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

A parallel genetic algorithm for single class pattern classification and its application for gene expression

Cuong C To1, Jiri Vohradsky

  • 1Laboratory of Bioinformatics, Institute of Microbiology, ASCR, Videnska 1083, 142 20 Prague, Czech Republic. cuongto@biomed.cas.cz <cuongto@biomed.cas.cz>

BMC Genomics
|February 15, 2007
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 Aspect of <i>Bacillus subtilis</i> σ<sup>B</sup> Regulatory Network on a Proteome Level-A Computational Simulation.

Biology·2024
Same author

Whole proteome analysis of germinating and outgrowing Bacillus subtilis 168.

Proteomics·2024
Same author

σ<sup>E</sup> of Streptomyces coelicolor can function both as a direct activator or repressor of transcription.

Communications biology·2024
Same author

Quantitative Aspect of <i>Bacillus subtilis</i> σB Regulatory Network-A Computational Simulation.

Biology·2022
Same author

Recommendations for connecting molecular sequence and biodiversity research infrastructures through ELIXIR.

F1000Research·2022
Same author

rboAnalyzer webserver: web service for non-coding RNA characterization from NCBI BLAST output.

Bioinformatics (Oxford, England)·2021

This study introduces a novel gene expression analysis method to identify genes with similar functions. The parallel genetic algorithm accurately predicts gene roles and active pathways in Streptomyces coelicolor.

Area of Science:

  • Bioinformatics
  • Systems Biology
  • Computational Biology

Background:

  • Analyzing gene expression over time reveals functional relationships between genes.
  • Identifying coordinately regulated genes aids in understanding biological processes.

Purpose of the Study:

  • To develop a supervised classification method for identifying genes with similar functions from time-series gene expression data.
  • To predict the functional roles of specific open reading frames (ORFs) using expression data.
  • To identify gene clusters and pathways involved in secondary metabolite production and transport.

Main Methods:

  • A parallel genetic algorithm, a supervised machine learning approach, was employed.
  • The algorithm leverages prior knowledge of gene function to classify unknown genes.

Related Experiment Videos

  • Performance was evaluated against seven other classification algorithms, including support vector machines.

    • Main Results:

    • The proposed algorithm demonstrated superior performance compared to other tested methods.
    • It successfully identified secondary metabolite gene clusters in Streptomyces coelicolor.
    • The method also uncovered pathways related to the export of secondary metabolites.

    Conclusions:

    • The algorithm effectively identifies genes of similar function from gene expression time series.
    • It accurately predicts functional roles and associated pathways active during experimental time courses.
    • This approach offers advantages over unsupervised clustering methods for gene function prediction.