Abstract
Inferring gene regulatory networks (GRNs) from single-cell transcriptomic data is crucial for biological discovery, yet existing approaches suffer from a fundamental misalignment with real-world needs. Researchers typically seek a small set of high-confidence regulatory interactions for experimental validation, often involving previously unseen genes. However, current benchmarks rely on transductive splits with global classification metrics, while prevailing models struggle to generalize under inductive settings.
To bridge this gap, we reformulate GRN inference as an inductive, ranking-centric graph completion problem and introduce enchmark, a new benchmark that incorporates an inductive gene-holdout split together with knowledge graph completion metrics to better evaluate top-ranked predictions.
Building on this, we propose hemethod, the first co-evolutionary discrete diffusion framework that jointly models biologically coherent discretized gene expression states and regulatory interactions for robust inductive generalization and improved top-ranked regulatory discovery. We further introduce TF-ALL Subgraph Sampling (TASS) for scalable training.
Extensive experiments on enchmark show that hemethod establishes new state-of-the-art performance, significantly outperforming existing methods in novel regulatory discovery, and ablation studies further verify the effectiveness of our design.
Blogger's Review: The CoDiffGRN framework proposed in this paper significantly enhances the inference capability of gene regulatory networks through inductive inference and graph completion methods, especially in the discovery of unseen genes. This innovative approach offers a new perspective for biological research, and we look forward to its widespread application in the future.