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

AI-powered therapeutic aptamer drug discovery: Targeting the CT-domain of CTGF for duchenne muscular dystrophy.

Acta pharmaceutica Sinica. B·2026

Same author

SymBOL: A General-Purpose Symbolic Learner for Scientific Discovery Using Bayesian Optimization-Enhanced Large Language Models.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Dynamic distribution of label-free polysaccharides after intestinal lymphatic absorption.

International journal of biological macromolecules·2026

Same author

Engineering thiamine pyrophosphate metabolism improves consolidated bioprocessing for cellulosic ethanol with inorganic nitrogen in Myceliophthora thermophila.

Biotechnology for biofuels and bioproducts·2026

Same author

From Five-Number Summary to Absolute Heterogeneity: Recent Methodological Advances in Meta-Analysis With Continuous Outcomes.

Journal of evidence-based medicine·2026

Same author

CSCN: Inference of Cell-Specific Causal Networks Using Single-Cell RNA-Seq Data.

Bioinformatics (Oxford, England)·2026

Search research articles

Related Experiment Video

Updated: Oct 23, 2025

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

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

Published on: May 22, 2017

DeepDRIM: a deep neural network to reconstruct cell-type-specific gene regulatory network using single-cell RNA-seq

Jiaxing Chen¹, ChinWang Cheong¹, Liang Lan¹

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

Briefings in Bioinformatics

|August 23, 2021

Summary

DeepDRIM, a novel deep neural network, reconstructs gene regulatory networks (GRNs) from single-cell RNA sequencing data. It effectively identifies cell-type-specific GRN alterations in diseases like COVID-19.

Keywords:

deep neural network gene regulatory network single-cell RNA sequencing transitive interactions

More Related Videos

Isolation of Adult Spinal Cord Nuclei for Massively Parallel Single-nucleus RNA Sequencing

Isolation of Adult Spinal Cord Nuclei for Massively Parallel Single-nucleus RNA Sequencing

Published on: October 12, 2018

Single-cell RNA Sequencing and Analysis of Human Pancreatic Islets

Single-cell RNA Sequencing and Analysis of Human Pancreatic Islets

Published on: July 18, 2019

Related Experiment Videos

Last Updated: Oct 23, 2025

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

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

Published on: May 22, 2017

Isolation of Adult Spinal Cord Nuclei for Massively Parallel Single-nucleus RNA Sequencing

Isolation of Adult Spinal Cord Nuclei for Massively Parallel Single-nucleus RNA Sequencing

Published on: October 12, 2018

Single-cell RNA Sequencing and Analysis of Human Pancreatic Islets

Single-cell RNA Sequencing and Analysis of Human Pancreatic Islets

Published on: July 18, 2019

Area of Science:

Genomics
Computational Biology
Bioinformatics

Background:

Single-cell RNA sequencing (scRNA-seq) allows high-resolution gene activity analysis.
Reconstructing cell-type-specific gene regulatory networks (GRNs) from scRNA-seq data is challenging due to dropout events and cellular heterogeneity.
Existing GRN reconstruction algorithms are often designed for bulk RNA-seq and struggle with scRNA-seq data characteristics.

Purpose of the Study:

To develop a novel supervised deep neural network, DeepDRIM, for accurate GRN reconstruction from scRNA-seq data.
To address the limitations of existing methods in handling scRNA-seq data, including dropout events and cellular heterogeneity.
To apply DeepDRIM for analyzing cell-type-specific GRN alterations in diseases, specifically COVID-19.

Main Methods:

Representing joint gene expression distribution of gene pairs as images.
Utilizing a supervised deep neural network (DeepDRIM) that processes TF-gene pair images and neighborhood context.
Comparing DeepDRIM against nine existing GRN reconstruction algorithms on scRNA-seq data from eight cell lines.

Main Results:

DeepDRIM demonstrated superior performance in GRN reconstruction from scRNA-seq data compared to existing algorithms.
The method proved robust to dropout rates, cell numbers, and training data size in simulations.
Application to COVID-19 patient B cells revealed cell-type-specific GRN alterations enriched in pathways like lysosome, apoptosis, and response to hypoxia.

Conclusions:

DeepDRIM offers an effective approach for reconstructing GRNs from scRNA-seq data, outperforming existing methods.
The tool is robust and reliable across various data conditions, including dropout events and varying sample sizes.
DeepDRIM facilitates the discovery of disease-associated GRN alterations, providing insights into disease mechanisms, as demonstrated in COVID-19.