Search papers, labs, and topics across Lattice.
This paper introduces Edge Generation-guided Relation-aware Learning (EGRL), a novel framework designed to enhance RNA-Protein Interaction (RPI) prediction by addressing limitations in existing Graph Neural Network (GNN) approaches. EGRL employs implicit meta-path learning and a multi-relation-aware attention mechanism to effectively model relational semantics and adaptively fuse interaction patterns, while also incorporating a graph generator for predicting potential edges to support cold-start scenarios. Evaluations on benchmark datasets reveal that EGRL significantly outperforms state-of-the-art methods, particularly in cold-start settings, achieving notable improvements in AUROC and AUPR metrics.
EGRL achieves an impressive 8.6% improvement in AUROC for cold-start RNA-protein interactions, showcasing its potential to revolutionize RPI prediction.
RNA-Protein Interactions (RPIs) are critical for regulating cellular functions. While traditional wet-lab experiments for RPI detection are costly and time-consuming, Deep Learning (DL) methods provide an efficient computational alternative for RPI Prediction (RPIP). In particular, Graph Neural Networks (GNNs) are promising, as they naturally model RPI networks. However, existing GNN-based methods often rely on homogeneous graphs or predefined meta-paths, which limit their ability to handle data sparsity and to generalize to cold-start scenarios involving unknown molecules. To address these limitations, we propose Edge Generation-guided Relation-aware Learning (EGRL), a novel framework with several key components: implicit meta-path learning to capture relational semantics without handcrafted paths; a multi-relation-aware attention mechanism for adaptive fusion of interaction patterns; a graph generator that predicts potential ("soft") edges to support cold-start nodes; and a multi-feature fusion predictor for final interaction scoring. EGRL is jointly trained with a primary task loss and an auxiliary generator loss. Comprehensive evaluations on four benchmark datasets demonstrate that EGRL achieves competitive overall performance. More importantly, it exhibits superior generalization in cold-start settings, achieving an Area Under the Receiver Operating Characteristic curve (AUROC) of 0.867 and an Area Under the Precision-Recall curve (AUPR) of 0.861 on unknown molecules, corresponding to improvements of 8.6% in AUROC and 5.0% in AUPR over prior state-of-the-art methods. The code will be released soon.
