Cross-validation strategies in QSPR modelling of chemical reactions

References

• M. Balls, B.J. Blaauboer, J.H. Fentem, L. Bruner, R.D. Combes, B. Ekwall, R.J. Fielder, A. Guillouzo, R.W. Lewis, D.P. Lovell, C.A. Reinhardt, G. Repetto, D. Sladowski, H. Spielmann, and F. Zucco, Practical aspects of the validation of toxicity test procedures, Altern. Lab. Anim. 23 (1995), pp. 129–146. doi:10.1177/026119299502300116.
   Web of Science ®Google Scholar
• A. Tropsha, P. Gramatica, and V. Gombar, The importance of being earnest: Validation is the absolute essential for successful application and interpretation of QSPR models, QSAR Comb. Sci. 22 (2003), pp. 69–77. doi:10.1002/qsar.200390007.
   Google Scholar
• I.V. Tetko, V.P. Solov’ev, A.V. Antonov, X. Yao, J.P. Doucet, B. Fan, F. Hoonakker, D. Fourches, P. Jost, N. Lachiche, and A. Varnek, Benchmarking of linear and nonlinear approaches for quantitative structure−property relationship studies of metal complexation with ionophores, J. Chem. Inf. Model. 46 (2006), pp. 808–819. doi:10.1021/ci0504216.
   PubMed Web of Science ®Google Scholar
• R. Veerasamy, H. Rajak, A. Jain, S. Sivadasan, C.P. Varghese, and R.K. Agrawal, Validation of QSAR models - Strategies and importance, Int. J. Drug Discov. 2 (2011), pp. 511–519.
   Google Scholar
• K. Roy, S. Kar, and R.N. Das, Validation of QSAR models, in Understanding the Basics of QSAR for Applications in Pharmaceutical Sciences and Risk Assessment, K. Roy (ed.), Elsevier, San Diego, 2015, pp. 231–289.
   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. doi:10.1021/acs.jcim.6b00088.
   PubMed Web of Science ®Google Scholar
• I. Oprisiu, E. Varlamova, E. Muratov, A. Artemenko, G. Marcou, P. Polishchuk, V. Kuz’min, and A. Varnek, QSPR approach to predict nonadditive properties of mixtures. Application to bubble point temperatures of binary mixtures of liquids, Mol. Inform. 31 (2012), pp. 491–502. doi:10.1002/minf.201200006.
   PubMed Web of Science ®Google Scholar
• E. Muratov, E.V. Varlamova, V.E. Kuzmin, A.G. Artemenko, N.N. Muratov, S. Mileyko, D. Fourches, and A. Tropsha, Everything out validation approach for qsar models of chemical mixtures, J. Clin. Pharm. 1 (2014), pp. 1005.
   Google Scholar
• M. Glavatskikh, T. Madzhidov, V. Solov’ev, G. Marcou, D. Horvath, and A. Varnek, Predictive models for the free energy of hydrogen bonded complexes with single and cooperative hydrogen bonds, Mol. Inform. 35 (2016), pp. 629–638. doi:10.1002/minf.201600070.
   PubMed Web of Science ®Google Scholar
• A.O. Aptula, N.G. Jeliazkova, T.W. Schultz, and M.T.D. Cronin, The better predictive model: High q2 for the training set or low root mean square error of prediction for the test set? QSAR Comb. Sci. 24 (2005), pp. 385–396. doi:10.1002/qsar.200430909.
   Google Scholar
• A. Golbraikh and A. Tropsha, Beware of q2!, J. Mol. Graph. Model. 20 (2002), pp. 269–276. doi:10.1016/S1093-3263(01)00123-1.
   PubMed Web of Science ®Google Scholar
• P. Gramatica, Principles of QSAR models validation: Internal and external, QSAR Comb. Sci. 26 (2007), pp. 694–701. doi:10.1002/qsar.200610151.
   Google Scholar
• J. Gasteiger and J. Zupan, Neural Networks in Chemistry, Angew. Chemie Int. Ed. English 32 (1993), pp. 503–527. doi:10.1002/anie.199305031.
   Web of Science ®Google Scholar
• J. Huuskonen, QSAR modeling with the electrotopological state: TIBO derivatives, J. Chem. Inf. Comput. Sci. 41 (2001), pp. 425–429. doi:10.1021/ci0001435.
   PubMedGoogle Scholar
• I.V. Tetko, V.V. Kovalishyn, and D.J. Livingstone, Volume learning algorithm artificial neural networks for 3D QSAR studies, J. Med. Chem. 44 (2001), pp. 2411–2420. doi:10.1021/jm010858e.
   PubMed Web of Science ®Google Scholar
• M. Snarey, N.K. Terrett, P. Willett, and D.J. Wilton, Comparison of algorithms for dissimilarity-based compound selection, J. Mol. Graph. Model. 15 (1997), pp. 372–385. doi:10.1016/S1093-3263(98)00008-4.
   PubMed Web of Science ®Google Scholar
• A. Golbraikh, Molecular dataset diversity indices and their applications to comparison of chemical databases and QSAR analysis, J. Chem. Inf. Comput. Sci. 40 (2000), pp. 414–425. doi:10.1021/ci990437u.
   PubMedGoogle Scholar
• C. Szántai-Kis, I. Kövesdi, G. Kéri, and L. Örfi, Validation subset selections for extrapolation oriented QSPAR models, Mol. Divers. 7 (2003), pp. 37–43. doi:10.1023/B:MODI.0000006538.99122.00.
   PubMed Web of Science ®Google Scholar
• D. Baumann and K. Baumann, Reliable estimation of prediction errors for QSAR models under model uncertainty using double cross-validation, J. Cheminform. 6 (2014), pp. 47. doi:10.1186/s13321-014-0047-1.
   PubMed Web of Science ®Google Scholar
• T. Gimadiev, T. Madzhidov, I. Tetko, R. Nugmanov, I. Casciuc, O. Klimchuk, A. Bodrov, P. Polishchuk, I. Antipinn, and A. Varnek, Bimolecular nucleophilic substitution reactions: Predictive models for rate constants and molecular reaction pairs analysis, Mol. Inform. 38 (2019), pp. 1800104. doi:10.1002/minf.201800104.
   Web of Science ®Google Scholar
• P. Polishchuk, T. Madzhidov, T. Gimadiev, A. Bodrov, R. Nugmanovn, and A. Varnek, Structure–reactivity modeling using mixture-based representation of chemical reactions, J. Comput. Aided. Mol. Des. 31 (2017), pp. 829–839. doi:10.1007/s10822-017-0044-3.
   PubMed Web of Science ®Google Scholar
• O. Engkvist, P.-O. Norrby, N. Selmi, Y. Lam, Z. Peng, E.C. Sherer, W. Amberg, T. Erhardn, and L.A. Smyth, Computational prediction of chemical reactions: Current status and outlook, Drug Discov. Today 23 (2018), pp. 1203–1218. doi:10.1016/j.drudis.2018.02.014.
   PubMed Web of Science ®Google Scholar
• H. Gao, T.J. Struble, C.W. Coley, Y. Wang, W.H. Green, and K.F. Jensen, Using machine learning to predict suitable conditions for organic reactions, ACS Cent. Sci. 4 (2018), pp. 1465–1476. doi:10.1021/acscentsci.8b00357.
   PubMed Web of Science ®Google Scholar
• I.I. Baskin, T.I. Madzhidov, I.S. Antipin, and A.A. Varnek, Artificial intelligence in synthetic chemistry: Achievements and prospects, Russ. Chem. Rev. 86 (2017), pp. 1127–1156. doi:10.1070/RCR4746.
   Web of Science ®Google Scholar
• D.T. Ahneman, J.G. Estrada, S. Lin, S.D. Dreher, and A.G. Doyle, Predicting reaction performance in C–N cross-coupling using machine learning, Science 360 (2018), pp. 186–190. doi:10.1126/science.aar5169.
   PubMed Web of Science ®Google Scholar
• F. Sandfort, F. Strieth-Kalthoff, M. Kühnemund, C. Beecks, and F. Glorius, A structure-based platform for predicting chemical reactivity, Chem 6 (2020), pp. 1379–1390. doi:10.1016/j.chempr.2020.02.017.
   Web of Science ®Google Scholar
• J.A. Kammeraad, J. Goetz, E.A. Walker, A. Tewari, and P.M. Zimmerman, What does the machine learn? Knowledge representations of chemical reactivity, J. Chem. Inf. Model. 60 (2020), pp. 1290–1301. doi:10.1021/acs.jcim.9b00721.
   PubMed Web of Science ®Google Scholar
• A.A. Kravtsov, P.V. Karpov, I.I. Baskin, V.A. Palyulin, and N.S. Zefirov, Prediction of rate constants of SN2 reactions by the multicomponent QSPR method, Dokl. Chem. 440 (2011), pp. 299–301. doi:10.1134/S0012500811100107.
   Web of Science ®Google Scholar
• A.A. Kravtsov, P.V. Karpov, I.I. Baskin, V.A. Palyulin, and N.S. Zefirov, Prediction of the preferable mechanism of nucleophilic substitution at saturated carbon atom and prognosis of SN1 rate constants by means of QSPR, Dokl. Chem. 441 (2011), pp. 314–317. doi:10.1134/S0012500811110048.
   Web of Science ®Google Scholar
• T.I. Madzhidov, A.V. Bodrov, T.R. Gimadiev, R.I. Nugmanov, I.S. Antipin, and A.A. Varnek, Structure–reactivity relationship in bimolecular elimination reactions based on the condensed graph of a reaction, J. Struct. Chem. 56 (2015), pp. 1227–1234. doi:10.1134/S002247661507001X.
   Web of Science ®Google Scholar
• T.I. Madzhidov, T.R. Gimadiev, D.A. Malakhova, R.I. Nugmanov, I.I. Baskin, I.S. Antipin, and A.A. Varnek, Structure–reactivity relationship in Diels–Alder reactions obtained using the condensed reaction graph approach, J. Struct. Chem. 58 (2017), pp. 650–656. doi:10.1134/S0022476617040023.
   Web of Science ®Google Scholar
• T.I. Madzhidov, P.G. Polishchuk, R.I. Nugmanov, A.V. Bodrov, A.I. Lin, I.I. Baskin, A.A. Varnek, and I.S. Antipin, Structure-reactivity relationships in terms of the condensed graphs of reactions, Russ. J. Org. Chem. 50 (2014), pp. 459–463. doi:10.1134/S1070428014040010.
   Web of Science ®Google Scholar
• T.R. Gimadiev, T.I. Madzhidov, R.I. Nugmanov, I.I. Baskin, I.S. Antipin, and A. Varnek, Assessment of tautomer distribution using the condensed reaction graph approach, J. Comput. Aided. Mol. Des. 32 (2018), pp. 401–414. doi:10.1007/s10822-018-0101-6.
   PubMed Web of Science ®Google Scholar
• A. Varnek, D. Fourches, F. Hoonakker, and V.P. Solov’ev, Substructural fragments: An universal language to encode reactions, molecular and supramolecular structures, J. Comput. Aided. Mol. Des. 19 (2005), pp. 693–703. doi:10.1007/s10822-005-9008-0.
   PubMed Web of Science ®Google Scholar
• F. Hoonakker, N. Lachiche, A. Varnek, and A. Wagner, Condensed graph of reaction: Considering a chemical reaction as one single pseudo molecule, Int. J. Artif. Intell. Tools 20 (2011), pp. 253–270. doi:10.1142/S0218213011000140.
   Google Scholar
• R.I. Nugmanov, R.N. Mukhametgaleev, T. Akhmetshin, T.R. Gimadiev, V.A. Afonina, T.I. Madzhidov, and A. Varnek, CGRtools: Python library for molecule, reaction, and condensed graph of reaction processing, J. Chem. Inf. Model. 59 (2019), pp. 2516–2521. doi:10.1021/acs.jcim.9b00102.
   PubMed Web of Science ®Google Scholar
• A. Varnek, D. Fourches, D. Horvath, O. Klimchuk, C. Gaudin, P. Vayer, V. Solov’ev, F. Hoonakker, I. Tetko, and G. Marcou, ISIDA - Platform for virtual screening based on fragment and pharmacophoric descriptors, Curr. Comput. Aided-Drug Des. 4 (2008), pp. 191–198. doi:10.2174/157340908785747465.
   Web of Science ®Google Scholar
• J. Catalán, V. López, P. Pérez, R. Martin-Villamil, and J.-G. Rodríguez, Progress towards a generalized solvent polarity scale: The solvatochromism of 2-(dimethylamino)-7-nitrofluorene and its homomorph 2-fluoro-7-nitrofluorene, Liebigs Ann. 1995 (1995), pp. 241–252. doi:10.1002/jlac.199519950234.
   Google Scholar
• J. Catalán, C. Díaz, and A. Generalized Solvent, Acidity Scale: The Solvatochromism ofo-tert-Butylstilbazolium Betaine Dye and Its Homomorpho,o′-Di-tert-butylstilbazolium Betaine Dye, Liebigs Ann. 1997 (1997), pp. 1941–1949. doi:10.1002/jlac.199719970921.
   Google Scholar
• R.W. Taft and M.J. Kamlet, The solvatochromic comparison method. 2. The .alpha.-scale of solvent hydrogen-bond donor (HBD) acidities, J. Am. Chem. Soc. 98 (1976), pp. 2886–2894. doi:10.1021/ja00426a036.
   Web of Science ®Google Scholar
• M.J. Kamlet and R.W. Taft, The solvatochromic comparison method. I. The .beta.-scale of solvent hydrogen-bond acceptor (HBA) basicities, J. Am. Chem. Soc. 98 (1976), pp. 377–383. doi:10.1021/ja00418a009.
   Web of Science ®Google Scholar
• M.J. Kamlet, J.L. Abboud, and R.W. Taft, The solvatochromic comparison method. 6. The .pi.* scale of solvent polarities, J. Am. Chem. Soc. 99 (1977), pp. 6027–6038. doi:10.1021/ja00460a031.
   Web of Science ®Google Scholar
• F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, A. Müller, J. Nothman, G. Louppe, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and É. Duchesnay, Scikit-learn: Machine Learning in Python, J. Mach. Learn. Res. 12 (2011), pp. 2825–2830.
   Google Scholar