Molecular Diversity

, Volume 14, Issue 3, pp 581–594 | Cite as

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

  • Natalja FjodorovaEmail author
  • Marjan Vračko
  • Marjan Tušar
  • Aneta Jezierska
  • Marjana Novič
  • Ralph Kühne
  • Gerrit Schüürmann
Full-Length Paper


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.


Counter propagation artificial neural network In silico Quantitative structure–activity relationship Qualitative (categorical) models Quantitative (continuous) models Rodent carcinogenicity Tumorgenic dose TD50 



Registration, Evaluation, Authorization and Restriction of Chemicals


Quantitative structure–activity relationship


Distributed Structure-Searchable Toxicity


Lois Gold Carcinogenic Potency Database


Principal component analysis


Counter propagation artificial neural network


Tumorgenic dose


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

11030_2009_9190_MOESM1_ESM.doc (1.5 mb)
ESM 1 (DOC 1.45 mb)


  1. 1.
    Benigni R (2005) Structure-activity relationship studies of chemical mutagens and carcinogens: mechanistic investigations and prediction approaches. Chem Rev 105: 1767–1800. doi: 10.1021/cr030049y CrossRefPubMedGoogle Scholar
  2. 2.
    OECD (2002) Guidance notes for analysis and evaluation of chronic toxicity and carcinogenicity studies. OECD Environment, Health and Safety Publications Series on Testing and Assessment No. 35, Paris, FranceGoogle Scholar
  3. 3.
    Combes RD (2000) The use of structure-activity relationships and markers of cell toxicity to detect non-genotoxic carcinogens. Toxicol In Vitro 14: 387–399. doi: 10.1016/S0887-2333(00)00026-6 CrossRefPubMedGoogle Scholar
  4. 4.
    Choy WN (2001) Genotoxic and non-genotoxic mechanisms of carcinogenesis. In: Choy WN (eds) Genetic toxicology and cancer risk assessment. Marcel Dekker, New York, pp 47–72CrossRefGoogle Scholar
  5. 5.
    Combes R, Grindon C, Cronin MTD, Roberts DW, Garrod JF (2007) Proposed integrated decision-tree testing strategies for mutagenicity and carcinogenicity in relation to the EU REACH Legislation. ATLA 35: 267–287PubMedGoogle Scholar
  6. 6.
    Fenech M (2000) The in vitro micronucleus technique. Mutat Res Fundam Mol Mech Mutagen 455: 81–95. doi: 10.1016/S0027-5107(00)00065-8 CrossRefGoogle Scholar
  7. 7.
    Bernauer U, Oberemm A, Madle S, Gundert-Remy U (2005) The use of in vitro data in risk assessment. Basic Clin Pharmacol Toxicol 96: 176–181. doi: 10.1111/j.1742-7843.2005.pto960306.x CrossRefPubMedGoogle Scholar
  8. 8.
    Knight A, Bailey J, Balcombe J (2006) Animal carcinogenicity studies: implications for the REACH systems. ATLA 34(Suppl 1): 139–147PubMedGoogle Scholar
  9. 9.
    Omenn GS (1995) Assessing the risk assessment paradigm. Toxicology 102: 23–28. doi: 10.1016/0300-483X(95)03034-D CrossRefPubMedGoogle Scholar
  10. 10.
    Long ME (2007) Predicting carcinogenicity in humans: the need to supplement animal-based toxicology. AATEX 14: 553–559Google Scholar
  11. 11.
    Helma C (eds) (2005) Predictive toxicology. Marcel Dekker, New YorkGoogle Scholar
  12. 12.
    Kuschner M (1995) The relevance of rodent tumors in assessing carcinogenicity in human beings. Regul Toxicol Pharmacol 21: 250–251. doi: 10.1006/rtph.1995.1037 CrossRefPubMedGoogle Scholar
  13. 13.
    IARC (2006) Preamble, IARC monographs on the evaluation of carcinogenic risks to humansGoogle Scholar
  14. 14.
    OECD (1981) Guidelines for the testing of chemicals test no. 451: carcinogenicity studiesGoogle Scholar
  15. 15.
    OECD (1981) Guidelines for the testing of chemicals test no. 452: chronic toxicity studiesGoogle Scholar
  16. 16.
    OECD (1981) Guidelines for the testing of chemicals test no. 453: combined chronic toxicity/carcinogenicity studiesGoogle Scholar
  17. 17.
    Benigni R, Giuliani A (2003) Putting the predictive toxicology challenge into perspective: reflections on the results. Bioinformatics 19: 1194–1200. doi: 10.1093/bioinformatics/btg099 CrossRefPubMedGoogle Scholar
  18. 18.
    Richard AM, Benigni R (2002) AI and SAR approaches for predicting chemical carcinogenicity: survey and status report. SAR QSAR Environ Res 13: 1–19. doi: 10.1080/10629360290002055 CrossRefGoogle Scholar
  19. 19.
    Benigni R, Bossa C (2008) Structure alerts for carcinogenicity, and the Salmonella assay system: a novel insight through the chemical relational databases technology. Mutat Res 659: 248–261. doi: 10.1016/j.mrrev.2008.05.003 CrossRefPubMedGoogle Scholar
  20. 20.
    Lill MA (2007) Multi-dimensional QSAR in drug discovery. Drug Discov Today 12: 1013–1017. doi: 10.1016/j.drudis.2007.08.004 CrossRefPubMedGoogle Scholar
  21. 21.
    Kruhlak NL, Contrera JF, Benz RD, Matthews EJ (2007) Progress in QSAR toxicity screening of pharmaceutical impurities and other FDA regulated products. Adv Drug Deliv Rev 59: 43–55. doi: 10.1016/j.addr.2006.10.008 CrossRefPubMedGoogle Scholar
  22. 22.
    Mager DE (2006) Quantitative structure—pharmacokinetic/pharmacodynamic relationships. Adv Drug Deliv Rev 58: 1326–1356. doi: 10.1016/j.addr.2006.08.002 CrossRefPubMedGoogle Scholar
  23. 23.
    Oprea TI, Matter H (2004) Integrating virtual screening in lead discovery. Curr Opin Chem Biol 8: 349–358. doi: 10.1016/j.cbpa.2004.06.008 CrossRefPubMedGoogle Scholar
  24. 24.
    Fjodorova N, Novich M, Vrachko M, Smirnov V, Kharchevnikova N, Zholdakova Z, Novikov S, Skvortsova N, Filimonov D, Poroikov V, Benfenati E (2008) Directions in QSAR modeling for regulatory uses in OECD member countries EU and in Russia. J Environ Sci Health C 26: 201–236. doi: 10.1080/10590500802135578 CrossRefGoogle Scholar
  25. 25.
    Fjodorova N, Novich M, Vrachko M, Kharchevnikova N, Zholdakova Z, Sinitsyna O, Benfenati E (2008) Regulatory assessment of chemicals within OECD member countries, EU and in Russia. J Environ Sci Health C 26: 40–88. doi: 10.1080/10590500801907365 CrossRefGoogle Scholar
  26. 26.
    Benigni R, Giuliani A, Franke R, Gruska A (2000) Quantitative structure-activity relationships of mutagenic and carcinogenic aromatic amines. Chem Rev 100: 3697–3714. doi: 10.1021/cr9901079 CrossRefPubMedGoogle Scholar
  27. 27.
    Benigni R, Bossa C, Netzeva T, Worth A (2007) Collection and evaluation of (Q)SAR Models for Mutagenicity and Carcinogenicity. European Commission Directorate General Joint Research Centre 2007 EUR 22772EN © European CommunitiesGoogle Scholar
  28. 28.
    Patlewicz G, Rodford R, Walker JD (2003) Quantitative structure-activity relationships for predicting mutagenicity and carcinogenicity. Environ Toxicol Chem 22: 1885–1893. doi: 10.1897/01-461 CrossRefPubMedGoogle Scholar
  29. 29.
    Helguera AM, Perez MCA, Combes RD, González MP (2005) The prediction of carcinogenicity from molecular structure. Curr Comput Aided Drug Des 1: 237–255. doi: 10.2174/1573409054367655 CrossRefGoogle Scholar
  30. 30.
    Morales Helguera A, Cabrera Perez MA, Perez González M, Molina Ruiz R, Gonzalez-Diaz H (2005) A topological substructural approach applied to the computational prediction of rodent carcinogenicity. Bioorg Med Chem 13: 2477–2488. doi: 10.1016/j.bmc.2005.01.035 CrossRefGoogle Scholar
  31. 31.
    Franke R, Gruska A, Giuliani A, Benigni R (2001) Prediction of rodent carcinogenicity of aromatic amines: a quantitative structure-activity relationships model. Carcinogenesis 22: 1561–1571. doi: 10.1093/carcin/22.9.1561 CrossRefPubMedGoogle Scholar
  32. 32.
    Gini G, Lorenzini M, Benfenati E, Grasso P, Bruschi M (1999) 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: 1076–1080. doi: 10.1021/ci9903096 PubMedGoogle Scholar
  33. 33.
    Helguera Morales A, Cabrera Pérez MA, Combes RD, Pérez González M (2006) Quantitative structure-activity relationships for the computational prediction of nitrocompounds carcinogenicity. Toxicology 220: 51–62. doi: 10.1016/j.tox.2005.11.024 CrossRefGoogle Scholar
  34. 34.
    Zhang L, Sannes K, Shusterman AJ, Hansch C (1992) The structure-activity relationships of skin carcinogenicity of aromatic hydrocarbons and heterocycles. Chem Biol Interact 81: 149–180. doi: 10.1016/0009-2797(92)90032-G CrossRefPubMedGoogle Scholar
  35. 35.
    Villemin D, Cherqaoui D, Mesbah A (1994) Predicting carcinogenicity of polycyclic aromatic hydrocarbons from back-propagation neural network. J Chem Inf Comput Sci 34: 1288–1293. doi: 10.1021/ci00022a010 Google Scholar
  36. 36.
    Richard AM, Woo YT (1990) A CASE-SAR analysis of polycyclic aromatic hydrocarbon carcinogenicity. Mutat Res 242: 285–303. doi: 10.1016/0165-1218(90)90047-6 CrossRefPubMedGoogle Scholar
  37. 37.
    Passerini L (2003) QSARs for individual classis of chemical mutagens and carcinogens. In: Benigni R (eds) Quantitative structure-activity relationship (QSARs). Models of mutagens and carcinogens. CRC Press, Boca Raton, pp 81–123Google Scholar
  38. 38.
    Benigni R (eds) (2003) Quantitative structure-activity relationship (QSAR) models of mutagens and carcinogens. CRC Press, Boca Raton, pp 88–144Google Scholar
  39. 39.
    Contrera JF, Matthews EJ, Benz RD (2003) Prediction the carcinogenic potential of pharmaceuticals in rodents using molecular structural similarity and E-state indices. Regul Toxicol Pharmacol 38: 243–259. doi: 10.1016/S0273-2300(03)00071-0 CrossRefPubMedGoogle Scholar
  40. 40.
    Loew GH, Poulsen M, Kirkjian E, Ferrell J, Sudhindra BS, Rebagliati M (1985) Computer-assisted mechanistic structure-activity studies: application to diverse classes of chemical carcinogens. Environ Health Perspect 61: 69–96. doi: 10.2307/3430063 CrossRefPubMedGoogle Scholar
  41. 41.
    Vračko M (1997) 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: 1037–1043. doi: 10.1021/ci970231y Google Scholar
  42. 42.
    Klopman G, Chakravarti SK, Zhu H, Ivanov JM, Saiakhov RD (2004) ESP: a method to predict toxicity and pharmacological properties of chemicals using multiple MCASE databases. J Chem Inf Comput Sci 44: 704–715. doi: 10.1021/ci030298n PubMedGoogle Scholar
  43. 43.
    Klopman G, Ivanov J, Saiakhov R, Chakravarti S (2005) MC4PC-An artificial intelligence approach to the discovery of quantitative structure-toxic activity relationship. In: Helma C (eds) Predictive toxicology. CRC Press, Boca Raton, pp 423–457Google Scholar
  44. 44.
    Matthews EJ, Contrera JF (1998) A new highly specific method for predicting the carcinogenic potential of pharmaceuticals in rodents using enhanced MCASEQSAR-ES software. Regul Toxicol Pharmacol 28: 242–264. doi: 10.1006/rtph.1998.1259 CrossRefPubMedGoogle Scholar
  45. 45.
    Woo Y-T, Lai DY (2005) OncoLogic: a mechanism-based expert system for predicting the carcinogenic potential of chemicals. In: Helma C (eds) Predictive toxicology. CRC Press, Boca Raton, pp 385–413Google Scholar
  46. 46.
    Lagunin AA, Dearden JC, Filimonov DA, Poroikov VV (2005) Computer-aided rodent carcinogenicity prediction. Mutat Res 586: 138–146. doi: 10.1016/j.mrgentox.2005.06.005 PubMedGoogle Scholar
  47. 47.
    Benfenati E, Gini G (1997) Computational predictive programs (expert systems) in toxicology. Toxicology 119: 213–225. doi: 10.1016/S0300-483X(97)03631-7 CrossRefPubMedGoogle Scholar
  48. 48.
    Benigni R, Richard AM (1998) Quantitative structure-based modeling applied to characterization and prediction of chemical toxicity. Methods 14: 264–276. doi: 10.1006/meth.1998.0583 CrossRefPubMedGoogle Scholar
  49. 49.
    Richard AM (1998) Structure-based methods for predicting mutagenicity and carcinogenicity: are we there yet?. Mutat Res 400: 493–507. doi: 10.1016/S0027-5107(98)00068-2 PubMedGoogle Scholar
  50. 50.
    Dearden JC, Barratt MD, Benigni R, Bristol DW, Combes RD, Cronin MTD, Judson PN, Payne MP, Richard AM, Tichy M, Worth AP, Yourick JJ (1997) The development and validation of expert systems for predicting toxicity. The report and recommendations of an ECVAM/ECB workshop (ECVAM Workshop 24). ATLA 25: 223–252Google Scholar
  51. 51.
    Klopman G (1992) MULTICASE 1. A hierarchical computer automated structure evaluation program. Quant Struct Act Relat 11: 176–184. doi: 10.1002/qsar.19920110208 CrossRefGoogle Scholar
  52. 52.
    Cunningham AR, Rosenkranz HS, Zhang YP, Klopman G (1998) Identification of “genotoxic” and “non-genotoxic” alerts for cancer in mice: the carcinogenicity potency data base. Mutat Res 398: 1–17. doi: 10.1016/S0027-5107(97)00202-9 PubMedGoogle Scholar
  53. 53.
    Rosenkranz HS, Cunningham AR, Zhang YP, Claycamp HG, Macina OT, Sussman NB, Grant SG, Klopman G (1999) Development, characterization and application of predictive-toxicology models. SAR QSAR Environ Res 10: 277–298. doi: 10.1080/10629369908039181 CrossRefPubMedGoogle Scholar
  54. 54.
    King RD, Srinivasan A (1996) A prediction of rodent carcinogenicity bioassays from molecular structure using inductive logic programming. Environ Health Perspect 104: 1031–1040CrossRefPubMedGoogle Scholar
  55. 55.
    Perrotta A, Malacarne D, Taningher M, Pesenti R, Paolucci M, Parodi S (1996) A computerized connectivity approach for analyzing the structural basis of mutagenicity in Salmonella and its relationship with rodent carcinogenicity. Environ Mol Mutagen 28: 31–50. doi: 10.1002/(SICI)1098-2280(1996)28:1<31::AID-EM7>3.0.CO;2-H CrossRefPubMedGoogle Scholar
  56. 56.
    Clare MG, Lorenzon G, Akhurst LC, Marzin D, van Delft J, Montero R, Botta A, Bertens A, Cinelli S, Thybaud V, Lorge E (2006) SFTG international collaborative study on in vitro micronucleus test II. Using human lymphocytes. Mutat Res 607: 37–60. doi: 10.1016/j.mrgentox.2006.04.001 PubMedGoogle Scholar
  57. 57.
    DiPaolo JA, Nelson RL, Donovan PJ (1971) Morphological, monogenic and carpological characteristics of Syrian hamster embryo cells transformed in vitro by carcinogenic polycyclic hydrocarbons. Cancer Res 31: 1118–1127PubMedGoogle Scholar
  58. 58.
    Kirkland D, Aardema M, Henderson L, Müller L (2005) Evaluation of the ability of a battery of 3 in vitro genotoxicity tests to discriminate rodent carcinogens and non-carcinogens. I. Sensitivity, specificity and relative predictability. Mutat Res 584: 1–256. doi: 10.1016/j.mrgentox.2005.10.002 PubMedGoogle Scholar
  59. 59.
    Kirsch-Volders M (2003) Report from the in vitro micronucleus assay working group. Mutat Res 540: 153–163. doi: 10.1016/j.mrgentox.2003.07.005 PubMedGoogle Scholar
  60. 60.
    (2006) Animal and in vitro toxicity testing, in toxicity testing for assessment of environmental agents: interim report. National Academies Press, Washington, pp 26–70Google Scholar
  61. 61.
    ESAC (2006) Statement on the scientific validity of the in vitro micronucleus test as an alternative to the in vitro chromosome aberration assay for genotoxicity testing. Joint Research Centre, European Commission, 2 ppGoogle Scholar
  62. 62.
    Gold LS, Zeiger E (eds) (1997) Handbook of carcinogenic potency and genotoxicity databases. CRC Press, Boca RatonGoogle Scholar
  63. 63.
    Hoshi M, Morimura K, Wanibuchi H, Wei M, Okochi E, Ushijima T, Takaoka K, Fukushima S (2004) No-observed effect levels for carcinogenicity and for in vivo mutagenicity of a genotoxic carcinogen. Toxicol Sci 81: 273–279. doi: 10.1093/toxsci/kfh241 CrossRefPubMedGoogle Scholar
  64. 64.
    Zupan J, Gasteiger J (1999) Neural networks in chemistry and drug design, 2nd edn. Wiley-VCH Verlag GmbH, WeinheimGoogle Scholar
  65. 65.
    Hecht-Nielsen R (1987) Counter propagation networks. In: Caudill M, Butler C (eds) Proceedings of the IEEE first international conference on neural networks, vol 2. SOS Printing, San Diego, pp 19–32Google Scholar
  66. 66.
    Zupan J, Novič M, Gasteiger J (1995) Neural networks with counter-propagation learning strategy used for modeling. Chemom Intell Lab Syst 27: 175–187. doi: 10.10169-7439(94)00016-C CrossRefGoogle Scholar
  67. 67.
    Eric S, Solmajer T, Zupan J, Novič M, Oblak M, Agbaba D (2004) Prediction of selectivity of α 1-adrenergic antagonists by counter propagation neural network (CP-ANN). Il Farmaco 59: 389–395. doi: 10.1016/j.farmac.2003.12.009 CrossRefPubMedGoogle Scholar
  68. 68.
    Novič M, Vračko M (2001) Comparison of spectrum-like representation of 3D chemical structure with other representations when used for modeling biological activity. Chemom Intell Lab Syst 59: 33–44. doi: 10.1016/S0169-7439(01)00142-3 CrossRefGoogle Scholar
  69. 69.
    Vračko M, Novič M, Zupan J (1999) Study of structure-toxicity relationship by a counter propagation neural network. Anal Chim Acta 384: 319–332. doi: 10.1016/S0003-2670(98)00782-X CrossRefGoogle Scholar
  70. 70.
    Computer Assisted Evaluation of industrial chemical Substances According to Regulations (CAESAR) project, Accessed 22 April 2009
  71. 71.
    Yeap SK, Walley RJ, Snarey M, van Hoorn WP, Mason JS (2007) Designing compound subsets: comparison of random and rational approaches using statistical simulation. J Chem Inf Model 47: 2149–2158. doi: 10.1021/ci600382m CrossRefPubMedGoogle Scholar
  72. 72.
    Leonard JT, Roy K (2006) On selection of training and test sets for the development of predictive QSAR models. QSAR Comb Sci 25: 235–251. doi: 10.1002/qsar.200510161 CrossRefGoogle Scholar
  73. 73.
    Schüürmann G, Kühne R, Kleint F, Ebert R-U, Rothenbacher C, Herth P (1997) A software system for automatic chemical property estimation from molecular structure. In: Chen F, Schüürmann G (eds) Quantitative structure-activity relationships in environmental sciences—VII. SETAC Press, Pensacola, pp 93–114Google Scholar
  74. 74.
    Schüürmann G, Ebert R-U, Nendza M, Dearden JC, Paschke A, Kühne R (2007) Prediction of fate-related compound properties. In: van Leeuwen K, Vermeire T (eds) Risk assessment of chemicals. An introduction. Springer Science, Dordrecht, pp 375–426CrossRefGoogle Scholar
  75. 75.
    Kier LB, Hall LH (1999) Molecular structure description: the electro topological state. Academic Press, New YorkGoogle Scholar
  76. 76.
    Kier LB, Hall LH (2001) Database organization and searching with E-state indices. SAR QSAR Environ Res 12: 55–74. doi: 10.1080/10629360108035371 CrossRefPubMedGoogle Scholar
  77. 77.
    Kier LB, Hall LH (1999) The electro topological state: structure modeling for QSAR and database analysis. In: Devillers J, Balaban AT (eds) Topological indices and related descriptors in QSAR and QSPR. Gordon and Breach, Reading, pp 491–562Google Scholar
  78. 78.
    Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biol Cybern 43: 59–69. doi: 10.1007/BF00337288 CrossRefGoogle Scholar
  79. 79.
    Kohonen T (1984) Self-organization and associative memory. Springer, BerlinGoogle Scholar
  80. 80.
    Kohonen T (2001) Self-organizing maps. Springer, BerlinGoogle Scholar
  81. 81.
    Vračko M (2005) Kohonen artificial neural network and counter propagation neural network in molecular structure-toxicity studies. Curr Comput Aided Drug Des 1: 73–78. doi: 10.2174/1573409052952224 CrossRefGoogle Scholar
  82. 82.
    Jezierska A, Vračko M, Basak SC (2004) Counter-propagation artificial neural network as a tool for the independent variable selection: structure-mutagenicity study on aromatic amines. Mol Divers 8: 371–377. doi: 10.1023/B:MODI.0000047502.66802.3d CrossRefPubMedGoogle Scholar
  83. 83.
    Roncaglioni A, Novič M, Vračko M, Benfenati E (2004) Classification of potential endocrine disrupters on the basis of molecular structure using a non-linear modeling method. J Chem Inf Comput Sci 44: 300–309. doi: 10.1021/ci030421a PubMedGoogle Scholar
  84. 84.
    Kirew DB, Chretien JR, Bernard P, Ros F (1998) Application of Kohonen Neural Networks in classification of biologically active compounds. SAR QSAR Environ Res 8: 93–107. doi: 10.1080/10629369808033262 CrossRefPubMedGoogle Scholar
  85. 85.
    Dayhoff JE (1990) Neural network architectures: an introduction. Van Nostrand-Reinhold, New YorkGoogle Scholar
  86. 86.
    Cherkassky V, Friedman JH, Wechsler H (1994) From statistics to neural networks-theory and pattern recognition applications. Springer, BerlinGoogle Scholar
  87. 87.
    Grošelj N, van der Veer G, Tušar M, Vračko M, Novič M (2008) Verification of the geological origin of bottled mineral water using artificial neural networks. Food Chem. doi: 10.1016/j.foodchem.2008.11.085
  88. 88.
    Golbraikh A, Tropsha A (2002) Beware of q2!. J Mol Graph Model 20: 269–276. doi: 10.1016/S1093-3263(01)00123-1 CrossRefPubMedGoogle Scholar
  89. 89.
    OECD (2004) Report from the expert group on (quantitative) structure-activity relationships ((Q)SARs) on the principles for the validation of (Q)SARs. OECD Environment Health and Safety Publications, Series on Testing and Assessment No. 49. Environment Directorate, OECD, Paris, FranceGoogle Scholar
  90. 90.
    Jaworska JS, Comber M, Auer C, Van Leeuwen CJ (2003) Summary of a workshop on regulatory acceptance of (Q)SARs for human health and environmental endpoints. Environ Health Perspect 111: 1358–1360. doi: 10.1289/ehp.5757 CrossRefPubMedGoogle Scholar
  91. 91.
    Benfenati E (ed) (2007) Quantitative structure-activity relationship (QSAR) of pesticide for regulatory purposes. Elsevier, The NetherlandsGoogle Scholar
  92. 92.
    Cronin MTD, Jaworska JS, Walker JD, Comber MHI, Watts CD, Worth AP (2003) Use of QSARs in international decision-making frameworks to predict health effects of chemical substances. Environ Health Perspect 111: 1391–1401. doi: 10.1289/ehp.5759 CrossRefPubMedGoogle Scholar
  93. 93.
    Cooper JA, Saracci R, Cole P (1979) Describing the validity of carcinogen screening test. Br J Cancer 39: 87–89PubMedCrossRefGoogle Scholar
  94. 94.
    Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Wadsworth International Group, BelmontGoogle Scholar
  95. 95.
    Jolliffe IT (2002) Principal component analysis, 2nd edn. Springer-Verlag, New YorkGoogle Scholar
  96. 96.
    Kier LB (1986) Molecular connectivity in structure-activity analysis. Wiley, New YorkGoogle Scholar
  97. 97.
    Hall LH, Kier LB (1991) The molecular connectivity chi indices and kappa shape indexes in structure-property relations. In: Boyd D, Lipkowitz K (eds) Reviews of computational chemistry. VCH Publishers, Inc., pp 367–422Google Scholar
  98. 98.
    Kellogg GE, Kier LB, Gaillard P, Hall LH (1996) E-state fields: applications to 3D QSAR. J Comput Aided Mol Des 10: 513–515. doi: 10.1007/BF00134175 CrossRefPubMedGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2009

Authors and Affiliations

  • Natalja Fjodorova
    • 1
    Email author
  • Marjan Vračko
    • 1
  • Marjan Tušar
    • 1
  • Aneta Jezierska
    • 1
    • 2
  • Marjana Novič
    • 1
  • Ralph Kühne
    • 3
  • Gerrit Schüürmann
    • 3
    • 4
  1. 1.National Institute of ChemistryLjubljanaSlovenia
  2. 2.Faculty of ChemistryUniversity of WrocławWrocławPoland
  3. 3.UFZ Department of Ecological ChemistryHelmholtz Centre for Environmental ResearchLeipzigGermany
  4. 4.Institute for Organic ChemistryTechnical University Bergakademie FreibergFreibergGermany

Personalised recommendations