Structure-mutagenicity modelling using counter propagation neural networks

Marjan Vracko, Denise Mills, Subhash C Basak

Research output: Contribution to journalArticlepeer-review

25 Scopus citations

Abstract

The set of 95 aromatic amines and their mutagenic potency was treated with counter propagation neural network, which enables analysis of self-organising maps (SOMs) and also the prediction of mutagenicity. Compounds were described with four classes of descriptors: topostructural (TS), topochemical (TC), geometrical, and quantum chemical (QC). The models were tested on their prediction ability with leave-one-out (LOO) cross-validation method. The squares of correlation coefficient lie between 0.65 and 0.75 and are comparable with models obtained by linear methods. In addition, we analysed self-organising maps and found clusters of structurally similar compounds.

Original languageEnglish (US)
Pages (from-to)25-36
Number of pages12
JournalEnvironmental Toxicology and Pharmacology
Volume16
Issue number1-2
DOIs
StatePublished - Mar 1 2004

Keywords

  • Aromatic amines
  • Counter propagation neural network
  • Hierarchical clustering
  • Mutagenicity
  • QSAR modelling
  • Self-organising map

Fingerprint Dive into the research topics of 'Structure-mutagenicity modelling using counter propagation neural networks'. Together they form a unique fingerprint.

Cite this