EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integration of multi-source gene interaction networks and omics data with graph attention networks to identify novel disease genes

Kaiyuan Yang iD, Jiabei Cheng iD, Shenghao Cao iD, Xiaoyong Pan iD, Hong-Bin Shen iD, Jin Cheng, Ye Yuan iD

Bioinformatics · 2025

DOI: 10.1093/bioinformatics/btaf181 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2025. Verfasst von Kaiyuan Yang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Biopharmaceutical Preparation and Delivery, State Key Laboratory of Biochemical Engineering, Institute of Process Engineering, Chin…. Hauptthemen laut MEDLINE: Gene Regulatory Networks, Computational Biology, Genomics, Disease. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation The pathogenesis of diseases is closely associated with genes, and the discovery of disease genes holds significant importance for understanding disease mechanisms and designing targeted therapeutics. However, biological validation of all genes for diseases is expensive and challenging. Results In this study, we propose DGP-AMIO, a computational method based on graph attention networks, to rank all unknown genes and identify potential novel disease genes by integrating multi-omics and gene interaction networks from multiple data sources. DGP-AMIO outperforms other methods significantly on 20 disease datasets, with an average AUROC and AUPR exceeding 0.9. The superior performance of DGP-AMIO is attributed to the integration of multiomics and gene interaction networks from multiple databases, as well as triGAT, a proposed GAT-based method that enables precise identification of disease genes in directed gene networks. Enrichment analysis conducted on the top 100 genes predicted by DGP-AMIO and literature research revealed that a majority of enriched GO terms, KEGG pathways and top genes were associated with diseases supported by relevant studies. We believe that our method can serve as an effective tool for identifying disease genes and guiding subsequent experimental validation efforts. Availability and implementation DGP-AMIO is publicly available at https://github.com/yangkaiyuan1027/DGP-AMIO.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Gene Regulatory NetworksComputational BiologyGenomicsDiseaseHumansDatabases, GeneticAlgorithmsSoftware

Autor:innen und Institutionen

  • Key Laboratory of Biopharmaceutical Preparation and Delivery, State Key Laboratory of Biochemical Engineering, Institute of Process Engineering, Chinese Academy of Sciences, Beijing 100190, China.
  • Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai 200240, China.
  • Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai 200240, China.
  • Medical Robot Research Institute, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China.

ORCID-Profile: Kaiyuan Yang, Jiabei Cheng, Shenghao Cao, Xiaoyong Pan, Hong-Bin Shen, Ye Yuan

Zitieren

APA

Yang, K., Cheng, J., Cao, S., Pan, X., Shen, H. B., Cheng, J., & Yuan, Y. (2025). Integration of multi-source gene interaction networks and omics data with graph attention networks to identify novel disease genes. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf181

Vancouver

Yang K, Cheng J, Cao S, Pan X, Shen HB, Cheng J, et al. Integration of multi-source gene interaction networks and omics data with graph attention networks to identify novel disease genes. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf181

BibTeX
@article{Yang2025,
  author = {Yang, Kaiyuan and Cheng, Jiabei and Cao, Shenghao and Pan, Xiaoyong and Shen, Hong-Bin and Cheng, Jin and Yuan, Ye},
  title = {Integration of multi-source gene interaction networks and omics data with graph attention networks to identify novel disease genes},
  journal = {Bioinformatics},
  year = {2025},
  doi = {10.1093/bioinformatics/btaf181}
}
Kostenlos starten →