Prediction of drug-target interactions based on multi-layer network representation learning

The prediction of drug-target interactions aims to identify potential targets for the treatment of new and rare diseases. The large number of unknown combinations between drugs and targets makes them difficult to verify with experimental methods. There are computational methods that predict drug-target interactions; however, these methods are insufficient in integrating multiple types of data and managing network noise, which affects the accuracy of the prediction. We report a multilayer network representation learning method for drug-target interaction prediction that can integrate useful information from different networks, reduce noise in the multilayer network, and learn the feature vectors of drugs and targets. The feature vectors of the drug and the target are put into the drug-target space to predict the potential drug-target interactions. This work improves the method of multilayer network representation learning and prediction accuracy by increasing the parameter regularization constraints.