Please use this identifier to cite or link to this item:
https://doi.org/10.1021/ci050135u
DC Field | Value | |
---|---|---|
dc.title | Effect of selection of molecular descriptors on the prediction of blood-brain barrier penetrating and nonpenetrating agents by statistical learning methods | |
dc.contributor.author | Li, H. | |
dc.contributor.author | Yap, C.W. | |
dc.contributor.author | Ung, C.Y. | |
dc.contributor.author | Xue, Y. | |
dc.contributor.author | Cao, Z.W. | |
dc.contributor.author | Chen, Y.Z. | |
dc.date.accessioned | 2014-12-02T06:52:41Z | |
dc.date.available | 2014-12-02T06:52:41Z | |
dc.date.issued | 2005-09 | |
dc.identifier.citation | Li, H., Yap, C.W., Ung, C.Y., Xue, Y., Cao, Z.W., Chen, Y.Z. (2005-09). Effect of selection of molecular descriptors on the prediction of blood-brain barrier penetrating and nonpenetrating agents by statistical learning methods. Journal of Chemical Information and Modeling 45 (5) : 1376-1384. ScholarBank@NUS Repository. https://doi.org/10.1021/ci050135u | |
dc.identifier.issn | 15499596 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/114321 | |
dc.description.abstract | The ability or inability of a drug to penetrate into the brain is a key consideration in drug design. Drugs for treating central nervous system (CNS) disorders need to be able to penetrate the blood-brain barrier (BBB). BBB nonpenetration is desirable for non-CNS-targeting drugs to minimize potential CNS-related side effects. Computational methods have been employed for the prediction of BBB-penetrating (BBB+) and -nonpenetrating (BBB-) agents at impressive accuracies of 75-92% and 60-80%, respectively. However, the majority of these studies give a substantially lower BBB- accuracy, and thus overall accuracy, than the BBB+ accuracy. This work examined whether proper selection of molecular descriptors can improve both the BBB- and the overall accuracies of statistical learning methods. The methods tested include logistic regression, linear discriminate analysis, k nearest neighbor, C4.5 decision tree, probabilistic neural network, and support vector machine. Molecular descriptors were selected by using a feature selection method, recursive feature elimination (RFE). Results by using 415 BBB+ and BBB- agents show that RFE substantially improves both the BBB- and the overall accuracy for all of the methods studied. This suggests that statistical learning methods combined with proper feature selection is potentially useful for facilitating a more balanced and improved prediction of BBB+ and BBB- agents. © 2005 American Chemical Society. | |
dc.description.uri | http://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1021/ci050135u | |
dc.source | Scopus | |
dc.type | Article | |
dc.contributor.department | COMPUTATIONAL SCIENCE | |
dc.contributor.department | BIOLOGICAL SCIENCES | |
dc.contributor.department | SINGAPORE-MIT ALLIANCE | |
dc.description.doi | 10.1021/ci050135u | |
dc.description.sourcetitle | Journal of Chemical Information and Modeling | |
dc.description.volume | 45 | |
dc.description.issue | 5 | |
dc.description.page | 1376-1384 | |
dc.identifier.isiut | 000232208200023 | |
Appears in Collections: | Staff Publications |
Show simple item record
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.