Revealing hidden regulatory dependencies: multi-perspective graph learning for single-cell gene regulatory network inference

Gene regulatory networks (GRNs) inform analyses of cellular state transitions, regulatory mechanisms, and disease processes. With the rapid development of single-cell sequencing technologies, accurate inference of GRNs from complex and high-dimensional single-cell transcriptomic data remains a core challenge. However, the effective use of multi-level structural and expression features among genes remains a major obstacle to improving inference accuracy. This study presents ATFGRN, an adaptive topology-feature fusion graph neural framework that integrates features from three complementary perspectives for accurate prediction of gene regulatory relationships. The subgraph structure encoding module focuses on local subgraphs of regulatory relationships and identifies structural patterns and topological dependencies. The expression-guided module integrates the gene expression matrix with the original regulatory network and employs a graph convolutional network with a self-attention mechanism to examine interactions between expression dynamics and network topology. The similarity structure module derives similarity information between genes through a KNN graph combined with a graph attention mechanism, which helps detect regulatory pairs with similar expression patterns that lack explicit structural links. Features from these three branches are fused through an attention-based weighting mechanism. This fusion achieves complementary integration of structural, expression, and similarity perspectives and produces more informative regulatory features for prediction. Evaluations on single-cell transcriptomic datasets across four types of networks show that ATFGRN improves AUROC performance by 5.09% over existing approaches, which confirms the effectiveness and applicability of its multi-perspective fusion strategy in GRN inference tasks.