1. SAGESDA: Multi-GraphSAGE networks for predicting SnoRNA-disease associations
- Author
-
Biffon Manyura Momanyi, Yu-Wei Zhou, Bakanina Kissanga Grace-Mercure, Sebu Aboma Temesgen, Ahmad Basharat, Lin Ning, Lixia Tang, Hui Gao, Hao Lin, and Hua Tang
- Subjects
Small nucleolar RNAs ,Diseases ,snoRNA-disease associations ,GraphSAGE ,Heterogeneous network ,Biology (General) ,QH301-705.5 - Abstract
Over the years, extensive research has highlighted the functional roles of small nucleolar RNAs in various biological processes associated with the development of complex human diseases. Therefore, understanding the existing relationships between different snoRNAs and diseases is crucial for advancing disease diagnosis and treatment. However, classical biological experiments for identifying snoRNA-disease associations are expensive and time-consuming. Therefore, there is an urgent need for cost-effective computational techniques that can enhance the efficiency and accuracy of prediction. While several computational models have already been proposed, many suffer from limitations and suboptimal performance. In this study, we introduced a novel Graph Neural Network-based (GNN) classification model, called SAGESDA, which is implemented through the GraphSAGE architecture with attention for the prediction of snoRNA-disease associations. The classifier leverages local neighbouring nodes in a heterogeneous network to generate new node embeddings through message passing. The mini-batch gradient descent technique was applied to divide the graph into smaller sub-graphs, which enhances the model's accuracy, speed and scalability. With these advancements, SAGESDA attained an area under the receiver operating characteristic (ROC) curve (AUC) of 0.92 using the standard dot product classifier, surpassing previous related studies. This notable performance demonstrates that SAGESDA is a promising model for predicting unknown snoRNA-disease associations with high accuracy. The SAGESDA implementation details can be obtained from https://github.com/momanyibiffon/SAGESDA.git.
- Published
- 2024
- Full Text
- View/download PDF