HALink: A VAE-Based and Hybrid GCN–GAT Architecture for Inferring Single-Cell Gene Regulatory Networks
Abstract
Gene regulatory networks (GRNs) describe the complex interactions that control gene expression and are key indicators of cellular function and disease progression. Although numerous methods have been developed for inferring GRNs from single-cell transcriptomic data, current methods have two limitations: sensitivity to data sparsity and technical noise in single-cell RNA sequencing, and inadequate integration of both global structural information and local dependencies within GRNs.
To address these limitations, we propose HALink. This method integrating a variational autoencoder-based model and Top-K sparsification strategy to address the data sparsity, reduce technical noise, and insufficient prior knowledge. Furthermore, it ulitizes a hybrid Graph Convolutional Network–Graph Attention Network (GCN–GAT) architecture that simultaneously captures both global structural information and local dependencies within GRNs, enabling more comprehensive and accurate GRN construction.
Experiments results demonstrate that both the VAE-based model with sparsification strategy and the hybrid GCN–GAT architecture are able to improve the prediction performance, while their integrated implementation yields synergistic improvements. Compared with the state-of-art methods, HALink achieves superior performance on most experimental cases across four benchmark datasets. Our method facilitates the identification of key gene regulatory networks underlying life processes and enables the discovery of biologically meaningful insights into disease pathogenesis.
References
1. Alberto de la Fuente. What are gene regulatory networks?. In Handbook of research
on computational methodologies in gene regulatory networks, pages 1–27. IGI Global,
2010.
2. Daniele Mercatelli, Laura Scalambra, Luca Triboli, Forest Ray, and Federico M.
Giorgi. Gene regulatory network inference resources: A practical overview. Biochim-
ica et Biophysica Acta (BBA)-Gene Regulatory Mechanisms, 1863(6):194430, 2020.
Elsevier.
3. Eric H. Davidson and Douglas H. Erwin. Gene regulatory networks and the evolution
of animal body plans. Science, 311(5762):796–800, 2006.
4. Douglas H. Erwin and Eric H. Davidson. The evolution of hierarchical gene regu-
latory networks. Nature Reviews Genetics, 10(2):141–148, 2009. Nature Publishing
Group UK London.
5. Junlin Xu, Changcheng Lu, Shuting Jin, Yajie Meng, Xiangzheng Fu, Xiangxiang
Zeng, Ruth Nussinov, and Feixiong Cheng. Deep learning-based cell-specific gene
regulatory networks inferred from single-cell multiome data. Nucleic Acids Research,
53(5):gkaf138, 2025. Oxford University Press.
6. Frank Emmert-Streib, Matthias Dehmer, and Benjamin Haibe-Kains. Gene regu-
latory networks and their applications: understanding biological and medical prob-
lems in terms of networks. Frontiers in Cell and Developmental Biology, 2:38, 2014.
Frontiers Media SA.
7. Benzhe Su, Weiwei Wang, Xiaohui Lin, Shenglan Liu, and Xin Huang. Identifying
the potential miRNA biomarkers based on multi-view networks and reinforcement
learning for diseases. Briefings in Bioinformatics, 25(1):bbad427, 2024.
8. Mengyuan Zhao, Wenying He, Jijun Tang, Quan Zou, and Fei Guo. A comprehensive
overview and critical evaluation of gene regulatory network inference technologies.
Briefings in Bioinformatics, 22(5):bbab009, 2021.
9. Guo Mao, Ruigeng Zeng, Jintao Peng, Ke Zuo, Zhengbin Pang, and Jie Liu. Recon-
structing gene regulatory networks of biological function using differential equations
of multilayer perceptrons. BMC Bioinformatics, 23(1):503, 2022.
10. Weixu Wang, Yichen Wang, Ruiqi Lyu, and Dominic Grün. Scalable identification
of lineage-specific gene regulatory networks from metacells with NetID. Genome
Biology, 25(1):275, 2024.
11. Yang Li, Anjun Ma, Yizhong Wang, Qi Guo, Cankun Wang, Hongjun Fu,
Bingqiang Liu, and Qin Ma. Enhancer-driven gene regulatory networks infer-
ence from single-cell RNA-seq and ATAC-seq data. Briefings in Bioinformatics,
25(5):bbae369, 2024.
12. Eva Hedlund and Qiaolin Deng. Single-cell RNA sequencing: technical advance-
ments and biological applications. Molecular Aspects of Medicine, 59:36–46, 2018.
13. Riet De Smet and Kathleen Marchal. Advantages and limitations of current net-
work inference methods. Nature Reviews Microbiology, 8(10):717–729, 2010.
14. Alicia T. Specht and Jun Li. LEAP: constructing gene co-expression networks
for single-cell RNA-sequencing data using pseudotime ordering. Bioinformatics,
33(5):764–766, 2017.
15. Thalia E. Chan, Michael P. H. Stumpf, and Ann C. Babtie. Gene regulatory
network inference from single-cell data using multivariate information measures.
Cell Systems, 5(3):251–267, 2017.
16. Jiayi Dong, Jiahao Li, and Fei Wang. Deep learning in gene regulatory network
inference: a survey. IEEE/ACM Transactions on Computational Biology and Bioin-
formatics, 2024.
17. Mengyuan Zhao, Wenying He, Jijun Tang, Quan Zou, and Fei Guo. A hybrid deep
learning framework for gene regulatory network inference from single-cell transcrip-
tomic data. Briefings in Bioinformatics, 23(2):bbab568, 2022.
18. Guo Mao, Zhengbin Pang, Ke Zuo, Qinglin Wang, Xiangdong Pei, Xinhai Chen,
and Jie Liu. Predicting gene regulatory links from single-cell RNA-seq data using
graph neural networks. Briefings in Bioinformatics, 24(6):bbad414, 2023.
19. Lin Yuan, Ling Zhao, Yufeng Jiang, Zhen Shen, Qinhu Zhang, Ming Zhang, Chun-
Hou Zheng, and De-Shuang Huang. scMGATGRN: a multiview graph attention
network–based method for inferring gene regulatory networks from single-cell tran-
scriptomic data. Briefings in Bioinformatics, 25(6):bbae526, 2024.
20. Weiming Yu, Zerun Lin, Miaofang Lan, and Le Ou-Yang. GCLink: a graph con-
trastive link prediction framework for gene regulatory network inference. Bioinfor-
matics, 41(3):btaf074, 2025.
21. Jiacheng Wang, Yaojia Chen, and Quan Zou. Inferring gene regulatory network
from single-cell transcriptomes with graph autoencoder model. PLOS Genetics,
19(9):e1010942, 2023.
22. Guangyi Chen and Zhi-Ping Liu. Graph attention network for link predic-
tion of gene regulations from single-cell RNA-sequencing data. Bioinformatics,
38(19):4522–4529, 2022.
23. Muhan Zhang and Yixin Chen. Link prediction based on graph neural networks.
Advances in Neural Information Processing Systems, 31, 2018.
24. Steffen Albrecht, Tommaso Andreani, Miguel A Andrade-Navarro, and Jean Fred
Fontaine. Single-cell specific and interpretable machine learning models for sparse
scChIP-seq data imputation. Plos One, 17(7):e0270043, 2022.
25. HaiYun Wang, JianPing Zhao, ChunHou Zheng, and YanSen Su. scDSSC: deep
sparse subspace clustering for scRNA-seq data. PLOS Computational Biology,
18(12):e1010772, 2022.
26. Aditya Pratapa, Amogh P. Jalihal, Jeffrey N. Law, Aditya Bharadwaj, and T.
M. Murali. Benchmarking algorithms for gene regulatory network inference from
single-cell transcriptomic data. Nature Methods, 17(2):147–154, 2020.
27. Kishan Kc, Rui Li, Feng Cui, Qi Yu, and Anne R. Haake. GNE: a deep learning
framework for gene network inference by aggregating biological information. BMC
Systems Biology, 13:1–14, 2019.
28. J. Gray Camp, Keisuke Sekine, Tobias Gerber, Henry Loeffler-Wirth, Hans Binder,
Malgorzata Gac, Sabina Kanton, Jorge Kageyama, Georg Damm, Daniel Seehofer,
et al. Multilineage communication regulates human liver bud development from
pluripotency. Nature, 546(7659):533–538, 2017.
29. Tetsutaro Hayashi, Haruka Ozaki, Yohei Sasagawa, Mana Umeda, Hiroki Danno,
and Itoshi Nikaido. Single-cell full-length total RNA sequencing uncovers dynamics
of recursive splicing and enhancer RNAs. Nature Communications, 9(1):619, 2018.
30. Alex K. Shalek, Rahul Satija, Joe Shuga, John J. Trombetta, Dave Gennert, Di-
ana Lu, Peilin Chen, Rona S. Gertner, Jellert T. Gaublomme, Nir Yosef, et al.
Single-cell RNA-seq reveals dynamic paracrine control of cellular variation. Nature,
510(7505):363–369, 2014.
31. Huilei Xu, Caroline Baroukh, Ruth Dannenfelser, Edward Y. Chen, Christopher
M. Tan, Yan Kou, Yujin E. Kim, Ihor R. Lemischka, and Avi Ma’ayan. ESCAPE:
database for integrating high-content published data collected from human and
mouse embryonic stem cells. Database, 2013:bat045, 2013.
32. Damian Szklarczyk, Annika L. Gable, David Lyon, Alexander Junge, Stefan Wyder,
Jaime Huerta-Cepas, Milan Simonovic, Nadezhda T. Doncheva, John H. Morris,
Peer Bork, et al. STRING v11: protein–protein association networks with increased
coverage, supporting functional discovery in genome-wide experimental datasets.
Nucleic Acids Research, 47(D1):D607–D613, 2019.
33. Luz Garcia-Alonso, Christian H. Holland, Mahmoud M. Ibrahim, Denes Turei, and
Julio Saez-Rodriguez. Benchmark and integration of resources for the estimation of
human transcription factor activities. Genome Research, 29(8):1363–1375, 2019.
34. Zhi-Ping Liu, Canglin Wu, Hongyu Miao, and Hulin Wu. RegNetwork: an inte-
grated database of transcriptional and post-transcriptional regulatory networks in
human and mouse. Database, 2015:bav095, 2015.
35. Heonjong Han, Jae-Won Cho, Sangyoung Lee, Ayoung Yun, Hyojin Kim, Dasom
Bae, Sunmo Yang, Chan Yeong Kim, Muyoung Lee, Eunbeen Kim, et al. TRRUST
v2: an expanded reference database of human and mouse transcriptional regulatory
interactions. Nucleic Acids Research, 46(D1):D380–D386, 2018.
36. Jill E. Moore, Michael J. Purcaro, Henry E. Pratt, Charles B. Epstein, Noam
Shoresh, Jessika Adrian, Trupti Kawli, Carrie A. Davis, Alexander Dobin, et al.
Expanded encyclopaedias of DNA elements in the human and mouse genomes. Na-
ture, 583(7818):699–710, 2020.
37. Shinya Oki, Tazro Ohta, Go Shioi, Hideki Hatanaka, Osamu Ogasawara, Yoshihiro
Okuda, Hideya Kawaji, Ryo Nakaki, Jun Sese, and Chikara Meno. ChIP-Atlas:
a data-mining suite powered by full integration of public ChIP-seq data. EMBO
Reports, 19(12):e46255, 2018.
38. Sonia Nestorowa, Fiona K. Hamey, Blanca Pijuan Sala, Evangelia Diamanti, Mairi
Shepherd, Elisa Laurenti, Nicola K. Wilson, David G. Kent, and Berthold Göttgens.
A single-cell resolution map of mouse hematopoietic stem and progenitor cell differ-
entiation. Blood, The Journal of the American Society of Hematology, 128(8):e20–
e31, 2016.
Metrics
DOI:
Submission ID:
Downloads
Posted
How to Cite
Download Citation
Declaration of Competing Interests
The authors declare no competing interests to disclose.
Copyright
The copyright holder for this preprint is the author/funder.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.