Please use this identifier to cite or link to this item:
Title: Consensus model for identification of novel PI3K inhibitors in large chemical library
Authors: Liew, C.Y.
Ma, X.H. 
Yap, C.W. 
Keywords: Consensus model
Drug discovery
Machine learning
Phosphoinositide 3-kinases
PI3K inhibitors
Virtual screening
Issue Date: Feb-2010
Citation: Liew, C.Y., Ma, X.H., Yap, C.W. (2010-02). Consensus model for identification of novel PI3K inhibitors in large chemical library. Journal of Computer-Aided Molecular Design 24 (2) : 131-141. ScholarBank@NUS Repository.
Abstract: Phosphoinositide 3-kinases (PI3Ks) inhibitors have treatment potential for cancer, diabetes, cardiovascular disease, chronic inflammation and asthma. A consensus model consisting of three base classifiers (AODE, kNN, and SVM) trained with 1,283 positive compounds (PI3K inhibitors), 16 negative compounds (PI3K non-inhibitors) and 64,078 generated putative negatives was developed for predicting compounds with PI3K inhibitory activity of IC50 10 μM. The consensus model has an estimated false positive rate of 0.75%. Nine novel potential inhibitors were identified using the consensus model and several of these contain structural features that are consistent with those found to be important for PI3K inhibitory activities. An advantage of the current model is that it does not require knowledge of 3D structural information of the various PI3K isoforms, which is not readily available for all isoforms. © 2010 Springer Science+Business Media B.V.
Source Title: Journal of Computer-Aided Molecular Design
ISSN: 0920654X
DOI: 10.1007/s10822-010-9321-0
Appears in Collections:Staff Publications

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


checked on Nov 28, 2020


checked on Nov 20, 2020

Page view(s)

checked on Nov 29, 2020

Google ScholarTM



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