%0 Journal Article
%T Prediction of PKC¦È Inhibitory Activity Using the Random Forest Algorithm
%A Ming Hao
%A Yan Li
%A Yonghua Wang
%A Shuwei Zhang
%J International Journal of Molecular Sciences
%D 2010
%I MDPI AG
%R 10.3390/ijms11093413
%X This work is devoted to the prediction of a series of 208 structurally diverse PKC¦È inhibitors using the Random Forest (RF) based on the Mold 2 molecular descriptors. The RF model was established and identified as a robust predictor of the experimental pIC 50 values, producing good external R 2 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¡ªthe number of group donor atoms for H-bonds (with N and O)¨Dhas been identified to play a crucial role in PKC¦È inhibitory activity. We hope that the developed RF model will be helpful in the screening and prediction of novel unknown PKC¦È inhibitory activity.
%K protein kinase C ¦È
%K Random Forest
%K Partial Least Square
%K Support Vector Machine
%U http://www.mdpi.com/1422-0067/11/9/3413