Deep and Probabilistic Models for Gene Regulatory Network Inference

IAGRN: An Interleaved-Attention Graph Neural Network for Gene Regulatory Network Inference

A structure-aware interleaved-attention graph learning framework, termed IAGRN, is proposed for GRN inference from scRNA-seq data that interleaves topology-constrained local attention with distance-aware global attention, enabling effective integration of structural priors and long-range regulatory signals.

A Bayesian Multi-Species Approach Infers Gene Regulatory Networks Across Non-Model Organisms

Spatially varying gene regulation network inference from spatial transcriptomics

Gene regulatory networks (GRNs) govern cellular functions by coordinating gene expression programs. These regulatory relationships are strongly shaped by local microenvironments, giving rise to dynamic, spatially varying regulatory patterns across tissues. Therefore, it is crucial to infer GRNs at higher, cell-specific resolution while jointly modeling spatial context. However, most existing GRN inference approaches focus on cell-type–level networks or infer cell-specific GRNs without incorporating neighborhood and positional information. We propose SVGRN, a deep learning framework for inferring spatially resolved, high-resolution GRNs from spatial transcriptomics data. SVGRN integrates gene expression, regulatory interactions, and spatial coordinates within a structural equation modeling framework implemented by a conditional variational autoencoder, to learn nonlinear, spatially varying regulatory programs in an unsupervised manner. By conditioning on target locations and incorporating neighborhood information, SVGRN refines tissue-level regulation into spot- or cell-specific GRNs. Across simulated datasets, SVGRN consistently outperforms existing methods under diverse and challenging settings. Applications to seqFISH mouse embryo data and Visium human cutaneous squamous cell carcinoma and fallopian tube datasets demonstrate that SVGRN captures spatially varying regulatory programs underlying development, tumor progression, and tissue organization, highlighting its robustness and broad applicability. The source code and data are available at https://github.com/lyrrrr/SVGRN. Supplementary data are available at Bioinformatics Advances online.

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

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 \textbf{\benchmark}, 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 \textbf{\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 {\benchmark} 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.

Large-scale, interpretable gene regulatory network inference through biologically informed matrix factorization

Gene regulatory networks (GRNs) provide a mechanistic framework for understanding how transcription factors coordinate gene expression to establish cellular identity and phenotype. Methods that integrate gene expression with motif-derived regulatory priors and other sources of biological information have substantially advanced gene regulatory network inference by reconstructing condition-specific regulatory architecture. These approaches estimate the evidence supporting regulatory interactions and have proven remarkably successful in a wide range of biological applications. A complementary view of regulatory networks, however, seeks to estimate the effect of those interactions on gene expression itself, providing a framework in which regulatory edges can be interpreted as activating or inhibitory influences on transcription. We developed Giraffe, a biologically informed matrix factorization framework that jointly estimates transcription factor activities and gene regulatory networks by integrating gene expression, motif-based regulatory priors, and transcription factor protein-protein interactions. Giraffe estimates signed partial regulatory effects whose magnitude and sign can be interpreted as the strength and direction of transcriptional regulation. Building directly on the biological framework established by methods such as PANDA, Giraffe provides a complementary representation of gene regulatory networks that emphasizes mechanistic interpretation while remaining scalable, flexible, and computationally efficient. Across synthetic benchmarks, six human tissues, yeast transcription factor perturbation experiments, and liver hepatocellular carcinoma, Giraffe accurately reconstructs regulatory interactions while distinguishing activating from inhibitory regulation with high accuracy. The inferred networks recover known features of tissue-specific regulation, correctly classify regulatory effects in transcription factor perturbation experiments, and identify biologically coherent changes in regulatory programs associated with liver cancer. Together, these results demonstrate that estimating the direction of transcriptional regulation provides a complementary perspective on gene regulatory networks that facilitates biological interpretation and hypothesis generation.

BoYueGRN: Zero-shot causal discovery of directed gene regulatory networks from single-cell transcriptomes via amortized inference over synthetic structural causal models