APPLICATION OF A PRUNING ALGORITHM TO OPTIMIZE ARTIFICIAL NEURAL NETWORKS FOR PHARMACEUTICAL FINGERPRINTING

Authors
TETKO IV VILLA AEP AKSENOVA TI ZIELINSKI WL BROWER J COLLANTES ER WELSH WJ
Citation
Iv. Tetko et al., APPLICATION OF A PRUNING ALGORITHM TO OPTIMIZE ARTIFICIAL NEURAL NETWORKS FOR PHARMACEUTICAL FINGERPRINTING, Journal of chemical information and computer sciences, 38(4), 1998, pp. 660-668
Citations number
26
Categorie Soggetti
Computer Science Interdisciplinary Applications","Computer Science Information Systems","Computer Science Interdisciplinary Applications",Chemistry,"Computer Science Information Systems
Journal title
Journal of chemical information and computer sciences → ACNP
ISSN journal
00952338
Volume
38
Issue
4
Year of publication
1998
Pages
660 - 668
Database
ISI
SICI code
0095-2338(1998)38:4<660:AOAPAT>2.0.ZU;2-F
Abstract
The present study investigates an application of artificial neural net works (ANNs) for use in pharmaceutical fingerprinting. Several pruning algorithms were applied to decrease the dimension of the input parame ter data set. A localized fingerprint region was identified within the original input parameter space from which a subset of input parameter s was extracted leading to enhanced ANN performance. The present resul ts confirm that ANNs can provide a fast, accurate, and consistent meth odology applicable to pharmaceutical fingerprinting.