Funnel graph neural networks with multi-granularity cascaded fusing for protein–protein interaction prediction
The identification of potential protein–protein interactions (PPIs) between humans and viruses is crucial for comprehending viral infection and disease mechanisms at the molecular level. Recently, graph neural networks (GNNs) have emerged as a promising approach to expedite PPI identification. Howev...
Gespeichert in:
Veröffentlicht in: | Expert systems with applications 2024-12, Vol.257, p.125030, Article 125030 |
---|---|
Hauptverfasser: | , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The identification of potential protein–protein interactions (PPIs) between humans and viruses is crucial for comprehending viral infection and disease mechanisms at the molecular level. Recently, graph neural networks (GNNs) have emerged as a promising approach to expedite PPI identification. However, GNNs often suffer from over-smoothing when capturing high-order neighbor information. To tackle this issue and effectively capture implicit collaborative information from multi-hop neighbors, we propose FGNN, Funnel Graph Neural Networks with Multi-Granularity Cascaded Fusing, facilitating the distillation of information in a funnel-like manner. Specifically, it enables the mapping of information flow from the full graph to subgraphs and ultimately to nodes. By regarding subgraphs as bridges connecting higher-order neighbors, we ensure the projection of multi-hop neighbors into the same subspace, thereby achieving a comprehensive mapping of the full graph into subgraphs. Moreover, we employ an encoder equipped with a multi-head attention mechanism to effectively map subgraphs onto nodes, facilitating further refinement and compression of information derived from high-order neighbors. FGNN can effectively capture high-order neighbor information whilst relieving over-smoothing. Extensive experiments demonstrate FGNN is superior to the state-of-the-art methods in terms of AUC value. The achieved improvements in the four cardiovascular disease datasets are 7.96 %, 2.3 %, 2.49 %, and 0.82 %, respectively. |
---|---|
ISSN: | 0957-4174 |
DOI: | 10.1016/j.eswa.2024.125030 |