EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

spaLLM: enhancing spatial domain analysis in multi-omics data through large language model integration

Longyi Li iD, Liyan Dong, Hao Zhang iD, Dong Xu iD, Yongli Li

Briefings in Bioinformatics · 02.07.2025 · 26 (4)

DOI: 10.1093/bib/bbaf304 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 03.07.2025. Verfasst von Longyi Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin Universi…. Hauptthemen laut MEDLINE: Software, Computational Biology, Genomics. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spatial multi-omics technologies provide valuable data on gene expression from various omics in the same tissue section while preserving spatial information. However, deciphering spatial domains within spatial omics data remains challenging due to the sparse gene expression. We propose spaLLM, the first multi-omics spatial domain analysis method that integrates large language models to enhance data representation. Our method combines a pre-trained single-cell language model (scGPT) with graph neural networks and multi-view attention mechanisms to compensate for limited gene expression information in spatial omics while improving sensitivity and resolution within modalities. SpaLLM processes multiple spatial modalities, including RNA, chromatin, and protein data, potentially adapting to emerging technologies and accommodating additional modalities. Benchmarking against eight state-of-the-art methods across four different datasets and platforms demonstrates that our model consistently outperforms other advanced methods across multiple supervised evaluation metrics. The source code for spaLLM is freely available at https://github.com/liiilongyi/spaLLM.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SoftwareComputational BiologyGenomicsHumansNeural Networks, ComputerAlgorithmsLarge Language ModelsMultiomics

Stichwörter der Autor:innen

graph neural networklarge language modelspatial domainspatial multi-omicsspatial resolved transcriptomics

Autor:innen und Institutionen

  • Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, 2699 Qianjin Street, Changchun 130012, Jilin, China.
  • Department of Electrical Engineering and Computer Science, Christopher S. Bond Life Sciences Center, University of Missouri, 1201 Rollins Street, Columbia, MO 65211, United States.
  • School of Information Science and Technology, Northeast Normal University, 5268 Renmin Street, Changchun 130117, Jilin, China.

ORCID-Profile: Longyi Li, Hao Zhang, Dong Xu

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Li, L., Dong, L., Zhang, H., Xu, D., & Li, Y. (2025). spaLLM: enhancing spatial domain analysis in multi-omics data through large language model integration. Briefings in Bioinformatics, 26(4). https://doi.org/10.1093/bib/bbaf304

Vancouver

Li L, Dong L, Zhang H, Xu D, Li Y. spaLLM: enhancing spatial domain analysis in multi-omics data through large language model integration. Briefings in Bioinformatics. 2025;26(4). doi:10.1093/bib/bbaf304

BibTeX
@article{Li2025,
  author = {Li, Longyi and Dong, Liyan and Zhang, Hao and Xu, Dong and Li, Yongli},
  title = {spaLLM: enhancing spatial domain analysis in multi-omics data through large language model integration},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  volume = {26},
  number = {4},
  doi = {10.1093/bib/bbaf304}
}
Kostenlos starten →