Prediction of Protein Subcellular Localization Using EDA based Ensemble Classifiers

Full Text (PDF, 186KB), PP.8-13

Views: 0 Downloads: 0


Ying Li 1,*

1. School of Information Technology, Shandong Women's University, Jinan, Shandong Province, China

* Corresponding author.


Received: 27 Aug. 2011 / Revised: 29 Sep. 2011 / Accepted: 3 Nov. 2011 / Published: 5 Dec. 2011

Index Terms

Protein subcellular location, Estimation of Distribution Algorithm (EDA), selective ensemble, Pseudo amino acid composition


The function of protein is closely correlated with its subcellular locations. New composed proteins can perform normal biological function only after they are translocated to correct subcellular locations. In this paper, a new selective ensemble classifiers based on EDA algorithm has been proposed. In the method, pseudo amino acid composition was firstly applied to form the protein feature sets, then 10 neural networks is generated to learn the subsets which are re-sampling from feature subsets with PSO algorithm. At last, appropriate classifiers are selected to construct the prediction committee with EDA algorithm. Experiment shows that the proposed method produces the best prediction accuracy than the other methods on SNL6 database.

Cite This Paper

Ying Li,"Prediction of Protein Subcellular Localization Using EDA based Ensemble Classifiers", IJEM, vol.1, no.6, pp.8-13, 2011. DOI: 10.5815/ijem.2011.06.02


[1] Fujiwara Y,Asogawa M.Prediction of subcellular localization using amino acid composition and order[J].Genome Informatics,2001,12:103-112 

[2] Mullar R H,Karsten M,Sven G.Solid lip id nanoparticles for controlled drug delivery2a review of the state or the art[J].Eur J Pharm B iopharm,2000,50(1):161-177.

[3] Nakaia K,Kanehisa M.A knowledge base for predicting protein localization sites in eukaryotic cells[J].Genomics,1992,14:897-911.

[4] Yuan Z.Prediction of protein subcellar location using Markov chain models[J].FEB S Letter,1999,451:23-26.

[5] Renhardt A,Hubbard T.Using neural networks for prediction of the subcellular location of proteins[J].Nucleic Acids Research,1998,26,2230-2236.

[6] Hua S,Sun Z.Support vector machine approach for protein subcellular localization prediction[J].Bioinformatics,2001,17:721-728

[7] Nakashima H,Nishikawa K.Discrimination of intracellular and ex-tracellular proteins using amino acid composition and residue – pair frequencies[J].J Mol Boil,1994,238:54-61.

[8] Chou K C.Prediction of protein cellular attributes using pseudo amino acid composition[J].Protein Struct. Funct. Genet,2001,43:246-255.

[9] Chou Z H,Wu J,Tang W.Ensembling neural networks: many could be better than all.Artificial Intelligence,2002,137(1-2):239-263

[10] Larranaga P, Lozano J A.Estimation of distribution algorithms:A new tool for Evolutionary Computation[M].Berlin:Kluwer Academic Publishers,2002 

[11] Lei Z,Dai Y.An SVM-based system for predicting protein subnuclear localization[J].BMC Bioinformatics,2005,6:291-298.

[12] Huang W L,Tung C W,Huang H L,et al.ProLoc:prediction of protein subnuclear localization using SVM with automatic selection from physico-chemical composition features[J].Biosystems,2007,90(2):573-581