Open links in new tab
  1. Hierarchical graph learning for protein–protein interaction

    • To validate the predictive power of our model, we compare HIGH-PPI with leading methods from four perspectives, including (1) the overall performance under a random data split, (2) the robustness of … See more

    Bottom Inside-Of-Protein View Improves The Performance

    We investigate the role of the bottom inside-of-protein view from four perspectives, including … See more

    Nature
    Top Outside-Of-Protein View Improves The Performance

    We investigate the role of top outside-of-protein view TGNN from three perspectives, including (1) the importance of degree and community recovery for predicting n… See more

    Nature
    High-Ppi Accurately Identifies Key Residues Constituting Functional Sites

    Typically, functional sites are spatially clustered sets of residues. They control protein functions and are thus important for PPI prediction. As our proposed model has the capacit… See more

    Nature
    Feedback