Table 4. Assessment of the performance of the optimized CDF model for various datasets.
Sample ratio = 1:1 (mean±S.D) | Sample ratio = 1:10 (mean±S.D) | |||||||
---|---|---|---|---|---|---|---|---|
Activatory DTIs | Inhibitory DTIs | Activatory DTIs | Inhibitory DTIs | |||||
AUROC | AUPR | AUROC | AUPR | AUROC | AUPR | AUROC | AUPR | |
Original dataset | 0.880±0.029 | 0.899±0.019 | 0.935±0.003 | 0.946±0.003 | 0.873±0.007 | 0.629±0.033 | 0.939±0.004 | 0.780±0.007 |
Additional dataset | 0.873±0.011 | 0.869±0.013 | 0.953±0.002 | 0.957±0.002 | 0.864±0.012 | 0.430±0.030 | 0.955±0.002 | 0.800±0.008 |
Separate model* | 0.875±0.011 | 0.878±0.011 | 0.944±0.002 | 0.952±0.002 | 0.867±0.009 | 0.488±0.022 | 0.947±0.002 | 0.790±0.004 |
Integrated model# | 0.875±0.010 | 0.881±0.008 | 0.943±0.002 | 0.951±0.001 | 0.869±0.008 | 0.489±0.023 | 0.946±0.002 | 0.786±0.005 |
Boldface indicates the highest value for each performance metric between the separate model and integrative model.
*Models trained on the original and additional datasets separately.
#Models trained on an integrated dataset.