Prediction of drug’s Anatomical Therapeutic Chemical (ATC) code by integrating drug–domain network

Display Omitted Predicting ATC code of drugs can provide valuable clues for drug repositioning.We discover important biological similarity features related to drugs and ATC codes.We propose a dD-Hybrid method to predict the unlabeled drug ATC-code pairs.Our method integrates drug-domain interaction network.Our hypothesis is domain is connected with a group of drugs sharing the same ATC code. Predicting Anatomical Therapeutic Chemical (ATC) code of drugs is of vital importance for drug classification and repositioning. Discovering new association information related to drugs and ATC codes is still difficult for this topic. We propose a novel method named drugdomain hybrid (dD-Hybrid) incorporating drugdomain interaction network information into prediction models to predict drugs ATC codes. It is based on the assumption that drugs interacting with the same domain tend to share therapeutic effects. The results demonstrated dD-Hybrid has comparable performance to other methods on the gold standard dataset. Further, several new predicted drug-ATC pairs have been verified by experiments, which offer a novel way to utilize drugs for new purposes effectively.