Open Access Open Access  Restricted Access Subscription Access

The Virtual Screening of the Drug Protein with a Few Crystal Structures based on the Adaboost-SVM


Affiliations
1 School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China
 

Using the theory of machine learning to assist the virtual screening (VS) has been an effective plan. However, the quality of the training set may reduce because of mixing with the wrong docking poses and it will affect the screening efficiencies. To solve this problem,we present a method using the ensemble learning to improve the support vector machine to process the generated proteinligand interaction fingerprint (IFP). By combining multiple classifiers, ensemble learning is able to avoid the limitations of the single classifier’s performance and obtain better generalization. According to the research of virtual screening experiment with SRC and Cathepsin K as the target, the results show that the ensemble learning method can effectively reduce the error because the sample quality is not high and improve the effect of the whole virtual screening process.
User
Notifications
Font Size

Abstract Views: 89

PDF Views: 1




  • The Virtual Screening of the Drug Protein with a Few Crystal Structures based on the Adaboost-SVM

Abstract Views: 89  |  PDF Views: 1

Authors

Meng-yu Wang
School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China
Peng Li
School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China
Pei-li Qiao
School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China

Abstract


Using the theory of machine learning to assist the virtual screening (VS) has been an effective plan. However, the quality of the training set may reduce because of mixing with the wrong docking poses and it will affect the screening efficiencies. To solve this problem,we present a method using the ensemble learning to improve the support vector machine to process the generated proteinligand interaction fingerprint (IFP). By combining multiple classifiers, ensemble learning is able to avoid the limitations of the single classifier’s performance and obtain better generalization. According to the research of virtual screening experiment with SRC and Cathepsin K as the target, the results show that the ensemble learning method can effectively reduce the error because the sample quality is not high and improve the effect of the whole virtual screening process.