GCNMDA: A novel Graph Convolution Network based framework for predicting Microbe-Drug Associations.
- adj: interaction pairs between microbes and drugs.
- drugs: IDs and names for drugs.
- microbes/viruses: IDs and names for microbes/viruses.
- drugfeatures: pre-processing feature matrix for drugs.
- microbefeatures: pre-processing feature matrix for microbes.
- drugsimilarity: integrated drug similarity matrix.
- microbesimilarity: integrated microbe similarity matrix.
- To generate training data and test data.
- Run train.py to train the model and obtain the predicted scores for microbe-drug associations.
- GCNMDA is implemented to work under Python 3.7.
- Tensorflow
- numpy
- scipy
- sklearn