Please use this identifier to cite or link to this item: http://repositorio.ufla.br/jspui/handle/1/41421
metadata.artigo.dc.title: Feature selection and linear/non-linear regression methods for the accurate prediction of glycogen synthase kinase-3β inhibitory activities
metadata.artigo.dc.creator: Goodarzi, Mohammad
Freitas, Matheus P.
Jensen, Richard
metadata.artigo.dc.subject: Bioinformatics
Computational biology
Algorithms
Layers
Structure activity relationship
Phenyls
metadata.artigo.dc.publisher: American Chemical Society (ACS)
metadata.artigo.dc.date.issued: Apr-2009
metadata.artigo.dc.identifier.citation: GOODARZI, M.; FREITAS, M. P.; JENSEN, R. Feature selection and linear/non-linear regression methods for the accurate prediction of glycogen synthase kinase-3β inhibitory activities. Journal of Chemical Information and Modeling, [S.l.], v. 49, n. 4, p. 824-832, Apr. 2009. DOI: 10.1021/ci9000103.
metadata.artigo.dc.description.abstract: Few variables were selected from a pool of calculated Dragon descriptors through three different feature selection methods, namely genetic algorithm (GA), successive projections algorithm (SPA), and fuzzy rough set ant colony optimization (fuzzy rough set ACO). Each set of selected descriptors was regressed against the bioactivities of a series of glycogen synthase kinase-3β (GSK-3β) inhibitors, through linear and nonlinear regression methods, namely multiple linear regression (MLR), artificial neural network (ANN), and support vector machines (SVM). The fuzzy rough set ACO/SVM-based model gave the best estimation/prediction results, demonstrating the nonlinear nature of this analysis and suggesting fuzzy rough set ACO, first introduced in chemistry here, as an improved variable selection method in QSAR for the class of GSK-3β inhibitors.
metadata.artigo.dc.identifier.uri: https://pubs.acs.org/doi/10.1021/ci9000103
http://repositorio.ufla.br/jspui/handle/1/41421
metadata.artigo.dc.language: en_US
Appears in Collections:DQI - Artigos publicados em periódicos

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.