SpatialPrompt: spatially aware scalable and accurate tool for spot deconvolution and domain identification in spatial transcriptomics

Abstract

Efficiently mapping of cell types in situ remains a major challenge in spatial transcriptomics. Most spot deconvolution tools ignore spatial coordinate information and perform extremely slow on large datasets. We introduce SpatialPrompt, a spatially aware and scalable tool for spot deconvolution and domain identification. SpatialPrompt integrates gene expression, spatial location, and single-cell RNA sequencing (scRNA-seq) dataset as reference to accurately infer cell-type proportions of spatial spots. At the core, SpatialPrompt uses non-negative ridge regression and graph neural network to efficiently capture local microenvironment information. Our extensive benchmarking analysis using human prefrontal cortex dataset demonstrated superior performance of SpatialPrompt over 11 existing tools. On mouse hippocampus dataset, SpatialPrompt achieves spot deconvolution and domain identification within 2 minutes for 50,000 spots. Overall, domain identification using SpatialPrompt was 44 to 150 times faster than existing methods. We build a database housing 40 plus curated scRNA-seq datasets for seamless integration with SpatialPrompt for spot deconvolution.