EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-omics data integration for enhanced cancer subtyping via interactive multi-kernel learning

Hongyan Cao iD, Tong Wang, Zhaoyang Xu, Xin Zhao, Gaiqin Liu, Xiaoling Yang, Ruiling Fang, Yanhong Luo, Ping Zeng iD, Hongmei Yu, Yanbo Zhang iD, Yuehua Cui iD

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf687 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Hongyan Cao und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Health Statistics, Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, School of Public Health, Shanxi Medical Universi…. Hauptthemen laut MEDLINE: Carcinoma, Renal Cell, Kidney Neoplasms, Computational Biology, Genomics. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Applied Basic Research Project of Shanxi Province, Shanxi Province Research Funding Project for Returned Overseas Scholars.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cancer is a highly heterogeneous disease characterized by complex molecular changes. Subtypes identified through multi-omics data hold significant promise for improving prognosis and facilitating personalized precision treatment. Recent multi-omics integration methods have mostly focused on capturing complementary information from different data types, often overlooking potential interactions between omics data. Here we develop a novel method named interactive multi-kernel learning (iMKL), which incorporates omics-omics interactions alongside heterogeneous data types under the unsupervised multi-kernel learning framework, to improve subtype identification. Using the sample-similarity kernel for each dataset, we propose a joint Hadamard product strategy to capture higher-order interactive effects from different omics data types. We applied iMKL to two renal cell carcinoma (RCC) datasets—clear renal cell carcinoma (ccRCC) and type II papillary renal cell carcinoma (type II pRCC)—both including miRNA expression, mRNA expression, and DNA methylation data. Stability analysis through random sampling of patients or features demonstrated that iMKL exhibits strong robustness and accuracy in identifying patient subtypes. The identified subtypes revealed dramatic differences in patient survival, with both ccRCC and type II pRCC classified into three distinct subtypes. The findings in the real application highlight potential biomarkers associated with adverse patient outcomes and demonstrate substantial advancement in cancer subtype identification. The iMKL method effectively identifies tumor molecular subtypes that are strongly associated with clinical features and survival rates, providing valuable insights for accurate cancer subtyping, clinical decision-making, and the realization of personalized treatment strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Carcinoma, Renal CellKidney NeoplasmsComputational BiologyGenomicsMachine LearningNeoplasmsHumansDNA MethylationBiomarkers, TumorMicroRNAsPrognosisMultiomics

Stichwörter der Autor:innen

interactive multi-kernel learningmulti-omics data integrationomics-omics interactionsubtype identificationunsupervised multi-kernel learning

Substanzen

Biomarkers, TumorMicroRNAs

Autor:innen und Institutionen

  • Department of Health Statistics, Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, School of Public Health, Shanxi Medical University, No. 56 South Xinjian Road, Yingze District, Taiyuan, Shanxi 030001…
  • MOE Key Laboratory of Coal Environmental Pathogenicity and Prevention, Shanxi Medical University, No. 56 South Xinjian Road, Yingze District, Taiyuan, Shanxi 030001, PR China.
  • Academy of Medical Sciences, Shanxi Medical University, No. 56 South Xinjian Road, Yingze District, Taiyuan, Shanxi 030001, PR China.
  • Department of Thoracic Oncology, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Tongji Shanxi Hospital, Third Hospital of Shanxi Medical University, No. 99 Longcheng Street, Xiaodian District, Taiyuan, Sha…
  • Department of Biostatistics, School of Public Health, Xuzhou Medical University, No. 209 Tongshan Road, Yunlong District, Xuzhou, Jiangsu 221004, PR China.
  • Department of Statistics and Probability, Michigan State University, 619 Red Cedar Road, East Lansing, MI 48824, USA.

ORCID-Profile: Hongyan Cao, Ping Zeng, Yanbo Zhang, Yuehua Cui

Förderung

  • National Natural Science Foundation of China
  • Applied Basic Research Project of Shanxi Province
  • Shanxi Province Research Funding Project for Returned Overseas Scholars
  • Shanxi Province Higher Education 'Billion Project' Science and Technology Guidance Project
  • Open Project Fund from Key Laboratory of Coal Environmental Pathogenicity and Prevention
  • Ministry of Education, China
  • Michigan State University
  • Shanxi Province Higher Education ‘Billion Project’ Science and Technology Guidance Project

Zitieren

APA

Cao, H., Wang, T., Xu, Z., Zhao, X., Liu, G., Yang, X., Fang, R., Luo, Y., Zeng, P., Yu, H., Zhang, Y., & Cui, Y. (2025). Multi-omics data integration for enhanced cancer subtyping via interactive multi-kernel learning. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf687

Vancouver

Cao H, Wang T, Xu Z, Zhao X, Liu G, Yang X, et al. Multi-omics data integration for enhanced cancer subtyping via interactive multi-kernel learning. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf687

BibTeX
@article{Cao2025,
  author = {Cao, Hongyan and Wang, Tong and Xu, Zhaoyang and Zhao, Xin and Liu, Gaiqin and Yang, Xiaoling and Fang, Ruiling and Luo, Yanhong and Zeng, Ping and Yu, Hongmei and Zhang, Yanbo and Cui, Yuehua},
  title = {Multi-omics data integration for enhanced cancer subtyping via interactive multi-kernel learning},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf687}
}
Kostenlos starten →