SPiCe: integrative spatial modelling of cellular plasticity using graph neural networks and geostatistics
Cellular plasticity, the ability of cells to change phenotype in response to intrinsic and environmental cues, is central to development and disease, yet remains difficult to quantify. We present SPiCe, a framework that integrates graph neural networks and spatial regression models to predict and explain cell state variation in spatial transcriptomics data. Applied to epithelial-mesenchymal plasticity (EMP) in breast cancer, SPiCe shows that mesenchymal states are stabilised by copy number alterations and microenvironmental cues, whereas hybrid states remain unpredictable, and uncovers long-range myofibroblast influences on EMP. Together, these analyses provide a framework for quantifying cellular plasticity and its spatial determinants.
Authors
- Cenk Celik (ORCID: https://orcid.org/0000-0001-8301-0172)
- Eloise Withnell (ORCID: https://orcid.org/0000-0002-7368-5149)
- Maria Secrier (ORCID: https://orcid.org/0000-0003-2758-1741)
Institutions
- University College London (GB)
Publication Details
- Journal
- Genome biology
- Published
- 2026-11-19
- DOI
- https://doi.org/10.1186/s13059-026-04350-1
- Primary Topic
- Single-cell and spatial transcriptomics
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Alan Turing Institute
- UK Research and Innovation
- Medical Research Council
- Biotechnology and Biological Sciences Research Council