Table 5.

Hyperparameters of machine learning algorithms in predicting the TMB group.

Algorithm	Optimal Hyperparameters
Logistic Regression	solver = ‘saga’, C = 2.015990003658406, penalty = ‘l1’
Random Forest	‘n_estimators’ = 5, ‘min_samples_split’ = 6, ‘min_samples_leaf’ = 3, ‘max_features’ = ‘auto’, ‘max_depth’ = 30, ‘bootstrap’ = False
Support Vector Machine	kernel = ’rbf’, gamma = 1 × 10−4, C = 10
Linear Discriminant Analysis	solver = ‘svd’
Light GBM	learning_rate = 0.005, num_leaves = 15, max_depth = 25, min_data_in_leaf = 15, feature_fraction = 0.6, bagging_fraction = 0.6
XGBoost	max_depth = 1, gamma = 9, colsample_bytree = 0.5, min_child_weight = 1