The unreliability of the reliability criteria in the estimation of QSAR for skin sensitivity: A pun or a reliable law?

Ambure, 2019, QSAR-Co: an open source software for developing robust multitasking or multitarget classification-based QSAR models, J. Chem. Inf. Model., 59, 2538, 10.1021/acs.jcim.9b00295 Aptula, 2005, 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, 385, 10.1002/qsar.200430909 Asturiol, 2016, Consensus of classification trees for skin sensitisation hazard prediction, Toxicol. In Vitro, 36, 197, 10.1016/j.tiv.2016.07.014 Balaban, 1982, Highly discriminating distance-based topological index, Chem. Phys. Lett., 89, 399, 10.1016/0009-2614(82)80009-2 Box, 1976, Science and statistics, J. Am. Stat. Assoc., 71, 791, 10.1080/01621459.1976.10480949 Casañola-Martin, 2014, Tyrosinase enzyme: 1. An overview on a pharmacological target, Curr. Top. Med. Chem., 14, 1494, 10.2174/1568026614666140523121427 Chirico, 2011, 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., 51, 2320, 10.1021/ci200211n CIR, 2020 Concu, 2017, Probing the toxicity of nanoparticles: a unified in silico machine learning model based on perturbation theory, Nanotoxicology, 11, 891, 10.1080/17435390.2017.1379567 Dearden, 2015, Mechanism- based QSAR modeling of skin sensitization, Chem. Res. Toxicol., 28, 1975, 10.1021/acs.chemrestox.5b00197 Doweyko, 2008, QSAR: dead or alive?, J. Comput. Aided Mol. Des., 22, 81, 10.1007/s10822-007-9162-7 FDA, 2019 FDA, 2020 Golbraikh, 2002, Beware of q2!, J. Mol. Graph. Model., 20, 269, 10.1016/S1093-3263(01)00123-1 Gutman, 1994, Selected properties of the Schultz molecular topological index, J. Chem. Inf. Comput. Sci., 34, 1087, 10.1021/ci00021a009 Hall, 1995, Electrotopological state indices for atom types: a novel combination of electronic, topological, and valence state information, J. Chem. Inform. Comput. Sci., 35, 1039, 10.1021/ci00028a014 Hartung, 2009, Food for thought. on in silico methods in toxicology, ALTEX - Alternatives to animal experimentation, 26, 155 Hemmateenejad, 2012, Quantitative structure-retention relationship study of analgesic drugs by application of combined data splitting-feature selection strategy and genetic algorithm-partial least square, J. Iran. Chem. Soc., 9, 53, 10.1007/s13738-011-0005-z Idehara, 2008, Characterization and evaluation of a modified local lymph node assay using ATP content as a non-radio isotopic endpoint, J. Pharmacol. Toxicol. Methods, 58, 1, 10.1016/j.vascn.2008.03.003 Johnson, 2008, The trouble with QSAR (or how i learned to stop worrying and embrace fallacy), J. Chem. Inf. Model., 48, 25, 10.1021/ci700332k Kleandrova, 2015, In silico assessment of the acute toxicity of chemicals: recent advances and new model for multitasking prediction of toxic effect, Mini Rev. Med. Chem., 15, 677, 10.2174/1389557515666150219143604 Kleandrova, 2020, Cell-based multi-target QSAR model for design of virtual versatile inhibitors of liver cancer cell lines, SAR QSAR Environ. Res., 10.1080/1062936X.2020.1818617 Kubinyi, 1996, Evolutionary variable selection in regression and PLS analyses, J. Chemom., 10, 119, 10.1002/(SICI)1099-128X(199603)10:2<119::AID-CEM409>3.0.CO;2-4 Kubinyi, 2004 Kumar, 2017, Use of the Monte Carlo method for OECD principles-guided QSAR modeling of SIRT1 inhibitors, Arch. Pharm., 350, e1600268, 10.1002/ardp.201600268 Kumar, 2018, Monte carlo method based QSAR studies of Mer kinase inhibitors in compliance with OECD principles, Drug Res., 68, 189, 10.1055/s-0043-119288 Lin, 1992, Assay validation using the concordance correlation coefficient, Biometrics, 48, 599, 10.2307/2532314 Messias Monteiro, 2020, In silico studies for bacterystic evaluation against staphylococcus aureus of 2-naphthoic acid analogues, Curr. Top. Med. Chem., 20, 293, 10.2174/1568026619666191206111742 Natsch, 2009, Filling the concept with data: integrating data from different in vitro and in silico assays on skin sensitizers to explore the battery approach for animal-free skin sensitization testing, Toxicol. Sci., 107, 106, 10.1093/toxsci/kfn204 Natsch, 2015, Predicting skin sensitizer potency based on in vitro data from keratinosens and kinetic peptide binding: global versus domain-based assessment, Toxicol. Sci., 143, 319, 10.1093/toxsci/kfu229 Natsch, 2018, Deriving a no expected sensitization induction level for fragrance ingredients without animal testing: an integrated approach applied to specific case studies, Toxicol. Sci., 165, 170, 10.1093/toxsci/kfy135 OECD, 1992 OECD, 2007 PCPC, 2014 Peters, 2015, Everything should be as simple as possible, but no simpler: towards a protocol for accumulating evidence regarding the active content of health behaviour change interventions, Health Psychol. Rev., 9, 1, 10.1080/17437199.2013.848409 Roy, 2014, The rm2 metrics and regression through origin approach: reliable and useful validation tools for predictive QSAR models (Commentary on’ is regression through origin useful in external validation of QSAR models?’), Eur. J. Pharm. Sci., 62, 111, 10.1016/j.ejps.2014.05.019 Roy, 2008, Exploring the impact of size of training sets for the development of predictive QSAR models, Chemometr. Intell. Lab. Syst., 90, 31, 10.1016/j.chemolab.2007.07.004 SCCS, 2018, 24 Schultz, 1989, Topological organic chemistry. 1. Graph theory and topological indices of alkanes, J. Chem. Inform. Comput. Sci., 29, 227, 10.1021/ci00063a012 Shayanfar, 2014, Is regression through origin useful in external validation of QSAR models?, Eur. J. Pharm. Sci., 59, 31, 10.1016/j.ejps.2014.03.007 Speck-Planche, 2020, Multi-scale QSAR approach for simultaneous modeling of ecotoxic effects of pesticides, 639 Speck-Planche, 2012, Predicting multiple ecotoxicological profiles in agrochemical fungicides: a multi-species chemoinformatic approach, Ecotoxicol. Environ. Saf., 80, 308, 10.1016/j.ecoenv.2012.03.018 Toropov, 2017, The index of ideality of correlation: a criterion of predictive potential of QSPR/QSAR models?, Mutat. Res. Genet. Toxicol. Environ. Mutagen., 819, 31, 10.1016/j.mrgentox.2017.05.008 Toropov, 2019, QSAR as a random event: criteria of predictive potential for a chance model, Struct. Chem., 30, 1677, 10.1007/s11224-019-01361-6 Toropov, 2020, Correlation Intensity Index: building up models for mutagenicity of silver nanoparticles, Sci. Total Environ., 737, 10.1016/j.scitotenv.2020.139720 Toropova, 2017, The index of ideality of correlation: a criterion of predictability of QSAR models for skin permeability?, Sci. Total Environ., 586, 466, 10.1016/j.scitotenv.2017.01.198 Toropova, 2017, Hybrid optimal descriptors as a tool to predict skin sensitization in accordance to OECD principles, Toxicol. Lett., 275, 57, 10.1016/j.toxlet.2017.03.023 Toropova, 2017, CORAL: binary classifications (active/inactive) for drug-induced liver injury, Toxicol. Lett., 268, 51, 10.1016/j.toxlet.2017.01.011 Weininger, 1988, SMILES, a chemical language and information system: 1: introduction to methodology and encoding rules, J. Chem. Inform. Comput. Sci., 28, 31, 10.1021/ci00057a005