Finding conserved regions in protein structures using support vector machines and structure alignment

Authors:
Tatsuya Akutsu;Morihiro Hayashida;Takeyuki Tamura
Affiliations:
Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji, Kyoto, Japan;Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji, Kyoto, Japan;Bioinformatics Center, Institute for Chemical Research, Kyoto University, Uji, Kyoto, Japan
Venue:
PRIB'12 Proceedings of the 7th IAPR international conference on Pattern Recognition in Bioinformatics
Year:
2012

Citing 9
Cited 0

Support-Vector Networks

Machine Learning
Making large-scale support vector machine learning practical

Advances in kernel methods
On the approximation of largest common subtrees and largest common point sets

Theoretical Computer Science
Gene Selection for Cancer Classification using Support Vector Machines

Machine Learning
Kernel Methods for Pattern Analysis

Kernel Methods for Pattern Analysis
Protein function prediction via graph kernels

Bioinformatics
Multiple flexible structure alignment using partial order graphs

Bioinformatics
A new progressive-iterative algorithm for multiple structure alignment

Bioinformatics
A structural alignment kernel for protein structures

Bioinformatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a novel method for finding conserved regions in three-dimensional protein structures. The method combines support vector machines (SVMs), feature selection and protein structure alignment. For that purpose, a new feature vector is developed based on structure alignment for fragments of protein backbone structures. The results of preliminary computational experiments suggest that the proposed method is useful to find common structural fragments in similar proteins.