EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

engGNN: a dual-graph neural network for omics-based disease classification and feature selection

Tiantian Yang iD, Yuxuan Wang iD, Zhenwei Zhou, Ching-Ti Liu iD

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag481 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Tiantian Yang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics and Statistical Science, University of Idaho, 875 Perimeter Drive, Moscow 83844, ID, United States. Hauptthemen laut MEDLINE: Graph Neural Networks, Computational Biology. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIGMS NIH HHS, NIDDK NIH HHS, NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Omics data, such as transcriptomics, proteomics, and metabolomics, provide critical insights into disease mechanisms and clinical outcomes. However, their high dimensionality, small sample sizes, and intricate biological networks pose major challenges for reliable prediction and meaningful interpretation. Graph neural networks offer a promising way to integrate prior knowledge by encoding feature relationships as graphs. Yet, existing methods typically rely solely on either an externally curated feature graph or a data-driven generated graph, which limits their ability to capture complementary information. To address this, we propose the external and generated Graph Neural Network (engGNN), a dual-graph framework that jointly leverages both external biological networks and data-driven generated graphs. Specifically, engGNN constructs a biologically informed undirected feature graph from established network databases and complements it with a directed feature graph derived from tree-ensemble models. This dual-graph design produces more comprehensive representations, thereby improving predictive performance and interpretability. Through extensive simulation studies and real-world applications to three independent gene expression datasets, engGNN consistently demonstrates strong classification performance compared with competitive baselines. Beyond classification, engGNN provides feature- and source-level interpretability, enabling biologically meaningful analyses such as pathway enrichment analysis. Taken together, these results highlight engGNN as a robust, flexible, and interpretable framework for disease classification and biomarker discovery in high-dimensional omics contexts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Graph Neural NetworksComputational BiologyHumansProteomicsMetabolomicsAlgorithmsMultiomicsGene Expression ProfilingGenomics

Stichwörter der Autor:innen

biological networksdisease classificationfeature selectiongraph neural networksomics data

Autor:innen und Institutionen

  • Department of Mathematics and Statistical Science, University of Idaho, 875 Perimeter Drive, Moscow 83844, ID, United States.
  • Department of Biostatistics, Boston University, 801 Mass Avenue, Boston 02118, MA, United States.
  • Center for Health Data Science, Boston University, 715 Albany Street, Boston 02118, MA, United States.

ORCID-Profile: Tiantian Yang, Yuxuan Wang, Ching-Ti Liu

Förderung

  • NIGMS NIH HHS
  • NIDDK NIH HHS
  • NIH HHS
  • National Institutes of Health
  • National Institute of General Medical Sciences

Zitieren

APA

Yang, T., Wang, Y., Zhou, Z., & Liu, C. T. (2026). engGNN: a dual-graph neural network for omics-based disease classification and feature selection. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag481

Vancouver

Yang T, Wang Y, Zhou Z, Liu CT. engGNN: a dual-graph neural network for omics-based disease classification and feature selection. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag481

BibTeX
@article{Yang2026,
  author = {Yang, Tiantian and Wang, Yuxuan and Zhou, Zhenwei and Liu, Ching-Ti},
  title = {engGNN: a dual-graph neural network for omics-based disease classification and feature selection},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag481}
}
Kostenlos starten →