Prediction of protein-protein interaction types using association rule based classification

BMC Bioinformatics

Table 4 Accuracy for difference classification methods

Method ^a	DT	RF	KNN	SVM	NB
All data ¹ :
ARBC ^b	0.924	0.968	0.943	0.999	0.476
CW AR ^c	0.926	0.971	0.978	0.999	0.531
UR ^d	0.873	0.933	0.893	0.970	0.519
No SSE data ² :
ARBC_WO_SSE ^e	0.917	0.951	0.936	0.992	0.451
CW AR_WO_SSE ^f	0.927	0.970	0.979	0.988	0.492
UR_WO_SSE ^g	0.800	0.850	0.800	0.890	0.483

^aMethod represents different classification methods such as Decision Tree (DT), Random Forest (RF), K Nearest Neighbor(KNN), Support Vector Machine (SVM) and Naive Bayes (NB);
^bARBC: Association rule based classification;
^cCW AR: Classification based on physicochemical properties;
^dUR: ARBC classification using 58 unique association rules;
^{e, f, g}: Data sets with exclusion of SSE content from All data¹;
¹All data: Data sets including SSE content;
²No SSE data: Data sets without inclusion of SSE content.

ISSN: 1471-2105