Counter propagation artificial neural network categorical models for prediction of carcinogenicity for non-congeneric chemicals

SAR and QSAR in Environmental Research

Volumn 21, Issue 1-2, 2010, Pages 57-75

  Fjodorova, N ^a   Vracko M ^a   Jezierska, A ^a,b   Novic M ^a  

^a NATIONAL INSTITUTE OF CHEMISTRY   (Slovenia)

^b UNIVERSITY OF WROC AW   (Poland)

Author keywords

Carcinogenicity; Categorical models; CP ANN; QSAR; REACH; ROC

Indexed keywords

COMPUTATIONAL CHEMISTRY; FORECASTING; INDICATORS (CHEMICAL); INDUSTRIAL CHEMICALS;

CARCINOGENIC POTENCY; CARCINOGENICITY; CATEGORICAL MODEL; COUNTER PROPAGATION; COUNTER PROPAGATION ARTIFICIAL NEURAL NETWORK; QSAR; REGISTRATION EVALUATION AND AUTHORIZATION OF CHEMICALS; ROC; SENSITIVITY AND SPECIFICITY; TEST SETS;

NEURAL NETWORKS;

ANIMALIA;

EID: 77951430265     PISSN: 1062936X     EISSN: 1029046X     Source Type: Journal    
DOI: 10.1080/10629360903563250     Document Type: Article

References (74)

1. N. Price, Hail Caesar, Chem. Ind. 15 (2008), pp. 18-19. Available at http://www.caesar-project.eu/index.php?page1/4results§ion1/4results2
2. R. Benigni and A. Giuliani, Putting the predictive toxicology challenge into perspective: reflections on the results, Bioinformatics 19 (2003), pp. 1194-1200.
3. A.M. Richard and R. Benigni, AI and SAR approaches for predicting chemical carcinogenicity: survey and status report, SAR QSAR Environ. Res. 13 (2002), pp. 1-19.
4. G. Patlewicz, R. Rodford, and J.D. Walker, Quantitative structure-activity relationships for predicting mutagenicity and carcinogenicity, Environ. Toxicol. Chem. 22 (2003), pp. 1885-1893.
5. A.M. Helguera, M.C.A. Perez, R.D. Combes, and M.P. Gonzalez, The prediction of carcinogenicity from molecular structure, Curr. Comput-Aided Drug Des. 1 (2005), pp. 237-255.
6. A. Morales Helguera, M.A. Cabrera Perez, M. Perez Gonzalez, R. Molina Ruiz, and H. Gonzalez-Diaz, A topological substructural approach applied to the computational prediction of rodent carcinogenicity, Bioorg Med. Chem. 13 (2005), pp. 2477-2488.
7. L. Passerini, QSARs for individual classis of chemical mutagens and carcinogens, in Quantitative Structure-Activity Relationship (QSARs). Models of mutagens and carcinogens, R. Benigni, ed., CRC Press, Boca Raton, FL, 2003, pp. 81-123.
8. R. Benigni, A. Giuliani, A. Gruska, and R. Franke, QSARs for the mutagenicity and carcinogenicity of Aromatic Amines, in Quantitative Structure-Activity Relationship (QSARs). Models of mutagens and carcinogens, R. Benigni, ed., CRC Press, Boca Raton, FL, 2003, pp. 125-144.
9. G. Gini, M. Lorenzini, E. Benfenati, P. Grasso, and M. Bruschi, Predictive carcinogenicity: a model for aromatic compounds, with nitrogen-containing substituents, based on molecular descriptors using an artificial neural network, J. Chem. Inf. Comput. Sci. 39 (1999), pp. 1076-1080.
10. G. Klopman, S.K. Chakravarti, H. Zhu, J.M. Ivanov, and R.D. Saiakhov, ESP: A method to predict toxicity and pharmacological properties of chemicals using multiple MCASE databases, J. Chem. Inf. Comput. Sci. 44 (2004), pp. 704-715.
11. G. Klopman, J. Ivanov, R. Saiakhov, and S. Chakravarti, MC4PC - An artificial intelligence approach to the discovery of quantitative structure-toxic activity relationship, in Predictive Toxicology, C. Helma, ed., CRC Press, Boca Raton, FL, 2005, pp. 423-457.
12. E.J. Matthews and J.F. Contrera, A new highly specific method for predicting the carcinogenic potential of pharmaceuticals in rodents using enhanced MCASEQSAR-ES software, Regul. Toxicol. Pharmacol. 28 (1998), pp. 242-264.
13. Y.T. Woo and D.Y. Lai, OncoLogic: A mechanism-based expert system for predicting the carcinogenic potential of chemicals, in Predictive Toxicology, C. Helma, ed., CRC Press, Boca Raton, FL, 2005, pp. 385-413.
14. A.A. Lagunin, J.C. Dearden, D.A. Filimonov, and V.V. Poroikov, Computer-aided rodent carcinogenicity prediction, Mutat. Res. 586 (2005), pp. 138-146.
15. E. Benfenati and G. Gini, Computational predictive programs (expert systems) in toxicology, Toxicology 119 (1997), pp. 213-225.
16. R. Benigni and A.M. Richard, Quantitative structure-based modeling applied to characterization and prediction of chemical toxicity, Methods 14 (1998), pp. 264-276.
17. A.M. Richard, Structure-based methods for predicting mutagenicity and carcinogenicity: are we there yet?, Mutat. Res. 400 (1998), pp. 493-507.
18. J.F. Contrera, E.J. Matthews, and R.D. Benz, Prediction the carcinogenic potential of pharmaceuticals in rodents using molecular structural similarity and E-state indices, Regul. Toxicol. Pharmacol. 38 (2003), pp. 243-259.
19. G.H. Loew, M. Poulsen, E. Kirkjian, J. Ferrell, B.S. Sudhindra, and M. Rebagliati, Computer-assisted mechanistic structure-activity studies: application to diverse classes of chemical carcinogens, Environ. Health. Perspect. 61 (1985), pp. 69-96.
20. E. Benfenati, R. Benigni, D.M. DeMarini, C. Helma, D. Kirkland, T.M. Martin, P. Mazzatorta, G. Ouedraogo-Arras, A.M. Richard, B. Schilter, W.G.E. Schoonen, R.D. Snyder, and C. Yang, Predictive models for carcinogenicity: frameworks, state-of-the-art, and perspectives, J. Environ. Sci. Health C 27 (2009), pp. 57-90.
21. R. Benigni and C. Bossa, Predictivity of QSAR, J. Chem. Inf. Model. 48 (2008), pp. 971-980.
22. R. Benigni, C. Bossa, T. Netzeva, and A. Worth, Collection and Evaluation of (Q)SAR Models for Mutagenicity and Carcinogenicity, European Commission Directorate General Joint Research Centre 2007, EUR 22772EN, European Communities, 2007, pp. 1-118.
23. D. Villemin, D. Cherqaoui, and A. Mesbah, Predicting carcinogenicity of polycyclic aromatic hydrocarbons from back-propagation neural network, J. Chem. Inf. Comput. Sci. 34 (1994), pp. 1288-1293.
24. R. Benigni and A.M. Richard, QSARS of mutagens and carcinogens: two case studies illustrating problems in the construction of models for non-congeneric chemicals, Mutat. Res. 371 (1996), pp. 29-46.
25. M. Vračko, A Study of structure-carcinogenic potency relationship with artificial neural networks. The using of descriptors related to geometrical and electronic structures, J. Chem. Inf. Comput. Sci. 37 (1997), pp. 1037-1043.
26. S. Haykin, Neural Networks: a Comprehensive Foundation, Macmillan College Publishing Company, New York, 1994.
27. J. Gasteiger and J. Zupan, Neural networks in chemistry, Angew. Chem. Int. Ed. 32 (1993), pp. 503-527.
28. D.A. Winkler and D.J. Madellena, QSAR and neural networks in life sciences, Ser. Math. Biol. Med. 5 (1995), pp. 126-163.
29. J. Devillers (ed.), Neural Networks in QSAR and Drug Design, Academic Press, London, 1996.
30. G. Schneider and P. Wrede, Artificial neural networks for computer-based molecular design, Prog. Biophys. Mol. Biol. 70 (1998), pp. 175-222.
31. J. Zupan and J. Gasteiger, Neural Networks in Chemistry and Drug Design, 2nd ed., Wiley-VCH Verlag GmbH, Weinheim, 1999.
32. G. Schneider, Neural networks are useful tools for drug design, Neural Networks 13 (2000), pp. 15-16.
33. H. Ichikawa, Hierarchy neural networks as applied to pharmaceutical problems, Adv. Drug. Delivery. Rev. 55 (2003), pp. 1119-1147.
34. T. Kohonen, Self-Organizing Maps, Springer, Berlin, 2001.
35. G. Schneider and P. Wrede, Artificial neural networks for computer-based molecular design, Prog. Biophys. Mol. Biol. 70 (1998), pp. 175-222.
36. J. Taskinen and J. Yliruusi, Prediction of physicochemical properties based on neural network modeling, Adv. Drug. Delivery Rev. 55 (2003), pp. 1163-1183.
37. CAESAR project web page, 2009. Available at http://www.caesar-project.eu
38. Distributed Structure-Searchable Toxicity (DSSTox) Public Database Network. Available at http://www.epa.gov/ncct/dsstox/sdf_cpdbas.html
39. Lois Gold Carcinogenic Potency Database (CPDB). Available at http://potency.berkeley.edu/ cpdb.html
40. R. Combes, C. Grindon, M.T. Cronin, D.W. Roberts, and J.F. Garrod, Integrated decision-tree testing strategies for mutagenicity and carcinogenicity with respect to the requirements of the EU REACH legislation, ATLA 36 (2008), pp. 43-63.
41. G. Schüürmann, R. Kühne, F. Kleint, R.U. Ebert, C. Rothenbacher, and P. Herth, A software system for automatic chemical property estimation from molecular structure, in Quantitative Structure-Activity Relationships in Environmental Sciences, Vol. VII, F. Chen and G. Schuurmann, eds., SETAC Press, Pensacola, FL, 1997, pp. 93-114.
42. G. Schüürmann, R.U. Ebert, M. Nendza, J.C. Dearden, A. Paschke, and R. Kühne, Prediction of fate-related compound properties, in Risk Assessment of Chemicals. An Introduction, 2nd ed., van K. Leeuwen and T. Vermeire, eds., Springer Science, Dordrecht, NL, 2007, pp. 375-426.
43. R. Todeschini and V. Consonni, Handbook of Molecular Descriptors, Willey-VCH, New York, 2000.
44. I. Tetko, J. Gasteiger, R. Todeschini, A. Mauri, D. Livingstone, P. Ertl, V. Palyulin, E. Radchenko, N. Zefirov, A. Makarenko, V. Tanchuk, and V. Prokopenko, Virtual computational chemistry laboratory - design and description, J. Comput-Aided Mol. Des. 19 (2005), pp. 453-463.
45. CODESSA PRO User's Manual, 2005. Available at http://www.codessa-pro.com/manuals/ manual.html
46. MDL-QSAR version 2.2, MDL Information Systems Inc., 14600 Catalina St., San Leonardo, CA 94577, USA, 2002-2004; software available at http://www.drugdiscoveryonline.com/ storefronts/mdl.html
47. DRAGON home page. Available at http://www.talete.mi.it/products/dragon_description.html
48. M.V. Diudea (ed.), QSPR/QSAR Studies by Molecular Descriptors, Nova Science Publishers, Huntington, New York, 2001.
49. M. Randić and M. Razinger, On characterization of 3D molecular structures, in From Chemical Topology to Three-Dimensional Geometry, A.T. Balaban, ed., Plenum Press, New York, 1997, pp. 159-236.
50. A. Langewisch, F. Choobineh, and H. Deng-Yuan, Selection procedures in linear models, J. Stat. Plan. Infer. 54 (1996), pp. 271-277.
51. A.D. Walmsley, Improved variable selection procedure for multivariate linear regression, Anal. Chim. Acta 354 (1997), pp. 225-232.
52. Y. Kano, Variable selection for structural models, J. Stat. Plan. Infer. 108 (2002), pp. 173-187.
53. Y.S. Shih and H.W. Tsai, Variable selection bias in regression trees with constant fits, Comput. Stat. Data. Anal. 45 (2004), pp. 595-607.
54. B. Lucić, N. Trinajstić, S. Sild, M. Karelson, and A.R. Katritzky, A new efficient approach for variable selection based on multiregression: prediction of gas chromatographic retention times and response factors, J. Chem. Inf. Comput. Sci. 39 (1999), pp. 610-621.
55. C.L. Waller and M.P. Bradley, Development and validation of a novel variable selection technique with application to multidimensional quantitative structure-activity relationships studies, J. Chem. Comput. Sci. 39 (1999), pp. 345-355.
56. W. Zheng and A. Tropsha, Novel variable selection quantitative structure-property relationship approach based on the k-nearest-neighbor principle, J. Chem. Comput. Sci. 40 (2000), pp. 185-194.
57. K. Tang and T. Li, Comparison of different partial least-squares methods in quantitative structure-activity relationships, Anal. Chim. Acta 476 (2003), pp. 85-92.
58. L. Xu and W.J. Zhang, Comparison of different methods for variable selection, Anal. Chim. Acta 446 (2001), pp. 475-481.
59. F. Despagne and D.L. Massart, Variable selection for neural networks in multivariate calibration, Chemom. Intell. Lab. Syst. 40 (1998), pp. 145-163.
60. G. Castellano and A.M. Fanelli, Variable selection using neural-network models, Neurocomputing 31 (2000), pp. 1-13.
61. Z. Ramadan, X.H. Song, P.K. Hopke, M.J. Johnson, and K.M. Scow, Variable selection in classification of environmental soil samples for partial least square and neural network models, Anal. Chim. Acta 44 (2001), pp. 231-242.
62. A. Yasri and D. Hartsough, Toward an optimal procedure for variable selection and QSAR model building, J. Chem. Comput. Sci. 45 (2001), pp. 1218-1227.
63. J. Zupan, M. Novič, and I. Ruisanchez, Kohonen and counterpropagation artificial neural networks in analytical chemistry, Chemom. Intell. Lab. Syst. 38 (1997), pp. 1-23.
64. P. Mazzatorta, M. Vračko, A. Jezierska, and E. Benfenati, Modeling toxicity by using supervised Kohonen neural networks, J. Chem. Inf. Comput. Sci. 43 (2003), pp. 485-492.
65. AnnToolbox for Windows, National Institute of Chemistry, Ljubljana, Slovenia; software available at http://www.ki.si/en/display-pages/equipment/?tx_ukki_pi1%5Buid%5D1/4318&cHash1/4e267f7b447
66. J.A. Cooper, R. Saracci, and P. Cole, Describing the validity of carcinogen screening test, Br. J. Cancer. 39 (1979), pp. 87-89.
67. T. Fawcett, An introduction to ROC analysis, Pattern Recognit. Lett. 27 (2006), pp. 861-874.
68. J. Fan, S. Upadhye, and A. Worster, Understanding receiver operating characteristic (ROC) curves, Can. J. Emerg. Med. 8 (2006), pp. 19-20.
69. H.L. Van Trees, Detection, Estimation, and Modulation Theory (Part I), Wiley, New York, 1968.
70. J.P. Egan, Signal Detection Theory and ROC Analysis, Academic Press, New York, 1975.
71. J.A. Swets, Measuring the accuracy of diagnostic systems, Science 240 (1988), pp. 1285-1293.
72. A.P. Bradley, The use of the area under the ROC curve in the evaluation of machine learning algorithms, Pattern Recognit. 30 (1997), pp. 1145-1159.
73. J.A. Swets, Signal Detection Theory and Roc Analysis in Psychology and Diagnostics, Collected Papers, Lawrence Erlbaum Associates, Mahwah, NJ, 1996.
74. F. Provost and T. Fawcett, Analysis and Visualization of Classifier Performance: Comparison under Imprecise Class and Cost Distributions, Proceedings of the Third International Conference of Knowledge Discovery and Data Mining (KDD-97), AAAI Press, Newport Beach, CA, 1997, pp. 43-48.