Neural Modelling of the Biodegradability of Benzene Derivatives
- 1 August 1993
- journal article
- research article
- Published by Taylor & Francis in SAR and QSAR in Environmental Research
- Vol. 1 (2-3) , 161-167
- https://doi.org/10.1080/10629369308028827
Abstract
The aim of this paper was to explore the usefulness of a backpropagation neural network (BNN) to estimate the biodegradability of benzene derivatives. 127 chemicals selected from the BIODEG data bank (Syracuse Research Corporation, 1992) were described by means of 20 structural descriptors taking into account the nature and position of the substituents on the benzene ring. Three classes of biodegradability were selected and modelled from the BNN. A 20/5/3 BNN (α = 0.8 and η = 0.5) correctly classified 92% (104/113) of the training and 86% (12/14) of the testing sets. The results were compared to those produced by the BIODEG probability program (Syracuse Research Corporation, Version 2.13).Keywords
This publication has 6 references indexed in Scilit:
- New Trends in Structure‐Biodegradability RelationshipsQuantitative Structure-Activity Relationships, 1993
- A systematic study of the aerobic and anaerobic biodegradation of 18 chlorophenols and 3 cresolsEnvironmental Toxicology and Water Quality, 1990
- Structural features associated with degradable and persistent chemicalsEnvironmental Toxicology and Chemistry, 1987
- Learning representations by back-propagating errorsNature, 1986
- Application of molecular topology to quantitative structure‐biodegradability relationshipsEnvironmental Toxicology and Chemistry, 1986
- Chemico-biological interactions in biological purification systems VI. Relation between biodegradation rate constants of di-n-alkyl phthalate esters and their retention times in reverse phase partition chromatographyChemosphere, 1979