Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Capturing Finer-grained Long-range Dependency for Dense Prediction in Medical Images: An Empirical Investigation of MLPs.

IEEE journal of biomedical and health informatics·2026

Same author

Hybrid-CMLP: Hybrid CNN-MLP Networks for Low-to-standard-dose PET Synthesis.

IEEE journal of biomedical and health informatics·2026

Same author

Potential treatment targets in the whole-tissue proteome of triple negative breast cancer.

NPJ breast cancer·2026

Same author

Estimating tumour immune infiltration: methodological convergence across histology and spatial technologies.

Briefings in bioinformatics·2026

Same author

Extensive antagonistic variants across the human genome.

Nature communications·2026

Same author

Examining the association between fetal HLA-C, maternal KIR haplotypes and birth weight.

PLoS genetics·2026

Same journal

Efficient evidence-based genome annotation with EviAnn.

Nature methods·2026

Same journal

ClairS: a deep-learning method for long-read tumor-normal pair somatic small variant calling.

Nature methods·2026

Same journal

RNAbpFlow: base pair-augmented SE(3) flow matching for conditional RNA 3D structure generation.

Nature methods·2026

Same journal

Spatio-DARLIN enables robust and efficient in situ lineage tracing in mice at single-cell resolution.

Nature methods·2026

Same journal

EasyGrid: a versatile platform for automated cryo-EM sample preparation and quality control.

Nature methods·2026

Same journal

Cloud-based microscope enables live neuroimaging for 24 h and beyond with worldwide access.

Nature methods·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jan 17, 2026

Mining Spatial Transcriptomics Datasets using DeepSpaceDB

Mining Spatial Transcriptomics Datasets using DeepSpaceDB

Published on: September 5, 2025

Spatial gene expression at single-cell resolution from histology using deep learning with GHIST.

Xiaohang Fu^1,2,3,4,5, Yue Cao^1,3,4,5, Beilei Bian^1,3,4

¹School of Mathematics and Statistics, The University of Sydney, Sydney, New South Wales, Australia.

|September 15, 2025

Summary

This summary is machine-generated.

GHIST, a deep learning framework, predicts single-cell spatial gene expression from histology images. This method enhances spatial transcriptomics data for scalable multi-omics analysis and biomarker discovery.

More Related Videos

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

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

Published on: July 6, 2022

Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research

Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research

Published on: June 21, 2024

Related Experiment Videos

Last Updated: Jan 17, 2026

Mining Spatial Transcriptomics Datasets using DeepSpaceDB

Mining Spatial Transcriptomics Datasets using DeepSpaceDB

Published on: September 5, 2025

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

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

Published on: July 6, 2022

Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research

Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research

Published on: June 21, 2024

Area of Science:

Genomics
Computational Biology
Biomedical Imaging

Background:

Spatially resolved transcriptomics offers insights into disease mechanisms but faces cost and complexity barriers.
Current methods predicting gene expression from histology images lack accuracy and spatial resolution, limiting translational applications.
There is a need for advanced computational tools to overcome limitations in spatial transcriptomics data generation and analysis.

Purpose of the Study:

To introduce GHIST, a novel deep learning framework for predicting single-cell resolution spatial gene expression.
To leverage subcellular spatial transcriptomics and multi-layered biological information for enhanced prediction accuracy.
To demonstrate the utility of in silico generation of spatial gene expression data for multi-omics analysis and biomarker identification.

Main Methods:

Development of a deep learning-based framework (GHIST) integrating subcellular spatial transcriptomics.
Utilizing synergistic relationships between multiple biological information layers for gene expression prediction.
Validation of GHIST using public datasets and The Cancer Genome Atlas (TCGA) data across various spatial resolutions.

Main Results:

GHIST demonstrates superior performance in predicting spatial gene expression at single-cell resolution.
The framework shows flexibility across different spatial resolutions, outperforming existing methodologies.
Successful validation using diverse public datasets and TCGA data confirms GHIST's robustness.

Conclusions:

GHIST enables the in silico generation of high-resolution spatial gene expression measurements, overcoming current technological limitations.
The framework can enrich existing datasets, facilitating scalable multi-omics analyses.
GHIST holds significant potential for advancing biomarker identification and understanding disease mechanisms through spatial omics data.