GET THE APP

Prelocabc: A Novel Predictor of Protein Sub-cellular Localization Using a Bayesian Classifier | Abstract
Journal of Proteomics & Bioinformatics

Journal of Proteomics & Bioinformatics
Open Access

ISSN: 0974-276X

Abstract

Prelocabc: A Novel Predictor of Protein Sub-cellular Localization Using a Bayesian Classifier

Yanqiong Zhang, Tao Li, Chunyuan Yang, Dong Li, Yu Cui, Ying Jiang, Lingqiang Zhang, Yunping Zhu and Fuchu He

Sub-cellular localization of proteins is crucial for the dynamic life of cells. Its ascertainment is an important step to elucidate proteins' biological functions. Various experimental and computational methods have been developed for this purpose. Using a Bayesian model, we integrated five sub-modules based on different protein features, such as homology, amino acid composition, sorting signals and functional motifs, to predict sub-cellular localization of non-plant eukaryotic protein. This method has higher accuracy and Matthew's correlation coefficient values than previous algorithms against five independent test datasets, and is able to predict efficiently nine major sub-cellular compartments for both single-localized and multiple-localized proteins. As an application, we also combined this method with the proteome mass-spectrum quantitative information, improving the performance of PreLocABC dramatically. This method has been developed into an online prediction system (PreLocABC). Users may submit their protein sequences online, and the prediction results for protein sub-cellular localization will be returned. The web interface of PreLocABC is available at http://61.50.138.123/PreLocABC.

Top