Advertisement

Artificial Neural Network Modeling in Environmental Toxicology

  • James DevillersEmail author
Part of the Methods in Molecular Biology™ book series (MIMB, volume 458)

Abstract

Artificial neural networks are increasingly used in environmental toxicology to find complex relationships between the ecotoxicity of xenobiotics and their structure or physicochemical properties. The raison d'être of these nonlinear tools is their ability to derive powerful QSARs for molecules presenting different mechanisms of action. In this chapter, the main QSAR models derived for aquatic and terrestrial species are reviewed. Their characteristics and modeling performances are deeply analyzed.

Keywords

Supervised artificial neural network noncongeneric QSAR bacteria protozoa crustacea, insects fish 

References

  1. 1.
    Russon CL, Breton RL, Walker JD, Bradbury SP (2003) An overview of the use of quantitative structure-activity relationships for ranking and prioritizing large chemical inventories for environmental risk assessments. Environ Toxicol Chem 22:1810–1821.CrossRefGoogle Scholar
  2. 2.
    Kaiser KLE (2003) Neural networks for effect prediction in environmental and health issues using large datasets. QSAR Comb Sci 22:185–190.CrossRefGoogle Scholar
  3. 3.
    Geladi P, Tosato ML (1990) Multivariate latent variable projection methods: SIMCA and PLS. In: Karcher W, Devillers J (eds) Practical applications of quantitative structure-activity relationships (QSAR) in Environmental Chemistry and Toxicology. Kluwer Academic Publishers, Dordrecht, The Netherlands, pp. 171–179.Google Scholar
  4. 4.
    Devillers J (1996) Neural networks in QSAR and drug design. Academic Press, London, p. 284.Google Scholar
  5. 5.
    Devillers J (2001) QSAR modeling of large heterogeneous sets of molecules. SAR QSAR Environ Res 12:515–528.CrossRefPubMedGoogle Scholar
  6. 6.
    Kaiser KLE (1998) Correlations of Vibrio fischeri bacteria test data with bioassay data for other organisms. Environ Health Pespect 106:583–591.CrossRefGoogle Scholar
  7. 7.
    Kaiser KLE, Devillers, J. (1994) Ecotoxicity of Chemicals to Photobacterium phosphoreum. Gordon and Breach Science Publishers, Reading, UK, p. 879.Google Scholar
  8. 8.
    Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536.CrossRefGoogle Scholar
  9. 9.
    Devillers J (1996) Strengths and weaknesses of the backpropagation neural network in QSAR and QSPR studies. In: Devillers J (ed) Neural networks in QSAR and drug design. Academic Press, London, pp. 1–46.CrossRefGoogle Scholar
  10. 10.
    Devillers J, Bintein S, Karcher W (1995) QSAR for predicting luminescent bacteria toxicity. In: Sanz F, Giraldo J, Manaut F, (eds) QSAR and molecular modelling: concepts, computational tools and biological applications. J.R. Prous, Barcelona, pp. 190–192.Google Scholar
  11. 11.
    Devillers J, Bintein S, Domine D, Karcher W (1995) A general QSAR model for predicting the toxicity of organic chemicals to luminescent bacteria (Microtox® test). SAR QSAR Environ. Res. 4, 29-38.CrossRefGoogle Scholar
  12. 12.
    Devillers J, Domine D (1999) A noncongeneric model for predicting toxicity of organic molecules to Vibrio fischeri. SAR QSAR Environ Res 10:61–70.CrossRefGoogle Scholar
  13. 13.
    Devillers J (1999) Autocorrelation descriptors for modeling (eco)toxicological endpoints. In: Devillers J, Balaban AT (eds) Topological indices and related descriptors in QSAR and QSPR. Gordon and Breach, The Netherlands, pp. 595–612.Google Scholar
  14. 14.
    Domine D, Devillers J, Wienke D, Buydens L (1996) Test series selection from nonlinear neural mapping. Quant Struct Act Relat 15:395–402.CrossRefGoogle Scholar
  15. 15.
    Baker L, Wesley, SK, Schultz TW (1988). Quantitative structure-activity relationships for alkylated and/or halogenated phenols eliciting the polar narcosis mechanism of toxic action. In: Turner JE, England MW, Schultz TW, Kwaak NJ (eds) QSAR 88: proceedings of the third international workshop on quantitative structure-activity relationships in environmental toxicology CONF-880520, pp. 165–168.Google Scholar
  16. 16.
    Kelley CT (2003) Solving nonlinear equations with Newton's method (fundamentals of algorithms). Society for Industrial and Applied Mathematics, Philadelphia, p. 116.CrossRefGoogle Scholar
  17. 17.
    Xu L, Ball JW, Dixon SL, Jurs PC (1994) Quantitative structure-activity relationships for toxicity of phenols using regression analysis and computational neural networks. Environ Toxicol Chem 13:841–851.CrossRefGoogle Scholar
  18. 18.
    Serra JR, Jurs PC, Kaiser KLE (2001) Linear regression and computational neural network prediction of Tetrahymena acute toxicity of aromatic compounds from molecular structure. Chem Res Toxicol 14:1535–1545.CrossRefPubMedGoogle Scholar
  19. 19.
    Burden FR, Winkler DA (2000) A Quantitative structure-activity relationships model for the acute toxicity of substituted benzenes to Tetrahymena pyriformis using Bayesian-regularized neural networks. Chem Res Toxicol 13:436–440.CrossRefPubMedGoogle Scholar
  20. 20.
    Neal RM (1996) Bayesian learning for neural networks. Lecture Notes in Statistics, 118, Springer, Berlin, p. 204.Google Scholar
  21. 21.
    Winkler D, Burden F (2003) Toxicity modelling using Bayesian neural nets and automatic relevance determination. In: Ford M, Livingstone D, Dearden J, van de Waterbeemd H (eds) EuroQSAR 2002: designing drugs and crop protectants: processes, problems and solutions. Blackwell Publishing, Malden, UK, pp. 251–254.Google Scholar
  22. 22.
    Devillers J (2004) Linear versus nonlinear QSAR modeling of the toxicity of phenol derivatives to Tetrahymena pyriformis. SAR QSAR Environ Res 15:237–249.CrossRefPubMedGoogle Scholar
  23. 23.
    Cronin MTD, Aptula, AO, Duffy JC, Netzeva TI, Rowe PH, Valkova IV, Schultz TW (2002) Comparative assessment of methods to develop QSARs for the prediction of the toxicity of phenols to Tetrahymena pyriformis. Chemosphere 49:1201–1221.CrossRefPubMedGoogle Scholar
  24. 24.
    Yao XJ, Panaye A, Doucet JP, Zhang RS, Chen HF, Liu MC, Hu ZD, Fan BT (2004) Comparative study of QSAR/QSPR correlations using support vector machines, radial basis function neural networks, and multiple linear regression. J Chem Inf Comput Sci. 44:1257–1266.PubMedGoogle Scholar
  25. 25.
    Bengio Y (1996) Neural networks for speech and sequence recognition. International Thomson Computer Press, London, Chapter 6, p. 167.Google Scholar
  26. 26.
    Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, Cambridge, UK, p. 189.Google Scholar
  27. 27.
    Ren S (2003) Modeling the toxicity of aromatic compounds to Tetrahymena pyriformis: The response surface methodology with nonlinear methods. J Chem Inf Comput Sci 43:1679–1687.PubMedGoogle Scholar
  28. 28.
    Hastie TJ, Tibshirani RJ (1990) Generalized additive models. Chapman and Hall, New York.Google Scholar
  29. 29.
    Osborne MR, Presnell B, Turlach BA (2000) On the LASSO and its dual. J Comput Graph Stat 9:319–337.CrossRefGoogle Scholar
  30. 30.
    Cleveland WS (1979) Robust locally weighted regression and smoothing scatterplots. J Am Stat Assoc 46:175–185.Google Scholar
  31. 31.
    Friedman JH (1991) Multivariate additive regression splines. Annals Stat 19:1–141.CrossRefGoogle Scholar
  32. 32.
    Friedman JH, Stuetzle W (1981) Projection pursuit regression. J Am Stat Assoc 76:817–823.CrossRefGoogle Scholar
  33. 33.
    Panaye A, Fan BT, Doucet JP, Yao XJ, Zhang RS, Liu MC, Hu ZD (2006) Quantitative structure-toxicity relationships (QSTRs): a comparative study of various non-linear methods. General regression neural network, radial basis function neural network and support vector machine in predicting toxicity of nitro- and cyano- aromatics to Tetrahymena pyriformis. SAR QSAR Environ Res 17:75–91.CrossRefPubMedGoogle Scholar
  34. 34.
    Novic M, Vracko, M. (2003) Artificial neural networks in molecular-structures-property studies. In: Leardi R (ed.) Nature-inspired methods in chemometrics: genetic algorithms and artificial neural networks. Elsevier, Amsterdam, pp. 231–256.Google Scholar
  35. 35.
    Zupan J, Gasteiger J (1993) Neural networks for chemists. VCH, Weinheim, p. 305.Google Scholar
  36. 36.
    Niculescu SP, Kaiser KLE, Schultz TW (2000) Modeling the toxicity of chemicals to Tetrahymena pyriformis using molecular fragment descriptors and probabilistic neural networks. Arch Environ Contam Toxicol 39:289–298.CrossRefPubMedGoogle Scholar
  37. 37.
    Wasserman PD (1993) Advanced methods in neural computing. Van Nostrand Reinhold, New York, p. 255.Google Scholar
  38. 38.
    Kaiser KLE, Niculescu SP, Schultz TW (2002) Probabilistic neural network modeling for the toxicity of chemicals to Tetrahymena pyriformis with molecular fragment descriptors. SAR QSAR Environ Res 13:57–67.CrossRefPubMedGoogle Scholar
  39. 39.
    Kaiser KLE, Niculescu, S. P. (2001) Modeling acute toxicity of chemicals to Daphnia magna: a probabilistic neural network approach. Environ Toxicol Chem 20:420–431.PubMedGoogle Scholar
  40. 40.
    ECOSAR, version 0.99f, January 2000.Google Scholar
  41. 41.
    Kaiser KLE, Dearden JC, Klein W, Schultz,TW. (1999) A note of caution to users of ECOSAR. Water Qual Res J Canada 34:179–182.Google Scholar
  42. 42.
    Devillers J (2003) A QSAR model for predicting the acute toxicity of pesticides to gammarids. In: Leardi R (ed) Nature-inspired methods in chemometrics: genetic algorithms and artificial neural networks. Elsevier, Amsterdam, pp. 323–339.Google Scholar
  43. 43.
    Devillers J (1996) Genetic algorithms in molecular modeling. Academic Press, London, p. 327.Google Scholar
  44. 44.
    Landrum PF, Fisher SW, Hwang H, Hickey J (1999) Hazard evaluation of ten organophosphorus insecticides against the midge, Chironomus riparius via QSAR. SAR QSAR Environ Res 10:423–450.CrossRefGoogle Scholar
  45. 45.
    Devillers J. (2000) Prediction of toxicity of organophosphorus insecticides against the midge, Chironomus riparius, via a QSAR neural network model integrating environmental variables. Toxicol Methods 10:69–79.CrossRefGoogle Scholar
  46. 46.
    Kaiser KLE, Niculescu SP, Schüürmann G. (1997) Feed forward backpropagation neural networks and their use in predicting the acute toxicity of chemicals to the fathead minnow. Water Qual Res J Canada 32:637–657.Google Scholar
  47. 47.
    Kaiser KLE, Niculescu SP, McKinnon MB (1997) On simple linear regression, multiple linear regression, and elementary probabilistic neural network with Gaussian kernel's performance in modeling toxicity values to fathead minnow based on Microtox data, octanol/water partition coefficient, and various structural descriptors for a 419-compound dataset. In: Chen F, Schüürmann G (eds) Proceedings of the 7th international workshop on QSAR in environmental sciences. SETAC Press, Pensacola, FL, pp. 285–297.Google Scholar
  48. 48.
    Eldred DV, Weikel CL, Jurs PC, Kaiser KLE (1999) Prediction of fathead minnow acute toxicity of organic compounds from molecular structure. Chem Res Toxicol 12:670–678.CrossRefPubMedGoogle Scholar
  49. 49.
    Moore DRJ, Breton RL, MacDonald DB (2003) A comparison of model performance for six quantitative structure-activity relationship packages that predict acute toxicity to fish. Environ Toxicol Chem 22:1799–1809.CrossRefPubMedGoogle Scholar
  50. 50.
    Niculescu SP, Kaiser KLE, Schüürmann G (1998) Influence of data preprocessing and kernel selection on probabilistic neural network modeling of the acute toxicity of chemicals to the fathead minnow and Vibrio fischeri bacteria. Water Qual Res J. Canada 33:153–165.Google Scholar
  51. 51.
    Kaiser KLE, Niculescu SP (1999) Using probabilistic neural networks to model the toxicity of chemicals to the fathead minnow (Pimephales promelas): a study based on 865 compounds. Chemosphere 38:3237–3245.CrossRefPubMedGoogle Scholar
  52. 52.
    Niculescu SP, Atkinson A, Hammond G, Lewis, M. (2004) Using fragment chemistry data mining and probabilistic neural networks in screening chemicals for acute toxicity to the fathead minnow. SAR QSAR Environ. Res 15:293–309.CrossRefPubMedGoogle Scholar
  53. 53.
    Espinosa G, Arenas A, Giralt F (2002) An integrated SOM-fuzzy ARTMAP neural system for the evaluation of toxicity. J Chem Inf Comput Sci 42:343–359.PubMedGoogle Scholar
  54. 54.
    Wienke D, Domine D, Buydens L, Devillers J (1996) Adaptive resonance theory based neural networks explored for pattern recognition analysis of QSAR data. In: Devillers J (ed) Neural networks in QSAR and drug design. Academic Press, London, pp. 119–156.CrossRefGoogle Scholar
  55. 55.
    Mazzatorta P, Benfenati E, Neagu CD, Gini G (2003) Tuning neural and fuzzy-neural networks for toxicity modeling. J Chem Inf Comput Sci 43:513–518.PubMedGoogle Scholar
  56. 56.
    Mazzatorta P, Vracko M, Jezierska A, Benfenati E (2003) Modeling toxicity by using supervised Kohonen neural networks. J Chem Inf Comput Sci 43:485–492.PubMedGoogle Scholar
  57. 57.
    Vracko M, Bandelj V, Barbieri P, Benfenati E, Chaudhry Q, Cronin M, Devillers J, Gallegos A, Gini G, Gramatica P, Helma C, Mazzatorta P, Neagu D, Netzeva T, Pavan M, Patlevicz G, Randic M, Tsakovska I, Worth A (2006) Validation of counter propagation neural network models for predictive toxicology according to the OECD principles: a case study. SAR QSAR Environ Res 17:265–284.CrossRefPubMedGoogle Scholar
  58. 58.
    Devillers J (2005) A new strategy for using supervised artificial neural networks in QSAR. SAR QSAR Environ Res 16:433–442.CrossRefPubMedGoogle Scholar
  59. 59.
    Devillers J, Chessel D (1995) Can the enucleated rabbit eye test be a suitable alternative for the in vivo eye test? A chemometrical response. Toxicol Model 1:21–34.Google Scholar
  60. 60.
    Klopman G (1998) The MultiCASE program II. Baseline activity identification algorithm (BAIA). J Chem Inf Comput Sci 38:78–81.PubMedGoogle Scholar
  61. 61.
    Klopman G, Saiakhov R, Rosenkranz HS, Hermens JLM (1999) Multiple computer-automated structure evaluation program study of aquatic toxicity 1: guppy. Environ Toxicol Chem 18:2497–2505.CrossRefGoogle Scholar
  62. 62.
    Klopman G, Saiakhov R, Rosenkranz HS (2000) Multiple computer-automated structure evaluation study of aquatic toxicity 2: fathead minnow. Environ Toxicol Chem 19:441–447.CrossRefGoogle Scholar
  63. 63.
    Devillers J, Flatin J (2000) A general QSAR model for predicting the acute toxicity of pesticides to Oncorhynchus mykiss. SAR QSAR Environ Res 11:25–43.CrossRefPubMedGoogle Scholar
  64. 64.
    Devillers J (2001) A general QSAR model for predicting the acute toxicity of pesticides to Lepomis macrochirus. SAR QSAR Environ Res 11:397–417.CrossRefPubMedGoogle Scholar
  65. 65.
    Devillers J, Pham-Delègue MH, Decourtye A, Budzinski H, Cluzeau S, Maurin G (2002) Structure-toxicity modeling of pesticides to honey bees. SAR QSAR Environ Res 13:641–648.CrossRefPubMedGoogle Scholar
  66. 66.
    Devillers J, Pham-Delègue MH, Decourtye A, Budzinski H, Cluzeau S, Maurin G (2003) Modeling the acute toxicity of pesticides to Apis mellifera. Bull Insect 56:103–109.Google Scholar

Copyright information

© Humana Press, a part of Springer Science + Business Media, LLC 2008

Authors and Affiliations

  1. 1.CTISRillieux La PapeFrance

Personalised recommendations