Prediction of the skin sensitising potential and potency of compounds via mechanism-based binary and ternary classification models.

Skin sensitisation, one of the most frequent forms of human immune toxicity, is authenticated to be a significant endpoint in the field of drug discovery and cosmetics. Due to the drawbacks of traditional animal testing methods, in silico methods have advanced to study skin sensitisation. In this study, mechanism-based binary and ternary classification models were constructed with a comprehensive data set. 1007 compounds were collected to develop five series of local and global models based on mechanisms. In each series, compounds were classified into five groups according to EC3 values, and applied as training sets, test sets and external validation sets. For each of the five series, 81 binary classification models and 81 ternary classification models were acquired via 9 molecular fingerprints and 9 machine learning methods using a novel KNIME workflow. Meanwhile, the applicability domains for the best 10 models were figured out to certify the rationality of prediction effect. In addition, 8 toxic substructures probably causing skin sensitisation were identified to speculate whether a compound is a skin sensitiser. The mechanism-based prediction models and the toxic substructures can be applied to predict the skin sensitising potential and potency of compounds.

[1]  Paul Watson,et al.  Naïve Bayes Classification Using 2D Pharmacophore Feature Triplet Vectors , 2008, J. Chem. Inf. Model..

[2]  D A Basketter,et al.  An expert system rulebase for identifying contact allergens. , 1994, Toxicology in vitro : an international journal published in association with BIBRA.

[3]  G Frank Gerberick,et al.  The Local Lymph Node Assay: Current Position in the Regulatory Classification of Skin Sensitizing Chemicals , 2007, Cutaneous and ocular toxicology.

[4]  David Allen,et al.  Pathway-based predictive approaches for non-animal assessment of acute inhalation toxicity. , 2018, Toxicology in vitro : an international journal published in association with BIBRA.

[5]  Daniel L Villeneuve,et al.  Adverse outcome pathways: A conceptual framework to support ecotoxicology research and risk assessment , 2010, Environmental toxicology and chemistry.

[6]  Chanita Kuseva,et al.  Towards AOP application--implementation of an integrated approach to testing and assessment (IATA) into a pipeline tool for skin sensitization. , 2014, Regulatory toxicology and pharmacology : RTP.

[7]  Andrew Worth,et al.  Applying Adverse Outcome Pathways (AOPs) to support Integrated Approaches to Testing and Assessment (IATA). , 2014, Regulatory toxicology and pharmacology : RTP.

[8]  D W Roberts,et al.  Predicting skin sensitization potency for Michael acceptors in the LLNA using quantum mechanics calculations. , 2013, Chemical research in toxicology.

[9]  I. B. Turksen,et al.  A review of developments in fuzzy system models: Fuzzy rule bases to fuzzy functions , 2011 .

[10]  Hongbin Yang,et al.  Corrigendum: In Silico Prediction of Chemical Toxicity for Drug Design Using Machine Learning Methods and Structural Alerts , 2018, Front. Chem..

[11]  Janine Ezendam,et al.  Evaluating the performance of integrated approaches for hazard identification of skin sensitizing chemicals. , 2014, Regulatory toxicology and pharmacology : RTP.

[12]  CHUN WEI YAP,et al.  PaDEL‐descriptor: An open source software to calculate molecular descriptors and fingerprints , 2011, J. Comput. Chem..

[13]  Jie Li,et al.  admetSAR 2.0: web‐service for prediction and optimization of chemical ADMET properties , 2018, Bioinform..

[14]  Janine Ezendam,et al.  State of the art in non-animal approaches for skin sensitization testing: from individual test methods towards testing strategies , 2016, Archives of Toxicology.

[15]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[16]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[17]  Alexander Golbraikh,et al.  A Novel Automated Lazy Learning QSAR (ALL-QSAR) Approach: Method Development, Applications, and Virtual Screening of Chemical Databases Using Validated ALL-QSAR Models , 2006, J. Chem. Inf. Model..

[18]  I Kimber,et al.  Skin sensitization testing in potency and risk assessment. , 2001, Toxicological sciences : an official journal of the Society of Toxicology.

[19]  Martina Klaric,et al.  Systematic evaluation of non-animal test methods for skin sensitisation safety assessment. , 2015, Toxicology in vitro : an international journal published in association with BIBRA.

[20]  Robert Landsiedel,et al.  Non-animal test methods for predicting skin sensitization potentials , 2012, Archives of Toxicology.

[21]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[22]  David Allen,et al.  Integrated decision strategies for skin sensitization hazard , 2016, Journal of applied toxicology : JAT.

[23]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[24]  A. Kligman,et al.  The Identification of Contact Allergens by Animal Assay. the Guinea Pig Maximization Test , 1969 .

[25]  E. Buehler,et al.  DELAYED CONTACT HYPERSENSITIVITY IN THE GUINEA PIG. , 1965, Archives of dermatology.

[26]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[27]  Bertrand Desprez,et al.  Non-animal methods to predict skin sensitization (II): an assessment of defined approaches** , 2018, Critical reviews in toxicology.

[28]  Andrew Worth,et al.  Computer models versus reality: how well do in silico models currently predict the sensitization potential of a substance. , 2013, Regulatory toxicology and pharmacology : RTP.

[29]  Romualdo Benigni,et al.  Structure alerts for carcinogenicity, and the Salmonella assay system: a novel insight through the chemical relational databases technology. , 2008, Mutation research.

[30]  Valérie Zuang,et al.  International regulatory requirements for skin sensitization testing. , 2018, Regulatory toxicology and pharmacology : RTP.

[31]  Detlef Keller,et al.  Guiding principles for the implementation of non-animal safety assessment approaches for cosmetics: skin sensitisation. , 2012, Regulatory toxicology and pharmacology : RTP.

[32]  T. Ramírez,et al.  Peptide reactivity associated with skin sensitization: The QSAR Toolbox and TIMES compared to the DPRA. , 2016, Toxicology in vitro : an international journal published in association with BIBRA.

[33]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[34]  S. Enoch,et al.  Identification of mechanisms of toxic action for skin sensitisation using a SMARTS pattern based approach , 2008, SAR and QSAR in environmental research.

[35]  Yizeng Liang,et al.  Tree-based ensemble methods and their applications in analytical chemistry , 2012 .

[36]  Thorsten Meinl,et al.  KNIME: The Konstanz Information Miner , 2007, GfKl.

[37]  Grace Patlewicz,et al.  Skin sensitization: reaction mechanistic applicability domains for structure-activity relationships. , 2005, Chemical research in toxicology.

[38]  A. M. Api,et al.  Allergic contact dermatitis: epidemiology, molecular mechanisms, in vitro methods and regulatory aspects , 2011, Cellular and Molecular Life Sciences.

[39]  A. Fedorowicz,et al.  A new descriptor selection scheme for SVM in unbalanced class problem: a case study using skin sensitisation dataset , 2007, SAR and QSAR in environmental research.

[40]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .