Table 4 Effect of different numbers of CNN layers on the performance of the model
From: iProL: identifying DNA promoters from sequence information based on Longformer pre-trained model
Model | Sn(%) | Sp(%) | Acc(%) | MCC | AUC |
|---|---|---|---|---|---|
CNN ×0 | 82.55 | 87.14 | 84.85 | 0.6981 | 0.9140 |
CNN ×1 | 84.12 | 86.72 | 85.42 | 0.7095 | 0.9196 |
CNN ×2 | 84.00 | 86.40 | 85.20 | 0.7048 | 0.9198 |
CNN ×3 (iProL) | 84.62 | 86.61 | 85.62 | 0.7130 | 0.9211 |