EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GONet: a molecular interaction-guided graph learning framework for multi-omics cancer classification

Yiyang Chen iD, Yunning Lu iD, Da Qi iD, Yong Bai iD, Guixue Hou iD, Siqi Liu iD

GigaScience · 21.01.2026 · 15

DOI: 10.1093/gigascience/giag097 ↗

Kurz gefasst

Fachartikel in der Zeitschrift GigaScience, online erschienen am 22.10.2026. Verfasst von Yiyang Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Life Sciences, University of Chinese Academy of Sciences, No. 1 Yanqihu East Rd, Huairou District,Beijing,100049, China. Hauptthemen laut MEDLINE: Neoplasms, Computational Biology. Die Arbeit nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Integrating multi-omics profiles with molecular interaction networks enables biologically informed representation learning by combining molecular measurements with prior biological knowledge. Although graph neural networks (GNNs) are well suited for modeling molecular interaction networks, existing multi-omics methods often rely on shallow representation learning or incomplete fusion strategies, which fail to fully capture complementary information and complex dependencies across heterogeneous omics layers, resulting in suboptimal performance and limited generalizability in cancer classification tasks.

Results

Here, we propose GONet, a hierarchical GNN framework that integrates omics expression profiles, including mRNA, miRNA, and protein data, with molecular interaction networks, where nodes represent omics features and edges represent molecular interactions. GONet learns global omics representations via an autoencoder, captures local structural dependencies using Deep Graph Infomax (DGI), and enhances omics-specific representations through an attention mechanism. A gated fusion module presentations through an attention mechanism. A further enables adaptive integration of heterogeneous features, improving cancer subtype and stage classification. GONet was systematically evaluated on 13 publicly available benchmark datasets used in prior studies, covering 10 cancer types, ensuring fair comparison across methods. Across mRNA and miRNA datasets, GONet achieved an average AUROC of 0.9262, outperforming representative GNN- and non-GNN-based methods by 13.77 and 6.35%, respectively. On an independent CPTAC cohort spanning 7 cancer types, it improved performance by 25.22 and 13.91%, respectively. Incorporating proteomics further improved cancer stage classification by 5.56%, demonstrating complementary predictive value. Ablation studies confirmed the effectiveness of the DGI-based module.

Conclusions

Overall, GONet provides a unified framework for biologically informed multi-omics graph representation learning and cancer classification.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NeoplasmsComputational BiologyHumansMultiomicsGraph Neural NetworksMicroRNAsRNA, MessengerGenomics

Stichwörter der Autor:innen

cancer classificationgraph neural networkmolecular interaction networkmulti-omics data integration

Substanzen

MicroRNAsRNA, Messenger

Autor:innen und Institutionen

  • College of Life Sciences, University of Chinese Academy of Sciences, No. 1 Yanqihu East Rd, Huairou District,Beijing,100049, China.
  • Department of Proteomics, BGI-Genomics, No. 9 Yunhua Road, Yantian District, Shenzhen, Guangdong, 518083, China.
  • School of Biology and Biological Engineering, South China University of Technology, Waihuan Dong Rd, Panyu District, Guangzhou, Guangdong, 510006, China.
  • BGI Research, 146 Beishan Road, Yantian District, Shenzhen, Guangdong, 518083, China.

ORCID-Profile: Yiyang Chen, Yunning Lu, Da Qi, Yong Bai, Guixue Hou, Siqi Liu

Förderung

  • National Key Research and Development Program of China

Zitieren

APA

Chen, Y., Lu, Y., Qi, D., Bai, Y., Hou, G., & Liu, S. (2026). GONet: a molecular interaction-guided graph learning framework for multi-omics cancer classification. GigaScience, 15. https://doi.org/10.1093/gigascience/giag097

Vancouver

Chen Y, Lu Y, Qi D, Bai Y, Hou G, Liu S. GONet: a molecular interaction-guided graph learning framework for multi-omics cancer classification. GigaScience. 2026;15. doi:10.1093/gigascience/giag097

BibTeX
@article{Chen2026,
  author = {Chen, Yiyang and Lu, Yunning and Qi, Da and Bai, Yong and Hou, Guixue and Liu, Siqi},
  title = {GONet: a molecular interaction-guided graph learning framework for multi-omics cancer classification},
  journal = {GigaScience},
  year = {2026},
  volume = {15},
  doi = {10.1093/gigascience/giag097}
}
Kostenlos starten →