Table 3.

Resulting performance measures when only sub-datasets corresponding to indices in the optimal sets were used in the classification tasks

Dataset	F1	Sn	Sp	PPV	ACC	AUC	MCC	#indices used (of 102 total)	#features used (of 1428 total)
Acetylation	0.87a	0.82	0.93	0.93	0.87	0.90a	0.76a	71	994
Phosphorylation	0.89a	0.81a	1.00	0.99	0.90a	0.92	0.82a	31	434
Ubiquitylation	0.86	0.81	0.92	0.93a	0.87	0.90	0.74a	86	1204

The maximum possible value for all measures is 1

^aSignificantly increased (t-test, α < 0.05) when compared with the use of all 102 indices