SpatialPrompt

SpatialPrompt integrates gene expression, spatial location, and scRNA-seq reference datasets to infer cell-type proportions of spatial spots and identify spatial domains in spatial transcriptomics data.

Key Features:

• Spot Deconvolution: SpatialPrompt infers cell-type proportions of spatial spots using gene expression, spatial location, and scRNA-seq reference datasets.
• Domain Identification: SpatialPrompt identifies spatial domains by capturing local microenvironment information.
• Scalable Performance: SpatialPrompt achieves spot deconvolution and domain identification within 2 minutes for 50,000 spots on mouse hippocampus dataset, with domain identification 44 to 150 times faster than existing methods.
• Reference Database Integration: SpatialPrompt integrates with a database housing 40 plus curated scRNA-seq datasets for seamless spot deconvolution.

Scientific Applications:

• Spatial Transcriptomics Analysis: SpatialPrompt maps cell types in situ across spatial transcriptomics platforms including Visium, Slide-seq, and MERFISH.
• Large Dataset Processing: SpatialPrompt enables efficient analysis of large spatial transcriptomics datasets such as mouse hippocampus with 50,000 spots.

Methodology:

SpatialPrompt uses non-negative ridge regression and graph neural network to capture local microenvironment information.