzuki Y, Ichikawa H. Neural networks applied to structure-activity relationships. J med chem. 1990;33(3):905–908.
   PubMed Web of Science ®Google Scholar
• Agatonovic-Kustrin S, Beresford R. Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. J Pharm Biomed Anal. 2000;22(5):717–727.
   PubMed Web of Science ®Google Scholar
• Winkler DA, Burden FR. Application of neural networks to large dataset QSAR, virtual screening, and library design. Combinatorial Library: Totowa, NJ: Springer; 2002. p. 325–367.
   Google Scholar
• Wikel JH, Dow ER. The use of neural networks for variable selection in QSAR. Bioorg Med Chem Lett. 1993;3(4):645–651.
   Web of Science ®Google Scholar
• Tetko IV, Tanchuk VY, Chentsova NP, et al. HIV-1 reverse transcriptase inhibitor design using artificial neural networks. J med chem. 1994;37(16):2520–2526.
   PubMed Web of Science ®Google Scholar
• Tetko IV, Villa AEP, Livingstone DJ. Neural network studies. 2. Variable selection. J Chem Inform Comput Sci. 1996;36(4):794–803.
   PubMedGoogle Scholar
• Andersson M. A comparison of nine PLS1 algorithms. J Chemom: J Chemometrics Soc. 2009;23(10):518–529.
   Web of Science ®Google Scholar
• Eberhart RC, Shi Y, editors. Comparing inertia weights and constriction factors in particle swarm optimization. Evolutionary computation, 2000. Proceedings of the 2000 Congress on Evolutionary Computation; 2000. Piscataway, NJ: IEEE.
   Google Scholar
• Eberhart RC, Shi Y, editors. Tracking and optimizing dynamic systems with particle swarms. Evolutionary computation, 2001. Proceedings of the 2001 Congress on Evolutionary Computation; 2001. Piscataway, NJ: IEEE.
   Google Scholar
• Eberhart R, Simpson P, Dobbins R. Computational intelligence PC tools. Boston, MA: Academic Press Professional, Inc.; 1996.
   Google Scholar
• Poli R, Kennedy J, Blackwell T. Particle swarm optimization. Swarm Intelligence. 2007;1(1):33–57.
   Google Scholar
• Sutter JM, Kalivas JH. Comparison of forward selection, backward elimination, and generalized simulated annealing for variable selection. Microchem J. 1993;47(1–2):60–66.
   Web of Science ®Google Scholar
• van Laarhoven PJ, Aarts EH. Simulated annealing: theory and applications. Netherlands: Springer; 1987.
   Google Scholar
• Ghosh P, Bagchi MC. QSAR modeling for quinoxaline derivatives using genetic algorithm and simulated annealing based feature selection. Curr Med Chem. 2009;16(30):4032–4048.
   PubMed Web of Science ®Google Scholar
• Ghosh P, Bagchi M. Comparative QSAR studies of nitrofuranyl amide derivatives using theoretical structural properties. Mol Simul. 2009;35(14):1185–1200.
   Web of Science ®Google Scholar
• Bhaisare ML, Karthikeyan C, Tanwar O, et al., editors. A QSAR analysis of some amino substituted Pyrido [3, 2-b] pyrazinones as potent and selective PDE-5 inhibitors. Proceedings of the 14th Int. Electron. Conf. Synth. Org. Chem. Sciforum Electronic Conferences Series Electronic conference hosted at https://sciforum.net/; 2010.
   Google Scholar
• Burden FR, Ford MG, Whitley DC, et al. Use of automatic relevance determination in QSAR studies using Bayesian neural networks. J Chem Inform Comput Sci. 2000;40(6):1423–1430.
   PubMedGoogle Scholar
• MacKay DJ. Bayesian non-linear modeling for the energy prediction competition. ASHRAE Transactions. 1994;100(pt 2):1053–1062.
   Google Scholar
• Burden F, Winkler D. Bayesian Regularization of neural networks. Artificial neural networks. Totowa, NJ: Springer; 2008. p. 23–42.
   Google Scholar
• Winkler DA, Burden FR. Modelling blood-brain barrier partitioning using Bayesian neural nets. J Mol Graph Model. 2004;22(6):499–505.
   PubMed Web of Science ®Google Scholar
• Duchowicz PR, Castro EA, Fernandez FM. Alternative algorithm for the search of an optimal set of descriptors in QSAR-QSPR studies. MATCH Commun Math Comput Chem. 2006;55:179–192.
   Web of Science ®Google Scholar
• Duchowicz PR, Fernã¡Ndez M, Caballero J, et al. QSAR for non-nucleoside inhibitors of HIV-1 reverse transcriptase. Bioorg Med Chem. 2006;14(17):5876–5889.
   PubMed Web of Science ®Google Scholar
• Morales AH, Duchowicz PR, Perez MAC, et al. Application of the replacement method as a novel variable selection strategy in QSAR. 1. Carcinogenic potential. Chemom Intell Lab Syst. 2006;81(2):180–187.
   Web of Science ®Google Scholar
• Duchowicz PR, Castro EA, Fernandez FM, et al. A new search algorithm for QSPR/QSAR theories: normal boiling points of some organic molecules. Chem Phys Lett. 2005;412(4–6):376–380.
   Web of Science ®Google Scholar
• Duchowicz PR, González MP, Helguera AM, et al. Application of the replacement method as novel variable selection in QSPR. 2. Soil sorption coefficients. Chemom Intell Lab Syst. 2007;88(2):197–203.
   Web of Science ®Google Scholar
• Duchowicz PR, Castañeta H, Castro EA, et al. QSPR prediction of the Dubinin–radushkevich’s k parameter for the adsorption of organic vapors on BPL carbon. Atmos Environ. 2006;40(16):2929–2934.
   Web of Science ®Google Scholar
• Zheng W, Tropsha A. Novel variable selection quantitative structure− property relationship approach based on the k-nearest-neighbor principle. J Chem Inform Comput Sci. 2000;40(1):185–194.
   PubMedGoogle Scholar
• Araujo M, Saldanha TCB, Galvao RKH, et al. The successive projections algorithm for variable selection in spectroscopic multicomponent analysis. Chemom Intell Lab Syst. 2001;57(2):65–73.
   Web of Science ®Google Scholar
• Daszykowski M, Stanimirova I, Walczak B, et al. Improving QSAR models for the biological activity of HIV reverse transcriptase inhibitors: aspects of outlier detection and uninformative variable elimination. Talanta. 2005;68(1):54–60.
   PubMed Web of Science ®Google Scholar
• Franke R. Theoretical drug design methods (Pharmacochemistry Library). Vol. 7. Amsterdam: Elsevier; 1984.
   Google Scholar
• Van Waterbeemd H. Chemometric methods in molecular design. Manhnhold R, Krogsgaard-Larsen P, Timmerman H, et al., editors. New York: Wiley-VCH; 1995.
   Google Scholar
• Leonard JT, Roy K. QSAR by LFER model of HIV protease inhibitor mannitol derivatives using FA-MLR, PCRA, and PLS techniques. Bioorg Med Chem. 2006;14(4):1039–1046.
   PubMed Web of Science ®Google Scholar
• Bhattacharya P, Leonard JT, Roy K. Exploring QSAR of thiazole and thiadiazole derivatives as potent and selective human adenosine A3 receptor antagonists using FA and GFA techniques. Bioorg Med Chem. 2005;13(4):1159–1165.
   PubMed Web of Science ®Google Scholar
• Roy K, Roy PP. Comparative chemometric modeling of cytochrome 3A4 inhibitory activity of structurally diverse compounds using stepwise MLR, FA-MLR, PLS, GFA, G/PLS and ANN techniques. European J Med Chem. 2009;44(7):2913–2922.
   PubMed Web of Science ®Google Scholar
• Roy K, Leonard JT. QSAR by LFER model of cytotoxicity data of anti-HIV 5-phenyl-1-phenylamino-1H-imidazole derivatives using principal component factor analysis and genetic function approximation. Bioorg Med Chem. 2005;13(8):2967–2973.
   PubMed Web of Science ®Google Scholar
• Weisberg S. Applied linear regression. Vol. 528. Hoboken: John Wiley & Sons; 2005.
   Google Scholar
• Schneider C, Catalano P, Biggio J, et al. Associations of neonatal adiponectin and leptin with growth and body composition in African American infants. Pediatr Obes. 2018;13(8):485–491.
   Web of Science ®Google Scholar
• Duchowicz PR. Linear regression QSAR models for Polo-Like Kinase-1 inhibitors. Cells. 2018;7(2):13.
   Web of Science ®Google Scholar
• Wang L, Chen B, Zhang T. Predicting hydrolysis kinetics for multiple types of halogenated disinfection byproducts via QSAR models. Chem Eng J. 2018;342:372–385.
   Web of Science ®Google Scholar
• Roy K, Ambure P. The “double cross-validation” software tool for MLR QSAR model development. Chemom Intell Lab Syst. 2016;159:108–126.
   Web of Science ®Google Scholar
• Frank LE, Friedman JH. A statistical view of some chemometrics regression tools. Technometrics. 1993;35(2):109–135.
   Web of Science ®Google Scholar
• Jolliffe I. Principal component analysis. International encyclopedia of statistical science: Springer. Berlin, Heidelberg; 2011;1094–1096.
   Google Scholar
• Liu RX, Kuang J, Gong Q, et al. Principal component regression analysis with SPSS. Comput Methods Programs Biomed. 2003;71(2):141–147.
   PubMed Web of Science ®Google Scholar
• Constantin C. Principal component analysis-a powerful tool in computing marketing information. Bull Transilvania Univ Brasov Econ Sci Ser. 2014;7(2):25.
   Google Scholar
• Valle S, Li W, Qin SJ. Selection of the number of principal components: the variance of the reconstruction error criterion with a comparison to other methods. Ind Eng Chem Res. 1999;38(11):4389–4401.
   Web of Science ®Google Scholar
• Wold S, Sjöström M, Eriksson L. PLS-regression: a basic tool of chemometrics. Chemom Intell Lab Syst. 2001;58(2):109–130.
   Web of Science ®Google Scholar
• Agrafiotis DK, Rassokhin DN, Lobanov VS. Multidimensional scaling and visualization of large molecular similarity tables. J Comput Chem. 2001;22(5):488–500.
   Web of Science ®Google Scholar
• Esposito Vinzi V, Russolillo G. Partial least squares algorithms and methods. Wiley Interdisciplinary Reviews: Comput Stat. 2013;5(1):1–19.
   Google Scholar
• Hoerl AE, Kennard RW. Ridge regression: applications to nonorthogonal problems. Technometrics. 1970;12(1):69–82.
   Web of Science ®Google Scholar
• Rogers D. G/SPLINES. In Proceedings of the Fourth International Conference on Genetic Algorithms; San Diego. A hybrid of Friedman’s multivariate adaptive regression splines (MARS) algorithm with Holland’s genetic algorithm. 1991.
   Google Scholar
• Rogers D, editor. Data analysis using G/SPLINES. Advances in Neural Information Processing Systems. San Mateo,, CA; 1992.
   Google Scholar
• Holland J. Adaptation in natural and artificial systems: an introductory analysis with application to biology,control and artificial intelligence. Cambridge, MA: MIT Press1975.
   Google Scholar
• Rogers D. Some theory and examples of genetic function approximation with comparison to evolutionary techniques. Genetic algorithms in molecular modeling. New York: Elsevier; 1996. p. 87–107.
   Google Scholar
• Livingstone DJ, Manallack DT, Tetko IV. Data modelling with neural networks: advantages and limitations. J Comput Aided Mol Des. 1997;11(2):135–142.
   PubMed Web of Science ®Google Scholar
• McCulloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys. 1943;5(4):115–133.
   Google Scholar
• Devillers J. Neural networks in QSAR and drug design. New York: Academic Press; 1996.
   Google Scholar
• Rumelhart DE, Hinton GE, Williams RJ. Learning internal representations by error propagation. California Univ San Diego La Jolla Inst for Cognitive Science. La Jolla, CA: 1985.
   Google Scholar
• Caudill M, Butler C. Naturally intelligent systems. Cambridge, MA: MIT press; 1992.
   Google Scholar
• Eberhart RC. Neural network PC tools: a practical guide. New York: Academic Press; 1990.
   Google Scholar
• Goh ATC. Back-propagation neural networks for modeling complex systems. Artif Intelligence Eng. 1995;9(3):143–151.
   Web of Science ®Google Scholar
• MacKay DJC. A practical Bayesian framework for backpropagation networks. Neural Comput. 1992;4(3):448–472.
   Web of Science ®Google Scholar
• Neal RM. Priors for infinite networks. Bayesian learning for neural networks. New York: Springer; 1996. p. 29–53.
   Google Scholar
• Fox T, Kriegl JM. Machine learning techniques for in silico modeling of drug metabolism. Curr Top Med Chem. 2006;6(15):1579–1591.
   PubMed Web of Science ®Google Scholar
• Baskin II. Machine learning methods in computational toxicology. Computational toxicology. New York: Springer; 2018;119–139.
   Google Scholar
• Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20(3):273–297.
   Web of Science ®Google Scholar
• Vapnik V. The nature of statistical learning theory. New York : Springer; 1995.
   Google Scholar
• Burges CJC. A tutorial on support vector machines for pattern recognition. Data Min Knowl Discov. 1998;2(2):121–167.
   Web of Science ®Google Scholar
• Andres C, Hutter MC. CNS permeability of drugs predicted by a decision tree. QSAR Comb Sci. 2006;25(4):305–309.
   Google Scholar
• Quinlan JR. Induction of decision trees. Mach Learn. 1986;1(1):81–106.
   Google Scholar
• Amit Y, Geman D. Shape quantization and recognition with randomized trees. Neural Comput. 1997;9(7):1545–1588.
   Web of Science ®Google Scholar
• Yee LC, Wei YC. Current modeling methods used in QSAR/QSPR. Statistical Modelling of Molecular Descriptors in QSAR/QSPR;.2012 2:1–31.
   Google Scholar
• Barandiaran I. The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell. 1998;20:8.
   Web of Science ®Google Scholar
• Breiman L. Random forests. Mach Learn. 2001;45(1):5–32.
   Web of Science ®Google Scholar
• Lavecchia A. Machine-learning approaches in drug discovery: methods and applications. Drug Discov Today.  2015;20(3):318–331.
   PubMed Web of Science ®Google Scholar
• Duda H, Hart PE, David G. Stork, pattern classification.  Weinheim, Germany:John Wiley & Sons; 2001.
   Google Scholar
• Kauffman GW, Jurs PC. QSAR and k-nearest neighbor classification analysis of selective cyclooxygenase-2 inhibitors using topologically-based numerical descriptors. J Chem Inform Comput Sci. 2001;41(6):1553–1560.
   PubMedGoogle Scholar
• Konovalov DA, Coomans D, Deconinck E, et al. Benchmarking of QSAR models for blood-brain barrier permeation. J Chem Inf Model. 2007;47(4):1648–1656.
   PubMed Web of Science ®Google Scholar
• The Codessa Project software. [cited 2018 Sept 26]. Available from: http://codessa-pro.com/
   Google Scholar
• Guha R. Chemical informatics functionality in R. J Stat Softw. 2007;18(5):1–16.
   Web of Science ®Google Scholar
• Roy K, Kar S, Das RN. A primer on QSAR/QSPR modeling: fundamental concepts (SpringerBriefs in molecular science). NY: Springer; 2015.
   Google Scholar
• Roy K, Mitra I. On various metrics used for validation of predictive QSAR models with applications in virtual screening and focused library design. Comb Chem High Throughput Screen. 2011;14(6):450–474.
   PubMed Web of Science ®Google Scholar
• Golbraikh A, Tropsha A. Beware of q2! J Mol Graph Model. 2002;20(4):269–276.
   PubMed Web of Science ®Google Scholar
• Roy K, Das RN, Ambure P, et al. Be aware of error measures. Further studies on validation of predictive QSAR models. Chemom Intell Lab Syst. 2016;152:18–33.
   Web of Science ®Google Scholar
• Gadaleta D, Mangiatordi GF, Catto M, et al. Applicability domain for QSAR models: where theory meets reality. Int J Quant Struct-Prop Relat. 2016;1(1):45–63.
   Google Scholar
• Melagraki G, Ntougkos E, Rinotas V, et al. Cheminformatics-aided discovery of small-molecule Protein-Protein Interaction (PPI) dual inhibitors of Tumor Necrosis Factor (TNF) and receptor activator of NF-κB ligand (RANKL). PLoS Comput Biol. 2017;13(4):e1005372.
   PubMed Web of Science ®Google Scholar
• Melagraki G, Afantitis A. A risk assessment tool for the virtual screening of metal oxide nanoparticles through enalos InSilicoNano platform. Curr Top Med Chem. 2015;15(18):1827–1836.
   PubMed Web of Science ®Google Scholar
• OECD. Validation of QSAR models; [cited 2018 Oct 24]. Available from: http://www.oecd.org/chemicalsafety/risk-assessment/validationofqsarmodels.htm
   Google Scholar
• Roy K, Ambure P, Kar S, et al. Is it possible to improve the quality of predictions from an “intelligent” use of multiple QSAR/QSPR/QSTR models? J Chemom. 2018;32(4):e2992.
   Web of Science ®Google Scholar
• Roy K, Ambure P, Kar S. How precise are our quantitative structure–activity relationship derived predictions for new query chemicals? ACS Omega. 2018;3(9):11392–11406.
   Web of Science ®Google Scholar
• Fujita T, Winkler DA. Understanding the roles of the “Two QSARs”. J Chem Inf Model. 2016;56(2):269−274.
   PubMed Web of Science ®Google Scholar
• Bhattarai B, Garg R, Gramatica P. Are mechanistic and statistical QSAR approaches really different? MLR studies on 158 cycloalkyl‐pyranones. Mol Inform. 2010;29(6–7):511–522.
   PubMed Web of Science ®Google Scholar
• Devinyak OT, Lesyk RB. 5-year trends in QSAR and its machine learning methods. Curr Comput Aided Drug Des. 2016;12(4):265–271.
   PubMed Web of Science ®Google Scholar
• Antanasijević D, Antanasijević J, Trišović N, et al. From classification to regression multitasking QSAR modeling using a novel modular neural network: simultaneous prediction of anticonvulsant activity and neurotoxicity of succinimides. Mol Pharm. 2017;14(12):4476–4484.
   PubMedGoogle Scholar