Table 4 The performance of traditional machine learning model on the fivefold cross -validation
From: Identification of plant vacuole proteins by using graph neural network and contact maps
Model | Acc (%) | F1-score | Sp (%) | Sn (%) | MCC | ROC-AUC | PR-AUC |
|---|---|---|---|---|---|---|---|
GaussianNB | 60.00 | 0.6163 | 54.46 | 65.02 | 0.1971 | 0.6096 | 0.7010 |
LR | 58.25 | 0.5791 | 58.45 | 57.80 | 0.1625 | 0.6141 | 0.6099 |
RF | 60.75 | 0.5980 | 63.07 | 58.44 | 0.1503 | 0.6127 | 0.5868 |
SVM | 54.50 | 0.5678 | 58.96 | 55.99 | 0.2166 | 0.5925 | 0.5427 |
LightGBM | 65.23 | 0.6868 | 70.43 | 67.85 | 0.3838 | 0.5809 | 0.5429 |
GBDT | 57.25 | 0.6569 | 67.38 | 65.05 | 0.3253 | 0.5751 | 0.5754 |
MLP | 52.50 | 0.4934 | 57.43 | 47.07 | 0.0447 | 0.5650 | 0.5462 |
KNN | 56.50 | 0.5189 | 59.02 | 49.68 | 0.0869 | 0.5722 | 0.8100 |
XGBoost | 56.50 | 0.5015 | 64.28 | 45.89 | 0.1043 | 0.6504 | 0.8100 |