EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

MODA: a graph convolutional network-based multi-omics integration framework for unraveling hub molecules and disease mechanisms

Jinhui Zhao, Yanyan Zhou, Han Bao, Xinjie Zhao, Xinxin Wang, Chunxia Zhao, Wangshu Qin iD, Xin Lu iD, Guowang Xu

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf532 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Jinhui Zhao und 8 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Medical Proteomics, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, No. 457 Zhongshan Road, Shahekou Distr…. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Computational Biology, Genomics. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China, Innovation Program of Science and Research from the DICP, CAS, AI S&T Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Advances in omics technologies provide unprecedented opportunities for systems biology, yet integrating multi-omics data remains challenging due to its complexity, heterogeneity, and the sparsity of prior knowledge networks. Here, we introduce a multi-omics data integration analysis (MODA) framework that fully incorporates prior knowledge to identify hub molecules and pathways, and elucidate biological mechanisms. By leveraging multiple machine learning approaches, MODA transforms raw omics data into a feature importance matrix that is mapped onto a biological knowledge graph to mitigate omics data noise. Then, it uses graph convolutional networks with attention mechanisms to capture intricate molecular relationships and rank molecules via a feature-selective layer. Ultimately, MODA transcends the limitations of predefined pathway annotations by employing an overlapping community detection algorithm to extract core functional modules that are involved in multiple pivotal disease pathways. Systematic evaluations show that MODA outperforms seven existing multi-omics integration methods in classification performance while maintaining biological interpretability. Moreover, MODA achieves superior stability in pan-cancer datasets. Application to the multi-omics datasets of prostate cancer reveals a key role for carnitine and palmitoylcarnitine, regulated by BBOX1 in the progression of prostate cancer. Population samples and in vitro experiments further validate these findings. With high data utilization efficiency and low computational cost, MODA serves as a robust tool for uncovering novel disease mechanisms and advancing precision medicine.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Prostatic NeoplasmsComputational BiologyGenomicsHumansAlgorithmsMachine LearningMaleSystems BiologyMultiomics

Stichwörter der Autor:innen

biological knowledge graphdeep learning, graph convolutional networksmulti-omics integrationprostate cancer

Autor:innen und Institutionen

  • State Key Laboratory of Medical Proteomics, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, No. 457 Zhongshan Road, Shahekou District, Dalian, Liaoning 116023, P.R. China.
  • University of Chinese Academy of Sciences, No. 1 Yanqihu East Road, Huairou District, Beijing 100049, P.R. China.
  • Liaoning Province Key Laboratory of Metabolomics, No. 457 Zhongshan Road, Shahekou District, Dalian, Liaoning 116023, P.R. China.
  • Hepatobiliary Surgery Department, Dalian Medical University, No. 9, West Section of Lvshun South Road, Dalian 116044, P.R. China.

ORCID-Profile: Wangshu Qin, Xin Lu

Förderung

  • National Natural Science Foundation of China
  • Innovation Program of Science and Research from the DICP, CAS
  • AI S&T Program
  • Yulin Branch, Dalian National Laboratory for Clean Energy, CAS, China
  • Liaoning Province International Science and Technology Cooperation Program Project

Zitieren

APA

Zhao, J., Zhou, Y., Bao, H., Zhao, X., Wang, X., Zhao, C., Qin, W., Lu, X., & Xu, G. (2025). MODA: a graph convolutional network-based multi-omics integration framework for unraveling hub molecules and disease mechanisms. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf532

Vancouver

Zhao J, Zhou Y, Bao H, Zhao X, Wang X, Zhao C, et al. MODA: a graph convolutional network-based multi-omics integration framework for unraveling hub molecules and disease mechanisms. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf532

BibTeX
@article{Zhao2025,
  author = {Zhao, Jinhui and Zhou, Yanyan and Bao, Han and Zhao, Xinjie and Wang, Xinxin and Zhao, Chunxia and Qin, Wangshu and Lu, Xin and Xu, Guowang},
  title = {MODA: a graph convolutional network-based multi-omics integration framework for unraveling hub molecules and disease mechanisms},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf532}
}
Kostenlos starten →