Table 3.
Pairwise permutation tests between prediction algorithms
| AveRNA | BL-FR∗ | BL∗ | CG∗ | DIM-CG | NOM-CG | CONTRAfold2.0 | CentroidFold | MaxExpect | CONTRAfold1.1 | T99 | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| AveRNA |
|
|
|
|
|
|
|
|
|
|
|
| BL-FR* |
0 |
|
|
|
|
|
|
|
|
|
|
| BL* |
0 |
0 |
|
|
|
|
|
|
|
|
|
| CG* |
0 |
0 |
0.0001 |
|
|
|
|
|
|
|
|
| DIM-CG |
0 |
0 |
0 |
0.0002 |
|
|
|
|
|
|
|
| NOM-CG |
0 |
0 |
0 |
0 |
0 |
|
|
|
|
|
|
| CONTRAfold2.0 |
0 |
0 |
0 |
0 |
0.0001 |
0.4193 |
|
|
|
|
|
| CentroidFold |
0 |
0 |
0 |
0 |
0 |
0.0001 |
0 |
|
|
|
|
| MaxExpect |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
|
|
|
| CONTRAfold1.1 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
|
|
| T99 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.1317 |
P-values obtained from permutation tests to determine the statistical significance of performance differences (in terms of F-measure over the S-STRAND2 dataset) between prediction algorithms. All p-values larger than a standard significance threshold of 0.05 are bolded, indicating cases where the performance differences are insignificant.