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

Feature selection for splice site prediction: a new method using EDA-based feature ranking.

Yvan Saeys1, Sven Degroeve, Dirk Aeyels

  • 1Department of Plant Systems Biology, Ghent University, Flanders Interuniversity Institute for Biotechnology (VIB), Technologiepark 927, B-9052 Ghent, Belgium. yvan.saeys@psb.ugent.be

BMC Bioinformatics
|May 25, 2004
PubMed
Summary

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

CytoScan: Automated Detection of Technical Anomalies for Cytometry Quality Control.

Cytometry. Part A : the journal of the International Society for Analytical Cytology·2026
Same author

CARGO: A Cytometry Analysis framework via Regularized Graph Optimal-transport.

PLoS computational biology·2026
Same author

iDeepLC: Chemical Structure Information Yields Improved Retention Time Prediction of Peptides with Unseen Modifications.

Analytical chemistry·2026
Same author

anndataR improves interoperability between R and Python in single-cell transcriptomics.

Bioinformatics (Oxford, England)·2026
Same author

Automated Computational Flow Cytometry Correlates Decreasing Neutrophil-to-Lymphocyte Ratio to Improved Survival in NSCLC After Immune Checkpoint Blockade.

Cancer immunology research·2026
Same author

IL-4 treatment induces apoptosis of blood monocytes and proliferation of recruited injury-associated macrophages to resolve liver injury.

Cell reports·2026

This study introduces a novel feature selection method for splice site prediction, offering a dynamic view of feature importance. The technique is faster and scales better than traditional methods for complex biological data analysis.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Identifying relevant biological features is crucial for understanding complex datasets.
  • Feature selection enhances classification accuracy and speed.
  • Robust methods for rapid feature selection are vital for biological data analysis.

Purpose of the Study:

  • To present a novel feature subset selection method for splice site prediction.
  • To derive a feature ranking from estimation of distribution algorithms.
  • To gain insights into the biological process of splicing.

Main Methods:

  • A novel method for feature subset selection based on estimation of distribution algorithms (EDAs).
  • Derivation of a feature ranking from the algorithm's estimated distribution.

Related Experiment Videos

  • Iterative discarding of features based on the derived ranking.

    • Main Results:

    • Application of the technique to splice site prediction.
    • Demonstration of gaining biological insights into splicing.
    • The method provides a dynamic view of feature selection, unlike traditional EDAs.

    Conclusions:

    • The novel technique is more robust than traditional EDAs for feature selection.
    • It offers a dynamic view of the feature selection process, similar to sequential wrapper methods.
    • The method is faster and scales better for datasets with numerous features.