A training algorithm for optimal margin classifiers
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Journal of Molecular Graphics
The nature of statistical learning theory
The nature of statistical learning theory
Making large-scale support vector machine learning practical
Advances in kernel methods
Learning to Classify Text Using Support Vector Machines: Methods, Theory and Algorithms
Learning to Classify Text Using Support Vector Machines: Methods, Theory and Algorithms
Functional Site Prediction on the DNA sequence by Artificial Neural Networks
IJSIS '96 Proceedings of the 1996 IEEE International Joint Symposia on Intelligence and Systems
Data Mining on Imbalanced Data Sets
ICACTE '08 Proceedings of the 2008 International Conference on Advanced Computer Theory and Engineering
Evolutionary-based selection of generalized instances for imbalanced classification
Knowledge-Based Systems
An introduction to kernel-based learning algorithms
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
Identification of protein-ligand binding site is an important task in structure-based drug design and docking algorithms. In the past two decades, different approaches have been developed to predict the binding site, such as the geometric, energetic, and sequence-based methods. When scores are calculated from these methods, the algorithm for doing classification becomes very important and can affect the prediction results greatly. In this paper, the support vector machine (SVM) is used to cluster the pockets that are most likely to bind ligands with the attributes of geometric characteristics, interaction potential, offset from protein, conservation score, and properties surrounding the pockets. Our approach is compared to LIGSITE, $({\rm LIGSITE}^{{\rm csc}})$, SURFNET, Fpocket, PocketFinder, Q-SiteFinder, ConCavity, and MetaPocket on the data set LigASite and 198 drug-target protein complexes. The results show that our approach improves the success rate from 60 to 80 percent at AUC measure and from 61 to 66 percent at top 1 prediction. Our method also provides more comprehensive results than the others.