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

Identifying DNA splice sites using hypernetworks with artificial molecular evolution.

Jose L Segovia-Juarez1, Silvano Colombano, Denise Kirschner

  • 1Department of Microbiology and Immunology, University of Michigan, Ann Arbor, MI, USA.

Bio Systems
|November 23, 2006
PubMed
Summary

Identifying DNA splice sites is crucial for gene hunting. A novel hypernetwork architecture, inspired by molecular evolution, demonstrates comparable generalization performance to existing algorithms and outperforms leading systems in splice site recognition.

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

<i>In vitro</i> dormancy models improve ability to predict treatment response in severe marmoset tuberculosis lesions.

bioRxiv : the preprint server for biology·2026
Same author

Distinct mechanisms drive post-antibiotic Tuberculosis relapse post-cure versus post-treatment-failure.

bioRxiv : the preprint server for biology·2026
Same author

A novel machine-learning based optimization: identifying new treatment regimens for tuberculosis.

Numerical algebra, control and optimization·2025
Same author

GEODE: an <i>in silico</i> tool that translates <i>in vitro</i> to <i>in vivo</i> predictions of tuberculosis antibiotic combination efficacy.

Frontiers in pharmacology·2025
Same author

Religious and culturally conscious sleep care for Muslim patients: Clinical considerations and recommendations.

Sleep medicine reviews·2025
Same author

Rankings of tuberculosis antibiotic treatment regimens are sensitive to spatial scale, detection limit, and initial host bacterial burden.

Journal of theoretical biology·2025

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Identifying DNA splice sites is a fundamental challenge in gene hunting and molecular biology.
  • Current methods for splice site recognition face limitations in accuracy and efficiency.

Purpose of the Study:

  • To introduce a novel hypernetwork architecture for identifying DNA splice sites.
  • To evaluate the generalization performance of the hypernetwork approach.
  • To develop a system (HyperExon) for splice site candidate identification.

Main Methods:

  • DNA sequences from GenBank were translated into binary strings.
  • A biologically inspired hypernetwork architecture, learning through molecular evolution, was employed for training.
  • Two-fold cross-validation was used to assess generalization performance.

Related Experiment Videos

  • The HyperExon system integrated the best hypernetwork with local information and heuristic rules.

    • Main Results:

    • The hypernetwork demonstrated generalization performance comparable to established classification algorithms.
    • The developed HyperExon system achieved superior performance compared to leading splice recognition systems on the tested sequences.

    Conclusions:

    • The hypernetwork architecture offers a promising novel approach for DNA splice site identification.
    • HyperExon, leveraging hypernetwork learning, represents an advancement in splice site recognition technology.
    • This biologically inspired computational method holds potential for improving gene hunting strategies.