Inference of Gene Regulatory Networks Based on Heterogeneous Graph Neural Networks

Liming Liu

doi:10.23977/acss.2025.090108

Inference of Gene Regulatory Networks Based on Heterogeneous Graph Neural Networks

Download as PDF

DOI: 10.23977/acss.2025.090108 | Downloads: 22 | Views: 642

Author(s)

Liming Liu ¹

Affiliation(s)

¹ School of Information Science and Technology, Yunnan Normal University, Kunming, China

Corresponding Author

Liming Liu

ABSTRACT

Gene Regulatory Networks (GRNs) are central to understanding the mechanisms of gene expression regulation, yet their construction is challenged by node heterogeneity and complex regulatory relationships. Traditional methods often simplify GRNs into homogeneous graphs, overlooking the functional differences between genes and regulatory factors. To address this limitation, we propose a novel GRN construction method, HGRN, based on Heterogeneous Graph Convolutional Networks. By modeling GRNs as heterogeneous graphs comprising two types of nodes—genes and regulatory factors—along with multiple regulatory relationships, and incorporating a multi-channel graph convolution mechanism, our model can separately learn gene expression features and regulatory factor functional features while capturing high-order regulatory dependencies. Experiments on non-specific ChIP-seq datasets demonstrate that this approach outperforms traditional methods in predicting regulatory relationships, significantly improving the accuracy of GRN construction. This study provides a new perspective for the precise inference of gene regulatory networks and offers a powerful tool for elucidating disease mechanisms and predicting drug targets in biomedical research.

KEYWORDS

Gene Regulatory Network, Heterogeneous Graph, Graph Convolutional Networks

CITE THIS PAPER

Liming Liu, Inference of Gene Regulatory Networks Based on Heterogeneous Graph Neural Networks. Advances in Computer, Signals and Systems (2025) Vol. 9: 50-54. DOI: http://dx.doi.org/10.23977/acss.2025.090108.

REFERENCES

[1] Xu J, Zhang A, Liu F, et al. STGRNS: an interpretable transformer-based method for inferring gene regulatory networks from single-cell transcriptomic data [J]. Bioinformatics, 2023, 39(4): btad165.
[2] McCall M N. Estimation of gene regulatory networks [J]. Postdoc journal: a journal of postdoctoral research and postdoctoral affairs, 2013, 1(1): 60.
[3] Mao G, Pang Z, Zuo K, et al. Predicting gene regulatory links from single-cell RNA-seq data using graph neural networks [J]. Briefings in Bioinformatics, 2023, 24(6): bbad414.
[4] Huynh-Thu V A, Irrthum A, Wehenkel L, et al. Inferring regulatory networks from expression data using tree-based methods[J]. PloS one, 2010, 5(9): e12776.
[5] Garcia-Alonso L, Holland C H, Ibrahim M M, et al. Benchmark and integration of resources for the estimation of human transcription factor activities [J]. Genome research, 2019, 29(8): 1363-1375.
[6] Chen G, Liu Z P. Graph attention network for link prediction of gene regulations from single-cell RNA-sequencing data [J]. Bioinformatics, 2022, 38(19): 4522-4529.

Subscription

E-Mail Alert

Downloads:	38554
Visits:	697976

Inference of Gene Regulatory Networks Based on Heterogeneous Graph Neural Networks

Author(s)

Affiliation(s)

Corresponding Author

ABSTRACT

KEYWORDS

CITE THIS PAPER

REFERENCES

RESOURCES

JOIN US

PUBLICATION SERVICES

CONTACT US