LPI-deepGBDT: a multiple-layer deep framework based on gradient boosting decision trees for lncRNA–protein interaction identification

Table 4 Parameter settings

Method	Parameter setting
LPI-BLS	s = 1, c = 10**-10, N1 = 3, N2 = 60, N3 = 900
LPI-CastBoost	learning_rate = 0.5, loss_function = ‘Logloss’
LPI-CastBoost	logging_level = ’Verbose’
PLIPCOM	learning_rate = 0.01, n_estimators = 100
PLIPCOM	min_samples_split = 2, max_depth = 3
LPI-deepGBDT	target_lr = 1.0, epsilon = 0.3, n_rounds=3, d = 100
LPI-deepGBDT	max_depth = 5, num_boost_round = 5, n_epochs = 15

ISSN: 1471-2105