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

Labeling DNA Probes03:31

Labeling DNA Probes

DNA probes are fragments of DNA labeled with a reporter tag to enable their detection or purification. The resulting labeled DNA probes can then hybridize to target nucleic acid sequences through complementary base-pairing, and may be used to recover or identify these regions.
Radioisotopes, fluorophores, or small molecule binding partners like biotin or digoxigenin, are the most widely used reporter tags for labeling DNA probes. These labels can be attached to the probe DNA molecule via...

You might also read

Related Articles

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

Sort by
Same author

Reconstructing voice identity from noninvasive auditory cortex recordings.

eLife·2026
Same author

Assessing the relative contributions of mosaic and regulatory developmental modes from single-cell trajectories.

PLoS computational biology·2025
Same author

Single-cell morphometrics reveals T-box gene-dependent patterns of epithelial tension in the Second Heart field.

Nature communications·2024
Same author

Limited column formation in the embryonic growth plate implies divergent growth mechanisms during pre- and postnatal bone development.

eLife·2024
Same author

Site Agnostic Approach to Early Detection of Cyberbullying on Social Media Networks.

Sensors (Basel, Switzerland)·2023
Same author

Random walk informed heterogeneity detection reveals how the lymph node conduit network influences T cells collective exploration behavior.

PLoS computational biology·2023

Related Experiment Video

Updated: Jun 12, 2026

Labeling of Single Cells in the Central Nervous System of Drosophila melanogaster
10:33

Labeling of Single Cells in the Central Nervous System of Drosophila melanogaster

Published on: March 4, 2013

12.8K

Partial label learning for automated classification of single-cell transcriptomic profiles.

Malek Senoussi1, Thierry Artieres1,2, Paul Villoutreix1,3

  • 1Aix Marseille Univ, Université de Toulon, CNRS, LIS, Turing Centre for Living Systems, Marseille, France.

Plos Computational Biology
|April 5, 2024
PubMed
Summary
This summary is machine-generated.

Automated classification of single-cell RNA sequencing data is crucial. This study introduces partial label learning, achieving high accuracy comparable to fully supervised methods using less stringent annotations.

More Related Videos

Method for Labeling Transcripts in Individual Escherichia coli Cells for Single-molecule Fluorescence In Situ Hybridization Experiments
07:51

Method for Labeling Transcripts in Individual Escherichia coli Cells for Single-molecule Fluorescence In Situ Hybridization Experiments

Published on: December 21, 2017

8.2K
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

Related Experiment Videos

Last Updated: Jun 12, 2026

Labeling of Single Cells in the Central Nervous System of Drosophila melanogaster
10:33

Labeling of Single Cells in the Central Nervous System of Drosophila melanogaster

Published on: March 4, 2013

12.8K
Method for Labeling Transcripts in Individual Escherichia coli Cells for Single-molecule Fluorescence In Situ Hybridization Experiments
07:51

Method for Labeling Transcripts in Individual Escherichia coli Cells for Single-molecule Fluorescence In Situ Hybridization Experiments

Published on: December 21, 2017

8.2K
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

Area of Science:

  • Developmental Biology
  • Computational Biology
  • Bioinformatics

Background:

  • Single-cell RNA sequencing (scRNASeq) generates high-dimensional data vital for understanding cell types and lineage. Manual annotation of scRNASeq profiles is challenging due to data volume and complexity. Automated classification methods are essential for efficient analysis.
  • Existing automated methods often require fully supervised training datasets, which are difficult to obtain at single-cell resolution. This limitation hinders the widespread application of scRNASeq in biological research.

Purpose of the Study:

  • To develop and evaluate automated classification methods for single-cell transcriptomic profiles using partial label learning.
  • To adapt state-of-the-art classification algorithms to a partial label learning framework, incorporating label set structures, particularly hierarchical ones relevant to developmental biology.
  • To assess the performance and accuracy of these methods on simulated and real scRNASeq datasets, comparing them to fully supervised approaches.

Main Methods:

  • Extended state-of-the-art multi-class classifiers (SVM, kNN, logistic regression, ensemble methods, prototype-based methods) to a partial label learning framework.
  • Investigated the incorporation of label set structures, focusing on hierarchical relationships common in developmental processes.
  • Evaluated methods using simulated and real scRNASeq datasets, analyzing the impact of label uncertainty on performance.

Main Results:

  • Partial label learning methods, especially a nonlinear prototype-based approach, demonstrated high accuracy in classifying single-cell transcriptomic profiles.
  • Methods trained with partially annotated data achieved performance comparable to those trained with fully supervised data.
  • The study identified key factors related to label uncertainty and provided insights into its effect on classification accuracy.

Conclusions:

  • Hierarchical and non-hierarchical partial label learning strategies offer effective solutions for automated classification of single-cell transcriptomic profiles.
  • These methods significantly reduce the stringent requirements for annotated datasets compared to traditional fully supervised learning.
  • The findings facilitate more accessible and accurate analysis of complex scRNASeq data, advancing developmental biology research.