Table 8.
Performance benchmark with the Remark 465 dataset under parameters that produced the highest Matthews Correlation Coefficient (MCC).
| Method | threshold | sensitivity | specificity | MCC | PE |
|---|---|---|---|---|---|
| DISOPRED2 | 0.09 | 0.433 | 0.937 | 0.388 | 0.370 |
| DisEMBL Rem465 | 1 | 0.316 | 0.958 | 0.338 | 0.274 |
| IUPred short | 0.49 | 0.421 | 0.914 | 0.328 | 0.335 |
| IUPred long | 0.53 | 0.355 | 0.921 | 0.284 | 0.276 |
| CAST | 24 | 0.349 | 0.887 | 0.218 | 0.235 |
| DisEMBL Coils | 1.9 | 0.290 | 0.907 | 0.200 | 0.198 |
| DisEMBL Hotloops | 2.9 | 0.217 | 0.944 | 0.198 | 0.161 |
| SEG25 | 2.95;3.25 | 0.229 | 0.935 | 0.191 | 0.164 |
| SEG12 | 1.95;2.25 | 0.065 | 0.994 | 0.170 | 0.059 |
| SEG45 | 3.30;3.60 | 0.192 | 0.942 | 0.166 | 0.134 |
Predictors were run and ranked as described in Table 7 but over the Remark 465 dataset including parameter optimization for this dataset with focus on short disorder.