Quantitative and qualitative models for carcinogenicity prediction for non-congeneric chemicals using CP ANN method for regulatory uses

The new European chemicals regulation Registration, Evaluation, Authorization and Restriction of Chemicals entered into force in June 2007 and accelerated the development of quantitative structure–activity relationship (QSAR) models for a variety of endpoints, including carcinogenicity. Here, we would like to present quantitative (continuous) and qualitative (categorical) models for non-congeneric chemicals for prediction of carcinogenic potency. A dataset of 805 substances was obtained after a preliminary screening of findings of rodent carcinogenicity for 1,481 chemicals accessible via Distributed Structure-Searchable Toxicity (DSSTox) Public Database Network originated from the Lois Gold Carcinogenic Potency Database (CPDB). Twenty seven two-dimensional MDL descriptors were selected using Kohonen mapping and principal component analysis. The counter propagation artificial neural network (CP ANN) technique was applied. Quantitative models were developed exploring the relationship between the experimental and predicted carcinogenic potency expressed as a tumorgenic dose TD50 for rats. The obtained models showed low prediction power with correlation coefficient less than 0.5 for the test set. In the next step, qualitative models were developed. We found that the qualitative models exhibit good accuracy for the training set (92%). The model demonstrated good predicted performance for the test set. It was obtained accuracy (68%), sensitivity (73%), and specificity (63%). We believe that CP ANN method is a good in silico approach for modeling and predicting rodent carcinogenicity for non-congeneric chemicals and may find application for o ther toxicological endpoints.

[1]  Johann Gasteiger,et al.  Neural networks with counter-propagation learning strategy used for modelling , 1995 .

[2]  Theo Vermeire,et al.  Risk assessment of chemicals , 2021, Bioanalytical Tools in Water Quality Assessment.

[3]  J. Contrera,et al.  A new highly specific method for predicting the carcinogenic potential of pharmaceuticals in rodents using enhanced MCASE QSAR-ES software. , 1998, Regulatory toxicology and pharmacology : RTP.

[4]  Maykel Pérez González,et al.  A topological substructural approach applied to the computational prediction of rodent carcinogenicity. , 2005, Bioorganic & medicinal chemistry.

[5]  Harry Wechsler,et al.  From Statistics to Neural Networks: Theory and Pattern Recognition Applications , 1996 .

[6]  John D. Walker,et al.  Use of QSARs in international decision-making frameworks to predict health effects of chemical substances. , 2003, Environmental health perspectives.

[7]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[8]  Maykel Pérez González,et al.  Quantitative structure activity relationship for the computational prediction of nitrocompounds carcinogenicity. , 2006, Toxicology.

[9]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[10]  T. Ushijima,et al.  No-observed effect levels for carcinogenicity and for in vivo mutagenicity of a genotoxic carcinogen. , 2004, Toxicological sciences : an official journal of the Society of Toxicology.

[11]  R. Hecht-Nielsen.  Counterpropagation networks. , 1987, Applied optics.

[12]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[13]  Robert Combes,et al.  Proposed Integrated Decision-tree Testing Strategies for Mutagenicity and Carcinogenicity in Relation to the EU REACH Legislation , 2007, Alternatives to laboratory animals : ATLA.

[14]  R. Saracci,et al.  Describing the validity of carcinogen screening tests. , 1979, British Journal of Cancer.

[15]  R. Benigni.  Structure-activity relationship studies of chemical mutagens and carcinogens: mechanistic investigations and prediction approaches. , 2005, Chemical reviews.

[16]  S Parodi,et al.  A computerized connectivity approach for analyzing the structural basis of mutagenicity in Salmonella and its relationship with rodent carcinogenicity , 1996, Environmental and molecular mutagenesis.

[17]  G H Loew,et al.  Computer-assisted mechanistic structure-activity studies: application to diverse classes of chemical carcinogens. , 1985, Environmental health perspectives.

[18]  J. DiPaolo,et al.  Morphological, oncogenic, and karyological characteristics of Syrian hamster embryo cells transformed in vitro by carcinogenic polycyclic hydrocarbons. , 1971, Cancer research.

[19]  A. Tropsha,et al.  Beware of q2! , 2002, Journal of molecular graphics & modelling.

[20]  Romualdo Benigni,et al.  Collection and Evaluation of (Q)SAR Models for Mutagenicity and Carcinogenicity , 2007 .

[21]  Marjan Vracko,et al.  A Study of Structure-Carcinogenic Potency Relationship with Artificial Neural Networks. The Using of Descriptors Related to Geometrical and Electronic Structures , 1997, J. Chem. Inf. Comput. Sci..

[22]  David Kirkland,et al.  Evaluation of the ability of a battery of three in vitro genotoxicity tests to discriminate rodent carcinogens and non-carcinogens III. Appropriate follow-up testing in vivo. , 2005, Mutation research.

[23]  A.M. Richard,et al.  AI and SAR approaches for predicting chemical carcinogenicity: Survey and status report , 2002, SAR and QSAR in environmental research.

[24]  E. Zeiger,et al.  Handbook of Carcinogenic Potency and Genotoxicity Databases , 1996 .

[25]  A M Richard,et al.  Structure-based methods for predicting mutagenicity and carcinogenicity: are we there yet? , 1998, Mutation research.

[26]  Lutz Müller,et al.  Erratum to “Evaluation of the ability of a battery of three in vitro genotoxicity tests to discriminate rodent carcinogens and non-carcinogens I. Sensitivity, specificity and relative predictivity” [Mut. Res. 584 (2005) 1–256] , 2005 .

[27]  A M Richard,et al.  A CASE-SAR analysis of polycyclic aromatic hydrocarbon carcinogenicity. , 1990, Mutation research.

[28]  J. Zupan,et al.  Prediction of selectivity of alpha1-adrenergic antagonists by counterpropagation neural network (CP-ANN). , 2004, Il Farmaco.

[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]  Lutz Müller,et al.  Evaluation of the ability of a battery of three in vitro genotoxicity tests to discriminate rodent carcinogens and non-carcinogens I. Sensitivity, specificity and relative predictivity. , 2005, Mutation research.

[31]  J R Chretien,et al.  Application of Kohonen Neural Networks in classification of biologically active compounds. , 1998, SAR and QSAR in environmental research.

[32]  Didier Villemin,et al.  Predicting Carcinogenicity of Polycyclic Aromatic Hydrocarbons from Back-Propagation Neural Network , 1994, Journal of chemical information and computer sciences.

[33]  V. Poroikov,et al.  Directions in QSAR Modeling for Regulatory Uses in OECD Member Countries, EU and in Russia , 2008, Journal of environmental science and health. Part C, Environmental carcinogenesis & ecotoxicology reviews.

[34]  Gerrit Schüürmann,et al.  Quantitative structure-activity relationships in environmental sciences, VII , 1997 .

[35]  Emilio Benfenati,et al.  Predictive Carcinogenicity: A Model for Aromatic Compounds, with Nitrogen‐Containing Substituents, Based on Molecular Descriptors Using an Artificial Neural Network. , 2000 .

[36]  J. Dearden,et al.  Predicting Fate-Related Physicochemical Properties , 2007 .

[37]  R. King,et al.  Prediction of rodent carcinogenicity bioassays from molecular structure using inductive logic programming. , 1996, Environmental health perspectives.

[38]  Naomi L Kruhlak,et al.  Progress in QSAR toxicity screening of pharmaceutical impurities and other FDA regulated products. , 2007, Advanced drug delivery reviews.

[39]  Ulrike Bernauer,et al.  The use of in vitro data in risk assessment. , 2005, Basic & clinical pharmacology & toxicology.

[40]  A. Knight,et al.  Animal carcinogenicity studies: implications for the REACH system. , 2006, Alternatives to laboratory animals : ATLA.

[41]  H S Rosenkranz,et al.  Development, characterization and application of predictive-toxicology models. , 1999, SAR and QSAR in environmental research.

[42]  A. Balaban,et al.  Topological Indices and Related Descriptors in QSAR and QSPR , 2003 .

[43]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[44]  R Benigni,et al.  Prediction of rodent carcinogenicity of aromatic amines: a quantitative structure-activity relationships model. , 2001, Carcinogenesis.

[45]  Romualdo Benigni,et al.  Quantitative Structure-Activity Relationship (QSAR) Models of Mutagens and Carcinogens , 2003 .

[46]  Marjan Vračko,et al.  Counter-propagation artificial neural network as a tool for the independent variable selection: Structure-mutagenicity study on aromatic amines , 2004, Molecular Diversity.

[47]  Vladimir V Poroikov,et al.  Computer-aided rodent carcinogenicity prediction. , 2005, Mutation research.

[48]  M. Fenech,et al.  Report from the In Vitro Micronucleus Assay Working Group , 2003, Mutation research.

[49]  Romualdo Benigni,et al.  The Development and Validation of Expert Systems for Predicting Toxicity The Report and Recommendations of an ECVAM / ECB Workshop ( ECVAM Workshop 24 ) , 2002 .

[50]  J. Jaworska,et al.  Summary of a workshop on regulatory acceptance of (Q)SARs for human health and environmental endpoints. , 2003, Environmental health perspectives.

[51]  J. Contrera,et al.  Predicting the carcinogenic potential of pharmaceuticals in rodents using molecular structural similarity and E-state indices. , 2003, Regulatory toxicology and pharmacology : RTP.

[52]  Marjan Vračko,et al.  Comparison of spectrum-like representation of 3D chemical structure with other representations when used for modelling biological activity , 2001 .

[53]  Laura Passerini,et al.  QSARs for Individual Classes of Chemical Mutagens and Carcinogens , 2003 .

[54]  Jure Zupan,et al.  Study of structure–toxicity relationship by a counterpropagation neural network , 1999 .

[55]  W. Choy,et al.  Genetic Toxicology and Cancer Risk Assessment , 2001 .

[56]  Christoph Helma,et al.  In silico predictive toxicology: the state-of-the-art and strategies to predict human health effects. , 2005, Current opinion in drug discovery & development.

[57]  M. Fenech.  The in vitro micronucleus technique. , 2000, Mutation research.

[58]  Lemont B. Kier,et al.  E-state fields: Applications to 3D QSAR , 1996, J. Comput. Aided Mol. Des..

[59]  Alessandro Giuliani,et al.  Putting the Predictive Toxicology Challenge Into Perspective: Reflections on the Results , 2003, Bioinform..

[60]  H S Rosenkranz,et al.  Identification of 'genotoxic' and 'non-genotoxic' alerts for cancer in mice: the carcinogenic potency database. , 1998, Mutation research.

[61]  Emilio Benfenati,et al.  Classification of Potential Endocrine Disrupters on the Basis of Molecular Structure Using a Nonlinear Modeling Method , 2004, J. Chem. Inf. Model..

[62]  Véronique Thybaud,et al.  SFTG international collaborative study on in vitro micronucleus test II. Using human lymphocytes. , 2006, Mutation research.

[63]  Marjan Vračko,et al.  Verification of the geological origin of bottled mineral water using artificial neural networks , 2010 .

[64]  L Zhang,et al.  The structure-activity relationship of skin carcinogenicity of aromatic hydrocarbons and heterocycles. , 1992, Chemico-biological interactions.

[65]  G. Klopman.  MULTICASE 1. A Hierarchical Computer Automated Structure Evaluation Program , 1992 .

[66]  Worth Andrew,et al.  The Development and Validation of Expert Systems for Predicting Toxicity. , 1998 .

[67]  Gilles Klopman,et al.  MC4PC—An Artificial Intelligence Approach to the Discovery of Quantitative Structure–Toxic Activity Relationships , 2005 .

[68]  E Benfenati,et al.  Computational predictive programs (expert systems) in toxicology. , 1997, Toxicology.

[69]  Markus A Lill,et al.  Multi-dimensional QSAR in drug discovery. , 2007, Drug discovery today.

[70]  Willem P. van Hoorn,et al.  Designing Compound Subsets: Comparison of Random and Rational Approaches Using Statistical Simulation , 2007, J. Chem. Inf. Model..

[71]  L B Kier,et al.  Database Organization and Searching with E-State Indices , 2001, SAR and QSAR in environmental research.

[72]  W. Choy,et al.  Genotoxic and Nongenotoxic Mechanisms of Carcinogenesis , 2001 .

[73]  Lemont B. Kier,et al.  Molecular structure description , 1999 .

[74]  Marjan Vracko,et al.  Kohonen Artificial Neural Network and Counter Propagation Neural Network in Molecular Structure-Toxicity Studies , 2005 .

[75]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[76]  Yin-tak Woo,et al.  OncoLogic: A Mechanism-Based Expert System for Predicting the Carcinogenic Potential of Chemicals , 2005 .

[77]  R D Combes,et al.  The use of structure-activity relationships and markers of cell toxicity to detect non-genotoxic carcinogens. , 2000, Toxicology in vitro : an international journal published in association with BIBRA.

[78]  Donald E Mager,et al.  Quantitative structure-pharmacokinetic/pharmacodynamic relationships. , 2006, Advanced drug delivery reviews.

[79]  G S Omenn,et al.  Assessing the risk assessment paradigm. , 1995, Toxicology.

[80]  R Benigni,et al.  Quantitative structure-based modeling applied to characterization and prediction of chemical toxicity. , 1998, Methods.

[81]  Tudor I. Oprea,et al.  Integrating virtual screening in lead discovery. , 2004, Current opinion in chemical biology.

[82]  Emilio Benfenati,et al.  Quantitative Structure-Activity Relationships (QSAR) for pesticide regulatory purposes , 2007 .

[83]  Alessandro Giuliani,et al.  Quantitative Structure—Activity Relationships of Mutagenic and Carcinogenic Aromatic Amines , 2000 .

[84]  Kunal Roy,et al.  On Selection of Training and Test Sets for the Development of Predictive QSAR models , 2006 .

[85]  E. Benfenati,et al.  Regulatory Assessment of Chemicals within OECD Member Countries, EU and in Russia , 2008, Journal of environmental science and health. Part C, Environmental carcinogenesis & ecotoxicology reviews.

[86]  Maykel Pérez González,et al.  The Prediction of Carcinogenicity from Molecular Structure , 2005 .

[87]  Judith E. Dayhoff,et al.  Neural Network Architectures: An Introduction , 1989 .

[88]  Gilles Klopman,et al.  ESP: A Method to Predict Toxicity and Pharmacological Properties of Chemicals Using Multiple MCASE Databases. , 2004 .

[89]  Johann Gasteiger,et al.  Neural networks in chemistry and drug design , 1999 .

[90]  I. W Nowell,et al.  Molecular Connectivity in Structure-Activity Analysis , 1986 .

[91]  A. Zuckerman,et al.  IARC Monographs on the Evaluation of Carcinogenic Risks to Humans , 1995, IARC monographs on the evaluation of carcinogenic risks to humans.

[92]  Grace Patlewicz,et al.  Quantitative structure‐activity relationships for predicting mutagenicity and carcinogenicity , 2003, Environmental toxicology and chemistry.

[93]  I. Jolliffe.  Principal Component Analysis , 2002 .

[94]  M. Long.  Predicting carcinogenicity in humans: The need to supplement animal-based toxicology , 2006 .