Skip to main content

Table 3 Results of an enhancer classification trial (trial 9 in Table 4) on the independent test dataset

From: iEnhancer-ECNN: identifying enhancers and their strength using ensembles of convolutional neural networks

Training : Validation (Ratio 4:1) ACC (%) AUC (%) SN(%) SP (%) MCC
Model 1 (Parts 2, 3, 4, 5 : Part 1) 0.700 0.764 0.780 0.620 0.405
Model 2 (Parts 1, 3, 4, 5 : Part 2) 0.660 0.740 0.720 0.600 0.322
Model 3 (Parts 1, 2, 4, 5 : Part 3) 0.670 0.730 0.850 0.490 0.364
Model 4 (Parts 1, 2, 3, 5 : Part 4) 0.665 0.715 0.660 0.670 0.330
Model 5 (Parts 1, 2, 3, 4 : Part 5) 0.600 0.681 0.680 0.520 0.203
Ensemble Model 0.695 0.759 0.840 0.550 0.408
  1. The highest value for each metric is in bold