Table 4 Model tuning. Best hyper-parameters
From: A machine learning approach for predicting methionine oxidation sites
Feature set | RF | SVM | NN | |||
|---|---|---|---|---|---|---|
| Â | mtry | Number of trees | Sigma | C | Size | Decay |
Primary | 7 | 1000 | 0.01124415 | 8 | 15 0.003162278 | |
Tertiary | 4 | 1000 | 0.04226239 | 8 | 3 | 0.0001995262 |
Whole | 8 | 1000 | 0.007670497 | 4 | 1 | 0.001584893 |
mRMR | 7 | 1000 | 0.01050984 | 4 | 19 | 0.001584893 |