A Disease-Drug Interaction Prediction Framework Based on Knowledge Graph and Graph Contrastive Learning for Recommendation System

Prediction of disease-drug interactions(DDIs) plays a vital role in drug development in various areas, such as precision medicine, drug development and overcoming the issue of drug resistance. Despite continuous advancements in methods for predicting disease-drug interactions(DDIs) and the achievement of promising results, current approaches are still limited by issues related to the homogeneity of data and the consistency of vector representations. Firstly, DDI prediction should consider a variety of heterogeneous relationships, such as drug-protein associations and drug-induced side effects in patients. These diverse relationships can help uncover potential associations between diseases and drugs. Secondly, neglecting the issue of inconsistency in vector representations within heterogeneous network embeddings may affect the accuracy of capturing relationships and similarities between entities. Here, we develop KGE GCLR, a framework for DDIs prediction by combining knowledge graph(KG) and graph contrastive learning for recommendation system. This framework firstly learns a low-dimensional representation for various entities in the KG, and then under the paradigm of graph contrastive learning provided to integrate heterogeneous auxiliary information into the recommendation system(GCLR). The KGE GCLR was evaluated in realistic scenarios, and achieved accurate and robust predictions on two benchmark datasets. Our results indicate that the KGE GCLR, by addressing the inconsistency challenges in embedding heterogeneous networks, provides valuable insights for integrating knowledge graph data and recommendation system-based techniques into a framework, thereby enhancing the predictive capabilities for disease-drug association discovery.