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

Kernel-based self-organized maps trained with supervised bias for gene expression data analysis.

Stergios Papadimitriou1, Spiridon D Likothanassis

  • 1Department of Information Management, Technological Education Institute of Kavala, 65404 Kavala, Greece. sterg@teikav.edu.gr

Journal of Bioinformatics and Computational Biology
|August 4, 2004
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

Quantitative brain stem assessment in discriminating neurodegenerative disorders from normal pressure hydrocephalus.

Journal of neuroimaging : official journal of the American Society of Neuroimaging·2024
Same author

Composite attenuation correction method using a <sup>68</sup>Ge-transmission multi-atlas for quantitative brain PET/MR.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2022
Same author

Risk Factors and Outcomes of <i>Klebsiella pneumoniae</i> Infection Before and After Allogeneic Hematopoietic Cell Transplantation.

Frontiers in medicine·2021
Same author

Accuracy and precision of zero-echo-time, single- and multi-atlas attenuation correction for dynamic [<sup>11</sup>C]PE2I PET-MR brain imaging.

EJNMMI physics·2020
Same author

Evaluation of zero-echo-time attenuation correction for integrated PET/MR brain imaging-comparison to head atlas and <sup>68</sup>Ge-transmission-based attenuation correction.

EJNMMI physics·2018
Same author

GIBA: a clustering tool for detecting protein complexes.

BMC bioinformatics·2009
Same journal

CNV-ECOD: A copy number variation detection method based on ECOD algorithm using next-generation sequencing data.

Journal of bioinformatics and computational biology·2026
Same journal

ReinVar: A model-free paradigm-based reinforcement learning approach to detect copy number variation.

Journal of bioinformatics and computational biology·2026
Same journal

When pipelines run but coordinates fail: A simple spatial specificity check for false locality in post-GWAS analysis.

Journal of bioinformatics and computational biology·2026
Same journal

Comparative benchmarking of template-based, evolutionary-diffusion, and generative language models for IsPETase structure prediction.

Journal of bioinformatics and computational biology·2026
Same journal

Trap spaces as labelled ideals of SCC posets: A structural-functional theory of reachability in asynchronous boolean networks.

Journal of bioinformatics and computational biology·2026
Same journal

Erratum - DDINet: Drug-drug interaction prediction network based on multi-molecular fingerprint features and multi-head attention centered weighted autoencoder.

Journal of bioinformatics and computational biology·2026
See all related articles

This study introduces the Kernel Supervised Dynamic Grid Self-Organized Map (KSDG-SOM), a novel approach for gene expression analysis. It integrates prior gene knowledge, dynamically grows, and refines functional labels for improved clustering.

Area of Science:

  • Genomics
  • Bioinformatics
  • Machine Learning

Background:

  • Self-Organized Maps (SOMs) are widely used for genome-wide expression data analysis.
  • Existing SOM methods often neglect functional gene category information and create rigid clusters.
  • Traditional approaches lack dynamic map extension and a balance between unsupervised and supervised learning.

Purpose of the Study:

  • To present a novel Self-Organizing Map, the Kernel Supervised Dynamic Grid Self-Organized Map (KSDG-SOM).
  • To develop a SOM that incorporates prior knowledge of gene functional categories.
  • To enable dynamic map growth and refinement of functional labels.

Main Methods:

  • The KSDG-SOM adapts parameters in a kernel space using Gaussian kernels.
  • Mean and variance components of kernels are adapted to optimize input density fitness.

Related Experiment Videos

  • The map grows dynamically based on statistical criteria, incorporating supervised bias for cluster formation.

    • Main Results:

    • The KSDG-SOM successfully integrates a priori gene functional information.
    • The model demonstrates the ability to revise potentially incorrect functional labels.
    • It overcomes limitations of existing methods by balancing unsupervised and supervised learning drives.

    Conclusions:

    • The KSDG-SOM offers an advanced clustering method for genomic data analysis.
    • This novel approach enhances the interpretability of gene expression patterns by incorporating functional knowledge.
    • The dynamic and supervised nature of KSDG-SOM provides a more flexible and accurate clustering solution.