Enhancing Protein-Protein Interaction Prediction with Hierarchical Motif-based Multimodal Protein Embedding

Protein-protein interactions (PPIs) are essential for a wide range of biological processes. However, existing PPI prediction approaches still face two major limitations. First, in aggregating residue features into global protein features, they ignore the hierarchical organization of proteins, in which meso-scale motifs are the key regulators of PPIs. Second, despite the availability of complementary information across the sequence, structure, and function modalities, current PPI methods fail to integrate all three modalities effectively. To address these limitations, we propose a Hierarchical Motif-based M ultiM odal protein Encoder for PPI Prediction (MMM-PPI), which constructs protein embeddings for PPI prediction in a bottom-up, multi-modal manner. (i) At the micro-scale, we encode three modal residue features; (ii) At the meso-scale, we use a novel multimodal motif encoder to aggregate residues into spatially-informed motif embeddings; (iii) At the macro-scale, we introduce a multimodal protein encoder to integrate motif embeddings into protein embeddings, considering both the relative importance of motifs in PPI and correlations between different modalities. The pre-trained encoder can be used off-the-shelf for large-scale PPI prediction. Extensive experiments on multiple PPI datasets demonstrate that MMM-PPI outperforms state-of-the-art multi-label PPI prediction models, particularly in scenarios with challenging data partitions and limited training data.