Skip to main content

Table 3 Correctly classified proteins by Weka algorithms

From: ProClaT, a new bioinformatics tool for in silico protein reclassification: case study of DraB, a protein coded from the draTGB operon in Azospirillum brasilense

Algorithm

Options

Correctly classified instances without cross-validation

Correctly classified instances with cross-validation

Multilayer Perceptron

-L 0.3 –M 0.2 –N 500 –V 0 –S 0 –E 20 –H a

99.61 %

99.41 %

Simple Cart

-S 1 –M 2.0 –N 5 –C 1.0

99.09 %

99.22 %

Nnge

-G 5 –I 5

99.09 %

99.02 %

J48

-C 0.25 –M 2

98.96 %

98.71 %

Ada BoostM1

-P 100 –S 1 –I 0 –W weka.classifiers.trees. DecisionStump

32.51 %

33.35 %

Naive Bayes

-

99.22 %

98.90 %

  1. Using the default parameters proposed by Weka, the neural network training and test files were submitted to the six algorithms above. MLPNN showed the best number of correctly classified proteins