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

Efficient remote homology detection using local structure.

Yuna Hou1, Wynne Hsu, Mong Li Lee

  • 1School of Computing, National University of Singapore, Singapore 117543. houyuna@comp.nus.edu.sg

Bioinformatics (Oxford, England)
|November 25, 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

Reply to determining MCID threshold for Knee Society Score to assess patient satisfaction in knee arthroplasty.

NPJ digital medicine·2026
Same author

Correction: Utility of a patient similarity-based digital tool for risk communication to patients with type 2 diabetes mellitus: Perspectives from primary care physicians in ambulatory care.

PloS one·2025
Same author

Patient perspectives on patient similarity-based risk communication for uncontrolled type 2 diabetes in primary care: A qualitative study.

PloS one·2025
Same author

Electrostatic potential is the dominant force in antigenic selection of naïve T-cells and B-cells for activation and maturation.

Immunology letters·2025
Same author

Non-invasive biopsy diagnosis of diabetic kidney disease via deep learning applied to retinal images: a population-based study.

The Lancet. Digital health·2025
Same author

Immobilization and enhancement of a heterodimeric fluorescence biosensor in fibrous protein biomaterials.

Protein science : a publication of the Protein Society·2025
Same journal

conMItion: an R package adjusting confounding factors for associations in multi-omics.

Bioinformatics (Oxford, England)·2026
Same journal

SpaMFG: a Spatial Multi-omics Integration Method based on Feature Grouping.

Bioinformatics (Oxford, England)·2026
Same journal

CSCN: Inference of Cell-Specific Causal Networks Using Single-Cell RNA-Seq Data.

Bioinformatics (Oxford, England)·2026
Same journal

Sparse CCA-Based Mediation Analysis with High-Dimensional Exposures and Mediators.

Bioinformatics (Oxford, England)·2026
Same journal

Enhancing Cross-Context Generalization in Drug Perturbation Prediction with a Multimodal Conditional Diffusion Framework.

Bioinformatics (Oxford, England)·2026
Same journal

Primer Design through Submodular Function Estimation.

Bioinformatics (Oxford, England)·2026
See all related articles

SVM-I-sites, a novel method, uses protein structure similarity for remote homology detection. It is more efficient and performs comparably to existing sequence-based methods.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Structural Biology

Background:

  • Inferring protein function relies on mapping sequences to homologous families.
  • Current accurate methods like SVM-pairwise use sequence similarity but ignore structure and are computationally inefficient.
  • There is a need for efficient methods that incorporate structural information for protein classification.

Purpose of the Study:

  • To present SVM-I-sites, a novel Support Vector Machine (SVM)-based method for protein classification.
  • To utilize protein structure similarity for remote homology detection.
  • To develop a computationally efficient alternative to existing sequence-based methods.

Main Methods:

  • The SVM-I-sites method encodes local structure information into feature vectors.

Related Experiment Videos

  • It employs a Support Vector Machine (SVM) framework for classification.
  • Experiments were conducted using the Structural Classification of Proteins (SCOP) 1.53 dataset.

    • Main Results:

    • SVM-I-sites demonstrated higher computational efficiency compared to SVM-pairwise.
    • The method achieved performance comparable to SVM-pairwise.
    • SVM-I-sites outperformed other sequence-based methods, including PSI-BLAST, SAM, and SVM-Fisher.

    Conclusions:

    • SVM-I-sites offers an efficient and effective approach for remote homology detection by leveraging protein structure similarity.
    • The method provides a valuable alternative to existing sequence-based techniques.
    • The framework for encoding local structure into feature vectors is available for academic and commercial use.