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 splicing sites in eukaryotic RNA: support vector machine approach.

Ying-Fei Sun1, Xiao-Dan Fan, Yan-Da Li

  • 1Institute of Bioinformatics, State Key Laboratory of Intelligent Technology and System, Tsinghua University, Beijing 100084, People's Republic of China. syfei@mail.au.tsinghua.edu.cn

Computers in Biology and Medicine
|December 18, 2002
PubMed
Summary

We developed a new method for splice site prediction using support vector machines (SVM). While RNA secondary structure information did not improve accuracy, the SVM approach demonstrated strong performance in identifying splice sites.

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

Morphological disparity in elateriform beetles: patterns, trends and implications.

Proceedings. Biological sciences·2026
Same author

Revisiting early angiosperm pollination: a reassessment of Angimordella beetle and co-occurring thrips from mid-Cretaceous amber.

BMC biology·2026
Same author

<i>Zavoticus yini</i> gen. et sp. nov., a New Euaesthetine Rove Beetle From Mid-Cretaceous Kachin Amber (Coleoptera: Staphylinidae).

Ecology and evolution·2025
Same author

<i>Fantosmium</i>, a New Genus of Onthophilinae From Mid-Cretaceous Kachin Amber (Coleoptera: Histeridae).

Ecology and evolution·2025
Same author

Specialized bark-gnawing beetles reveal phragmotic defence and subcortical ecology in the Cretaceous.

Proceedings. Biological sciences·2025
Same author

Modeling compositional heterogeneity resolves deep phylogeny of flowering plants.

Plant diversity·2025

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Splice site prediction is crucial for understanding gene structure and function.
  • Support Vector Machines (SVM) are powerful tools for supervised pattern classification.
  • Previous methods for splice site prediction have varying degrees of success.

Purpose of the Study:

  • To introduce and evaluate a novel method for splice site prediction using Support Vector Machines (SVM).
  • To assess the impact of incorporating RNA secondary structure information on splice site recognition accuracy.

Main Methods:

  • The study employed Support Vector Machines (SVM) for supervised pattern classification.
  • Statistical information from RNA secondary structures near donor and acceptor sites was analyzed.

Related Experiment Videos

  • Performance was evaluated by comparing recognition ratios of true positives and true negatives.

    • Main Results:

    • The SVM method achieved good performance in splice site identification.
    • Incorporating RNA secondary structure information did not significantly benefit, and in some cases lowered, the recognition rate.
    • Three-fold cross-validation confirmed the SVM method's effectiveness.

    Conclusions:

    • SVM is a viable and effective method for splice site prediction.
    • RNA secondary structure information may not be a critical feature for accurate splice site identification using this SVM approach.
    • Further research could explore alternative feature sets or machine learning models.