EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SpaBiT: enhancing spatial transcriptomics resolution via bidirectional attention transformers

Xiaofei Liu iD, Ao Li iD, Wenwen Min iD

Bioinformatics · 02.07.2026 · 42 (7)

DOI: 10.1093/bioinformatics/btag443 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 02.07.2026. Verfasst von Xiaofei Liu und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Engineering, Yunnan University, Yunnan 650500, China. Hauptthemen laut MEDLINE: Spatial Transcriptomics, Software, Image Processing, Computer-Assisted, Computational Biology. Die Arbeit 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)

Motivation Spatial transcriptomics (STs) enables the precise mapping of gene expression within tissue architecture, however its application is often limited by low spatial resolution and sparse sampling. While existing deep learning methods leverage histology images, spatial coordinates, or low-resolution expression data to predict high-density profiles, these methods are limited in either capturing the intrinsic constraints between histological context and spatial topology or ignoring the complex local neighborhood relationships between spots. Results To address these limitations, we propose SpaBiT, a multimodal framework designed to enhance ST resolution via a bidirectional attention mechanism. At its core, SpaBiT employs a bidirectional cross-attention module to facilitate precise information exchange between image features and neighborhood-aware representations learned via a graph attention network. This design explicitly models the synergistic constraints between local morphology and spatial graph topology, yielding high-fidelity, high-density gene expression maps. SpaBiT exhibits competitive performance in reconstructing complex spatial gene expression, outperforming the benchmark models utilized in this study across various quantitative metrics, providing a robust tool for deciphering complex tissue microenvironments. Availability and implementation The source code and datasets are available at https://github.com/wenwenmin/SpaBiT.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spatial TranscriptomicsSoftwareImage Processing, Computer-AssistedComputational BiologyGene Expression ProfilingGraph Neural NetworksAlgorithmsDeep LearningAnimalsHumans

Autor:innen und Institutionen

  • School of Information Science and Engineering, Yunnan University, Yunnan 650500, China.

ORCID-Profile: Xiaofei Liu, Ao Li, Wenwen Min

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Liu, X., Li, A., & Min, W. (2026). SpaBiT: enhancing spatial transcriptomics resolution via bidirectional attention transformers. Bioinformatics, 42(7). https://doi.org/10.1093/bioinformatics/btag443

Vancouver

Liu X, Li A, Min W. SpaBiT: enhancing spatial transcriptomics resolution via bidirectional attention transformers. Bioinformatics. 2026;42(7). doi:10.1093/bioinformatics/btag443

BibTeX
@article{Liu2026,
  author = {Liu, Xiaofei and Li, Ao and Min, Wenwen},
  title = {SpaBiT: enhancing spatial transcriptomics resolution via bidirectional attention transformers},
  journal = {Bioinformatics},
  year = {2026},
  volume = {42},
  number = {7},
  doi = {10.1093/bioinformatics/btag443}
}
Kostenlos starten →