Modelling methods and cross-validation variants in QSAR: a multi-level analysis^$

References

• C. Hansch and T. Fujita, p-σ-π analysis. A method for the correlation of biological activity and chemical structure, J. Am. Chem. Soc. 86 (1964), pp. 1616–1626.
   Google Scholar
• C. Hansch, P.P. Maloney, T. Fujita, and R.M. Muir, Correlation of biological activity of phenoxyacetic acids with Hammett substituent constants and partition coefficients, Nature 194 (1962), pp. 178–180.
   Web of Science ®Google Scholar
• L.P. Hammett, The effect of structure upon the reactions of organic compounds. Benzene derivatives, J. Am. Chem. Soc. 59 (1937), pp. 96–103.
   Google Scholar
• H. Kubinyi, QSAR : Hansch Analysis and Related Approaches, Wiley-VCH, Weinheim, Germany, 1993.
   Google Scholar
• A. Cherkasov, E.N. Muratov, D. Fourches, A. Varnek, I.I. Baskin, M. Cronin, J. Dearden, P. Gramatica, Y.C. Martin, R. Todeschini, V. Consonni, V.E. Kuz’min, R. Cramer, R. Benigni, C. Yang, J. Rathman, L. Terfloth, J. Gasteiger, A. Richard, and A. Tropsha, QSAR modeling: Where have you been? Where are you going to? J. Med. Chem. 57 (2014), pp. 4977–5010.
   Web of Science ®Google Scholar
• D. Bajusz, A. Rácz, and K. Héberger, Chemical data formats, fingerprints, and other molecular descriptions for database analysis and searching, in Comprehensive Medicinal Chemistry III, S. Chackalamannil, D.P. Rotella, and S.E. Ward, eds., Elsevier, Oxford, 2017, pp. 329–378.
   Google Scholar
• T. Hastie, R. Tibshirani, and J.H. Friedman, Cross-validation, in The Elements of Statistical Learning: Data Mining, Inference, and Prediction, T. Hastie, R. Tibshirani, and J.H. Friedman, eds., Springer, New York, 2009, pp. 241–249.
   Google Scholar
• R.D. Cramer, D.E. Patterson, and J.D. Bunce, Comparative molecular field analysis (CoMFA). 1. Effect of shape on binding of steroids to carrier proteins, J. Am. Chem. Soc. 110 (1988), pp. 5959–5967.
   PubMed Web of Science ®Google Scholar
• J. Verma, V. Khedkar, and E. Coutinho, 3D-QSAR in drug design – A review, Curr. Top. Med. Chem. 10 (2010), pp. 95–115.
   PubMed Web of Science ®Google Scholar
• S. Alam and F. Khan, 3D-QSAR studies on maslinic acid analogs for anticancer activity against breast cancer cell line MCF-7, Sci. Rep. 7 (2017), pp.1-13. article no: 6019.
   Google Scholar
• A.M. Doweyko, 3D-QSAR illusions, J. Comput. Aided. Mol. Des. 18 (2004), pp. 587–596.
   PubMed Web of Science ®Google Scholar
• K.H. Esbensen and P. Geladi, Principles of proper validation: Use and abuse of re-sampling for validation, J. Chemom. 24 (2010), pp. 168–187.
   Web of Science ®Google Scholar
• P. Gramatica, Principles of QSAR models validation: Internal and external, QSAR Comb. Sci. 26 (2007), pp. 694–701.
   Web of Science ®Google Scholar
• D.M. Hawkins, S.C. Basak, and D. Mills, Assessing model fit by cross-validation, J. Chem. Inf. Comput. Sci. 43 (2003), pp. 579–586.
   PubMedGoogle Scholar
• D.M. Hawkins, The problem of overfitting, J. Chem. Inf. Comput. Sci. 44 (2004), pp. 1–12.
   PubMedGoogle Scholar
• A. Rácz, D. Bajusz, and K. Héberger, Consistency of QSAR models: Correct split of training and test sets, ranking of models and performance parameters, SAR QSAR Environ. Res. 26 (2015), pp. 683–700.
   Google Scholar
• K. Héberger, A. Rácz, and D. Bajusz, Which performance parameters are best suited to assess the predictive ability of models? in Advances in QSAR Modeling, K. Roy, ed., Springer,  International Publishing, New York, USA, 2017, pp. 89–104.
   Google Scholar
• J.C. Dearden, M.T.D. Cronin, and K.L.E. Kaiser, How not to develop a quantitative structure–activity or structure–property relationship (QSAR/QSPR), SAR QSAR Environ. Res. 20 (2009), pp. 241–266.
   Google Scholar
• T. Hanser, C. Barber, J.F. Marchaland, and S. Werner, Applicability domain: Towards a more formal definition, SAR QSAR Environ. Res. 27 (2016), pp. 893–909.
   Google Scholar
• P. Gramatica and A. Sangion, A historical excursus on the statistical validation parameters for QSAR Models: A clarification concerning metrics and terminology, J. Chem. Inf. Model. 56 (2016), pp. 1127–1131.
   PubMed Web of Science ®Google Scholar
• O. Farkas and K. Héberger, Comparison of ridge regression, partial least squares, pair-wise correlation, forward- and best subset selection methods for prediction of retention indices for aliphatic alcohols, J. Chem. Inf. Model. 45 (2005), pp. 339–346.
   PubMed Web of Science ®Google Scholar
• J.P. Doucet, E. Papa, A. Doucet-Panaye, and J. Devillers, QSAR models for predicting the toxicity of piperidine derivatives against Aedes aegypti, SAR QSAR Environ. Res. 28 (2017), pp. 451–470.
   Google Scholar
• J.A. Castillo-Garit, G.M. Casañola-Martin, S.J. Barigye, H. Pham-The, F. Torrens, and A. Torreblanca, Machine learning-based models to predict modes of toxic action of phenols to Tetrahymena pyriformis, SAR QSAR Environ. Res. 28 (2017), pp. 735–747.
   Google Scholar
• S. Bitam, M. Hamadache, and S. Hanini, QSAR model for prediction of the therapeutic potency of N-benzylpiperidine derivatives as AChE inhibitors, SAR QSAR Environ. Res. 28 (2017), pp. 471–489.
   Google Scholar
• D. Qu, A. Yan, and J.S. Zhang, SAR and QSAR study on the bioactivities of human epidermal growth factor receptor-2 (HER2) inhibitors, SAR QSAR Environ Res. 28 (2017), pp. 111–112.
   Google Scholar
• K. Héberger, S. Kolarević, M. Kračun-Kolarević, K. Sunjog, Z. Gačić, Z. Kljajić, M. Mitrić, and B. Vuković-Gačić, Evaluation of single-cell gel electrophoresis data: Combination of variance analysis with sum of ranking differences, Mutat. Res. Genet. Toxicol. Environ. Mutagen. 771 (2014), pp. 15–22.
   PubMed Web of Science ®Google Scholar
• C. Bertinetto, C. Duce, R. Solaro, K. Héberger, A. Miličević,  and S. Nikolić, Modeling of the acute toxicity of benzene derivatives by complementary QSAR methods, Match-Comm. Math. Comput. Chem. 70 (2013), pp. 1005–1021.
   Web of Science ®Google Scholar
• M. Cassotti, D. Ballabio, V. Consonni, A. Mauri, I. V Tetko, and R. Todeschini, Prediction of acute aquatic toxicity toward Daphnia magna by using the GA-kNN method, Altern. Lab. Anim. 42 (2014), pp. 31–41.
   Web of Science ®Google Scholar
• QikProp, Release 2017-4. Schrödinger, LLC, New York, NY, 2017.
   Google Scholar
• RDKit: Open-Source Cheminformatics Software; software available at http://rdkit.org/.
   Google Scholar
• PLS Toolbox, Eigenvector Research Inc.; software available at: http://www.eigenvector.com/index.htm.
   Google Scholar
• A. Rácz, M. Fodor, and K. Héberger, Development and comparison of regression models for the determination of quality parameters in margarine spread samples using NIR spectroscopy, Anal. Meth. 10 (2018), pp. 3089–3099.
   Web of Science ®Google Scholar
• K. Héberger, Sum of ranking differences compares methods or models fairly, TrAC Trends Anal. Chem. 29 (2010), pp. 101–109.
   Web of Science ®Google Scholar
• K. Kollár-Hunek and K. Héberger, Method and model comparison by sum of ranking differences in cases of repeated observations (ties), Chemom. Intell. Lab. Syst. 127 (2013), pp. 139–146.
   Web of Science ®Google Scholar
• D. Bajusz, A. Rácz, and K. Héberger, Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations? J. Cheminform. 7 (2015), pp.1-13. Article no: 20.
   Google Scholar
• G. Tóth, Z. Bodai, and K. Héberger, Estimation of influential points in any data set from coefficient of determination and its leave-one-out cross-validated counterpart, J. Comput. Aided Mol. Des. 27 (2013), pp. 837–844.
   PubMed Web of Science ®Google Scholar