Jul 2026· 2026 8th International Conference on Electronics and Communication, Network and Computer Technology (ECNCT)· pp. 920-923· 0 citations· 16 references
Abstract
Reconstruction of gene regulatory networks (GRNs) is essential for uncovering regulatory relationships between transcription factors (TFs) and target genes. With advances in single-cell RNA sequencing (scRNA-seq), cell-type-specific GRN inference has become an important direction in systems biology; however, existing deep learning methods still struggle with noisy expression, symmetric link scoring that cannot capture regulatory direction, and difficulty separating co-expression and co-regulation from direct regulation. Built upon the variational autoencoder (VAE)-graph attention network (GAT) framework of GRANet [1], we propose DMVD-GRN with enhanced VAE multi-view denoising, skew-symmetric directed decoding, and structure-aware joint decoding, integrating expression correlation, second-order adjacency, and Jaccard co-regulation priors. On 14 tasks of the STRING benchmark, DMVD-GRN achieves superior AUROC and AUPRC, with more pronounced AUPRC gains, thereby improving identification of true regulatory edges under extreme class imbalance.
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.
Yue Wang, Si-Cheng Tian, Dan Li· International Journal of Mol...· 0 citations
Direct prior-guided graph learning can improve the robustness and biological interpretability of GRN inference in data-limited settings and demonstrate that directed prior-guided graph learning can improve the robustness and biological interpretability of GRN inference in data-limited settings.
N. Alkhateeb, Mamoun A. Awad· Frontiers in Bioinformatics· 1 citation
A network structure refinement scheme, termed HSTXGB (a hyperparameter self-tuning XGBoost method integrating pre- and post-processing), to infer GRNs from time-course expression data by leveraging the nonlinear modeling capability of XGBoost while integrating prior knowledge and posterior statistics.
Ming-Qing Huang, Shun Guo, Feng-Ze Jiang et al.· Frontiers in Genetics· 0 citations
DMGRN, a novel GRN inference frame work built upon an improved Denoising Diffusion Probabilistic Model (DDPM), achieves the highest Early Precision Ratio (EPR) on 18 out of 28 BEELINE benchmark configurations, demonstrating superior stability and computational efficiency compared to state-of-the-art methods.
Rong-Yuan Li, Jing-Li Wu, Chun-Feng Chen et al.· IEEE transactions on computa...· 0 citations
Mamba-GRN is presented, a compact Mamba-inspired gene representation and edge-decoding framework evaluated under a corrected no-overlap protocol in which validation and test negatives are excluded from the training-negative pool, supporting Mamba-GRN as a controlled framework for held-out edge recovery.
ScGFormer is equipped with a biology-guided adaptive contrastive learning strategy, which is designed to account for zero inflation, balance class distributions, and refine dynamic graphs during training, thereby facilitating robustness and adaptability.
Zi-Qi Yuan, Hong-Wei Zhang, Cheng Liu et al.· IEEE Transactions on Computa...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
