Your browser doesn't support javascript.
loading
SAGESDA: Multi-GraphSAGE networks for predicting SnoRNA-disease associations.
Momanyi, Biffon Manyura; Zhou, Yu-Wei; Grace-Mercure, Bakanina Kissanga; Temesgen, Sebu Aboma; Basharat, Ahmad; Ning, Lin; Tang, Lixia; Gao, Hui; Lin, Hao; Tang, Hua.
Afiliación
  • Momanyi BM; School of Computer Science and Engineering, Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu, China.
  • Zhou YW; School of Health Care Technology, Chengdu Neusoft University, Chengdu, China.
  • Grace-Mercure BK; School of Life Science and Technology, Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu, 610054, China.
  • Temesgen SA; School of Life Science and Technology, Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu, 610054, China.
  • Basharat A; School of Life Science and Technology, Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu, 610054, China.
  • Ning L; School of Health Care Technology, Chengdu Neusoft University, Chengdu, China.
  • Tang L; School of Life Science and Technology, Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu, 610054, China.
  • Gao H; School of Life Science and Technology, Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu, 610054, China.
  • Lin H; School of Computer Science and Engineering, Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu, China.
  • Tang H; School of Life Science and Technology, Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu, 610054, China.
Curr Res Struct Biol ; 7: 100122, 2024.
Article en En | MEDLINE | ID: mdl-38188542
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.
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Prognostic_studies / Risk_factors_studies Idioma: En Revista: Curr Res Struct Biol Año: 2024 Tipo del documento: Article País de afiliación: China Pais de publicación: Países Bajos
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Prognostic_studies / Risk_factors_studies Idioma: En Revista: Curr Res Struct Biol Año: 2024 Tipo del documento: Article País de afiliación: China Pais de publicación: Países Bajos