Phi-Former: A Pairwise Hierarchical Approach for Compound-Protein Interactions Prediction

2025-12-15

IEEE International Conference on Bioinformatics and Biomedicine

AI Summary

This work addresses the limitation of existing deep learning approaches for compound–protein interaction (CPI) prediction, which often overlook the critical role of molecular functional groups in biological recognition and thus fail to capture authentic binding mechanisms. To bridge this gap, we propose Phi-Former, the first CPI modeling framework that explicitly incorporates functional groups into a hierarchical architecture encompassing atom–atom, group–group, and atom–group interactions. By integrating hierarchical graph representations, cross-granularity attention mechanisms, pairwise pretraining, and multitask learning, Phi-Former enables synergistic modeling of multiscale structural and semantic information. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple CPI benchmarks and accurately identifies key interaction sites, offering interpretable insights to support rational drug design.

Technology Category

• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Drug discovery remains time-consuming, labor-intensive, and expensive, often requiring years and substantial investment per drug candidate. Predicting compound-protein interactions (CPIs) is a critical component in this process, enabling the identification of molecular interactions between drug candidates and target proteins. Recent deep learning methods have successfully modeled CPIs at the atomic level, achieving improved efficiency and accuracy over traditional energy-based approaches. However, these models do not always align with chemical realities, as molecular fragments (motifs or functional groups) typically serve as the primary units of biological recognition and binding. In this paper, we propose Phi-former, a pairwise hierarchical interaction representation learning method that addresses this gap by incorporating the biological role of motifs in CPIs. Phi-former represents compounds and proteins hierarchically and employs a pairwise pre-training framework to model interactions systematically across atom-atom, motifmotif, and atom-motif levels, reflecting how biological systems recognize molecular partners. We design intra-level and interlevel learning pipelines that make different interaction levels mutually beneficial. Experimental results demonstrate that Phiformer achieves superior performance on CPI-related tasks. A case study shows that our method accurately identifies specific atoms or motifs activated in CPIs, providing interpretable model explanations. These insights may guide rational drug design and support precision medicine applications.

Problem

• compound-protein interactions
• molecular motifs
• biological recognition
• drug discovery
• interaction prediction

Innovation

• compound-protein interaction
• hierarchical representation
• motif-level modeling
• pairwise pre-training
• interpretable deep learning