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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Accuracy and Variability of Spatial Localization of Infarct Core Predicted by CT Perfusion.

Journal of computer assisted tomography·2026
Same author

Evaluating integrative strategies for incorporating phenotypic features in spatial transcriptomics.

Journal of microscopy·2026
Same author

Identifying and targeting abnormal mitochondrial localization associated with psychosis.

bioRxiv : the preprint server for biology·2026
Same author

In vivo imaging of central nervous system fluid spaces using synchrotron radiation-based micro computed tomography.

Nature communications·2026
Same author

GloBIAS: strengthening the foundations of bioimage analysis.

Nature methods·2026
Same author

Cell Painting for cytotoxicity and mode-of-action analysis in primary human hepatocytes.

Cell systems·2026

Related Experiment Video

Updated: Sep 12, 2025

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection
09:19

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection

Published on: July 6, 2022

5.0K

Evaluating Integrative Strategies for Incorporating Phenotypic Features in Spatial Transcriptomics.

Levin M Moser1,2, Ahmad Kamal Hamid1, Esteban Miglietta1

  • 1Imaging Platform, Broad Institute of MIT and Harvard, Cambridge MA, USA.

Arxiv
|August 6, 2025
PubMed
Summary
This summary is machine-generated.

Variational autoencoders (VAEs) effectively extract spatial transcriptomics data, even with limited datasets. These learned representations improve cell type identification and integrate imaging data better than traditional methods.

Keywords:
Spatial transcriptomicscell type deconvolutionmorphological featuresmulti-modal integrationvariational autoencoder

More Related Videos

Author Spotlight: Integrating Organoid Models with Single-Cell and Spatial Transcriptomics Technologies
05:45

Author Spotlight: Integrating Organoid Models with Single-Cell and Spatial Transcriptomics Technologies

Published on: March 29, 2024

2.6K
Spatially Compact Arrangement of Larval Zebrafish Sections for Spatial Transcriptomic Analysis
07:40

Spatially Compact Arrangement of Larval Zebrafish Sections for Spatial Transcriptomic Analysis

Published on: May 16, 2025

460

Related Experiment Videos

Last Updated: Sep 12, 2025

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection
09:19

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection

Published on: July 6, 2022

5.0K
Author Spotlight: Integrating Organoid Models with Single-Cell and Spatial Transcriptomics Technologies
05:45

Author Spotlight: Integrating Organoid Models with Single-Cell and Spatial Transcriptomics Technologies

Published on: March 29, 2024

2.6K
Spatially Compact Arrangement of Larval Zebrafish Sections for Spatial Transcriptomic Analysis
07:40

Spatially Compact Arrangement of Larval Zebrafish Sections for Spatial Transcriptomic Analysis

Published on: May 16, 2025

460

Area of Science:

  • Spatial transcriptomics
  • Bioinformatics
  • Computational biology

Background:

  • Spatial transcriptomics (ST) enables spatially informed analysis of biological samples.
  • Integrating ST with imaging modalities for morphological insights is challenging.
  • Real-world constraints include limited data, class imbalance, and segmentation issues.

Purpose of the Study:

  • Evaluate variational autoencoders (VAEs) for extracting informative low-dimensional representations from ST data.
  • Assess VAE performance under experimental constraints.
  • Compare VAE-derived latent spaces (LSs) with traditional image-based features.

Main Methods:

  • Used a murine ileum MERFISH dataset.
  • Extracted VAE LSs from cell crops (spot counts, stains, or combined).
  • Assessed embeddings using PERMANOVA, cross-validated classification, and Leiden clustering.
  • Compared VAE LSs with CellProfiler features.

Main Results:

  • Transcript counts generally outperformed other feature spaces.
  • VAE LSs captured biological variation and improved cell type label recovery.
  • Morphology-trained LSs showed predictive power for gene expression.
  • Combining transcript counts with VAE LSs enhanced cluster homogeneity.
  • VAE LSs outperformed CellProfiler features.

Conclusions:

  • VAEs extract biologically meaningful signals from imaging data under constrained conditions.
  • VAEs offer a promising strategy for multi-modal integration in spatial transcriptomics.
  • Learned representations from VAEs are advantageous over hand-crafted features.