EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Adaptive multi-view information bottleneck for multi-omics data clustering

Zhen Tian, Xiaojiao Wei, Zhengzheng Lou, Zhixia Teng, Shouli Fu

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbaf717 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Zhen Tian und 4 weiteren Autor:innen. Beteiligte Einrichtung: Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, No. 1, Chengdian Road, Kecheng District, Quzhou 32…. Hauptthemen laut MEDLINE: Multiomics, Computational Biology. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China, Municipal Government of Quzhou, Natural Science Foundation of Henan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation: Recent advances in single-cell sequencing have transformed precise measurement of gene expression at cellular resolution, enabling unprecedented dissection of cellular heterogeneity and intricate biological processes. The accumulation of multi-omics data offers new avenues for cell clustering—a critical foundation for cell-type identification and downstream analyses. However, substantial challenges persist in simultaneously achieving effective integration of complementary information in multi-omics data and their appropriate weight allocation. Results: Here, we propose an Adaptive Multi-View clustering framework with the Information Bottleneck principle to solve the multi-omics data clustering task (named scAMVIB). The proposed model could learn multi-view omics representations that capture both inter-omics associations and omics-specific patterns, with the adaptive weight allocation. Specifically, multi-view data comprise two components: (i) the integrated omics feature matrix derived from the similarity network fusion strategy and (ii) omics-specific representations from distinct platforms. These inputs are processed through a multi-view information bottleneck clustering framework that leverages cross-view complementarity to enhance representations. View weights are adaptively assigned via maximum entropy regularization, proportional to their information content. The final cell partitions are obtained through sequential iterative optimization. Comprehensive experiments across multiple datasets demonstrate that scAMVIB has strong competitiveness in clustering while maintaining biological interpretability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MultiomicsComputational BiologyClustering AlgorithmsCluster AnalysisAlgorithmsHumans

Stichwörter der Autor:innen

adaptive weighting mechanismsmulti-omics data clusteringmulti-view information bottleneck

Autor:innen und Institutionen

  • Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, No. 1, Chengdian Road, Kecheng District, Quzhou 324000, China.
  • School of Computer and Artificial Intelligence, Zhengzhou University, No. 100, Kexue Road, Gaoxin District, Zhengzhou 450000, China.
  • The Patent Examination Cooperation (Jiangsu) Center of the Patent Office of China National Intellectual Property Administration, 145 Hanzhongmen Street, Jianye District, Nanjing 210000, China.
  • College of Computer and Control Engineering, Northeast Forestry University, 26 Hexing Road, Xiangfang District, Harbin 150040, China.
  • School of Cyber Science and Engineering, Zhengzhou University, No. 97, Wenhua Road, Zhengzhou 450000, China.

Förderung

  • National Natural Science Foundation of China
  • Municipal Government of Quzhou
  • Natural Science Foundation of Henan
  • Natural Science Foundation of Heilongjiang Province

Zitieren

APA

Tian, Z., Wei, X., Lou, Z., Teng, Z., & Fu, S. (2026). Adaptive multi-view information bottleneck for multi-omics data clustering. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf717

Vancouver

Tian Z, Wei X, Lou Z, Teng Z, Fu S. Adaptive multi-view information bottleneck for multi-omics data clustering. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbaf717

BibTeX
@article{Tian2026,
  author = {Tian, Zhen and Wei, Xiaojiao and Lou, Zhengzheng and Teng, Zhixia and Fu, Shouli},
  title = {Adaptive multi-view information bottleneck for multi-omics data clustering},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbaf717}
}
Kostenlos starten →