CASPER: Cross-modal Alignment of Spatial and single-cell Profiles for Expression Recovery
This work addresses the high cost and experimental constraints in spatial transcriptomics for researchers in genomics and computational biology, representing an incremental advance in modality translation methods.
The paper tackles the problem of limited gene measurement in Spatial Transcriptomics by proposing CASPER, a cross-attention framework that integrates Single-Cell RNA Sequencing data to predict unmeasured genes, showing significant improvement in nine out of twelve metrics across four dataset pairs.
Spatial Transcriptomics enables mapping of gene expression within its native tissue context, but current platforms measure only a limited set of genes due to experimental constraints and excessive costs. To overcome this, computational models integrate Single-Cell RNA Sequencing data with Spatial Transcriptomics to predict unmeasured genes. We propose CASPER, a cross-attention based framework that predicts unmeasured gene expression in Spatial Transcriptomics by leveraging centroid-level representations from Single-Cell RNA Sequencing. We performed rigorous testing over four state-of-the-art Spatial Transcriptomics/Single-Cell RNA Sequencing dataset pairs across four existing baseline models. CASPER shows significant improvement in nine out of the twelve metrics for our experiments. This work paves the way for further work in Spatial Transcriptomics to Single-Cell RNA Sequencing modality translation. The code for CASPER is available at https://github.com/AI4Med-Lab/CASPER.