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

Comprehensive characterization of the major nemoglobin from the giant kidney worm Dioctophyme renale.

International journal of biological macromolecules·2026
Same author

On the state of protein function prediction: a report on the fourth CAFA challenge.

bioRxiv : the preprint server for biology·2026
Same author

Human broadly neutralizing influenza B virus antibodies recognizing hemagglutinin computationally optimized broadly reactive antigens.

Frontiers in immunology·2026
Same author

Placental transcriptome profiling in congenital Chagas disease: gene networks associated with transmission.

Frontiers in cellular and infection microbiology·2026
Same author

ET-Pfam: ensemble transfer learning for protein family prediction.

Bioinformatics (Oxford, England)·2026
Same author

Systems analysis of leaf anatomy and transcriptome using unsupervised machine learning provides insight on photosynthesis development and evolution in non-model grasses.

Plant direct·2026

Related Experiment Video

Updated: May 1, 2026

A Pathway Association Study Tool for GWAS Analyses of Metabolic Pathway Information
05:01

A Pathway Association Study Tool for GWAS Analyses of Metabolic Pathway Information

Published on: July 1, 2020

4.7K

Improving clustering with metabolic pathway data.

Diego H Milone1, Georgina Stegmayer, Mariana López

  • 1Research Center for Signals, Systems and Computational Intelligence, sinc(i), FICH-UNL, CONICET, Ciudad Universitaria UNL, (3000) Santa Fe, Argentina. d.milone@ieee.org.

BMC Bioinformatics
|April 11, 2014
PubMed
Summary

This study introduces a biologically-inspired clustering algorithm (bSOM) that integrates prior biological knowledge during cluster formation. The bSOM method improves clustering performance and biological relevance compared to standard self-organizing maps (SOMs).

More Related Videos

A Web Tool for Generating High Quality Machine-readable Biological Pathways
08:01

A Web Tool for Generating High Quality Machine-readable Biological Pathways

Published on: February 8, 2017

21.2K
Author Spotlight: Emerging Technologies and Advanced Tools for Decoding Metabolomics Data Analysis
07:11

Author Spotlight: Emerging Technologies and Advanced Tools for Decoding Metabolomics Data Analysis

Published on: November 10, 2023

3.1K

Related Experiment Videos

Last Updated: May 1, 2026

A Pathway Association Study Tool for GWAS Analyses of Metabolic Pathway Information
05:01

A Pathway Association Study Tool for GWAS Analyses of Metabolic Pathway Information

Published on: July 1, 2020

4.7K
A Web Tool for Generating High Quality Machine-readable Biological Pathways
08:01

A Web Tool for Generating High Quality Machine-readable Biological Pathways

Published on: February 8, 2017

21.2K
Author Spotlight: Emerging Technologies and Advanced Tools for Decoding Metabolomics Data Analysis
07:11

Author Spotlight: Emerging Technologies and Advanced Tools for Decoding Metabolomics Data Analysis

Published on: November 10, 2023

3.1K

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Systems Biology

Background:

  • Manual validation of clusters using prior biological knowledge is common but occurs post-clustering.
  • Integrating biological knowledge into the clustering process can enhance the biological relevance of results.
  • Current clustering methods often do not leverage biological pathways during cluster formation.

Purpose of the Study:

  • To develop and evaluate a novel clustering algorithm that incorporates biological information during training.
  • To improve the biological interpretability and value of clusters in biological data analysis.
  • To enhance the convergence and performance of clustering algorithms by leveraging biological pathway data.

Main Methods:

  • A biologically-inspired self-organizing map (bSOM) training algorithm was developed.
  • The bSOM algorithm modifies distance calculations to include information from metabolic pathways.
  • Tested on transcript and metabolite data from Solanum lycopersicum and Arabidopsis thaliana, comparing bSOM with standard SOM.

Main Results:

  • The bSOM algorithm demonstrated improved convergence and performance compared to standard SOM.
  • A new validation measure incorporating biological connectivity confirmed bSOM's effectiveness.
  • Clustering solutions generated by bSOM showed enhanced biological relevance.

Conclusions:

  • Incorporating biological information directly into the training phase significantly increases the biological value of clusters.
  • The bSOM method simplifies the analysis of biological data by producing more interpretable clusters.
  • The bSOM algorithm is available as a web demo and its source code and datasets are publicly accessible.