Method | Parameter setting |
---|---|
LPI-NRLMF | Cfix = 5, num_factors = 10, K1 = 5, max_iter = 100 |
Lambda_t = 0.625, alpha = 0.1, beta = 0.1 | |
K2=5, theta = 1.0, lambda_d = 0.625 | |
Capsule-LPI | EPOCH = 30, lr = 0.001, BATCH_SIZE = 100 |
LPI-CNNCP | Filters1 = 24, kernel_size1 = (49, 10) |
Kernel_size2 = (64, 10), strides2 = (1, 3) | |
Strides1 = (1, 1), filters2 = 24 | |
LPI-HyADBS | DNN: Adam(model.parameters(), lr = 0.0001), |
Loss_fn=BCELoss(), batch = 128, epochs = 100 | |
XGBoost: learning_rate = 0.1, n_estimators = 100 | |
Objective =“binary:logistic”, max_depth = 6 | |
C-SVM: kernel=“rbf”, gamma = “auto”, | |
Probability = True, colsample_btree = 0.8 | |
\(\alpha =0.4\), \(\beta = 0.3\), \(\theta = 0.3\) | |
LPLNP | Neighbor_num = [6, 23, 100, num of lncRNA-100, 100], |
Regulation = ’regulation2’, alpha = [0.5, 0.3, 0.7, 0.1, 0.9] |