Abstract
Predictive chemical models, commonly called quantitative structure-activity relationships (QSAR), are facing a period of changes and challenges. There is a transition from classical models to new models, more sophisticated. Meanwhile, there is an increased interest in regulators on QSAR in fields as toxicity assessment. This requires more standardisation, even though the research is very dynamic and no common opinion exists on many issues. The present article is a contribution to the discussion on how to standardize data and compare models, with a special attention to advanced QSAR methods, identifying the problems and targets in the field.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Walker, J.D. (ed.): QSARs for Pollution Prevention, Toxicity Screening, Risk Assessment, and Web Applications. Society of Environmental Toxicology and Chemistry (SETAC), Pensacola FL, USA (2003)
Gini, G.C., Katritzky, A.R. (eds.): Predictive Toxicology of Chemicals: Experiences and Impact of AI Tools. AAAI 1999 Spring Symposium Series. AAAI Press, Menlo Park (1999)
Benfenati, E., Piclin, N., Roncaglioni, A., Varì, M.R.: Factors Influencing Predictive Models for Toxicology. SAR and QSAR in environmental research 12, 593–603 (2001)
Russom, C.L., Bradbury, S.P., Broderius, S.J., Hammermeister, D.E., Drummond, R.A.: Predicting modes of action from chemical structure: Acute toxicity in the Fathead Minnow (Pimephales Promelas). Environmental Tox. and Chem. 16, 948–957 (1997)
Benfenati, E., Pelagatti, S., Grasso, P., Gini, G.: COMET: the approach of a project in evaluating toxicity. In: Gini, G.C., Katritzky, A.R. (eds.) Predictive Toxicology of Chemicals: Experiences and Impact of AI Tools. AAAI 1999 Spring Symposium Series, pp. 40–43. AAAI Press, Menlo Park (1999)
Rudén, C., Hansson, S.O.: How accurate are the European Union.s classifications of chemical substances. Toxicology Letters 44, 159–172 (2003)
Roncaglioni, A., Benfenati, E., Boriani, E., Clook, M.: A protocol to select high quality datasets of ecotoxicity values for pesticides. Journal of Environ. Science and Health, Part B 39, 641–652 (2004)
Hermens, J.L.M.: Quantitative structure-activity relationships for predicting fish toxicity. In: Karcher, W., Devillers, J. (eds.) Practical Applications of Quantitative structure-activity relationships (QSAR) in Environmental Chemistry and Toxicology, pp. 263–280. Kluwer Academic Publishers, Dordrecht (1990)
Benfenati, E., Gini, G., Piclin, N., Roncaglioni, A., Varì, M.R.: Predicting LogP of pesticides using different software. Chemosphere 53, 1155–1164 (2003)
Roncaglioni, A.: Comparison of chemical descriptors calculated in four laboratories. In: The Second IMAGETOX Seminars, Descriptors, analysis tools and industrial applications in modeling toxicity of compounds, Tartu, Estonia, June 2-4 (2003)
Smiesko, M., Benfenati, E.: Alerts on preparing datasets for QSAR studies in toxicity predictions. In: The 14 Annual Meeting, SETAC Europe, Prague, Czech Republic (April 18-22, 2004)
Roncaglioni, A., Fratev, F., Benfenati, E., Gustafsson, J.-Å.: Studies on oestrogen receptor: species and subtypes differences. In: The 11th International Workshop on Quantitative Structure-Activity Relationships in the Human Health and Environmental Sciences (QSAR 2004), Liverpool, England, (May 9-13, 2004)
Arciniegas, F., Bennett, K., Breneman, C., Embrechts, M.: Molecular database mining using self-organizing maps for the design of novel pharmaceuticals. In: Dagli, C.H. (ed.) Intelligent Engineering Systems through Artificial Neural Networks: Smart Engineering System Design, vol. 10, pp. 477–482. ASME Press, Washington (2000)
Allen, D.M.: The relationship between variable selection and data augmentation and a method for prediction. Technometrics 16, 125–127 (1974)
Clark, R.D.: Boosted leave-many-out cross-validation: the effect of training and test set diversity on PLS statistics. J. Comp.-Aided Mol. Des. 17, 265–275 (2003)
Golbraikh, A., Tropsha, A.: Beware of q2! Journal of Molecular Graphics and Modelling 20, 269–276 (2002)
Hawkins, D.M.: The problem of overfitting. J. Chem. Inf. Comput. Sci. 44, 1–12 (2004)
Renners, I., Grauel, A., Ludwig, L.A., Benfenati, E., Pelegatti, S., Robert, D., Carbó-Dorca, R., Girones, X.: Modeling toxicity with molecular descriptors and similarity measures via B-spline networks. In: Proceedings of the 8th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, IPMU 2000, Madrid, Spain, July 3-7, vol. II, pp. 1021–1026 (2000)
Katritzky, A.R., Lobanov, V.S., Karelson, M.: CODESSA: Comprehensive Descriptors for Structural and Statistical Analysis, version 2.2.1. Reference Manual. University of Florida, Gainesville, Florida, U.S.A (1994)
Roncaglioni, A., Colombo, A., Maran, U., Karelson, M., Benfenati, E.: Prediction of acute aquatic Toxicity to Fish Comparing Different QSAR Approaches. In: 41st Congress of the European Societies of Toxicology, Florence, Italy, (September 28 - October 1, 2003)
Lemke, F., Benfenati, E., Gini, G., Netzeva, T., Cronin, M., Aynur, A.O., Schüürmann, G.: GMDH Models for fathead minnow toxicity using ab initio or AM1 descriptors. In: The 11th International Workshop on Quantitative Structure-Activity Relationships in the Human Health and Environmental Sciences (QSAR 2004), Liverpool, England, May 9-13 (2004)
Toropov, A.A., Benfenati, E.: QSAR modelling of aldehyde toxicity by means of optimization of correlation weights of nearest neighbourings code. J. Mol. Struct (THEOCHEM) 676, 165–169 (2004)
Smiesko, M., Benfenati, E.: Predictive models for aquatic toxicity of aldehydes designed for various model chemistries. J. Chem. Inf. Comput. Sci. 44, 976–984 (2004)
König, C., Gini, G., Marian, C., Benfenati, E.: Multi-class classifier from a combination experts: towards distributed computation real-problem classifiers. International Journal of Pattern Recognition and Artificial Intelligence (in press)
Benfenati, E., Gini, G., König, C., Craciun, M.: Prediction of Aquatic Toxicity with combined Neural Networks. The 14 Annual Meeting, SETAC Europe, Prague, Czech Republic, (April 18-22, 2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Benfenati, E. (2004). Modelling Aquatic Toxicity with Advanced Computational Techniques: Procedures to Standardize Data and Compare Models. In: López, J.A., Benfenati, E., Dubitzky, W. (eds) Knowledge Exploration in Life Science Informatics. KELSI 2004. Lecture Notes in Computer Science(), vol 3303. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30478-4_20
Download citation
DOI: https://doi.org/10.1007/978-3-540-30478-4_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23927-7
Online ISBN: 978-3-540-30478-4
eBook Packages: Springer Book Archive