Using motifs in the prediction of eukaryotic protein subcellular localization

Author

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

Author_Institution

Dept. of Electron. Sci. & Technol., Univ. of Sci. & Technol. of China, Hefei

fYear

2006

Firstpage

2802

Lastpage

2804

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

Keywords

biology computing; cellular biophysics; molecular biophysics; molecular configurations; proteins; LOCSVMPSI; PROSITE; eukaryotic protein subcellular localization prediction; Accuracy; Amino acids; Bioinformatics; Biology; Data mining; Extracellular; Nuclear power generation; Proteins; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2005. IEEE-EMBS 2005. 27th Annual International Conference of the

Conference_Location

Shanghai

Print_ISBN

0-7803-8741-4

Type

conf

DOI

10.1109/IEMBS.2005.1617055

Filename

1617055