share
Acta Chimica Sinica ›› 2007, Vol. 65 ›› Issue (3): 197-202. Previous Articles Next Articles
Original Articles
饶含兵1, 李泽荣*,1, 陈晓梅1, 李象远*,2
投稿日期:
修回日期:
发布日期:
通讯作者:
RAO Han-Bing1; LI Ze-Rong*,1; CHEN Xiao-Mei1; LI Xiang-Yuan*,2
Received:
Revised:
Published:
Contact:
Share
In order to predict the activity of HIV protease inhibitors, constitutional and topological descriptors, in total 462, were calculated to characterize the structural and physicochemical properties for each molecule under study. The Kennard-Stone method and a random method were adopted to design the training set and the test set. Monte Carlo simulated annealing method was applied to the variable selection. Machine learning methods including support vector machine, artificial neural network, logistic regression, and k-nearest neighbor, were applied to the development of inhibitor models. It was shown that the support vector machine method outperforms the other methods and the final model developed using the SVM method gave a prediction accuracy of 98.24%.
Key words: protease inhibitor, molecular descriptor, machine-learning method, variable selection
RAO Han-Bing; LI Ze-Rong*,1; CHEN Xiao-Mei; LI Xiang-Yuan*,2. Activity Prediction of HIV-1 Protease Inhibitors Using Support Vector Machine[J]. Acta Chimica Sinica, 2007, 65(3): 197-202.
Export EndNote|Reference Manager|ProCite|BibTeX|RefWorks