Figures for‘Prediction of Protein--Protein Interaction based on Interaction-Specific Learning and Hierarchical Information’

Fig1: A schematic diagram of HI-PPI. （a） The preprocess of protein data. The heterogeneous GNN encoder is adopted to extract the latent representation in contact map of protein structure. (b) A PPI graph is constructed based on PPI network and extracted feature. The node representation of each protein is updated iteratively by hyperbolic graph convolutional layer. Subsequently, the importance of pairwise information is controlled by a gating mechanism in interaction-specific network. The resulting embedding of PPI is processed to a classifier for prediction.Fig2: Precision-recall curves of PPI prediction of SHS27K, showing the performance of HI-PPI compared to MAPE-PPI, HIGH-PPI, BaPPI, AFTGAN, LDMGNN and PIPR. (a) Under the BFS partitioning. (b) Under the DFS partitioning. The shade indicates the range between the highest and lowest results.Fig3: Robustness evaluation of HI-PPI against random perturbations with different ratios.Fig4: The performance of four advanced PPI prediction methods on PPI types of SHS27K.Fig5: The visualization of 195 proteins related in 2D hyperbolic space.