CASTLE: Cell-type aware SpaTial domain detection via contrastive learning embedding
PLOS Genetics · 17.11.2026 · 22 (11) · e1012365
DOI: 10.1371/journal.pgen.1012365 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Genetics, online erschienen am 17.11.2026. Verfasst von Lai Wei und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics and Probability, Michigan State University, East Lansing, Michigan, United States of America. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
With advances in spatially resolved transcriptomics across platforms and resolutions, it is now possible to measure gene-expression profiles while preserving the tissue microenvironment. Spatial clustering is central to these analyses, and recent graph neural network (GNN)-based approaches have greatly improved their accuracy. Nevertheless, precisely delineating spatial domain boundaries remains a significant challenge. Here we present a novel method CASTLE (Cell-type Aware SpaTial domain detection via contrastive Learning Embedding), by leveraging cell type information for improved spatial domain detection. CASTLE first integrates spatial proximity to construct a spatial graph, refined from cell-type similarity or expression similarity when cell type information is unavailable. Then, a self-supervised, local-context contrastive objective aligns embeddings with their immediate microenvironments. Evaluated across multiple tissues and technology resolutions, CASTLE generally achieves competitive or superior performance across datasets and metrics, with particularly strong accuracy and stability on several benchmarks, and detects spatial domains more accurately and consistently. In downstream analyses, it resolves fine-grained tissue structures and differentiates functional subtypes, supporting more nuanced biological interpretation.
Autor:innen und Institutionen
- Department of Statistics and Probability, Michigan State University, East Lansing, Michigan, United States of America.
ORCID-Profile: Lai Wei, Yuehua Cui
Zitieren
APA
Wei, L., Xie, A., & Cui, Y. (2026). CASTLE: Cell-type aware SpaTial domain detection via contrastive learning embedding. PLOS Genetics, 22(11), e1012365. https://doi.org/10.1371/journal.pgen.1012365
Vancouver
Wei L, Xie A, Cui Y. CASTLE: Cell-type aware SpaTial domain detection via contrastive learning embedding. PLOS Genetics. 2026;22(11):e1012365. doi:10.1371/journal.pgen.1012365
BibTeX
@article{Wei2026,
author = {Wei, Lai and Xie, Aoqi and Cui, Yuehua},
title = {CASTLE: Cell-type aware SpaTial domain detection via contrastive learning embedding},
journal = {PLOS Genetics},
year = {2026},
volume = {22},
number = {11},
pages = {e1012365},
doi = {10.1371/journal.pgen.1012365}
}
EUVIMED