Prediction of PKCθ Inhibitory Activity Using the Random Forest Algorithm

Int. J. Mol. Sci. 2010, 11(9), 3413-3433; doi:10.3390/ijms11093413

Author

Ming Hao ¹

, Yan Li ^1,* , Yonghua Wang ²

 and Shuwei Zhang ¹

¹

School of Chemical Engineering, Dalian University of Technology, Dalian, Liaoning 116012, China

²

Center of Bioinformatics, Northwest A&F University, Yangling, Shaanxi 712100, China

^*

Author to whom correspondence should be addressed. 

Received: 19 July 2010 / Revised: 24 August 2010 / Accepted: 3 September 2010 / Published: 20 September 2010

View Full-Text   |     Download PDF [382 KB, uploaded 19 June 2014]   |    

 Browse Figures

 

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 R²_pred 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. View Full-Text

Keywords: protein kinase C θ;  Random Forest;  Partial Least Square;  Support Vector Machine

This is an open access article distributed under the Creative Commons Attribution License (CC BY 3.0).

For further details log on website :
http://www.mdpi.com/1422-0067/11/9/3413