Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

SpaIM: Single-cell Spatial Transcriptomics Imputation via Style Transfer.

Bo Li1, Ziyang Tang2, Aishwarya Budhkar3

  • 1Department of Computer and Information Science, University of Macau, Taipa, Macau SAR, China.

Biorxiv : the Preprint Server for Biology
|February 20, 2025
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

scDeepAPA: a deep learning framework for single-cell alternative polyadenylation identification.

Briefings in bioinformatics·2026
Same author

VIRSE: a variational Bayesian framework for RNA structural ensemble inference.

Briefings in bioinformatics·2026
Same author

Socioeconomic and Clinical Determinants Driving Access to BRCA Genetic Testing in Cancer : A Case-Control Study Using Observational Electronic Health Records Across Multiple Sites.

medRxiv : the preprint server for health sciences·2026
Same author

SpaGene: A Deep Adversarial Framework for Spatial Gene Imputation.

Computational and structural biotechnology journal·2026
Same author

ShapeRNA: an integrated web server for RNA secondary structure, ensemble, and functional analysis.

Nucleic acids research·2026
Same author

GatorST: A Versatile Contrastive Meta-Learning Framework for Spatial Transcriptomic Data Analysis.

Small methods·2026
Same journal

Genetic Impacts on Variability of Body Fat Distribution Uncover Gene-Environment and Gene-Gene Interactions.

bioRxiv : the preprint server for biology·2026
Same journal

16S ribosomal RNA modification drives transcript-specific translation efficiency.

bioRxiv : the preprint server for biology·2026
Same journal

FlcE latches onto the FliL-stator complex to turbocharge flagellar motility in <i>Borrelia burgdorferi</i>.

bioRxiv : the preprint server for biology·2026
Same journal

Synaptic pruning, myelination and the emergence of psychiatric disorders in late adolescence.

bioRxiv : the preprint server for biology·2026
Same journal

Structural and functional insights into the Rcs phosphorelay.

bioRxiv : the preprint server for biology·2026
Same journal

The structural basis of RanGAP1 regulation and catalysis in nuclear transport.

bioRxiv : the preprint server for biology·2026
See all related articles
This summary is machine-generated.

SpaIM enhances spatial transcriptomics (ST) by using single-cell RNA sequencing (scRNA-seq) to predict missing gene expressions, improving gene coverage and analysis accuracy for cellular ecosystems.

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Spatial transcriptomics (ST) offers insights into cellular ecosystems but suffers from sparse gene signals and limited detection.
  • Single-cell RNA sequencing (scRNA-seq) provides comprehensive gene expression data but lacks spatial context.

Purpose of the Study:

  • To develop a novel method, SpaIM, that integrates scRNA-seq data to enrich spatial transcriptomics profiles.
  • To address limitations in gene coverage and expression accuracy in ST data.

Main Methods:

  • SpaIM, a style transfer learning model, segregates scRNA-seq and ST data into content and style components.
  • It leverages shared content to impute unmeasured gene expressions in ST data.

Main Results:

Related Experiment Videos

  • SpaIM significantly improves gene coverage and expression accuracy in ST data.
  • Outperforms 12 existing methods across 53 diverse ST datasets (sequencing- and imaging-based).
  • Enhances downstream analyses like ligand-receptor interaction detection and spatial domain characterization.

Conclusions:

  • SpaIM effectively enriches spatial transcriptomics data using scRNA-seq, overcoming data sparsity and limited gene detection.
  • The open-source software advances spatial transcriptomics analysis and gene expression imputation.