KGCNA-CNN-BiLSTM：Knowledge graph and hybrid neural networks for drugs association prediction

Abstract

Drug association (DDIs) prediction is also called drug interaction prediction, which refers to the interactions between drug and drug that lead to unexpected side effects when two or more drugs are taken simultaneously or successively. Previous studies on DDIs prediction using methods such as molecular representation and network embedding were extremely complex, expensive and time-consuming, and were limited in acquiring rich neighborhood information about drug entities and their surroundings during the forecasting process. A drug linkage prediction method based on knowledge graphs and hybrid neural networks was proposed based on the deficiencies of the above methods. This method is mainly based on methods such as knowledge graphs, graph convolutional network, Convolutional-BiLSTM network and attention mechanisms to solve the limitations in acquiring rich neighborhood information about KG entities during the forecasting process. It transforms drug linkage prediction research into a link prediction problem and views drug relationships with known interactions as edges in the interaction graph. It can effectively discover interactions of unknown drugs; meanwhile, performance comparisons are performed with existing DDIs prediction methods. The results show that higher performance is achieved in terms of indicators such as ACC and F1 values, which validate the effectiveness of the model. Finally, future directions in this field are proposed based on an analysis and summary of challenges faced by current DDIs predictions.