Skip to main content
. 2019 Apr 8;7:1933. Originally published 2018 Dec 14. [Version 2] doi: 10.12688/f1000research.17363.2

Table 3. The Decision Tree classifier performance for predicting TF targets using the siRNA-generated knockdown data.

TF Excluding DHS information † Including DHS information †
Sensitivity Specificity Accuracy Sensitivity Specificity Accuracy
BATF 0.96 0.97 0.96 0.85 1 0.93
JUND 0.86 0.90 0.88 0.80 1 0.90
NFE2L1 0.92 0.95 0.94 0.71 0.93 0.82
PAX5 0.96 0.97 0.96 0.88 0.98 0.93
POU2F2 0.97 0.97 0.97 0.89 0.99 0.94
RELA 0.95 0.96 0.96 0.83 0.97 0.90
RXRA 0.93 0.91 0.92 0.84 0.95 0.89
SP1 0.98 0.98 0.98 0.89 0.99 0.94
TCF12 0.98 0.98 0.98 0.86 0.99 0.93
USF1 0.97 0.98 0.97 0.83 0.98 0.90
YY1 1 1 1 0.55 0.99 0.77

†The average performance of 10 rounds of 10-fold cross validation is indicated. The accuracy of each individual round is shown in Additional file 5 22. The siRNA-generated knockdown data were obtained from Cusanovich et al. 13.