Premium
Spage2vec: Unsupervised representation of localized spatial gene expression signatures
Author(s) -
Partel Gabriele,
Wählby Carolina
Publication year - 2021
Publication title -
the febs journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.981
H-Index - 204
eISSN - 1742-4658
pISSN - 1742-464X
DOI - 10.1111/febs.15572
Subject(s) - transcriptome , encode , computational biology , gene expression , representation (politics) , computer science , spatial analysis , graph , pattern recognition (psychology) , segmentation , artificial intelligence , gene , biology , genetics , geography , theoretical computer science , remote sensing , politics , political science , law
Spatial investigation of cellular heterogeneity is essential to understand tissue organization and function. We present spage2vec, an unsupervised segmentation‐free approach for analyzing the spatial transcriptomic landscape at subcellular resolution. Spage2vec models the spatial gene expression as a graph and extracts localized gene expression signatures involved in cellular and subcellular biological processes.