SpaGE: Spatial Gene Enhancement using scRNA-seq

TLDR

Single‑cell RNA sequencing reveals cellular heterogeneity but lacks spatial context, while spatial transcriptomics preserves location yet measures only a limited set of transcripts. The authors aim to develop SpaGE, a method that integrates spatial and scRNA‑seq data to predict whole‑transcriptome expression in spatial context. SpaGE combines spatial transcriptomics and scRNA‑seq datasets to infer full‑transcriptome expression patterns across spatial coordinates. SpaGE outperforms existing methods, scales to large datasets, and accurately predicts novel spatial gene patterns validated by Allen Mouse Brain Atlas in situ hybridization.

Abstract

Single-cell technologies are emerging fast due to their ability to unravel the heterogeneity of biological systems. While scRNA-seq is a powerful tool that measures whole-transcriptome expression of single cells, it lacks their spatial localization. Novel spatial transcriptomics methods do retain cells spatial information but some methods can only measure tens to hundreds of transcripts. To resolve this discrepancy, we developed SpaGE, a method that integrates spatial and scRNA-seq datasets to predict whole-transcriptome expressions in their spatial configuration. Using five dataset-pairs, SpaGE outperformed previously published methods and showed scalability to large datasets. Moreover, SpaGE predicted new spatial gene patterns that are confirmed independently using in situ hybridization data from the Allen Mouse Brain Atlas.