CASPER: Cross-modal Alignment of Spatial and single-cell Profiles for Expression Recovery

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kumar, Amit, Kaur, Maninder, Mall, Raghvendra, Gupta, Sukrit
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912718565408768
author Kumar, Amit
Kaur, Maninder
Mall, Raghvendra
Gupta, Sukrit
author_facet Kumar, Amit
Kaur, Maninder
Mall, Raghvendra
Gupta, Sukrit
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_15139
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CASPER: Cross-modal Alignment of Spatial and single-cell Profiles for Expression Recovery
Kumar, Amit
Kaur, Maninder
Mall, Raghvendra
Gupta, Sukrit
Genomics
Artificial Intelligence
Machine Learning
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.
title CASPER: Cross-modal Alignment of Spatial and single-cell Profiles for Expression Recovery
topic Genomics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2511.15139