PT  - JOURNAL ARTICLE
AU  - Weber, Lukas M.
AU  - Saha, Arkajyoti
AU  - Datta, Abhirup
AU  - Hansen, Kasper D.
AU  - Hicks, Stephanie C.
TI  - nnSVG for the scalable identification of spatially variable genes using nearest-neighbor Gaussian processes
AID  - 10.1101/2022.05.16.492124
DP  - 2023 Jan 01
TA  - bioRxiv
PG  - 2022.05.16.492124
4099  - http://biorxiv.org/content/early/2023/06/15/2022.05.16.492124.short
4100  - http://biorxiv.org/content/early/2023/06/15/2022.05.16.492124.full
AB  - Feature selection to identify spatially variable genes or other biologically informative genes is a key step during analyses of spatially-resolved transcriptomics data. Here, we propose nnSVG, a scalable approach to identify spatially variable genes based on nearest-neighbor Gaussian processes. Our method (i) identifies genes that vary in expression continuously across the entire tissue or within a priori defined spatial domains, (ii) uses gene-specific estimates of length scale parameters within the Gaussian process models, and (iii) scales linearly with the number of spatial locations. We demonstrate the performance of our method using experimental data from several technological platforms and simulations. A software implementation is available at https://bioconductor.org/packages/nnSVG.Competing Interest StatementThe authors have declared no competing interest.