CoDiffGRN: Rethinking Gene Regulatory Network Inference via the BEELINE-KGC Benchmark and Co-evolutionary Discrete Diffusion

arXiv:2607.13120v1 Announce Type: cross 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 extbf{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 extbf{method}, 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 {method} 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.

Related

• Towards Universal Gene Regulatory Network Inference: Unlocking Generalizable Regulatory Knowledge in Single-cell Foundation Models
• GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis
• GRAFT: Biological Graph and Hypergraph Benchmarks for Linked Gene Expression and Phenotypic Trait Prediction in Arabidopsis thaliana

Source: arXiv cs.AI | 2026-07-16