Research Article
CirBiTree: Citrullination Site Inference Based on a Fuzzy Neural Network and Flexible Neural Tree
Table 1
The performances of different features in length 15.
| Features | Sn (%) | Sp (%) | F1 | MCC |
| Binary encoding | 55.36 | 75.25 | 0.6147 | 0.3123 | AA composition | 62.87 | 60.53 | 0.6214 | 0.2341 | Grouping AA composition | 68.33 | 71.94 | 0.6959 | 0.4030 | Physicochemical properties | 72.06 | 73.04 | 0.7241 | 0.4510 | KNN features | 74.37 | 65.70 | 0.7128 | 0.4023 | Secondary tendency structure | 66.47 | 77.09 | 0.7019 | 0.4380 | PSSM | 67.75 | 76.75 | 0.7095 | 0.4469 | BPB | 71.06 | 76.29 | 0.7297 | 0.4741 | Proposed algorithm | 78.19 | 79.28 | 0.7862 | 0.5747 |
|
|