The covariance environment defines cellular niches for spatial inference Journal Article

   


Authors: Haviv, D.; Remšík, J.; Gatie, M.; Snopkowski, C.; Takizawa, M.; Pereira, N.; Bashkin, J.; Jovanovich, S.; Nawy, T.; Chaligne, R.; Boire, A.; Hadjantonakis, A. K.; Pe'er, D.
Article Title: The covariance environment defines cellular niches for spatial inference
Abstract: A key challenge of analyzing data from high-resolution spatial profiling technologies is to suitably represent the features of cellular neighborhoods or niches. Here we introduce the covariance environment (COVET), a representation that leverages the gene-gene covariate structure across cells in the niche to capture the multivariate nature of cellular interactions within it. We define a principled optimal transport-based distance metric between COVET niches that scales to millions of cells. Using COVET to encode spatial context, we developed environmental variational inference (ENVI), a conditional variational autoencoder that jointly embeds spatial and single-cell RNA sequencing data into a latent space. ENVI includes two decoders: one to impute gene expression across the spatial modality and a second to project spatial information onto single-cell data. ENVI can confer spatial context to genomics data from single dissociated cells and outperforms alternatives for imputing gene expression on diverse spatial datasets. Using gene-gene covariance structure to represent cellular neighborhoods improves the integration of single-cell RNA sequencing and spatial transcriptomics data.
Keywords: mice; interneurons; somatostatin; mutations; expression; cells; homeobox gene; defects; multiplex; homeotic transformation
Journal Title: Nature Biotechnology
Volume: 43
Issue: 2
ISSN: 1087-0156
Publisher: Nature Publishing Group  
Date Published: 2025-02-01
Start Page: 269
End Page: 280
Language: English
ACCESSION: WOS:001195788200005
DOI: 10.1038/s41587-024-02193-4
PROVIDER: wos
PMCID: PMC11445396
PUBMED: 38565973
Notes: Article -- MSK Cancer Center Support Grant (P30 CA008748) acknowledged in PubMed and PDF -- MSK corresponding author is Dana Pe'er -- Source: Wos
Altmetric
What is Altmetric?
Citation Impact
What is Dimensions Citation Badge?
BMJ Impact Analytics
MSK Authors
  1. Anna-Katerina Hadjantonakis
    192 Hadjantonakis
  2. Adrienne Boire
    106 Boire
  3. Dana Pe'er
    110 Pe'er
  4. Jan Remsik
    25 Remsik
  5. Tal Nawy
    15 Nawy
  6. Ronan Chaligne
    36 Chaligne
  7. Doron Haviv
    6 Haviv
  8. Meril Takizawa
    5 Takizawa
  9. Catherine Snopkowski
    3 Snopkowski
  10. Mohamed Ibrahim Gatie
    2 Gatie
Related MSK Work