Research Article
CirBiTree: Citrullination Site Inference Based on a Fuzzy Neural Network and Flexible Neural Tree
Table 3
The performances of different features in length 17.
| Features | Sn (%) | Sp (%) | F1 | MCC |
| Binary encoding | 55.51 | 74.89 | 0.6146 | 0.3099 | AA composition | 64.63 | 62.28 | 0.6388 | 0.2691 | Grouping AA composition | 71.63 | 71.39 | 0.7154 | 0.4301 | Physicochemical properties | 74.88 | 72.33 | 0.7394 | 0.4723 | KNN features | 73.69 | 64.62 | 0.7049 | 0.3847 | Secondary tendency structure | 69.52 | 76.49 | 0.7203 | 0.4612 | PSSM | 70.44 | 77.23 | 0.7291 | 0.4778 | BPB | 72.52 | 76.99 | 0.7418 | 0.4956 | Proposed algorithm | 80.09 | 78.86 | 0.7960 | 0.5896 |
|
|