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 Videos

Semi-supervised learning via penalized mixture model with application to microarray sample classification.

Wei Pan1, Xiaotong Shen, Aixiang Jiang

  • 1Division of Biostatistics, School of Public Health, University of Minnesota, MN, USA. weip@biostat.umn.edu

Bioinformatics (Oxford, England)
|July 28, 2006
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

Gradient of CD79B expression in diffuse large B-cell lymphoma corresponds to stages of germinal center B-cell differentiation.

Haematologica·2026
Same author

LySeqST: a targeted sequencing assay for robust genomic classification of diffuse large B-cell lymphoma.

Blood advances·2026
Same author

Multidimensional Characterization of Tumor-Immune Architecture Reveals Clinically Relevant Classic Hodgkin Lymphoma Subtypes.

Cancer discovery·2026
Same author

Population-wide introduction of dose-adjusted EPOCH-R in high-grade B-cell lymphoma with MYC/BCL2 rearrangements, DLBCL morphology.

Blood advances·2025
Same author

Utility of the Central Nervous System International Prognostic Index in patients with primary mediastinal large B-cell lymphoma treated with rituximab-containing chemoimmunotherapy.

Haematologica·2025
Same author

Tumor microenvironment differences between diagnostic and relapsed classic Hodgkin lymphoma revealed by scRNA-seq.

Blood advances·2025

Human blood outgrowth endothelial cells (BOECs) were analyzed using a novel penalized mixture model. Results show BOECs form a distinct class, separate from large vessel endothelial cells (LVECs) and microvascular endothelial cells (MVECs).

Area of Science:

  • Endothelial cell biology
  • Bioinformatics
  • Genomics

Background:

  • Human blood outgrowth endothelial cells (BOECs) classification remains unclear, with prior studies suggesting proximity to microvascular endothelial cells (MVECs).
  • Distinguishing BOECs from large vessel endothelial cells (LVECs) and MVECs requires advanced analytical methods for global expression profiling.

Purpose of the Study:

  • To determine the precise classification of BOECs relative to LVECs and MVECs using global expression profiling.
  • To develop and apply a novel semi-supervised learning approach for high-dimensional biological data analysis and feature selection.

Main Methods:

  • A semi-supervised learning approach utilizing a penalized mixture model with a weighted L1 penalty was developed.
  • The model was applied to a dataset comprising 27 BOEC, 28 LVEC, and 25 MVEC samples.

Related Experiment Videos

  • Automatic feature selection and novel class discovery were key components of the methodology.

    • Main Results:

    • Analysis revealed that BOEC samples formed a distinct, novel class separate from LVECs and MVECs.
    • The penalized mixture model demonstrated superior performance in identifying relevant genes and forming clusters compared to standard methods.
    • Simulation studies validated the model's effectiveness in high-dimensional data analysis.

    Conclusions:

    • The penalized mixture model is effective for high-dimensional data, enabling novel class discovery and automatic feature selection.
    • Human blood outgrowth endothelial cells represent a unique endothelial cell class.
    • This approach offers a promising tool for future biological data classification and discovery.