A Novel Sparse-Aware Topology Reconstruction and Global Dependency Enhanced Method for Predicting Human Microbe-Disease Associations

The study of human microbe-disease associations (MDAs) contributes to early diagnosis, personalized treatment, and novel drug and biomarker discovery. However, experimental verification is time-consuming and labor-intensive, underscoring the need for efficient computational prediction methods. However, existing methods have some limitations in dealing with data sparsity and effectively modeling global dependencies. To address these issues, we propose a sparseaware topology reconstruction and global dependencyenhanced method (STAGE) for MDA prediction. STAGE firstly employs an encoder-decoder structure combining Graph Attention Networks (GAT) and Graph Convolutional Networks (GCN). The GAT encoder captures key features from sparse networks, while the GCN decoder reconstructs potential associations to supplement missing information. An adaptive gating mechanism dynamically fuses original and reconstructed information to strengthen representation learning. Furthermore, an improved domain transformer, DAFormer, integrates relative position encoding, biased multi-head attention, and soft masking to enhance global dependency modeling while preserving graph topology. Finally, a multilayer perceptron (MLP) produces the final prediction scores. Experimental results demonstrate that STAGE outperforms existing methods, and case studies further validate its effectiveness and generalization capability.