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

Overview Of Cell Separation And Isolation01:20

Overview Of Cell Separation And Isolation

Cell separation was first achieved in 1964 by S. H. Seal, who separated large tumor cells from the smaller blood cells using filtration. Two years later, Pohl and Hawk performed experiments on how cells respond differently to a nonuniform electric field based on the cell type. Such observations were the inception of cell separation methods, which allow isolating a single cell type from a heterogeneous sample.

You might also read

Related Articles

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

Sort by
Same author

A spatial in situ hybridization approach to T cell clonotype analysis using T cell receptor variable gene probes.

Cell reports·2026
Same author

SCALE: unsupervised multiscale domain identification in spatial omics data.

Nucleic acids research·2026
Same author

A systematic analysis of the impact of data variation on AI-based histopathological grading of prostate cancer.

Medical image analysis·2025
Same author

BioContextAI is a community hub for agentic biomedical systems.

Nature biotechnology·2025
Same author

Spatiotemporal interaction of immune and renal cells controls glomerular crescent formation in autoimmune kidney disease.

Nature immunology·2025
Same author

A stronger type I interferon signature distinguishes ANCA-associated vasculitis phenotypes and predicts kidney prognosis.

Kidney international·2025

Related Experiment Video

Updated: May 12, 2026

Single-cell RNA-Seq of Defined Subsets of Retinal Ganglion Cells
11:26

Single-cell RNA-Seq of Defined Subsets of Retinal Ganglion Cells

Published on: May 22, 2017

13.8K

DISSECT: deep semi-supervised consistency regularization for accurate cell type fraction and gene expression

Robin Khatri1, Pierre Machart1, Stefan Bonn2

  • 1Institute of Medical Systems Biology, Center for Molecular Neurobiology, Center for Biomedical AI, University Medical Center Hamburg-Eppendorf, Hamburg, Germany.

Genome Biology
|April 30, 2024
PubMed
Summary

This study introduces DISSECT, a novel deep learning algorithm that enhances cell deconvolution by overcoming data scarcity and domain shift issues. DISSECT significantly improves the accuracy of estimating cell type fractions and gene expression from mixed biological data.

Keywords:
Cell deconvolutionDeep learningSemi-supervised learning

More Related Videos

Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues
10:12

Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues

Published on: January 10, 2019

18.5K
Isolation and Profiling of Human Primary Mesenteric Arterial Endothelial Cells at the Transcriptome Level
09:45

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

Published on: March 14, 2022

2.9K

Related Experiment Videos

Last Updated: May 12, 2026

Single-cell RNA-Seq of Defined Subsets of Retinal Ganglion Cells
11:26

Single-cell RNA-Seq of Defined Subsets of Retinal Ganglion Cells

Published on: May 22, 2017

13.8K
Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues
10:12

Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues

Published on: January 10, 2019

18.5K
Isolation and Profiling of Human Primary Mesenteric Arterial Endothelial Cells at the Transcriptome Level
09:45

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

Published on: March 14, 2022

2.9K

Area of Science:

  • Computational biology
  • Bioinformatics
  • Genomics

Background:

  • Cell deconvolution estimates cell type proportions and gene expression from mixed biological samples.
  • Existing methods face challenges with limited realistic training data and domain shift in synthetic data.

Purpose of the Study:

  • To develop a novel deep learning algorithm for improved cell deconvolution.
  • To address the scarcity of realistic training data and domain shift issues in cell deconvolution.

Main Methods:

  • Developed two novel deep neural networks incorporating simultaneous consistency regularization for target and training domains.
  • Implemented the DISSECT algorithm for cell deconvolution tasks.

Main Results:

  • The DISSECT algorithm significantly improved cell deconvolution performance.
  • DISSECT outperformed competing algorithms by up to 14 percentage points in cell fraction and gene expression estimation.
  • Demonstrated adaptability of DISSECT to other biomedical data types, including proteomics.

Conclusions:

  • Novel deep neural networks with consistency regularization enhance cell deconvolution accuracy.
  • DISSECT offers a robust solution for cell deconvolution, improving upon existing methods.
  • The DISSECT algorithm shows broad applicability across different biomedical data modalities.