an end-to-end deep learning-based method named IIFDTI is developed to predict DTIs based on independent features of drug-target pairs and interactive features of their substructures.
- python >= 3.5
- torch >= 1.4.0
- RDkit >= 2019.03.30
- gensim >= 3.4.0
- numpy >= 1.16.1
- pandas >= 1.1.4
- transformers >= 3.1.0
- model.py: the construction of the neural network
- data_preprocess: Process the data to get the input of the model
- main.py: start file for model training
if you have any questions or suggestions with the codes, please let us know, Contact Zhongjian Cheng at zj_cheng@qq.com