EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SpaBalance: Balanced Learning for Efficient Spatial Multi‐Omics Decoding

Yingbo Cui iD, Yong Zhao, Canqun Yang, Tao Tang, Xiangke Liao, Hongyu Zhang, Huiying Zhao, Zheng Wang, Yuansong Zeng iD

Advanced Science · 2025-12 · 12 (48)

DOI: 10.1002/advs.202512973 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 14.10.2025. Verfasst von Yingbo Cui und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, National University of Defense Technology, Changsha, 410073, China. Hauptthemen laut MEDLINE: Computational Biology, Proteomics, Genomics. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Innovation Key R&D Program of Chongqing, National Natural Science Foundation of China, National Natural Science Foundation of China Youth Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent breakthroughs in spatially resolved multi‐omics have unlocked the ability to simultaneously profile multiple molecular layers within tissues, offering unprecedented insights into their coordinated roles in development and disease. Despite these advancements, integrative analysis of multi‐omics data remains a formidable challenge due to inherent biological and technical discrepancies across assays, often leading to gradient conflicts during joint learning. These conflicts arise as optimization trajectories from different omics compete or contradict, thereby constraining integration performance. To overcome this challenge, SpaBalance, a unified computational framework designed to harmonize cross‐omics learning via gradient coordination and adaptive feature decomposition, is proposed. SpaBalance introduces a novel gradient equilibrium mechanism that dynamically balances inter‐omics contributions during backpropagation, resolving conflicts through task‐specific prioritization without requiring manual weighting. Concurrently, SpaBalance leverages a dual‐stream architecture to simultaneously learn shared representations and preserve omics‐specific features. Extensive evaluations across a variety of spatial omics datasets, including paired epigenome‐transcriptome and proteome‐transcriptome data from human tumors and brain tissues, demonstrate SpaBalance's superior ability to delineate complex spatial domains and uncover previously hidden multi‐omics regulatory hubs, significantly improving clustering accuracy and biological interpretability. Moreover, SpaBalance flexibly scales to integrate multiple omics, bridging data integration with biological discovery and advancing spatially resolved systems biology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computational BiologyProteomicsGenomicsHumansTranscriptomeProteomeMultiomics

Stichwörter der Autor:innen

cross‐omics integrationmulti‐omics balanced learningprivate and shared learningspatial multi‐omics

Substanzen

Proteome

Autor:innen und Institutionen

  • College of Computer Science and Technology, National University of Defense Technology, Changsha, 410073, China.
  • School of Big Data and Software Engineering, Chongqing University, Chongqing, 401331, China.
  • Department of Pathology, Department of Medical Research Center, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, 510120, China.
  • Jinfeng Laboratory, Chongqing, 400039, China.
  • School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, 510006, China.

ORCID-Profile: Yingbo Cui, Yuansong Zeng

Förderung

  • Science and Technology Innovation Key R&D Program of Chongqing
  • National Natural Science Foundation of China
  • National Natural Science Foundation of China Youth Program
  • Science and Technology Innovation Program of Hunan
  • Innovative Talent Program of National University of Defense Technology
  • National Key R&D Program of China
  • Research and Development Project of Pazhou Lab
  • National Key Research and Development Program of China

Zitieren

APA

Cui, Y., Zhao, Y., Yang, C., Tang, T., Liao, X., Zhang, H., Zhao, H., Wang, Z., & Zeng, Y. (2025). SpaBalance: Balanced Learning for Efficient Spatial Multi‐Omics Decoding. Advanced Science, 12(48). https://doi.org/10.1002/advs.202512973

Vancouver

Cui Y, Zhao Y, Yang C, Tang T, Liao X, Zhang H, et al. SpaBalance: Balanced Learning for Efficient Spatial Multi‐Omics Decoding. Advanced Science. 2025;12(48). doi:10.1002/advs.202512973

BibTeX
@article{Cui2025,
  author = {Cui, Yingbo and Zhao, Yong and Yang, Canqun and Tang, Tao and Liao, Xiangke and Zhang, Hongyu and Zhao, Huiying and Wang, Zheng and Zeng, Yuansong},
  title = {SpaBalance: Balanced Learning for Efficient Spatial Multi‐Omics Decoding},
  journal = {Advanced Science},
  year = {2025},
  volume = {12},
  number = {48},
  doi = {10.1002/advs.202512973}
}
Kostenlos starten →