Tuning Neural and Fuzzy-Neural Networks for Toxicity Modeling
- 23 January 2003
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Computer Sciences
- Vol. 43 (2) , 513-518
- https://doi.org/10.1021/ci025585q
Abstract
The need for general reliable models for predicting toxicity has led to the use of artificial intelligence. We applied neural and fuzzy-neural networks with the QSAR approach. We underline how the networks have to be tuned on the data sets generally involved in modeling toxicity. This study was conducted on 562 organic compounds in order to establish models for predictive the acute toxicity in fish.Keywords
This publication has 8 references indexed in Scilit:
- The Importance of Scaling in Data Mining for Toxicity PredictionJournal of Chemical Information and Computer Sciences, 2002
- Factors Influencing Predictive Models for ToxicologySAR and QSAR in Environmental Research, 2001
- Predictive Carcinogenicity: A Model for Aromatic Compounds, with Nitrogen-Containing Substituents, Based on Molecular Descriptors Using an Artificial Neural NetworkJournal of Chemical Information and Computer Sciences, 1999
- Are multilayer perceptrons adequate for pattern recognition and verification?Published by Institute of Electrical and Electronics Engineers (IEEE) ,1998
- A Study of Structure−Carcinogenic Potency Relationship with Artificial Neural Networks. The Using of Descriptors Related to Geometrical and Electronic StructuresJournal of Chemical Information and Computer Sciences, 1997
- Computational predictive programs (expert systems) in toxicologyToxicology, 1997
- Predicting modes of toxic action from chemical structure: Acute toxicity in the fathead minnow (Pimephales promelas)Environmental Toxicology and Chemistry, 1997
- QSARS of mutagens and carcinogens: Two case studies illustrating problems in the construction of models for noncongeneric chemicalsMutation Research/Genetic Toxicology, 1996