Table 2. Amino acids sequences dataset list.
Data class | Label | n sequences |
---|---|---|
Training | Positive | 1,038 |
Negative | 5,190 | |
Balanced training | Positive | 1,038 |
Negative | 1,038 | |
Validation | Positive | 1,131 |
Negative | 3,033 | |
Balanced validation | Positive | 1,131 |
Negative | 1,131 | |
Independent (Test) | Positive | 260 |
Negative | 260 |