Table 3.
Step | Representation | Dataset | Classifier | Micro-metrics (averaged over samples) |
Macro-metrics (averaged over classes) |
||||
---|---|---|---|---|---|---|---|---|---|
Precision | Recall | F1 | Precision | Recall | F1 | ||||
(ii) | 3-mers | ECO-18K | RF | 0.6 ± 0.01 | 0.6 ± 0.01 | 0.6 ± 0.01 | 0.63 ± 0.02 | 0.6 ± 0.01 | 0.57 ± 0.01 |
4-mers | 0.67 ± 0.01 | 0.67 ± 0.01 | 0.67 ± 0.01 | 0.7 ± 0.01 | 0.67 ± 0.01 | 0.65 ± 0.01 | |||
5-mers | 0.72 ± 0.01 | 0.72 ± 0.01 | 0.72 ± 0.01 | 0.74 ± 0.01 | 0.72 ± 0.01 | 0.71 ± 0.01 | |||
6-mers | 0.75 ± 0.01 | 0.75 ± 0.01 | 0.75 ± 0.01 | 0.76 ± 0.01 | 0.75 ± 0.01 | 0.73 ± 0.01 | |||
7-mers | 0.74 ± 0.01 | 0.74 ± 0.01 | 0.74 ± 0.01 | 0.76 ± 0.01 | 0.74 ± 0.01 | 0.73 ± 0.01 | |||
8-mers | 0.72 ± 0.01 | 0.72 ± 0.01 | 0.72 ± 0.01 | 0.74 ± 0.01 | 0.72 ± 0.01 | 0.71 ± 0.01 | |||
(ii) | 3-mers | 5GUTS-3100 | RF | 0.8 ± 0.02 | 0.8 ± 0.02 | 0.8 ± 0.02 | 0.8 ± 0.02 | 0.8 ± 0.02 | 0.79 ± 0.02 |
4-mers | 0.84 ± 0.01 | 0.84 ± 0.01 | 0.84 ± 0.01 | 0.84 ± 0.01 | 0.84 ± 0.01 | 0.83 ± 0.01 | |||
5-mers | 0.86 ± 0.02 | 0.86 ± 0.02 | 0.86 ± 0.02 | 0.86 ± 0.02 | 0.86 ± 0.02 | 0.85 ± 0.02 | |||
6-mers | 0.87 ± 0.01 | 0.87 ± 0.01 | 0.87 ± 0.01 | 0.87 ± 0.01 | 0.87 ± 0.01 | 0.87 ± 0.01 | |||
7-mers | 0.87 ± 0.01 | 0.87 ± 0.01 | 0.87 ± 0.01 | 0.88 ± 0.02 | 0.87 ± 0.01 | 0.87 ± 0.01 | |||
8-mers | 0.86 ± 0.01 | 0.86 ± 0.01 | 0.86 ± 0.01 | 0.87 ± 0.01 | 0.86 ± 0.01 | 0.86 ± 0.01 | |||
(iv) | 6-mers | ECO-18K | RF | 0.75 ± 0.01 | 0.75 ± 0.01 | 0.75 ± 0.01 | 0.76 ± 0.01 | 0.75 ± 0.01 | 0.73 ± 0.01 |
SVM | 0.79 ± 0.01 | 0.79 ± 0.01 | 0.79 ± 0.01 | 0.79 ± 0.01 | 0.79 ± 0.01 | 0.79 ± 0.01 | |||
DNN-3L | 0.78 ± 0.01 | 0.78 ± 0.01 | 0.78 ± 0.01 | 0.78 ± 0.01 | 0.78 ± 0.01 | 0.78 ± 0.01 | |||
(iv) | 6-mers | 5GUTS-3100 | RF | 0.87 ± 0.01 | 0.87 ± 0.01 | 0.87 ± 0.01 | 0.87 ± 0.01 | 0.87 ± 0.01 | 0.87 ± 0.01 |
SVM | 0.88 ± 0.02 | 0.88 ± 0.02 | 0.88 ± 0.02 | 0.89 ± 0.01 | 0.88 ± 0.02 | 0.88 ± 0.02 | |||
DNN-5L | 0.87 ± 0.01 | 0.87 ± 0.01 | 0.87 ± 0.01 | 0.87 ± 0.01 | 0.87 ± 0.01 | 0.87 ± 0.01 | |||
(iv) | 6-mers | ECO-180K | RF | 0.83 ± 0.0 | 0.83 ± 0.0 | 0.83 ± 0.0 | 0.84 ± 0.0 | 0.83 ± 0.0 | 0.83 ± 0.0 |
(10× larger) | SVM | 0.86 ± 0.0 | 0.86 ± 0.0 | 0.86 ± 0.0 | 0.87 ± 0.01 | 0.86 ± 0.0 | 0.86 ± 0.0 | ||
DNN-5L | 0.88 ± 0.0 | 0.88 ± 0.0 | 0.88 ± 0.0 | 0.88 ± 0.0 | 0.88 ± 0.0 | 0.88 ± 0.0 |
Note: The classifiers (Random Forest, Support Vector Machine and neural network classifiers) are tuned and evaluated in a stratified 10×fold cross-validation setting in three datasets ECO-18K, 5GUTS-3100 and ECO-180K. The step column refers to the steps in Figure 3.