EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DBCL-DFNet: Dual-Branch Contrastive Learning for Multi-Omics Dynamic Fusion

Yun Dang, Xiaoran Yan, Li Zhou, Dongxi Li

Entropy · 30.05.2026 · 28 (6) · 616

DOI: 10.3390/e28060616 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 30.05.2026. Verfasst von Yun Dang und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan 030024, China. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Basic Research Programs of Shanxi Province, Key Research and Development Programs of Shanxi Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal omics data portray biological processes across molecular layers, yet their heterogeneity and high dimensionality hinder a unified representation. Existing integrative approaches either focus on local feature interactions or adopt static fusion, often overlooking the complementary global sequential context and the dynamic relevance among omics sources. Consequently, clinically critical tasks such as accurate cancer-subtype classification and therapy selection still lack sufficient accuracy and robustness. We introduce the Dual-Branch Contrastive Learning for Multi-Omics Dynamic Fusion Network (DBCL-DFNet), a dual-branch contrastive-learning framework that simultaneously encodes local heterogeneous graphs and global omics sequences, distills key features via contrastive objectives, and employs a dynamic attention mechanism for adaptive, data-driven fusion. Benchmarked on three public cancer multi-omics datasets, DBCL-DFNet outperforms both conventional machine-learning models and state-of-the-art deep-integration methods, establishing a competitive and reliable framework for multi-omics integration and demonstrating potential for precision-oncology decision-making. From an information-theoretic perspective, the framework integrates Copula-entropy-guided feature selection with mutual-information-maximizing contrastive alignment, providing a principled foundation for robust multi-omics integration.

Schlagwörter

Stichwörter der Autor:innen

GATcontrastive learningcopula entropyheterogeneous graphmambamulti-omics integration

Autor:innen und Institutionen

  • College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan 030024, China.
  • College of Artificial Intelligence, Taiyuan University of Technology, Taiyuan 030024, China.
  • College of Artificial Intelligence, Wuhan University, Wuhan 430072, China.

Förderung

  • National Natural Science Foundation of China
  • Basic Research Programs of Shanxi Province
  • Key Research and Development Programs of Shanxi Province
  • Chinese Academy of Engineering
  • Key Research and Development Program of Shanxi Province

Zitieren

APA

Dang, Y., Yan, X., Zhou, L., & Li, D. (2026). DBCL-DFNet: Dual-Branch Contrastive Learning for Multi-Omics Dynamic Fusion. Entropy, 28(6), 616. https://doi.org/10.3390/e28060616

Vancouver

Dang Y, Yan X, Zhou L, Li D. DBCL-DFNet: Dual-Branch Contrastive Learning for Multi-Omics Dynamic Fusion. Entropy. 2026;28(6):616. doi:10.3390/e28060616

BibTeX
@article{Dang2026,
  author = {Dang, Yun and Yan, Xiaoran and Zhou, Li and Li, Dongxi},
  title = {DBCL-DFNet: Dual-Branch Contrastive Learning for Multi-Omics Dynamic Fusion},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {6},
  pages = {616},
  doi = {10.3390/e28060616}
}
Kostenlos starten →