Identification of Human Enzymes Using Amino Acid Composition and the Composition of -Spaced Amino Acid Pairs

Table 2

Comparison of the performance of various mainstream classifiers and the classifier implemented in our paper. ACC, SP, and SE of different classifiers on both the training set and the test set are compared.

Classifiers	Training set			Test set
	ACC	SP	SE	ACC	SP	SE
This work (SVM)	76.2135%	0.753	0.676	76.4585%	0.762	0.657
Naive Bayes	61.0697%	0.466	0.833	65.7625%	0.507	0.794
Random Forest	74.3781%	0.703	0.454	74.7691%	0.710	0.472
Logistic	69.5274%	0.598	0.374	68.4237%	0.587	0.329
KNN	62.8420%	0.474	0.646	63.0502%	0.480	0.658
Ensembles for Boosting	69.6206%	0.588	0.420	68.6796%	0.573	0.411