# CASTLE: Cell-type aware SpaTial domain detection via contrastive learning embedding

Source: [PLOS Genetics](https://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1012365) · 2026-11-17 · Life
Page: https://themorning.science/story/castle-cell-type-aware-spatial-domain-detection-via-contrastive-learning-embeddi-0e12c9fc77d9645c
Kind: research · Impact: low

## In brief

- CASTLE is a cell-type aware method for detecting spatial domains in spatially resolved transcriptomics data.
- It uses contrastive learning to produce embeddings for spatial clustering.
- The method is described in a PLOS Genetics article by Lai Wei, Aoqi Xie and Yuehua Cui, published 2026-11-17.

## Why it matters

Spatial clustering is central to analysing spatial transcriptomics data, so a new method for identifying tissue domains while accounting for cell types may matter to researchers in this field.

## Timeline

- 2026-11-17: CASTLE method published in PLOS Genetics

## Coverage

- [CASTLE: Cell-type aware SpaTial domain detection via contrastive learning embedding](https://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1012365) — PLOS Genetics, 2026-11-17

Tags: spatial transcriptomics, spatial domain detection, contrastive learning, cell-type aware, bioinformatics, gene expression

---

Brief generated by AI (claude-haiku-5-5) from the reporting listed under Coverage. Headlines belong to their publishers. The Morning Science – https://themorning.science
