Research Article
Analysis of DNA Sequence Classification Using CNN and Hybrid Models
Table 3
Models performance concerning different class with Label and
-mer encoding.
| Model class | Label encoding | -mer encoding | a | b | c | d | e | f | a | b | c | d | e | f |
| CNN | Accuracy | 0.93 | 0.99 | 0.92 | 0.99 | 0.99 | 0.99 | 0.93 | 0.99 | 0.93 | 0.99 | 0.99 | 0.99 | Precision | 0.90 | 0.97 | 0.77 | 0.99 | 1.00 | 0.99 | 0.89 | 0.97 | 0.94 | 1.00 | 0.99 | 0.99 | F1 | 0.94 | 0.93 | 0.5 | 0.99 | 0.99 | 0.99 | 0.94 | 0.96 | 0.49 | 0.99 | 0.99 | 0.99 | Sensitivity | 0.98 | 0.90 | 0.37 | 0.99 | 0.99 | 0.99 | 0.99 | 0.96 | 0.33 | 0.99 | 0.99 | 0.99 | Specificity | 0.86 | 0.99 | 0.98 | 0.99 | 1.00 | 0.99 | 0.84 | 0.99 | 0.99 | 1.00 | 0.99 | 0.99 |
| CNN-LSTM | Accuracy | 0.93 | 0.99 | 0.92 | 0.99 | 1.00 | 0.99 | 0.93 | 0.99 | 0.93 | 0.99 | 0.99 | 0.99 | Precision | 0.89 | 0.98 | 0.82 | 0.99 | 1.00 | 0.99 | 0.89 | 0.94 | 0.93 | 0.98 | 0.99 | 0.99 | F1 | 0.94 | 0.95 | 0.49 | 0.99 | 1.00 | 0.99 | 0.94 | 0.95 | 0.48 | 0.99 | 0.99 | 0.99 | Sensitivity | 0.98 | 0.93 | 0.35 | 0.99 | 1.00 | 0.99 | 0.99 | 0.96 | 0.32 | 0.99 | 0.99 | 0.99 | Specificity | 0.85 | 0.99 | 0.99 | 0.99 | 1.00 | 0.99 | 0.84 | 0.99 | 0.99 | 0.99 | 0.99 | 0.99 |
| CNN-bidirectional LSTM | Accuracy | 0.93 | 0.99 | 0.92 | 0.99 | 0.99 | 0.99 | 0.93 | 0.99 | 0.93 | 0.99 | 0.99 | 0.99 | Precision | 0.89 | 0.95 | 0.84 | 0.93 | 0.98 | 0.99 | 0.89 | 0.98 | 0.94 | 0.99 | 0.99 | 0.99 | F1 | 0.94 | 0.82 | 0.40 | 0.96 | 0.99 | 0.99 | 0.94 | 0.96 | 0.48 | 0.99 | 0.99 | 0.99 | Sensitivity | 0.99 | 0.72 | 0.26 | 0.99 | 0.99 | 0.99 | 0.99 | 0.95 | 0.33 | 0.99 | 0.99 | 0.99 | Specificity | 0.84 | 0.99 | 0.99 | 0.99 | 0.99 | 0.99 | 0.84 | 0.99 | 0.99 | 0.99 | 0.99 | 0.99 |
|
|