ART 2-A FOR OPTIMAL TEST SERIES DESIGN IN QSAR

Authors
DOMINE D DEVILLERS J WIENKE D BUYDENS L
Citation
D. Domine et al., ART 2-A FOR OPTIMAL TEST SERIES DESIGN IN QSAR, Journal of chemical information and computer sciences, 37(1), 1997, pp. 10-17
Citations number
40
Categorie Soggetti
Information Science & Library Science","Computer Application, Chemistry & Engineering","Computer Science Interdisciplinary Applications",Chemistry,"Computer Science Information Systems
Journal title
Journal of chemical information and computer sciences → ACNP
ISSN journal
00952338
Volume
37
Issue
1
Year of publication
1997
Pages
10 - 17
Database
ISI
SICI code
0095-2338(1997)37:1<10:A2FOTS>2.0.ZU;2-Y
Abstract
The family of adaptive resonance theory (ART) based systems concerns d istinct artificial neural networks for unsupervised and supervised clu stering analysis. Among them, the ART 2-A paradigm presents numerous s trengths for data analysis. After a rapid presentation of the ART 2-A theory and algorithmic information, the usefulness of this neural netw ork for the selection of optimal test series is estimated. The results are compared with those obtained from hierarchical cluster analysis a nd visual mapping methods. The advantages and drawbacks of each method are discussed. We show that ART 2-A represents a new useful nonlinear statistical tool for QSAR and drug design.