Table 1.
Pro. Len.—Average and standard deviation of the protein length in the training and test sets of each dataset. Epitope Len.—Number of epitope residues in each protein. Fraction—Fraction of residues in the protein that are in epitopes. Num. of Pro.—number of proteins. Residue epitope—the number of all residues that are in epitopes. Residue non-epitope—the number of residues that are not in epitopes
| Pro. len | Epitope len | Fraction | Num of Pro. | Residue epitope | Residue non-epitope | ||
|---|---|---|---|---|---|---|---|
| Linear | Train |
|
|
|
10 552 | 147 646 | 7078 382 |
| Linear | Test |
|
|
|
1173 | 16 414 | 737 189 |
| Conformational | Train |
|
|
|
1320 | 24 958 | 256 971 |
| Conformational | Test |
|
|
|
146 | 3204 | 25 222 |