Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Use of automatic relevance determination in QSAR studies using Bayesian neural networks
Autore:
Burden, FR; Ford, MG; Whitley, DC; Winkler, DA;
Indirizzi:
Monash Univ, Sch Chem, Clayton, Vic 3800, Australia Monash Univ Clayton Vic Australia 3800 Chem, Clayton, Vic 3800, Australia Univ Portsmouth, Inst Biomed & Biomol Sci, Ctr Mol Design, Portsmouth PO1 2DY, Hants, England Univ Portsmouth Portsmouth Hants England PO1 2DY PO1 2DY, Hants, England CSIRO, Div Mol Sci, Clayton, Vic 3169, Australia CSIRO Clayton Vic Australia 3169 iv Mol Sci, Clayton, Vic 3169, Australia
Titolo Testata:
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES
fascicolo: 6, volume: 40, anno: 2000,
pagine: 1423 - 1430
SICI:
0095-2338(200011/12)40:6<1423:UOARDI>2.0.ZU;2-1
Fonte:
ISI
Lingua:
ENG
Soggetto:
SELECTIVE MUSCARINIC AGONISTS; BENZODIAZEPINE RECEPTOR; VARIABLE SELECTION; TETRAHYMENA-PYRIFORMIS; LIGANDS; ANALOGS; MODEL; IMIDAZO<1,2-B>PYRIDAZINES; PHARMACOPHORE; TOXICITY;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Physical, Chemical & Earth Sciences
Citazioni:
40
Recensione:
Indirizzi per estratti:
Indirizzo: Burden, FR Monash Univ, Sch Chem, Clayton, Vic 3800, Australia Monash Univ Clayton Vic Australia 3800 on, Vic 3800, Australia
Citazione:
F.R. Burden et al., "Use of automatic relevance determination in QSAR studies using Bayesian neural networks", J CHEM INF, 40(6), 2000, pp. 1423-1430

Abstract

We describe the use of Bayesian regularized artificial neural networks (BRANNs) coupled, with automatic relevance determination (ARD) in the development of quantitative structure-activity relationship (QSAR) models. These BRANN-ARD networks have the potential to solve a number of problems which,arise in QSAR modeling such as the following: choice of model; robustness of model; choice of validation set; size of validation effort; and optimizationof network architecture. The ARD method ensures that irrelevant or highly correlated indices used in the modeling are neglected as well as showing which are the most important variables in modeling the activity data. The application of the methods to QSAR of compounds active at the benzodiazepine and muscarinic receptors as well as some, toxicological data of the effect of substituted benzenes on Tetetrahymena pyriformis is illustrated.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 06/04/20 alle ore 02:07:17