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 Experiment Video

Updated: Aug 9, 2025

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

18.6K

Batch alignment of single-cell transcriptomics data using deep metric learning.

Xiaokang Yu1, Xinyi Xu2, Jingxiao Zhang3

  • 1Center for Applied Statistics, School of Statistics, Renmin University of China, 100872, Beijing, China.

Nature Communications
|February 22, 2023
PubMed
Summary
This summary is machine-generated.

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

SpaJoint: a transfer learning method for spatial transcriptomics deconvolution.

Briefings in bioinformatics·2026
Same author

Toward Computationally Complete Spatial Omics.

bioRxiv : the preprint server for biology·2026
Same author

Multiscale confidence quantification for virtual spatial transcriptomics with UTOPIA.

bioRxiv : the preprint server for biology·2026
Same author

HistoSweep enables cellular-resolution tissue quality control for gigapixel images in digital pathology and spatial omics.

bioRxiv : the preprint server for biology·2026
Same author

Scalable and distributed individualized treatment rules for multicenter datasets.

Biometrics·2026
Same author

scHSC: enhancing single-cell RNA-seq clustering via hard sample contrastive learning.

Briefings in bioinformatics·2025
Same journal

Plasmonic nanocomposite helices for weather-adaptive LiDAR function.

Nature communications·2026
Same journal

Multidirectional strain-insensitive stretchable RF electronics.

Nature communications·2026
Same journal

In-scanner thoughts contribute to resting-state functional connectivity.

Nature communications·2026
Same journal

Metal-center electron affinity modulates multicolor electrochromism in 2D conjugated metal-organic frameworks.

Nature communications·2026
Same journal

Hyperbranched dielectric polymer networks exhibiting giant energy storage density at 250 °C.

Nature communications·2026
Same journal

3D nanoprinting of metals by spatiotemporally confined hot electrons via multiple-electron excitations in nanocrystals.

Nature communications·2026
See all related articles

scDML, a novel deep metric learning model, effectively corrects batch effects in single-cell RNA sequencing (scRNA-seq) data. This method improves cell type detection and preserves rare cell populations, advancing the study of cellular heterogeneity.

Area of Science:

  • Genomics
  • Computational Biology
  • Bioinformatics

Background:

  • Single-cell RNA sequencing (scRNA-seq) reveals cellular heterogeneity but faces challenges with batch effects and cell type identification.
  • Existing scRNA-seq algorithms often prioritize batch effect removal before clustering, potentially missing rare cell types.

Purpose of the Study:

  • To develop scDML, a deep metric learning model for robust batch effect correction in scRNA-seq data.
  • To enhance the accuracy of cell type detection and preserve subtle cell populations.

Main Methods:

  • scDML utilizes deep metric learning guided by intra- and inter-batch nearest neighbor information and initial clustering.
  • The model was evaluated across diverse species and tissues to assess its performance.

More Related Videos

Transcriptome Analysis of Single Cells
07:27

Transcriptome Analysis of Single Cells

Published on: April 25, 2011

30.0K
Single-cell RNA Sequencing and Analysis of Human Pancreatic Islets
11:34

Single-cell RNA Sequencing and Analysis of Human Pancreatic Islets

Published on: July 18, 2019

16.5K

Related Experiment Videos

Last Updated: Aug 9, 2025

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

18.6K
Transcriptome Analysis of Single Cells
07:27

Transcriptome Analysis of Single Cells

Published on: April 25, 2011

30.0K
Single-cell RNA Sequencing and Analysis of Human Pancreatic Islets
11:34

Single-cell RNA Sequencing and Analysis of Human Pancreatic Islets

Published on: July 18, 2019

16.5K

Main Results:

  • scDML effectively removes batch effects and improves clustering performance in scRNA-seq datasets.
  • The method accurately recovers true cell types and outperforms established algorithms like Seurat 3, scVI, and Harmony.
  • scDML preserves subtle cell types and enables the discovery of novel cell subtypes, demonstrating scalability to large datasets.

Conclusions:

  • scDML provides a valuable tool for analyzing complex cellular heterogeneity in scRNA-seq studies.
  • The model's ability to preserve rare cell types and its scalability make it suitable for large-scale biological investigations.