Table 3.
Performance evaluation for bioinformatics databases
| Group truth dataset used (AUC) | ||||||||
|---|---|---|---|---|---|---|---|---|
| Mode | Method | A549 | CD8T | Hela | HEK293 (sysy) | HEK293 (abacm) | MOLM13 | Average AUC |
| Full Transcript | RMBase | 0.825 | 0.788 | 0.832 | 0.837 | 0.701 | 0.733 | 0.786 |
| MetDB | 0.835 | 0.802 | 0.843 | 0.848 | 0.719 | 0.744 | 0.798 | |
| Mature mRNA | RMBase | 0.768 | 0.716 | 0.790 | 0.752 | 0.707 | 0.682 | 0.736 |
| MetDB | 0.775 | 0.730 | 0.795 | 0.762 | 0.716 | 0.683 | 0.744 | |
Note: To ensure the results are comparable to Table 2, only the unique sites not previously reported in the training data of predictors were considered. Please see Supplementary Table S4 for the results when all sites from the independent testing samples were considered.