GRNFormer: accurate gene regulatory network inference using graph transformer
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag144 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Akshata Hegde und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, Missouri, 65211, United States. Hauptthemen laut MEDLINE: Gene Regulatory Networks, Computational Biology, Software. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Sscience Foundation (NSF), Department of Energy.
Abstract (Originalsprache)
Motivation Deciphering gene regulatory networks (GRNs) from single-cell transcriptomics data remains a fundamental challenge in computational biology. It is hindered by data sparsity, high dimensionality, and the lack of scalable, generalizable inference models. To address this, we present GRNFormer, a generalizable graph transformer framework for accurate GRN inference from transcriptomics data across species, cell types, and platforms without requiring cell-type annotations or prior regulatory information. Results GRNFormer integrates a transformer-based gene expression encoder (Gene-Transcoder) with a variational graph autoencoder (GraViTAE) employing pairwise attention to jointly learn the representations of genes (nodes) and their co-expression relationships (edges). Leveraging TF-Walker, a transcription factor-anchored subgraph sampling strategy, it effectively captures gene regulatory interactions from either single-cell or bulk RNA-seq datasets. Benchmarking on standard datasets demonstrates that GRNFormer outperforms existing traditional and deep learning state-of-the-art methods in blind evaluations, achieving average sampled area under the receiver operating characteristic curve (Sampled_AUROC) and sampled area under the precision–recall curve (Sampled_AUPRC) values between 0.90 and 0.98 as well as 0.87–0.98 average sampled F1 score. The model robustly recovers both known and novel regulatory networks, including pluripotency circuits in human embryonic stem cells (hESCs) and immune cell modules in peripheral blood mononuclear cells (PBMCs). The architecture enables scalable, biologically interpretable GRN inference across various datasets, cell types, and species, establishing GRNFormer as a robust and transferable tool for network biology. Availability and implementation GRNFormer is available on GitHub (https://github.com/BioinfoMachineLearning/GRNformer); the version used in this work is archived on Zenodo (https://doi.org/10.5281/zenodo.18868395), with evaluation resources for reproducibility.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, Missouri, 65211, United States.
- Roy Blunt Nextgen Precision Health, University of Missouri, Columbia, Missouri, 65211, United States.
ORCID-Profile: Akshata Hegde, Jianlin Cheng
Förderung
- National Sscience Foundation (NSF)
- Department of Energy
Zitieren
APA
Hegde, A., & Cheng, J. (2026). GRNFormer: accurate gene regulatory network inference using graph transformer. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag144
Vancouver
Hegde A, Cheng J. GRNFormer: accurate gene regulatory network inference using graph transformer. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag144
BibTeX
@article{Hegde2026,
author = {Hegde, Akshata and Cheng, Jianlin},
title = {GRNFormer: accurate gene regulatory network inference using graph transformer},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag144}
}
EUVIMED