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

SVM-based detection of distant protein structural relationships using pairwise probabilistic suffix trees.

Hasan Oğul1, Erkan U Mumcuoğlu

  • 1Department of Computer Engineering, Başkent University, 06530 Ankara, Turkey. hogul@baskent.edu.tr

Computational Biology and Chemistry
|August 2, 2006
PubMed
Summary

A new method using probabilistic suffix trees (PSTs) improves protein classification accuracy. This SVM-PST approach offers efficient and accurate comparison of distantly related protein sequences.

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

Investigation on radiation interactions with some quenched alloys used in nuclear reactors.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2025
Same author

Loss of WWOX contributes to cisplatin resistance in triple-negative breast cancer cells by modulating miR-182 and miR-214.

Turkish journal of medical sciences·2024
Same author

A study on the interaction parameters of charged and uncharged radiation types with some indoor plants.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2024
Same author

Estimation of neutron and gamma-ray attenuation characteristics of some ferrites: Geant4, FLUKA and WinXCom studies.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2023
Same author

MobileNet-SVM: A Lightweight Deep Transfer Learning Model to Diagnose BCH Scans for IoMT-Based Imaging Sensors.

Sensors (Basel, Switzerland)·2023
Same author

Identifying the tumor location-associated candidate genes in development of new drugs for colorectal cancer using machine-learning-based approach.

Medical & biological engineering & computing·2022

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Structural Bioinformatics

Background:

  • Accurate protein classification is crucial for understanding protein function and evolution.
  • Existing methods for comparing distantly related protein sequences have limitations in accuracy or computational efficiency.

Purpose of the Study:

  • To develop a novel, accurate, and efficient method for pairwise comparison of distantly related protein sequences.
  • To enhance protein classification using a discriminative framework incorporating probabilistic suffix trees.

Main Methods:

  • A new definition of probabilistic suffix trees (PSTs) was developed for pairwise protein sequence comparison.
  • A discriminative framework employing support vector machines (SVMs) was used for classification, encoding features with PST-based similarity scores.

Related Experiment Videos

  • The SVM-PST system was evaluated on the SCOP family classification task.

    • Main Results:

    • The SVM-PST method demonstrated higher accuracy than SVM-BLAST, which uses BLAST similarity scores.
    • SVM-PST showed competitive accuracy compared to SVM-Pairwise, which relies on dynamic programming alignment scores.
    • PST-based sequence comparison proved significantly more computationally efficient than dynamic programming methods.
    • The proposed method outperformed the original family-based PST approach for protein classification.

    Conclusions:

    • The SVM-PST method offers a significant advancement in protein classification accuracy and computational efficiency.
    • This approach provides a superior alternative for classifying distantly related protein sequences compared to existing methods.
    • The study highlights the effectiveness of PSTs within a discriminative framework for bioinformatics tasks.