Skip to main content
SpringerLink
Log in

Counter-Propagation Artificial Neural Network Models for Prediction of Carcinogenicity of Non-congeneric Chemicals for Regulatory Uses

  • Chapter
  • First Online:
Advances in QSAR Modeling

Part of the book series: Challenges and Advances in Computational Chemistry and Physics ((COCH,volume 24))

  • 1495 Accesses

Abstract

The evaluation of carcinogenic hazard of chemicals to human is nowadays one of the most challenging tasks. Quantitative structure–activity relationship (QSAR) models are welcome tools to cope with complex, expensive and time consuming experimental methods for evaluation of carcinogenic potency. Therefore, in last decade, vast effort was involved to introduce new in silico models for prediction of carcinogenicity of non-congeneric chemicals that can be effectively used for regulatory purposes in the scope of new legislation REACH (Registration, Evaluation, Authorisation and Restriction of Chemicals). In this chapter we focus on models developed in the scope of CAESAR and PROSIL projects which were implemented in on-line available internet platform VEGA (http://www.vega-qsar.eu/use-qsar.html). These QSAR models for prediction of carcinogenic potency are based on counter propagation artificial neural network algorithm (CPANN). CP ANN algorithm represents a suitable tool for modeling of complex biological data like carcinogenicity. We emphasized on the representation of key development steps needed to be involved in model construction to meet requirement of five OECD principles. First of all, it reported the description of carcinogenicity endpoint and analysis of quality of chemical and biological data (principle 1), followed by an explanation of the CPANN algorithm selected for modelling (principle 2). Next, the interpretation of domain of applicability for non-congeneric chemicals (principle 3) was given. Furthermore, the statistical performance characteristics of models in sense of its goodness-of-fit, robustness and predictivity was reported (principle 4), and finally, the mechanistic interpretation of models on the basis of selected types of descriptors and structural alerts of studied chemicals was represented (principle 5).

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 349.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 449.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 449.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Abbreviations

AC:

Accuracy

AD:

Applicability domain

CAESAR:

Computer Assisted Evaluation of industrial chemical Substances According to Regulation

CPANN:

Counter propagation artificial neural network

CPDB:

Carcinogenic Potency Database

ECHA:

European Chemical Agency

ED:

Euclidean distances

FN:

False negatives

FP:

False positives

IARC:

International Agency for Research of Cancer

IATA:

Integrated Approach to Testing and Assessment

NP:

Not positive

P:

Positive

QSAR:

Quantitative structure–activity relationship

REACH:

Registration, Evaluation, Authorization and Restriction of Chemicals

SA:

Structural alerts

SAR:

Structure–activity relationship

TD:

Tumourgenic dose

TN:

True negatives

TP:

True positives

References

  • Ashby, J. (1985). Fundamental structural alerts to potential carcinogenicity or noncarcinogenicity. Environmental Mutagenesis, 7, 919–921.

    Article  CAS  Google Scholar 

  • Ashby, J., & Tennant, R. (1991). Definitive relationships among chemical structure, carcinogenicity and mutagenicity. Mutation Research, 257(3), 229–306.

    Article  CAS  Google Scholar 

  • Bailey, A., Chanderbhan, N., Collazo-Braier, N., Cheeseman, M., & Twaroski, M. (2005). The use of structure-activity relationship analysis in the food contact notification program. Regulatory Toxicology and Pharmacology, 42, 225–235.

    Article  CAS  Google Scholar 

  • Benfenati, E., Benigni, R., DeMarini, D., Helma, C., Kirkland, D., Martin, T., et al. (2009). Predictive models for carcinogenicity: Frameworks, state-of-the-art, and perspectives. Journal of environmental science and health. Part C, 27, 57–90.

    Article  CAS  Google Scholar 

  • Benigni, R., & Bossa, C. (2008a). Structure alerts for carcinogenicity, and the Salmonella assay system: A novel insight through the chemical relational databases technology. Mutation Research, 659, 248–261.

    Article  CAS  Google Scholar 

  • Benigni, R., Bossa, C., Jeliazkova, N., Netzeva, T., & Worth, A. (2008b) The Benigni/Bossa rulebase for mutagenicity and carcinogenicity—a module of Toxtree. EUR 23241 EN. Retrieved July 18, 2016, from http://ecb.jrc.ec.europa.eu/qsar/publications.

  • Benigni, R., & Bossa, C. (2008c). Predictivity of QSAR. Journal of Chemical Information and Modeling, 48, 971–980.

    Article  CAS  Google Scholar 

  • Benigni, R., Bossa, C., & Worth, A. (2010). Structural analysis and predictive value of the rodent in vivo micronucleus assay results. Mutagenesis, 25(4), 335–341.

    Article  CAS  Google Scholar 

  • Benigni, R., Bossa, C., Jeliazkova, N., Netzeva, T., & Worth, A. (2008b). The Benigni/Bossarulebase for mutagenicity and carcinogenicity—a module of Toxtree. European Commission report EUR 23241 EN.

    Google Scholar 

  • Benigni, R., Bossa, C., Tcheremenskaia, O., & Worth, A. (2009) Development of structural alerts for the in vivo micronucleus assay in rodents. EUR 23844 EN. Retrieved July 18, 2016, from http://ecb.jrc.ec.europa.eu/qsar/publications.

  • ChemFinder Ultra 10.0. (2009). CambridgeSoft Corp., Cambridge, MA.FDA, SAR Carcinogenicity database, Leadscope Inc., Columbus, OH.

    Google Scholar 

  • Combes, R., Grindon, C., Cronin, M., Roberts, D., & Garrod, J. (2008). Integrated decision-tree testing strategies for mutagenicity and carcinogenicity with respect to the requirements of the EU REACH legislation. ATLA, 36, 43–63.

    Google Scholar 

  • Contrera, J., Hall, L., Kier, L., & MacLaughlin, P. (2005a). QSAR modeling of carcinogenic risk using discriminant analysis and topological molecular descriptors. Current Drug Discovery Technologies, 2, 55–67.

    Article  CAS  Google Scholar 

  • Contrera, J., Matthews, E., Kruhlak, N., & Benz, R. (2005b). In silico screening of chemicals for bacterial mutagenicity using electrotopological E-state indices and MDL QSAR software. Regulatory Toxicology and Pharmacology, 43(3), 313–323.

    Article  CAS  Google Scholar 

  • Contrera, J., Matthews, E., & Benz, R. (2003). Prediction the carcinogenic potential of pharmaceuticals in rodents using molecular structural similarity and E-state indeces. Regulatory Toxicology and Pharmacology, 38, 243–259.

    Article  CAS  Google Scholar 

  • Cooper, J., Saracci, R., & Cole, P. (1979). Describing the validity of carcinogen screening test. British Journal of Cancer, 39, 87–89.

    Article  CAS  Google Scholar 

  • EC. (2008). Council Regulation (EC) No 440/2008 of 30 May 2008 laying down test methods pursuant to Regulation (EC) No 1907/2006 of the European Parliament and of the Council on the Registration, Evaluation, Authorisation and Restriction of Chemicals (REACH). Official Journal L 142.

    Google Scholar 

  • ECHA. (2014). The use of alternatives to testing on animals for the REACH regulation. Second report under Article 117(3) of the REACH Regulation.

    Google Scholar 

  • Enslein, K., Gombar, V., & Blake, B. (1994). International commission for protection against environmental mutagens and carcinogens. Use of SAR in computer-assisted prediction of carcinogenicity and mutagenicity of chemicals by the TOPKAT program. Mutation Research, 205, 47–61.

    Article  Google Scholar 

  • Eriksson, L., Johansson, E., Wold, S., (1996). QSAR model validation. In: Quantitative structure–activity relationships in environmental sciences VII. Proceedings of the 7th international workshop on QSAR in environmental sciences 24–28 June 1997 (pp. 381–397). Pensacola, FL, Denmark: SETAC Press.

    Google Scholar 

  • Eriksson, L., Jaworska, J., Worth, A., Cronin, M., McDowell, R., & Gramatica, P. (2003). Methods for reliability, uncertainty assessment, and applicability evaluations of classification and regression based QSARs. Environmental Health Perspectives, 111, 1361–1375.

    Article  CAS  Google Scholar 

  • Fjodorova, N., Vračko, M., Novič, M., Roncaglioni, A., Benfenati, E. (2010a). New public QSAR model for carcinogenicity. Chemistry Central Journal, 4(1), 1–15. Retrieved July 18, 2016, from http://www.journal.chemistrycentral.com/content/4/S1/S3.

  • Fjodorova, N., VraČko, M., Tuša, M., Jezierska, A., Novič, M., Kühne, R., et al. (2010b). Quantitative and qualitative models for carcinogenicity prediction for non-congeneric chemicals using CP ANN method for regulatory uses. Molecular Diversity, 14(3), 581–594.

    Article  CAS  Google Scholar 

  • Fjodorova, N., Vračko, M., Jezierska-Mazzarello, A., & Novič, M. (2010c). Counter propagation artificial neural networks categorical models for prediction of carcinogenicity for non-congeneric chemicals. SAR and QSAR in Environmental Research, 21(1–2), 57–75.

    Article  CAS  Google Scholar 

  • Fjodorova, N., & Novič, M. (2012). Integration of QSAR and SAR methods for the mechanistic interpretation of predictive models for carcinogenicity. Computational and Structural Biotechnology Journal, 1(2).

    Google Scholar 

  • Fjodorova, N., & Novič, M. (2014). Comparison of criteria used to access carcinogenicity in CPANN QSAR models versus the knowledge-based expert system Toxtree. SAR and QSAR in Environmental Research, 25(6), 423–441.

    Article  CAS  Google Scholar 

  • Fjodorova, N., Novič, M., Roncaglioni, A., & Benfenati, E. (2011). Evaluating the applicability domain in the case of classification predictive models for carcinogenicity based on the counter propagation artificial neural network. Journal of Computer-Aided Molecular Design, 25, 1147–1158.

    Article  CAS  Google Scholar 

  • Fjodorova, N., & Novič, M. (2011). Some findings relevant to the mechanistic interpretation in the case of predictive models for carcinogenicity based on the counter propagation artificial neural network. Journal of Computer-Aided Molecular Design, 25, 1159–1169.

    Article  CAS  Google Scholar 

  • Fjodorova, N., & Novič, M. (2013). Rodent carcinogenicity dataset. Dataset Papers in Medicine, 1, 1–6.

    Article  Google Scholar 

  • Golbraikh, A., & Tropsha, A. (2002). A: Beware of q2! Journal of Molecular Graphics and Modelling, 20, 269–276.

    Article  CAS  Google Scholar 

  • Hall, L., & Hall, L. (2005). QSAR modeling based on structure-information for properties of interest in human health. SAR and QSAR in Environmental Research, 16(1–2), 13–41.

    Article  CAS  Google Scholar 

  • Hall, L. (2004). A Structure-Information Approach to the Prediction of Biological Activities and Properties. Chemistry & Biodiversity, 1(1), 183–201.

    Article  CAS  Google Scholar 

  • Helma, C. (2006). Lazy structure-activity relationships (lazar) for the prediction of rodent carcinogenicity and Salmonella mutagenicity. Molecular Diversity, 10(2), 147–158.

    Article  CAS  Google Scholar 

  • IARC. (2016). Monographs on the Evaluation of Carcinogenic Risks to Human. Retrieved July 18, 2016, from http://monographs.iarc.fr/ENG/Classification.

  • Jacobs, M., Colacci, A., Louekari, K., Luijten, M., Hakkert, B., Paparella, M., et al. (2016). International regulatory needs for development of an IATA for non-genotoxic carcinogenic chemical substances. ALTEX. Published online. Retrieved July 18, 2016, from http://www.altex.ch/resources/epub_Jacobs_of_1604272.pdf.

  • Kazius, J., McGuire, R., & Bursi, R. (2005). Derivation and validation of toxicophores for mutagenicity prediction. Journal of Medicinal Chemistry, 48(1), 312–320.

    Article  CAS  Google Scholar 

  • Kier, L., & Hall, L. (2005). The prediction of ADMET properties using structure information representations. Chemistry & Biodiversity, 2(11), 1428–1437.

    Article  CAS  Google Scholar 

  • Kier, L., & Hall, L. (1999a). Molecular structure description: the electrotopological state. New York: Academic Press.

    Google Scholar 

  • Kier, L., & Hall, L. (1999b). The electrotopological state: structure modeling for QSAR and database analysis. In: J. Devillers & A. T. Balaban (Eds.), Topological Indices and Related Descriptors in QSAR and QSPR (pp. 491–562). Reading, UK: Gordon and Breach.

    Google Scholar 

  • Kier, L., & Hall, L. (2001). Database organization and searching with E-state indices. SAR and QSAR in Environmental Research, 12, 55–74.

    Article  CAS  Google Scholar 

  • Lewis, D., Bird, M., & Jacobs, M. (2002). Human carcinogens: an evaluation study via the COMPACT and Hazard Expert procedures. Human and Experimental Toxicology, 21(3), 115–122.

    Article  CAS  Google Scholar 

  • Maran, E., Novic, M., Barbieri, P., & Zupan, J. (2004). Application of counterpropagation artificial neural network for modelling properties of fish antibiotics. SAR and QSAR in Environmental Research, 15(5–6), 469–480.

    Article  CAS  Google Scholar 

  • Marchant, C. (1996). Prediction of rodent carcinogenicity using the DEREK system for 30 chemicals currently being tested by the National Toxicology Program. The DEREK Collaborative Group. Environmental Health Perspectives, 104 (Suppl 5), 1065–1073.

    Google Scholar 

  • Matthews, E., & Contrera, J. (1998). A new highly specific method for predicting the carcinogenic potential of pharmaceuticals in rodents using enhanced MCASE QSAR-ES software. Regulatory Toxicology and Pharmacology, 28(3), 242–264.

    Article  CAS  Google Scholar 

  • Matthews, E., Kruhlak, N., Cimino, M., Benz, R., & Contrera, J. (2006a). An analysis of genetic toxicity, reproductive and developmental toxicity, and carcinogenicity data: I. Identification of carcinogens using surrogate endpoints. Regulatory Toxicology and Pharmacology, 44, 83–96.

    Article  CAS  Google Scholar 

  • Matthews, E., Kruhlak, N., Cimino, M., Benz, R., & Contrera, J. (2006b). An analysis of genetic toxicity, reproductive and developmental toxicity, and carcinogenicity data: II. Identification of genotoxicants, reprotoxicants, and carcinogens using in silico methods. Regulatory Toxicology and Pharmacology, 44(2), 97–110.

    Article  CAS  Google Scholar 

  • Mazzatorta, P., Vračko, M., Jezierska, A., & Benfenati, E. (2003). Modeling toxicity by using supervised Kohonen neural networks. Journal of Chemical Information and Computer Sciences, 43, 485–492.

    Article  CAS  Google Scholar 

  • Minovski, N., Župerl, Š., Drgan, V., & Novič, M. (2013). Assessment of applicability domain for multivariate counter-propagation artificial neural network predictive models by minimum euclidean distance space analysis: a case study. Analytica Chimica Acta, 759, 28–42.

    Article  CAS  Google Scholar 

  • Netzeva, T., Worth, A., Aldenberg, T., Benigni, R., Cronin, M., Gramatica, P., et al. (2005). Current status of methods for defining the applicability domain of (quantitative) structure–activity relationships. The report and recommendations of ECVAM Workshop 52. ATLA, 33, 155–173.

    Google Scholar 

  • OECD. (2002). OECD Environment, health and safety publications series on testing and assessment №35 guidance notes for analysis and evaluation of chronic toxicity and carcinogenicity studies, Paris, France.

    Google Scholar 

  • OECD. (2004a). OECD principles for the validation, for regulatory purposes, of (quantitative) structure-activity relationship models. Retrieved July 18, 2016, from http://www.oecd.org/chemicalsafety/risk-assessment/37849783.pdf.

  • OECD. (2004b). The report from the expert group on (quantitative) structure-activity relationships [(Q)SARS] on the principles for the validation of (Q)SARS. OECD SERIES ON TESTING AND ASSESSMENT, Number 49.ENV/JM/MONO(2004)24, 206. Retrieved July 18, 2016, from http://www.oecd.org/officialdocuments/publicdisplaydocumentpdf/?doclanguage=en&cote=env/jm/mono(2004)24.

  • OECD. (2007). Guidance document on the validation of (quantitative)structure-activity relationships[(Q)SAR]models.ENV/JM/MONO(2007) 2 (pp. 154). Retrieved July 18, 2016, from http://www.oecd.org/officialdocuments/publicdisplaydocumentpdf/?doclanguage=en&cote=env/jm/mono(2007)2.

  • OECD. (2015). Fundamental and Guiding Principles for (Q)SAR Analysis Of Chemical Carcinogens With Mechanistic Considerations. Series on Testing and Assessment 229. Retrieved July 18, 2016, from http://www.oecd.org/officialdocuments/publicdisplaydocumentpdf/?cote=env/jm/mono(2015)46&doclanguage=en.

  • OECD TG 451. (2009). Carcinogenicity Studies. Retrieved July 18, 2016, from http://www.oecdilibrary.org/docserver/download/9745101e.pdf?expires=1469696732&id=id&accname=guest&checksum=446DC8255BE3BC7EB69E834508462EEC.

  • OECD TG 453. (2009). Combined Chronic Toxicity\Carcinogenicity Studies. Retrieved July 18, 2016, from http://www.oecd-ilibrary.org/docserver/download/9745301e.pdf?expires=1469696071&id=id&accname=guest&checksum=FE97C483DBD87757F34D3ADADECA817C.

  • Perkins, R., Rang, H., Tong, W., & Welsh, W. (2003). Quantitative structure– activity relationship methods: perspectives on drug discovery and toxicology. Environmental Toxicology and Chemistry, 22, 1666–1679.

    Article  CAS  Google Scholar 

  • Peto, R., Pike, M., Bernstein, L., Gold, L., & Ames, B. (1984). The TD50: A proposed general convention for the numerical description of the carcinogenic potency of chemicals in chronic-exposure animal experiments. Environmental Health Perspectives, 58, 1–8.

    CAS  Google Scholar 

  • Prival, M. (2001). Evaluation of the TOPKAT system for predicting the carcinogenicity of chemicals. Environmental and Molecular Mutagenesis, 37, 55–69.

    Article  CAS  Google Scholar 

  • Poroikov, V., Filimonov, D., & Lagunin, A. (2010). Multi-targeted natural products evaluation based on biological activity prediction with PASS. Current Pharmaceutical Design, 15, 1703–1717.

    Google Scholar 

  • Richard, A. (2004). DSSTox website launch: improving public access to databases for building structure-toxicity prediction models. Preclinica, 2(2), 103–108.

    CAS  Google Scholar 

  • Richard, A., & Williams, C. (2001). Distributed structure-searchable toxicity (DSSTox) public database network: a proposal. Mutation Research New Frontiers Issue, 499(1), 27–52.

    Article  Google Scholar 

  • Rose, K., & Hall, L. (2003). E-State Modeling of Fish Toxicity Independent of 3D Structure Information. SAR and QSAR in Environmental Research, 14, 113–129.

    Article  CAS  Google Scholar 

  • Schüürmann, G., Kühne, R., Kleint, F., Ebert, R., Rothenbacher, C., Herth, P. (1997). A software system for automatic chemical property estimation from molecular structure. In F. Chen & G. Schüürmann (Eds.), Quantitative Structure-Activity Relationships in Environmental Sciences. VII (pp. 93–114). Pensacola, FL: SETAC Press.

    Google Scholar 

  • Schüürmann, G., Ebert, R., Nendza, M., Dearden, J., Paschke, A., Kühne, R. (2007). Prediction of fate-related compound properties. In K. van Leeuwen & T. Vermeire (Eds.), Risk Assessment of Chemicals. An Introduction (pp. 375–426). Dordrecht, NL: Springer Science.

    Google Scholar 

  • Serafimova, R., Todorov, M., Pavlov, T., Kotov, S., Jacob, E., Aptul, A. A., et al. (2007). Identification of the structural requirements for mutagenicity, by incorporating molecular flexibility and metabolic activation of chemicals. II. General ames mutagenicity model. Chemical Research in Toxicology, 20(4), 662–676.

    Google Scholar 

  • Serafimova, R., Gatnik, M., Worth, A. (2010). Review of QSAR models and software tools for predicting genotoxicity and carcinogenicity, JRC 59068. EUR 24427, 49. Retrieved July 18, 2016, from https://eurl-ecvam.jrc.ec.europa.eu/laboratories-research/predictive_toxicology/doc/EUR_24427_EN.pdf.

  • Tennant, R., & Zeiger, E. (1993). Genetic toxicology: current status of methods of carcinogen identification. Environmental Health Perspectives, 100, 307–315.

    Article  CAS  Google Scholar 

  • Valerio, L., Arvidson, K., Chanderbhan, R., & Contrera, J. (2007). Prediction of rodent carcinogenic potential of naturally occurring chemicals in the human diet using high-throughput QSAR predictive modeling. Toxicology and Applied Pharmacology, 222(1), 1–16.

    Article  CAS  Google Scholar 

  • Votano, J., Parham, M., Hall, L., Kier, L., Orloff, S., Tropsha, A., et al. (2004). Three new consensus QSAR models for the prediction of ames genotoxicity. Mutagenesis, 19, 365–378.

    Article  CAS  Google Scholar 

  • Vračko, M., Mills, D., & Basak, S. (2004). Structure-mutagenicity modeling using counter propagation neural networks. Environmental Toxicology and Pharmacology, 16, 25–36.

    Article  Google Scholar 

  • Vračko, M., Novič, M., & Zupan, J. (1999). Study of structure-toxicity relationship by a counterpropagation neural network. Analytica Chimica Acta, 384(3), 319–332.

    Article  Google Scholar 

  • Woo, Y., Lai, D. (2005). OncoLogic: A mechanism-based expert system for predicting the carcinogenic potential of chemicals. In C. Helma (Ed.), Predictive Toxicology (pp. 385–413). Boca Raton FL, USA: CRC Press.

    Google Scholar 

  • Zupan, J., & Gasteiger, J. (1999). Neural networks in chemistry and drug design (2nd ed.). Weinheim: Wiley-VCH Verlag GmbH.

    Google Scholar 

  • Zupan, J., Novic, M., & Ruisainchez, I. (1997). Kohonen and counterpropagation artificial neural networks in analytical chemistry. Chemometrics and Intelligent Laboratory Systems.Tutorial, 38, 1–23.

    Article  CAS  Google Scholar 

Download references

Acknowledgements

The financial supports of the European Union through CAESAR project (SSPI-022674), the Slovenian Ministry of Higher Education, Science and Technology (grant P1-017) and the project LIFE PROSIL, LIFE12 ENV/IT/000154 are gratefully acknowledged.

Author information

Authors and Affiliations

  1. National Institute of Chemistry, Hajdrihova 19, 1001, Ljubljana, Slovenia

    N. Fjodorova, M. Novic, S. Zuperl & K. Venko

Authors
  1. N. Fjodorova
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. Novic
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. S. Zuperl
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. K. Venko
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to N. Fjodorova .

Editor information

Editors and Affiliations

  1. Department of Pharmaceutical Technology, Jadavpur University, Kolkata, India

    Kunal Roy

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this chapter

Cite this chapter

Fjodorova, N., Novic, M., Zuperl, S., Venko, K. (2017). Counter-Propagation Artificial Neural Network Models for Prediction of Carcinogenicity of Non-congeneric Chemicals for Regulatory Uses. In: Roy, K. (eds) Advances in QSAR Modeling. Challenges and Advances in Computational Chemistry and Physics, vol 24. Springer, Cham. https://doi.org/10.1007/978-3-319-56850-8_14

Download citation

Publish with us

Policies and ethics

Search

Navigation