Reconstructing multi-scale tissue spatial architecture from single-cell RNA-seq with REMAP
Year: 2026
Type: preprint
Abstract: Understanding spatial organization of cells is critical for deciphering tissue function and disease. Single-cell RNA-sequencing (scRNA-seq) profiles transcriptomes at scale but loses spatial context, while spatial transcriptomics (ST) preserves spatial information but is constrained by cost and gene coverage. Here, we present REMAP, a deep learning framework that integrates gene expression with neighborhood-level gene-gene covariance to reconstruct multi-scale spatial organization of scRNA-seq data using one or multiple ST references. Across 2D and 3D mouse brain, human fetal cortex, and seven human cancer types, REMAP consistently outperformed existing approaches. Applied to a human multiple sclerosis atlas, REMAP resolved microglial neighborhood heterogeneity, and identified a rare pro-inflammatory microglia-astrocyte subpopulation. Across diverse cancers, REMAP recovered conserved spatially-defined cancer-associated fibroblast subtypes with known prognostic significance. By transforming cost-efficient single-cell datasets into spatially interpretable tissue maps, REMAP enables spatial hypothesis generation, microenvironment discovery, and population-scale inference of conserved and perturbed architectural principles in human disease.
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: green
Awards: Human Epilepsy Genetics - Neuronal Migration Disorders, Integration of spatial transcriptomics, genetics, and histomorphology for causal inference in atherosclerotic cardiovascular disease, Sox9 signaling in lung adenocarcinoma, Using artificial intelligence to discover spatial, genomic, and pathologic biomarkers to guide and augment immune checkpoint inhibitor therapy for gastric cancer, Cell Identity Determination in Human Brain: Somatic Mutation and Cell Lineage, Statistical methods and tools for enhancing polygenic risk prediction and discovery of causal gene pathways, Development of Distinct Areas in the Human Cerebral Cortex, Integrative analysis of spatial transcriptomics with histology images and single cells, Multi-ethnic risk prediction for complex human diseases integrating multi-source genetic and non-genetic information, Center for Gastric Pre-Cancer Atlas of Multidimensional Evolution in 3D (GAME3D), Developing informatics tools to predict virtual spatial transcriptomics data with single-cell resolution in large-scale studies
OpenAlex ID: W7130957184