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

Nanostructured Er2O3 thin films grown by metalorganic chemical vapour deposition.

Journal of nanoscience and nanotechnology·2014

Same author

Alterations in amplitude of low frequency fluctuation in treatment-naïve major depressive disorder measured with resting-state fMRI.

Human brain mapping·2014

Same author

The inhibitory and apoptotic effects of docetaxel-loaded mesoporous magnetic colloidal nanocrystal clusters on bladder cancer T24 cells in vitro.

Journal of biomedical nanotechnology·2014

Same author

Novel experimental model of enlarging abdominal aortic aneurysm in rabbits.

Journal of vascular surgery·2014

Same author

Optical coherence tomographic evaluation of transplant coronary artery vasculopathy with correlation to cellular rejection.

Circulation. Cardiovascular interventions·2014

Same author

Impact of multiple complex plaques on short- and long-term clinical outcomes in patients presenting with ST-segment elevation myocardial infarction (from the Harmonizing Outcomes With Revascularization and Stents in Acute Myocardial Infarction [HORIZONS-AMI] Trial).

The American journal of cardiology·2014

Search research articles

Related Experiment Video

Updated: Sep 11, 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

Mitigation of multi-scale biases in cell-type deconvolution for spatially resolved transcriptomics using HarmoDecon.

Zirui Wang¹, Ke Xu¹, Yang Liu¹

¹Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong, SAR.

Bioinformatics (Oxford, England)

|August 12, 2025

Summary

HarmoDecon, a new deep learning model, accurately deconvolutes cell types in spatial transcriptomics data by addressing multiple bias scales. It improves spatial domain clustering and cancer cell identification in human breast cancer samples.

More Related Videos

Isolation and Profiling of Human Primary Mesenteric Arterial Endothelial Cells at the Transcriptome Level

Isolation and Profiling of Human Primary Mesenteric Arterial Endothelial Cells at the Transcriptome Level

Published on: March 14, 2022

Multiplexed Analysis of Retinal Gene Expression and Chromatin Accessibility Using scRNA-Seq and scATAC-Seq

Multiplexed Analysis of Retinal Gene Expression and Chromatin Accessibility Using scRNA-Seq and scATAC-Seq

Published on: March 12, 2021

Related Experiment Videos

Last Updated: Sep 11, 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

Isolation and Profiling of Human Primary Mesenteric Arterial Endothelial Cells at the Transcriptome Level

Isolation and Profiling of Human Primary Mesenteric Arterial Endothelial Cells at the Transcriptome Level

Published on: March 14, 2022

Multiplexed Analysis of Retinal Gene Expression and Chromatin Accessibility Using scRNA-Seq and scATAC-Seq

Multiplexed Analysis of Retinal Gene Expression and Chromatin Accessibility Using scRNA-Seq and scATAC-Seq

Published on: March 12, 2021

Area of Science:

Genomics
Bioinformatics
Computational Biology

Background:

Spatially resolved transcriptomics (SRT) offers insights into tissue molecular microenvironments.
Existing SRT platforms often lack single-cell resolution, requiring cell-type deconvolution.
Current deconvolution methods struggle with biases at spot, sample, and cross-dataset levels.

Purpose of the Study:

To introduce HarmoDecon, a novel semi-supervised deep learning model for spatial cell-type deconvolution.
To address biases in cell-type proportion estimation across individual spots, entire tissues, and between SRT and scRNA-seq datasets.
To improve the accuracy and reliability of cell-type deconvolution in SRT.

Main Methods:

HarmoDecon utilizes pseudo-spots generated from single-cell RNA sequencing (scRNA-seq) data.
Employs Gaussian Mixture Graph Convolutional Networks for deconvolution.
A semi-supervised deep learning approach is implemented.

Main Results:

HarmoDecon outperformed 11 state-of-the-art methods in simulations using STARmap and osmFISH data.
Achieved superior accuracy in spatial domain clustering on legacy SRT and 10x Visium datasets.
Demonstrated strong correlations between cancer markers and cancer cells in human breast cancer samples.

Conclusions:

HarmoDecon effectively mitigates biases in spatial cell-type deconvolution.
The model enhances the accuracy of cell-type proportion estimation in SRT.
HarmoDecon advances the analysis of spatial transcriptomics, particularly in complex tissues like human breast cancer.