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

Approaches for Benchmarking Single-Cell Gene Regulatory Network Methods.

Bioinformatics and biology insights·2024
Same author

Identification and Characterization of Chemotherapy-Resistant High-Risk Neuroblastoma Persister Cells.

Cancer discovery·2024
Same author

ER stress elicits non-canonical CASP8 (caspase 8) activation on autophagosomal membranes to induce apoptosis.

Autophagy·2023
Same author

Endothelial MEKK3-KLF2/4 signaling integrates inflammatory and hemodynamic signals during definitive hematopoiesis.

Blood·2022
Same author

Single-cell multiomics reveals increased plasticity, resistant populations, and stem-cell-like blasts in KMT2A-rearranged leukemia.

Blood·2021
Same author

Identifying noncoding risk variants using disease-relevant gene regulatory networks.

Nature communications·2018

Related Experiment Video

Updated: Apr 18, 2026

Reusable Single Cell for Iterative Epigenomic Analyses
10:28

Reusable Single Cell for Iterative Epigenomic Analyses

Published on: February 11, 2022

1.8K

scMultiPreDICT: A single-cell predictive framework with transcriptomic and epigenetic signatures.

Ewura-Esi Manful1, Yasin Uzun1,2

  • 1Department of Pediatrics, Pennsylvania State University College of Medicine, 700 HMC Crescent Road, Hershey, USA.

Biorxiv : the Preprint Server for Biology
|April 17, 2026
PubMed
Summary
This summary is machine-generated.

Single-cell multiomics reveals that RNA expression generally predicts gene activity better than chromatin accessibility. Integrating both layers improves predictions only for specific genes and contexts, highlighting gene-specific regulatory contributions.

Keywords:
chromatin accessibilitygene expression predictionmachine learningsingle-cell multiomics

More Related Videos

Multiplexed Single Cell mRNA Sequencing Analysis of Mouse Embryonic Cells
08:30

Multiplexed Single Cell mRNA Sequencing Analysis of Mouse Embryonic Cells

Published on: January 7, 2020

14.1K
Multiplexed Analysis of Retinal Gene Expression and Chromatin Accessibility Using scRNA-Seq and scATAC-Seq
06:24

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

Published on: March 12, 2021

4.3K

Related Experiment Videos

Last Updated: Apr 18, 2026

Reusable Single Cell for Iterative Epigenomic Analyses
10:28

Reusable Single Cell for Iterative Epigenomic Analyses

Published on: February 11, 2022

1.8K
Multiplexed Single Cell mRNA Sequencing Analysis of Mouse Embryonic Cells
08:30

Multiplexed Single Cell mRNA Sequencing Analysis of Mouse Embryonic Cells

Published on: January 7, 2020

14.1K
Multiplexed Analysis of Retinal Gene Expression and Chromatin Accessibility Using scRNA-Seq and scATAC-Seq
06:24

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

Published on: March 12, 2021

4.3K

Area of Science:

  • Genomics
  • Computational Biology
  • Epigenetics

Background:

  • Cellular responses to genetic changes involve both gene expression and epigenetic factors.
  • Single-cell multiomics offers insights into gene expression and chromatin accessibility simultaneously.
  • The distinct contributions of transcriptional and epigenetic layers to gene expression are not fully understood.

Purpose of the Study:

  • To develop and apply a computational framework, scMultiPreDICT, for comparing the predictive power of transcriptional versus epigenetic features on gene expression.
  • To systematically benchmark RNA-only, ATAC-only, and multimodal feature sets using various machine learning models.
  • To elucidate the gene-specific and context-dependent contributions of different regulatory layers.

Main Methods:

  • Developed scMultiPreDICT, a computational framework for comparative predictive modeling using single-cell multiomics data.
  • Benchmarked RNA and ATAC-derived features against six machine learning models (regression, tree-based, deep learning).
  • Performed feature importance analysis to identify key regulatory drivers across different genes and cellular contexts.

Main Results:

  • RNA-derived features demonstrated strong predictive power for gene expression.
  • Chromatin accessibility (ATAC-only) showed modest predictive performance.
  • Multimodal integration did not consistently enhance prediction accuracy, with benefits being gene-specific and context-dependent.
  • Transcriptional features were dominant for most genes, while epigenetic features contributed significantly to a subset.

Conclusions:

  • Regulatory layers contribute differentially to gene expression, with transcriptional regulation often being dominant.
  • scMultiPreDICT provides a systematic approach to identify the relative importance of transcriptional and epigenetic regulation.
  • Findings can guide targeted perturbation studies and prioritize regulatory layers for therapeutic interventions.