EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

From Black Box to Biological Insight: AttentioFuse Unlocks Multi-Omics Dynamics in Lung Cancer

Yuhang Huang iD, Yungang He, Liyan Zeng, Lei Liu iD, Fan Zhong

Cancers · 09.03.2026 · 18 (5) · 878

DOI: 10.3390/cancers18050878 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancers, online erschienen am 09.03.2026. Verfasst von Yuhang Huang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institutes of Biomedical Sciences, Fudan University, 131 Dongan Road, Shanghai 200032, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Shanghai Science and Technology Innovation Action Plan in Computational Biology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Lung adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC), the major subtypes of non-small cell lung cancer (NSCLC), exhibit distinct molecular landscapes that demand precision in prognosis and therapy. While deep learning models can achieve high predictive accuracy, their black-box nature limits clinical translation.

Methods

We introduce AttentioFuse, an interpretable deep learning framework employing a Reactome-guided mid-fusion strategy for multi-omics integration. AttentioFuse builds on three pillars: (i) dual-phase learning with omics-specific encoders to preserve modality-unique patterns, (ii) hierarchical attention mechanisms (cross-omics, feature-level, and fusion-layer) to quantify layer contributions dynamically, and (iii) integrated explainability combining DeepSHAP and global attention weights for gene-to-pathway interpretation. Two depth variants are instantiated under identical priors: a three-layer configuration (3F) for main discrimination and a five-layer configuration (AttentioFuse-5X) for deeper hierarchical interpretation; the 5X variant is trained end-to-end and yields comparable accuracy while enhancing pathway-level resolution.

Results

Evaluated on The Cancer Genome Atlas (TCGA) LUAD/LUSC cohorts, AttentioFuse matches state-of-the-art performance in TNM staging while uncovering actionable biological insights, including pan-NSCLC AKT/mTOR metabolic control, histology-divergent Notch signaling roles, and additional pathways related to developmental reactivation, microbiota-associated metastasis, and extracellular matrix remodeling.

Conclusions

By design, AttentioFuse-5X bridges predictive performance with hierarchical, pathway-resolved explanations, advancing oncology by transforming black-box predictions into biologically grounded decision support.

Schlagwörter

Stichwörter der Autor:innen

NSCLChierarchical attentioninterpretable deep learningmid-fusionmulti-omics

Autor:innen und Institutionen

  • Institutes of Biomedical Sciences, Fudan University, 131 Dongan Road, Shanghai 200032, China.
  • Intelligent Medicine Institute, Fudan University, Shanghai 200032, China.
  • Shanghai Institute of Infectious Disease and Biosecurity, Fudan University, Shanghai 200032, China.
  • Shanghai Institute of Stem Cell Research and Clinical Translation, Shanghai 200120, China.

ORCID-Profile: Yuhang Huang, Lei Liu

Förderung

  • National Key Research and Development Program of China
  • Shanghai Science and Technology Innovation Action Plan in Computational Biology

Zitieren

APA

Huang, Y., He, Y., Zeng, L., Liu, L., & Zhong, F. (2026). From Black Box to Biological Insight: AttentioFuse Unlocks Multi-Omics Dynamics in Lung Cancer. Cancers, 18(5), 878. https://doi.org/10.3390/cancers18050878

Vancouver

Huang Y, He Y, Zeng L, Liu L, Zhong F. From Black Box to Biological Insight: AttentioFuse Unlocks Multi-Omics Dynamics in Lung Cancer. Cancers. 2026;18(5):878. doi:10.3390/cancers18050878

BibTeX
@article{Huang2026,
  author = {Huang, Yuhang and He, Yungang and Zeng, Liyan and Liu, Lei and Zhong, Fan},
  title = {From Black Box to Biological Insight: AttentioFuse Unlocks Multi-Omics Dynamics in Lung Cancer},
  journal = {Cancers},
  year = {2026},
  volume = {18},
  number = {5},
  pages = {878},
  doi = {10.3390/cancers18050878}
}
Kostenlos starten →