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

Gene expression data analysis with a dynamically extended self-organized map that exploits class information.

Seferina Mavroudi1, Stergios Papadimitriou, Anastasios Bezerianos

  • 1Department of Medical Physics, School of Medicine, University of Patras, 26500 Patras, Greece. severina@heart.med.upatras.gr

Bioinformatics (Oxford, England)
|November 9, 2002
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

Dual Role of Cancer Epithelial-Specific TRAF3 in Regulating Breast Cancer Cell Survival and Lymphocyte Activity.

International journal of molecular sciences·2026
Same author

Molecular-level understanding of the aging bone and regeneration mechanisms using computational methods.

Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA·2026
Same author

Time-frequency-spatial channel attention network for semantic decoding: an exploratory EEG study.

Medical & biological engineering & computing·2026
Same author

Heart Rate Variability via Poincaré Mapping as an Early Biomarker Post-Cardiac Arrest.

IEEE transactions on bio-medical engineering·2025
Same author

Investigating the dynamics of intracranial pressure and cerebral autoregulation during extracorporeal cardiopulmonary resuscitation using a porcine model.

Resuscitation plus·2025
Same author

Unravelling the human taste receptor interactome: machine learning and molecular modelling insights into protein-protein interactions.

NPJ science of food·2025
Same journal

conMItion: an R package adjusting confounding factors for associations in multi-omics.

Bioinformatics (Oxford, England)·2026
Same journal

SpaMFG: a Spatial Multi-omics Integration Method based on Feature Grouping.

Bioinformatics (Oxford, England)·2026
Same journal

CSCN: Inference of Cell-Specific Causal Networks Using Single-Cell RNA-Seq Data.

Bioinformatics (Oxford, England)·2026
Same journal

Sparse CCA-Based Mediation Analysis with High-Dimensional Exposures and Mediators.

Bioinformatics (Oxford, England)·2026
Same journal

Enhancing Cross-Context Generalization in Drug Perturbation Prediction with a Multimodal Conditional Diffusion Framework.

Bioinformatics (Oxford, England)·2026
Same journal

Primer Design through Submodular Function Estimation.

Bioinformatics (Oxford, England)·2026
See all related articles

This study introduces a novel supervised Network Self-Organized Map (sNet-SOM) for analyzing gene expression data. sNet-SOM adaptively determines cluster numbers, offering efficient and effective multi-labeled data analysis.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Clustering is a popular method for analyzing genome-wide expression data.
  • Existing clustering methods often require a priori specification of the number of clusters and ignore prior biological knowledge.
  • Current tools lack effective integration of unsupervised and supervised learning for high-dimensional expression data analysis.

Purpose of the Study:

  • To adapt a novel Self-Organizing Map, the supervised Network Self-Organized Map (sNet-SOM), for multi-labeled gene expression data.
  • To develop a method that adaptively determines the number of clusters and integrates unsupervised and supervised learning.
  • To provide an effective framework for analyzing high-dimensional expression data with multiple functional class labels.

Main Methods:

Related Experiment Videos

  • The study adapts a supervised Network Self-Organized Map (sNet-SOM) for multi-labeled gene expression data.
  • sNet-SOM employs a dynamic extension process to adaptively determine the number of clusters.
  • This process balances unsupervised, supervised, and model complexity criteria, dynamically constructing multiple models for optimal selection.

Main Results:

  • sNet-SOM adaptively determines the number of clusters using a dynamic extension process.
  • The method balances unsupervised, supervised, and model complexity criteria for optimal cluster identification.
  • sNet-SOM demonstrates competitive performance compared to existing supervised classification approaches with reduced computational cost.

Conclusions:

  • sNet-SOM offers an effective and computationally efficient approach for analyzing multi-labeled gene expression data.
  • The method provides extensive exploratory analysis potential within a comprehensible framework.
  • sNet-SOM overcomes limitations of traditional clustering by adaptively determining cluster numbers and integrating biological knowledge.