Our model SPGA consistently outperforms all competing baseline methods, including IGCNSDA, iPiDA_GCN, VGAMF, NSAMDA, NIMCGCN, and AMHMDA, with p -values well below the 0.001 threshold in both AUC and AUPR metrics, indicating highly significant performance differences.
← all excerpts
SPGA: graph representation learning and attention fusion for enhanced disease-associated snoRNA prediction.
1
—
—