Prediction of Associations Between Nanoparticle, Drug and Cancer Using Variational Graph Autoencoder

Abstract

Predicting implicit drug-disease associations is critical to the development of new drugs, with the aim of minimizing side effects and development costs. Existing drug-disease prediction methods typically focus on either single or multiple drug-disease networks. Recent advances in nanoparticles particularly in cancer research show improvements in bioavailability and pharmacokinetics by reducing toxic side effects. Thus, the interaction of the nanoparticles with drugs and diseases tends to improve during the development phase. In this study, it presents a variational graph autoencoder model to the cell-specific drug delivery data, including the class interactions between nanoparticle, drug, and cancer types as a knowledge base for targeted drug delivery. The cell-specific drug delivery data is transformed into a bipartite graph where relations only exist between sequences of these class interactions. Experimental results show that the knowledge graph enhanced Variational Graph Autoencoder model with VGAE-ROC-AUC (0.9627) and VGAE-AP (0.9566) scores performs better than the Graph Autoencoder model.