Feature subset selection for protein subcellular localization prediction

Authors:
Qing-Bin Gao;Zheng-Zhi Wang
Affiliations:
Institute of Automation, National University of Defense Technology, Changsha, Hunan, People's Republic of China;Institute of Automation, National University of Defense Technology, Changsha, Hunan, People's Republic of China
Venue:
ICIC'06 Proceedings of the 2006 international conference on Computational Intelligence and Bioinformatics - Volume Part III
Year:
2006

Citing 6
Cited 0

New techniques for extracting features from protein sequences

IBM Systems Journal - Deep computing for the life sciences
Predicting subcellular localization of proteins in a hybridization space

Bioinformatics
PSLpred: prediction of subcellular localization of bacterial proteins

Bioinformatics
MultiLoc: prediction of protein subcellular localization using N-terminal targeting sequences, sequence motifs and amino acid composition

Bioinformatics
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)
A comparison of methods for multiclass support vector machines

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Most of the existing methods for protein subcellular localization prediction are based on a large number of features that are considered to be potentially useful for determining protein subcellular localizations. However, predictors with large numbers of input variables usually suffer from the curse of dimensionality as well as the risk of overfitting. Using only those features that are relevant for protein subcellular localization might improve the prediction performance and might also provide us with some biologically useful knowledge. In this paper, we present a feature ranking based feature subset selection approach for subcellular localization prediction of proteins in the context of support vector machines (SVMs). Experimental results show that this method improves the prediction performance with selected subsets of features. It is anticipated that the proposed method will be a powerful tool for large-scale annotation of biological data.