Research Article
CirBiTree: Citrullination Site Inference Based on a Fuzzy Neural Network and Flexible Neural Tree
Table 7
The performances of different features in length 21.
| Features | Sn (%) | Sp (%) | F1 | MCC |
| Binary encoding | 57.25 | 77.00 | 0.6352 | 0.3493 | AA composition | 65.01 | 63.51 | 0.6452 | 0.2852 | Grouping AA composition | 72.31 | 72.11 | 0.7224 | 0.4443 | Physicochemical properties | 75.80 | 74.22 | 0.7521 | 0.5003 | KNN features | 75.35 | 66.29 | 0.7208 | 0.4181 | Secondary tendency structure | 70.49 | 78.43 | 0.7340 | 0.4907 | PSSM | 72.12 | 79.41 | 0.7485 | 0.5167 | BPB | 72.92 | 78.56 | 0.7504 | 0.5157 | Proposed algorithm | 83.07 | 80.50 | 0.8201 | 0.6359 |
|
|