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

Profile-based string kernels for remote homology detection and motif extraction.

Rui Kuang1, Eugene Ie, Ke Wang

  • 1Department of Computer Science, Columbia University, New York, NY 10027, USA.

Proceedings. IEEE Computational Systems Bioinformatics Conference
|February 2, 2006
PubMed
Summary

We developed novel profile-based string kernels for protein classification and homology detection. These kernels, using PSI-BLAST profiles with support vector machines (SVMs), outperform existing methods and identify meaningful protein sequence motifs.

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

Author Correction: Ontogeny and transcriptional regulation of Thetis cells.

Nature·2026
Same author

Postmitotic transcription and 3D regulation show locus-specific and differentiation-specific sensitivity to cohesin depletion.

Nature genetics·2026
Same author

Ontogeny and transcriptional regulation of Thetis cells.

Nature·2026
Same author

Robust CD4<sup>+</sup> CAR T cell Expansion Is Associated with Non-ICANS Neurotoxicities Following Ciltacabtagene Autoleucel.

medRxiv : the preprint server for health sciences·2025
Same author

A wave of Thetis cells imparts tolerance to food antigens early in life.

Science (New York, N.Y.)·2025
Same author

Post-mitotic transcriptional activation and 3D regulatory interactions show locus- and differentiation-specific sensitivity to cohesin depletion.

bioRxiv : the preprint server for biology·2025

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning

Background:

  • Protein classification and remote homology detection are crucial in bioinformatics.
  • Existing methods often struggle with scalability and identifying subtle sequence similarities.
  • Support Vector Machines (SVMs) are powerful tools but require effective feature representation.

Purpose of the Study:

  • To introduce novel profile-based string kernels for protein classification and remote homology detection.
  • To enhance the performance of SVMs in analyzing protein sequences.
  • To develop a computationally efficient method for large-scale biological data analysis.

Main Methods:

  • Developed profile-based string kernels utilizing probabilistic profiles from PSI-BLAST.

Related Experiment Videos

  • Employed an efficient data structure for rapid kernel computation.
  • Applied kernels with SVM classifiers to protein sequence datasets, including the SCOP database.
  • Investigated the extraction of discriminative sequence motifs from learned SVM models.

    • Main Results:

    • Profile-based string kernels significantly outperformed existing supervised SVM methods in remote homology detection.
    • The method demonstrated comparable performance to cluster kernels but with superior scalability.
    • Extracted discriminative sequence motifs corresponded to biologically meaningful structural features.
    • Kernel computation and SVM training were faster than PSI-BLAST profile generation.

    Conclusions:

    • Profile-based string kernels offer a powerful and efficient approach for protein classification and remote homology detection.
    • The method leverages semi-supervised learning through PSI-BLAST profiles for improved accuracy.
    • The ability to extract discriminative motifs provides insights into protein structure-function relationships.
    • This approach presents a scalable solution for analyzing large protein sequence datasets.