Table 2. The Decision Tree classifier performance for predicting TF targets using the CRISPR-generated knockdown data.

TF	Excluding DHS information †			Including DHS information †
	Sensitivity	Specificity	Accuracy	Sensitivity	Specificity	Accuracy
EGR1	0.58	0.62	0.60	0.78	0.81	0.80
ELF1	0.59	0.65	0.62	0.83	0.87	0.85
ELK1	0.59	0.59	0.59	0.80	0.81	0.81
ETS1	0.59	0.6	0.59	0.81	0.81	0.81
GABPA	0.55	0.57	0.56	0.72	0.75	0.74
IRF1	0.54	0.55	0.54	0.76	0.64	0.70
YY1	0.50	0.51	0.51	0.45	0.69	0.57

†The average performance of 10 rounds of 10-fold cross validation when setting ε to 1.05 is indicated. The accuracy of each individual round is indicated in Additional file 5 ²². The CRISPR-generated knockdown data were obtained from Dixit et al. ¹⁶.