TRACER: twin-contrastive learning for fine-grained and rare spatial domain identification in spatial transcriptomics
Bioinformatics · 02.11.2026 · 42 (11)
DOI: 10.1093/bioinformatics/btag805 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 30.10.2026. Verfasst von Qiaoming Liu und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence, Henan University, Zhengzhou 450000, China. Hauptthemen laut MEDLINE: Spatial Transcriptomics, Machine Learning, Software. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, the Science and Technology Key Project of Henan Provincial Department of Science and Technology.
Abstract (Originalsprache)
Motivation Fine-grained and rare spatial domains are difficult to identify in spatial transcriptomics because they contain few spots, show subtle transcriptional differences, and are strongly influenced by neighboring regions. Results We present TRACER, a twin-contrastive learning framework that integrates a graph convolutional autoencoder with neighborhood-aware instance-level and cluster-level contrastive learning. By jointly preserving local spatial continuity and enhancing domain separability, TRACER achieved competitive and generally robust performance compared with representative spatial domain identification methods across multiple spatially resolved transcriptomic datasets, including human dorsolateral prefrontal cortex generated by 10× Visium, mouse brain datasets generated by STARmap, osmFISH, and BARISTAseq, and human breast cancer. TRACER recovered major cortical and anatomical structures, improved the identification of rare or transitional domains in the mouse somatosensory cortex, and revealed candidate functionally distinct small domains within a broadly annotated breast cancer region. Availability and implementation The source code of TRACER is available at https://github.com/luxin-heart/TRACER.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Artificial Intelligence, Henan University, Zhengzhou 450000, China.
- Faculty of Computing, Harbin Institute of Technology, Harbin 150001, China.
- Zhengzhou Advanced Research Institute, Harbin Institute of Technology, Zhengzhou 450000, China.
- School of Computer Science and Artificial Intelligence, Northeast Forestry University, Harbin 150040, China.
- School of Computer and Information Engineering, Henan University of Economics and Law, Zhengzhou 450000, China.
ORCID-Profile: Murong Zhou, Yuming Zhao
Förderung
- National Natural Science Foundation of China
- the Science and Technology Key Project of Henan Provincial Department of Science and Technology
Zitieren
APA
Liu, Q., Lu, X., Song, B., Wei, Q., Feng, W., Guo, K., Wang, J., Zhou, M., Zhao, Y., & Wang, G. (2026). TRACER: twin-contrastive learning for fine-grained and rare spatial domain identification in spatial transcriptomics. Bioinformatics, 42(11). https://doi.org/10.1093/bioinformatics/btag805
Vancouver
Liu Q, Lu X, Song B, Wei Q, Feng W, Guo K, et al. TRACER: twin-contrastive learning for fine-grained and rare spatial domain identification in spatial transcriptomics. Bioinformatics. 2026;42(11). doi:10.1093/bioinformatics/btag805
BibTeX
@article{Liu2026,
author = {Liu, Qiaoming and Lu, Xin and Song, Bingsen and Wei, Qianran and Feng, Wenzhe and Guo, Kexin and Wang, Jian and Zhou, Murong and Zhao, Yuming and Wang, Guohua},
title = {TRACER: twin-contrastive learning for fine-grained and rare spatial domain identification in spatial transcriptomics},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {11},
doi = {10.1093/bioinformatics/btag805}
}
EUVIMED