Using motifs in the prediction of eukaryotic protein subcellular localization

Dan Xie; Ao Li; Xiaojun Lin; Minghui Wang; Zhaohui Jiang; Huanqing Feng

doi:10.1109/IEMBS.2005.1617055

Using motifs in the prediction of eukaryotic protein subcellular localization

Conf Proc IEEE Eng Med Biol Soc. 2005:2005:2802-4. doi: 10.1109/IEMBS.2005.1617055.

Authors

Dan Xie¹, Ao Li, Xiaojun Lin, Minghui Wang, Zhaohui Jiang, Huanqing Feng

Affiliation

¹ Department of Electronic Science and Technology, University of Science and Technology of China, Hefei, P R, China.

PMID: 17282824
DOI: 10.1109/IEMBS.2005.1617055

Abstract

Subcellular location of a protein is one of the key functional characters as proteins must be localized correctly at the subcellular level to have normal biological functions. In this paper, all motifs in PROSITE were examined and those that are indicative to eukaryotic protein subcellular localizations were picked out. A corresponding motif module was built and combined to our former work: LOCSVMPSI. Prediction results of this combined method were compared to LOCSVMPSI as well as several other existing methods for subcellular localization. The combined method achieved highest overall prediction accuracy among all listed methods and improved the over-all and each-location accuracies of LOCSVMPSI by 3%-8%. Further analysis indicates the combined motif method is very effective in eukaryotic protein subcellular localization prediction.