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

Marginalized kernels for RNA sequence data analysis.

Taishin Kin1, Koji Tsuda, Kiyoshi Asai

  • 1Computational Biology Research Center, National Institute of Advanced Industrial Science and Technology, 2-41-6 Aomi, Koto-ku, Tokyo 135-0064, Japan. taishin@cbrc.jp

Genome Informatics. International Conference on Genome Informatics
|October 23, 2003
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

SERIPH: A Two-Step Extraction Protocol for Selective Enrichment of Semi-Extractable RNAs.

RNA (New York, N.Y.)·2026
Same author

LinearCapR: linear-time computation of per-nucleotide structural-context probabilities of RNA without base-pair span limits.

Bioinformatics (Oxford, England)·2026
Same author

The role of the tryptophan-rich allosteric network and sodium egress in GPCR activation.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Molecular Design with Artificial Intelligence: Progress and Perspectives for Small Molecules.

Chemical reviews·2026
Same author

A method for estimating energy parameters of RNAs by differentiating base-pairing probabilities.

NAR genomics and bioinformatics·2025
Same author

PseudoknotVisualizer: Visualization of pseudoknots on three-dimensional RNA structures.

PLoS computational biology·2025

We developed new methods to compare RNA sequences based on their structures. These novel kernels, including the marginalized count kernel (MCK), accurately analyze RNA similarities and aid in classification tasks.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Comparing RNA sequences is crucial for understanding gene function and regulation.
  • Existing methods often overlook the critical role of RNA secondary structures in sequence similarity.
  • Accurate RNA structure prediction is essential for functional genomic analysis.

Purpose of the Study:

  • To introduce novel kernel methods for quantifying RNA sequence similarity, incorporating secondary structure information.
  • To develop and evaluate a marginalized count kernel (MCK) for RNA sequences lacking known structures.
  • To demonstrate the utility of these kernels in visualizing and classifying RNA data.

Main Methods:

  • Development of two novel kernel functions for RNA sequence comparison.

Related Experiment Videos

  • Implementation of stochastic context-free grammar (SCFG) for secondary structure estimation in the MCK.
  • Application of kernel principal component analysis (kernel PCA) for similarity visualization.
  • Utilizing support vector machines (SVMs) for supervised classification tasks.

    • Main Results:

    • The proposed kernels effectively capture similarity between RNA sequences based on their structures.
    • Kernel PCA successfully visualized similarities within human tRNA sequence datasets.
    • Supervised classification using SVMs demonstrated the discriminative power of the MCK.
    • Both experimental approaches yielded promising results, validating the effectiveness of the novel kernels.

    Conclusions:

    • The novel kernels provide a powerful approach for RNA sequence analysis by integrating secondary structure information.
    • The marginalized count kernel (MCK) is a promising tool for analyzing RNA sequences with unknown structures.
    • These methods offer advancements in bioinformatics for RNA research, aiding in functional prediction and classification.