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

Self-explaining artificial intelligence for the classification of B cell non-Hodgkin lymphoma: A diagnostic decision support study.

PLoS medicine·2026
Same author

Voronoi tessellation as a complement or replacement for confidence ellipses in the visualization of data projection and clustering results.

PloS one·2026
Same author

Self-organizing neural network-based generative AI with embedded error inflation control enhances effective knowledge extraction from preclinical studies with reduced sample size.

Pharmacological research·2026
Same author

A model-agnostic framework for dataset-specific selection of missing value imputation methods in pain-related numerical data.

Canadian journal of pain = Revue canadienne de la douleur·2026
Same author

Resolving Interpretation Challenges in Machine Learning Feature Selection With an Iterative Approach in Biomedical Pain Data.

European journal of pain (London, England)·2026
Same author

Integrating AI and Machine Learning Into Pain Research and Therapy.

European journal of pain (London, England)·2025

Related Experiment Video

Updated: Jan 1, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.9K

Current Projection Methods-Induced Biases at Subgroup Detection for Machine-Learning Based Data-Analysis of

Jörn Lötsch1,2, Alfred Ultsch3

  • 1Institute of Clinical Pharmacology, Goethe-University, Theodor-Stern-Kai 7, 60590 Frankfurt am Main, Germany.

International Journal of Molecular Sciences
|December 22, 2019
PubMed
Summary

t-distributed stochastic neighbor embedding (t-SNE) can misrepresent structures in high-dimensional flow cytometry data. Emergent self-organizing maps (ESOM) offer a more reliable alternative for accurate subgroup identification.

Keywords:
computational techniquesdata scienceemergent self-organizing mapsflow cytometryhigh-dimensional data setsimmunological researchmachine-learningt-distributed stochastic neighbor embedding

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

16.1K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.6K

Related Experiment Videos

Last Updated: Jan 1, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.9K
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

16.1K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.6K

Area of Science:

  • Computational biology
  • Data science
  • Immunology

Background:

  • Flow cytometry generates large, high-dimensional datasets.
  • Computational methods are crucial for visualizing and identifying subgroups in this data.
  • Accurate data representation is essential for reliable subgroup discovery.

Purpose of the Study:

  • To evaluate the reliability of t-distributed stochastic neighbor embedding (t-SNE) for high-dimensional flow cytometry data.
  • To identify potential pitfalls of t-SNE in subgroup analysis.
  • To propose and validate a robust alternative method for data visualization and subgroup identification.

Main Methods:

  • Analysis of t-distributed stochastic neighbor embedding (t-SNE) performance on artificial and real biomedical datasets.
  • Application of emergent self-organizing maps (ESOM) combined with U-matrix methods.
  • Comparison of subgroup identification accuracy between t-SNE and ESOM.

Main Results:

  • t-SNE inaccurately introduced cluster structures in homogeneous data.
  • t-SNE occasionally misidentified the number of subgroups or merged distinct subgroups.
  • ESOM with U-matrix methods correctly identified homogeneous data and accurately displayed subgroup structures.

Conclusions:

  • Widely used t-SNE may lead to erroneous conclusions in high-dimensional cytometry subgroup detection.
  • Emergent self-organizing maps (ESOM) provide a robust and accurate alternative for analyzing complex flow cytometry data.
  • This study highlights critical considerations for computational methods in biomedical data analysis.