Skip to main content
. 2018 Nov 20;19(Suppl 14):418. doi: 10.1186/s12859-018-2386-9

Table 5.

Area under the ROC curve performances on the first group of dataset

N_score [16] NuPop [17] NucEnergEN [14] Segal [10] Field [11] Kaplan [12] Heijden [13] Finestr [15] DLNN-3 DLNN-5
HM-LC ∼0.65 (0.6,0.65) (0.6,0.65) (0.35,0.4) ∼0.65 ∼0.65 ∼0.6 (0.6, 0.65) 0.79 0.81
DM-LC 0.59 (0.65,0.70) ∼0.7 0.33 (0.70,0.75) (0.70,0.75) (0.65,0.70) 0.57 0.71 0.71
YS-WG 0.77 0.74 (0.65,0.70) 0.49 0.77 ∼0.7 ∼0.65 ∼0.7 0.79 0.83
HM-PM (0.6,0.65) 0.67 (0.6,0.65) (0.4,0.45) (0.6,0.65) ∼0.6 ∼0.55 ∼0.55 0.77 0.77
DM-PM 0.62 ∼0.7 (0.70,0.75) 0.32 (0.70,0.75) (0.70,0.75) (0.55,0.6) (0.5,0.55) 0.72 0.73
YS-PM 0.70 0.74 (0.7,0.75) 0.52 0.79 (0.7,0.75) ∼0.65 ∼0.7 0.73 0.83
HM-5U (0.55,0.6) ∼0.65 ∼0.7 0.37 ∼0.65 ∼0.65 ∼0.6 (0.55,0.6) 0.67 0.68
DM-5U 0.54 (0.6,0.65) (0.65,0.70) 0.38 (0.65,0.70) (0.65,0.70) (0.55,0.6) ∼0.5 0.66 0.67

Each column refers to a computational method for nucleosome positioning. The rst eight column show the values reported in the paper by Liu et al. [47], sometimes with approximate values (interval range or close to symbol”). Last two columns regard our proposed method. Best values are in bold