SVM-based detection of distant protein structural relationships using pairwise probabilistic suffix trees

Authors:
Hasan Oğul;Erkan í. Mumcuoğlu
Affiliations:
Department of Computer Engineering, Başkent University, 06530 Ankara, Turkey and Informatics Institute, Middle East Technical University, 06531 Ankara, Turkey;Informatics Institute, Middle East Technical University, 06531 Ankara, Turkey
Venue:
Computational Biology and Chemistry
Year:
2006

Citing 4
Cited 3

Support-Vector Networks

Machine Learning
Algorithms on strings, trees, and sequences: computer science and computational biology

Algorithms on strings, trees, and sequences: computer science and computational biology
Algorithms for variable length Markov chain modeling

Bioinformatics
A comparison of methods for multiclass support vector machines

IEEE Transactions on Neural Networks

Subcellular Localization Prediction with New Protein Encoding Schemes

IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
Fast and Adaptive Variable Order Markov Chain Construction

WABI '08 Proceedings of the 8th international workshop on Algorithms in Bioinformatics
Prediction of human breast and colon cancers from imbalanced data using nearest neighbor and support vector machines

Computer Methods and Programs in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new method based on probabilistic suffix trees (PSTs) is defined for pairwise comparison of distantly related protein sequences. The new definition is adopted in a discriminative framework for protein classification using pairwise sequence similarity scores in feature encoding. The framework uses support vector machines (SVMs) to separate structurally similar and dissimilar examples. The new discriminative system, which we call as SVM-PST, has been tested for SCOP family classification task, and compared with existing discriminative methods SVM-BLAST and SVM-Pairwise, which use BLAST similarity scores and dynamic-programming-based alignment scores, respectively. Results have shown that SVM-PST is more accurate than SVM-BLAST and competitive with SVM-Pairwise. In terms of computational efficiency, PST-based comparison is much better than dynamic-programming-based alignment. We also compared our results with the original family-based PST approach from which we were inspired. The present method provides a significantly better solution for protein classification in comparison with the family-based PST model.