![](https://d3ilqtpdwi981i.cloudfront.net/DgmRNB33D6Q9u3Q-fWPC6SDtaao=/425x550/smart/https://bepress-attached-resources.s3.amazonaws.com/uploads/c3/a3/56/c3a3569b-26ec-474d-a8b1-a533fd3c11f9/thumbnail_9b194153-8a6d-45ce-968e-44d5956be0ad.jpg)
Article
Comparing Kernels For Predicting Protein Binding Sites From Amino Acid Sequence
The 2006 IEEE International Joint Conference on Neural Network Proceedings
Document Type
Conference Proceeding
Disciplines
Conference
2006 International Joint Conference on Neural Networks
Publication Version
Accepted Manuscript
Publication Date
1-1-2006
DOI
10.1109/IJCNN.2006.246626
Conference Title
2006 International Joint Conference on Neural Networks
Conference Date
July 16-21, 2006
Geolocation
(49.2827291, -123.12073750000002)
Abstract
The ability to identify protein binding sites and to detect specific amino acid residues that contribute to the specificity and affinity of protein interactions has important implications for problems ranging from rational drug design to analysis of metabolic and signal transduction networks. Support vector machines (SVM) and related kernel methods offer an attractive approach to predicting protein binding sites. An appropriate choice of the kernel function is critical to the performance of SVM. Kernel functions offer a way to incorporate domain-specific knowledge into the classifier. We compare the performance of 3 types of kernels functions: identity kernel, sequence-alignment kernel, and amino acid substitution matrix kernel for predicting protein-protein, protein-DNA and protein-RNA binding sites. The results show that the identity kernel is quite effective in on all three tasks, with the substitution kernel based on amino acid substitution matrices that take into account structural or evolutionary conservation or physicochemical properties of amino acids yields modest improvement in the performance of the resulting SVM classifiers for predicting protein-protein, protein-DNA and protein-RNA binding sites.
Rights
© 2006 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Copyright Owner
IEEE
Copyright Date
2006
Language
en
File Format
application/pdf
Citation Information
Feihong Wu, Byron Olson, Drena Dobbs and Vasant Honavar. "Comparing Kernels For Predicting Protein Binding Sites From Amino Acid Sequence" Vancouver, BC, CanadaThe 2006 IEEE International Joint Conference on Neural Network Proceedings (2006) p. 1612 - 1616 Available at: http://works.bepress.com/drena-dobbs/49/
This is a proceeding from International Joint Conference on Neural Networks (2006): 1612, doi: 10.1109/IJCNN.2006.246626. Posted with permission.