EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AutoGERN: single-cell RNA-seq gene regulatory network inference via explicit link modeling and adaptive architectures

Jiacheng Wang iD, Yaojia Chen iD, Quan Zou iD, Ximei Luo iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag143 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Jiacheng Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu, 611731, China. Hauptthemen laut MEDLINE: Gene Regulatory Networks, RNA-Seq, Single-Cell Analysis, Computational Biology. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Municipal Government Found of Quzhou.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Single-cell RNA sequencing (scRNA-seq) enables transcriptome-wide profiling at single-cell resolution, revealing heterogeneous regulatory programs and making gene regulatory network (GRN) inference both central and challenging. Recent graph neural network (GNN)-based approaches for GRN inference typically model edges only implicitly (for example, via concatenated node embeddings), which limits their ability to capture complex regulatory dependencies. In addition, distributional shifts across scRNA-seq datasets make a single fixed GNN architecture poorly suited for broad generalization. Results We present AutoGERN, a GNN framework tailored for GRN inference from scRNA-seq data. AutoGERN explicitly models regulatory information in the message-passing space and learns expressive link (edge) embeddings, which a lightweight multilayer perceptron uses to score gene–gene regulatory associations. To enhance flexibility and representational power, AutoGERN employs dual message-passing spaces (within-layer and cross-layer) and integrates a robust AutoGNN-based architecture search to adapt the network design to differing dataset distributions. Extensive experiments on multiple real scRNA-seq datasets demonstrate that AutoGERN consistently achieves superior performance and robustness compared with state-of-the-art baselines. Availability and implementation The code and data of AutoGERN are available on GitHub at https://github.com/JChander/AutoGERN and on Zenodo at https://doi.org/10.5281/zenodo.18659807.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Gene Regulatory NetworksRNA-SeqSingle-Cell AnalysisComputational BiologySequence Analysis, RNASoftwareGraph Neural NetworksSingle-Cell Gene Expression AnalysisAlgorithms

Autor:innen und Institutionen

  • Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu, 611731, China.
  • Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou, Zhejiang, 324003, China.

ORCID-Profile: Jiacheng Wang, Yaojia Chen, Quan Zou, Ximei Luo

Förderung

  • National Natural Science Foundation of China
  • Municipal Government Found of Quzhou

Zitieren

APA

Wang, J., Chen, Y., Zou, Q., & Luo, X. (2026). AutoGERN: single-cell RNA-seq gene regulatory network inference via explicit link modeling and adaptive architectures. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag143

Vancouver

Wang J, Chen Y, Zou Q, Luo X. AutoGERN: single-cell RNA-seq gene regulatory network inference via explicit link modeling and adaptive architectures. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag143

BibTeX
@article{Wang2026,
  author = {Wang, Jiacheng and Chen, Yaojia and Zou, Quan and Luo, Ximei},
  title = {AutoGERN: single-cell RNA-seq gene regulatory network inference via explicit link modeling and adaptive architectures},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag143}
}
Kostenlos starten →