Prediction of PKCθ Inhibitory Activity Using the Random Forest Algorithm
Open Access
- 20 September 2010
- journal article
- research article
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 11 (9) , 3413-3433
Abstract
This work is devoted to the prediction of a series of 208 structurally diverse PKCθ inhibitors using the Random Forest (RF) based on the Mold2 molecular descriptors. The RF model was established and identified as a robust predictor of the experimental pIC50 values, producing good external R2pred of 0.72, a standard error of prediction (SEP) of 0.45, for an external prediction set of 51 inhibitors which were not used in the development of QSAR models. By using the RF built-in measure of the relative importance of the descriptors, an important predictor—the number of group donor atoms for H-bonds (with N and O)―has been identified to play a crucial role in PKCθ inhibitory activity. We hope that the developed RF model will be helpful in the screening and prediction of novel unknown PKCθ inhibitory activity.Keywords
This publication has 55 references indexed in Scilit:
- QSAR study on melanocortin-4 receptors by support vector machineEuropean Journal of Medicinal Chemistry, 2010
- Optimization of 5-phenyl-3-pyridinecarbonitriles as PKCθ inhibitorsBioorganic & Medicinal Chemistry Letters, 2009
- Mold2, Molecular Descriptors from 2D Structures for Chemoinformatics and ToxicoinformaticsJournal of Chemical Information and Modeling, 2008
- Quantitative structure activity relationship model for predicting the depletion percentage of skin allergic chemical substances of glutathioneAnalytica Chimica Acta, 2007
- QSAR Analyses of 3-(4-Benzylpiperidin-1-yl)-N-phenylpropylamine Derivatives as Potent CCR5 AntagonistsJournal of Chemical Information and Modeling, 2005
- Modified support vector machines in financial time series forecastingNeurocomputing, 2002
- Support vector machines for predicting HIV protease cleavage sites in proteinJournal of Computational Chemistry, 2001
- Support-vector networksMachine Learning, 1995
- Partial least-squares regression: a tutorialAnalytica Chimica Acta, 1986
- Cross-Validatory Estimation of the Number of Components in Factor and Principal Components ModelsTechnometrics, 1978