Skip to content
Open access

Integrative graph deep learning with directional decoding for robust gene regulatory network inference from single-cell transcriptomics

Sep 2026 · Journal of Zhejiang University SCIENCE B · Vol 27, pp. 1129 - 1139 · 0 citations · 22 references
Medicine

TL;DR

Overall, scGRAIL enhances structural modeling and directional discrimination in single-cell GRN inference by using multi-hop graph aggregation to capture long-range regulatory dependencies, expression reconstruction constraints to improve cross-dataset robustness, and an asymmetric decoding mechanism to explicitly model the regulatory directionality between TFs and target genes.

Abstract

While gene regulatory networks (GRNs) are fundamental to understanding complex cellular mechanisms, the accurate inference from single-cell RNA-sequencing (scRNA-seq) data is hindered by the inherent noise, transcriptional dropout events, and dynamic nature of gene regulation. Current computational approaches often overlook long-range regulatory interactions, lack explicit modeling of regulatory directionality, and suffer from limited generalizability. To address these limitations, we introduce scGRAIL, a supervised deep learning framework that combines inductive local-aware graph aggregation (LGA) with an asymmetric relation decoder to enable robust GRN inference. Within this framework, LGA performs multi-hop neighborhood aggregation on a transcription factor (TF)–target graph, jointly leveraging topological structure and gene expression to capture long-range regulatory dependencies. A node reconstruction autoencoder (NAE) imposes gene expression reconstruction constraints on the latent embeddings, thereby enhancing robustness to noise and data heterogeneity and improving generalization. An asymmetric difference mechanism is introduced during decoding for distinct modeling of TFs and target genes; by computing an ordered difference vector between their embeddings, the model explicitly captures the directionality and target specificity of TF–target regulatory interactions, facilitating more accurate identification of potential causal regulatory relationships. Comprehensive evaluations demonstrate the model’s superiority: it achieves optimal performance on 86.4% of benchmark datasets (38/44), surpassing state-of-the-art methods. Notably, scGRAIL achieves a 4.25% increase in average area under the receiver operating characteristic curve (AUROC) across four real-world networks compared to the graph contrastive link prediction (GCLink) model, yielding a 17.64% AUROC improvement for the TF500+ Non-Specific network in the mouse hematopoietic stem cells with lymphoid-lineage (mHSC-L) dataset, demonstrating its resilience to noise and scalability for large-scale GRNs. These results establish scGRAIL as a transformative tool for uncovering gene regulatory logic in single-cell transcriptomics. Overall, scGRAIL enhances structural modeling and directional discrimination in single-cell GRN inference by using multi-hop graph aggregation to capture long-range regulatory dependencies, expression reconstruction constraints to improve cross-dataset robustness, and an asymmetric decoding mechanism to explicitly model the regulatory directionality between TFs and target genes.

Read PDF

Similar papers

Sep 2026

Graph Masked Autoencoder With Multi-Head Latent Attention Mechanism for Gene Regulatory Link Prediction.

GMAMLink reconstructed metastasis-specific regulatory networks and identified NUPR1 as a central hub gene in glycolytic pathways, with its elevated expression significantly correlated with metastatic progression and poor patient survival, highlighting its potential to uncover context-specific regulatory programs and pr...

Zhiwei Cao, Xu-Peng Wang, Wen-Hao Li et al. · 0 citations
Oct 2026

Inferring gene regulatory networks from single-cell transcriptomics jointly through graph neural networks and Transformer.

Inferring gene regulatory networks (GRNs) is crucial for understanding the complex regulatory relationships that govern gene expression in cells. Recently, several computational methods have been proposed for reconstructing GRNs from single-cell RNA sequencing (scRNA-seq) data. However, most of these methods primarily...

Yang-Lan Gan, Tao Liu, Guang-Wei Xu et al. · 0 citations
Open access Sep 2026

DeepSCENIC: transfer learning from sequence-to-function models enables causal gene regulatory network inference

Sequence-to-function (S2F) deep learning models have become an important aid to decipher the genomic cis-regulatory code. However, current S2F models do not take the cellular trans-environment of transcription factors (TF) into account. Conversely, methods for gene regulatory network (GRN) inference often rely on heuri...

Gabriele Partel, Seppe De Winter, Vasilis Konstantakos et al. · 0 citations
Open access Sep 2026

Multi-model biological and sequence information fusion for gene regulatory network inference from single-cell transcriptomics

Identification of transcription factor–target gene interactions and construction of the gene regulatory networks (GRNs) are essential for understanding the molecular mechanisms underlying transcriptional gene regulation. Large-scale single-cell transcriptomics across different tissues offers unprecedented resolution of...

Lin Zhong, Bin Yan, Jun-Wen Wang et al. · 0 citations
Preprint Nov 2026

Bridging Graph and Pairwise Learning for Gene Regulatory Network Inference from scRNA-seq Data

By fusing global representations with subgraph-enhanced local features, the scGPL framework bridges the gap between the two paradigms, incorporating essential whole-graph topological dependencies while retaining the data abundance advantage of pairwise methods.

Han Li, Jia-Xin Qi, Yan Cui et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.