The dataset used in the article "Evidential Deep Learning for Guided Drug-Target Interaction Prediction"

The file consists of two parts, the first part is the feature file used for model training and the second part is the saved model.

bond_angle file is the feature file for the drugbank dataset, KIBA file is the feature file for the kiba dataset, davis is the feature file for the davis dataset. case_drugbank is the dungbank feature file for the independent test set and case_len_drug is the feature file for the patent validation dataset in the TKIs feature file.len_vs is the feature file for TKIs virtual screening dataset.

In the runs folder, the models saved by random division on the Drugbank, KIBA, and Davis datasets are stored.

The bert_weights_encoderMedium_10.h5 is the parameter for the small molecule pre-training model, MG-BERT.