Luiz C. Borro, Stanley R.M. Oliveira, Michel E.B. Yamagishi, Adaulto L. Mancini, José G. Jardine, Ivan Mazoni, Roberto H. Higa, Paula R. Kuser, Goran Neshich, Edgard H. dos Santos
Published: March 31, 2006
Genet. Mol. Res. 5 (1) : 193-202

Cite this Article:
L.C. Borro, S.R.M. Oliveira, M.E.B. Yamagishi, A.L. Mancini, J.G. Jardine, I. Mazoni, R.H. Higa, P.R. Kuser, G. Neshich, E.H. dos Santos (2006). Predicting enzyme class from protein structure using Bayesian classification. Genet. Mol. Res. 5(1): 193-202.

About the Authors
Luiz C. Borro, Stanley R.M. Oliveira, Michel E.B. Yamagishi, Adaulto L. Mancini, José G. Jardine, Ivan Mazoni, Roberto H. Higa, Paula R. Kuser, Goran Neshich, Edgard H. dos Santos

Corresponding author
M.E.B. Yamagishi
E-mail: michel@cbi.cnptia.embrapa.br

ABSTRACT

Predicting enzyme class from protein structure parameters is a challenging problem in protein analysis. We developed a method to predict enzyme class that combines the strengths of statistical and data-mining methods. This method has a strong mathematical foundation and is simple to implement, achieving an accuracy of 45%. A comparison with the methods found in the literature designed to predict enzyme class showed that our method outperforms the existing methods.

Key words: Protein function prediction, Protein structure, Naive Bayes, Enzyme classification number, Bayesian classifier, Data classification.