Predicting and Detection of drug side effects based on Graph Attention Network (Preprint)

Abstract

In the last decade, many studies have investigated on predicting the potential side effects of drugs. In general, this study could be divided into two categories; detection and prediction. Detection aims to detect the side effects of existing drugs. In Prediction, the side effects of new drugs are studied. In general, when a new drug enters the drug discovery cycle, its side effects are unknown.

Despite the positive effects of drugs for the prevention, diagnosis, and treatment of diseases, the side effects of some drugs could not be ignored. Many diseases and death are reported annually due to drug side effects. In general, predicting drug side effects using laboratory methods is very costly and time-consuming. On the other hand, these methods are not able to diagnose all the drug side effects due to many limitations.

We attempt to obtain effective embedding for drugs and their probable side effects using the Graph attention network. Furthermore, drug side effects links are predicted using these embedding.

Using semantic and structural properties of drug network has properly increased the prediction and further detection of side effects. The results indicate Area Under Precision-Recall of 0.7258 and 0.7184 on this research dataset, respectively.

Using positive and negative examples in loss function and self-attention deployment in Graph attention network result in more reliable embedding and better accuracy results in prediction. Moreover, the significant effect of embedding in predicting links has been shown in this study.