ARF-GNN: Adaptive receptive field graph neural network for protein function prediction

Protein function prediction is one of the core challenges in bioinformatics, which plays a key role in resolving cellular mechanisms and driving drug discovery. A core challenge in this field is that protein function depends on both local structural motifs and long-range spatial interactions, and traditional Graph neural networks (GNNS) are limited by fixed receptive fields, which are difficult to comprehensively model these two features in different protein structures. To overcome this limitation, we propose ARF-GNN, an adaptive receptive field graph neural network tailored for protein function prediction. Our approach dynamically models structural context via hierarchical multi-hop neighborhood aggregation and introduces a dual-branch meta-learning framework: the Task branch performs multi-label functional annotation, while the Meta branch jointly learns sample-specific optimal receptive field sizes, thus thereby enabling structure-aware, input-adaptive information integration and mitigating noise and redundancy inherent in static neighborhood definitions. Empirical evaluation shows that ARF-GNN has significant improvements over the existing best benchmark models: in the PDBch benchmark test set, it has significant enhancements in the AUPR, Fmax, and Smin evaluation metrics. Ablation and interpretability analyses further confirm that the adaptive mechanism robustly captures functionally relevant multi-scale structural patterns, establishing a principled paradigm that unifies expressive structural representation with data-driven neighborhood adaptation.