MIA-QSAR modeling of activities of a series of AZT analogues: bi- and multilinear PLS regression

dc.creatorGoodarzi, Mohammad
dc.creatorFreitas, Matheus Puggina de
dc.date2020-07-12T20:48:53Z
dc.date2020-07-12T20:48:53Z
dc.date2010
dc.date.accessioned2023-09-28T19:54:36Z
dc.date.available2023-09-28T19:54:36Z
dc.identifierGOODARZI, M.; FREITAS, M. P. MIA-QSAR modeling of activities of a series of AZT analogues: bi- and multilinear PLS regression. Molecular Simulation, [S.l.], v. 36, n. 4, p. 267-272, 2010. DOI: 10.1080/08927020903278001.
dc.identifierhttps://www.tandfonline.com/doi/abs/10.1080/08927020903278001
dc.identifierhttp://repositorio.ufla.br/jspui/handle/1/41801
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/9039899
dc.descriptionThe activities of a series of azidothymidine derivatives, compounds with anti-HIV potency, were computationally modelled using multivariate image analysis applied to quantitative structure–activity relationships (MIA-QSAR). Two regression methods were tested in order to find the best correlation between actual and predicted activities: bilinear (traditional) partial least squares (PLS), applied to the unfolded dataset, and multilinear PLS (N-PLS), applied to the three-way array. The predictive abilities of the PLS- and N-PLS-based models were found to be nearly equivalent, and both the methods derived QSAR models that are statistically superior to conventional QSAR, in which physicochemical descriptors and multiple linear regression were applied.
dc.languageen_US
dc.publisherTaylor & Francis
dc.rightsrestrictAccess
dc.sourceMolecular Simulation
dc.subjectMIA-QSAR
dc.subjectAZT analogues
dc.subjectHIV
dc.subjectPLS
dc.subjectN-PLS
dc.subjectMultivariate image analysis applied to quantitative structure-activity relationship (MIA-QSAR)
dc.subjectAzidothymidine (AZT)
dc.subjectPartial least squares (PLS)
dc.subjectMultiway partial least squares (N-PLS)
dc.titleMIA-QSAR modeling of activities of a series of AZT analogues: bi- and multilinear PLS regression
dc.typeArtigo


Este ítem pertenece a la siguiente institución