Feature Selection and Linear/Nonlinear Regression Methods for the Accurate Prediction of Glycogen Synthase Kinase-3Β Inhibitory Activities

H...............H

Show simple item record

dc.contributor.author Jensen, Richard
dc.contributor.author Goodarzi, Mohammad
dc.contributor.author Freitas, Matheus P.
dc.date.accessioned 2009-05-27T07:34:13Z
dc.date.available 2009-05-27T07:34:13Z
dc.date.issued 2009-04-01
dc.identifier.citation Jensen , R , Goodarzi , M & Freitas , M P 2009 , ' Feature Selection and Linear/Nonlinear Regression Methods for the Accurate Prediction of Glycogen Synthase Kinase-3Β Inhibitory Activities ' Journal of Chemical Information and Modeling , pp. 824 . en
dc.identifier.issn 1549-960X
dc.identifier.other PURE: 106449
dc.identifier.other dspace: 2160/2397
dc.identifier.uri http://hdl.handle.net/2160/2397
dc.identifier.uri http://pubs.acs.org/doi/abs/10.1021/ci9000103 en
dc.description M. Goodarzi, M.P. Freitas and R. Jensen. Feature Selection and Linear/Nonlinear Regression Methods for the Accurate Prediction of Glycogen Synthase Kinase-3Β Inhibitory Activities. Journal of Chemical Information and Modeling, vol. 49, no. 4, pp. 824–832, 2009. en
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. en
dc.format.extent 824 en
dc.language.iso eng
dc.relation.ispartof Journal of Chemical Information and Modeling en
dc.title Feature Selection and Linear/Nonlinear Regression Methods for the Accurate Prediction of Glycogen Synthase Kinase-3Β Inhibitory Activities en
dc.type Text en
dc.type.publicationtype Article (Journal) en
dc.contributor.institution Department of Computer Science en
dc.contributor.institution Advanced Reasoning Group en
dc.description.status Peer reviewed en


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Cadair


Advanced Search

Browse

My Account