Developing explainable models for lncRNA-Targeted drug discovery using graph autoencoders

Abstract

The application of explainable artificial intelligence technology is crucial in lncRNA-targeted drug discovery, given lncRNA’s role in regulating a broad spectrum of diseases, including cancer. Current advanced deep learning models efficiently predict the association between lncRNA and disease, facilitating the discovery of potential lncRNA-targeted drug. However, these models have notable limitations, including a tendency to overfit due to their focus on integrating various similarity networks for feature extraction of lncRNA and diseases. Additionally, they employ complex classifiers to predict unknown lncRNA-disease associations (LDAs), resulting in reduced interpretability. We designed an explainable model named EM-LTDD, utilizing graph autoencoders (GAE) and self-supervised learning strategies, aimed at identifying potential drugs targeting lncRNA. The EM-LTDD model improves self-supervised training by employing a novel strategy that masks parts of the known lncRNA-disease network. This approach not only enhances the model’s interpretability but also mitigates the impact of noise. Furthermore, the EM-LTDD model reconstructs the lncRNA-disease network with a robust collaborative decoder, minimizing information loss caused by occlusion and improving node representation. Experimental results demonstrate the effectiveness of our model compared to existing leading models, promising to significantly aid in the discovery and design of lncRNA-targeted drugs. Our code and data are available at: https://github.com/huiyingliulevy/EM-LTDD.