Predicting drug-drug interactions using heterogeneous graph neural networks: HGNN-DDI

Abstract

This research centers on predicting drug-drug interactions (DDIs) using a novel approach involving graph neural networks (GNNs) with integrated attention mechanisms. In this method, drugs and proteins are depicted as nodes within a heterogeneous graph. This graph is characterized by different types of edges symbolizing not only DDIs but also drug-protein interactions (DPIs) and protein-protein interactions (PPIs). To analyze the chemical structures of drugs, we employ a pretrained model named ChemBERTa, which utilizes simplified molecular input line entry system (SMILES) strings. The similarity between drug structures based on their SMILES strings is determined using the RDkit tool. Our model is designed to establish and link heterogeneous graph neural networks, taking into account the DPIs and PPIs as key input data. For the final prediction of interaction types between various drugs, we use the Multi-Layer Perception (MLP) technique. This model's primary objective is to enhance the accuracy of DDI predictions by factoring in additional data on both drug-protein and protein-protein interactions. The forecasted DDIs are presented with associated probabilities, offering valuable insights to healthcare professionals. These insights are crucial for assessing the potential risks and advantages of combining different drugs, particularly for patients with diseases at different stages of progression.