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

Using the Fisher kernel method to detect remote protein homologies.

T Jaakkola1, M Diekhans, D Haussler

  • 1Department of Computer Science, University of California, Santa Cruz 95064, USA. tommi@ai.mit.edu

Proceedings. International Conference on Intelligent Systems for Molecular Biology
|April 29, 2000
PubMed
Summary

A novel Fisher kernel method effectively detects remote protein homologies. This approach combines hidden Markov models and support vector machines for improved protein domain classification.

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

Development and evaluation of the Capability, Opportunity, and Motivation to deliver Physical Activity in School Scale (COM-PASS).

The international journal of behavioral nutrition and physical activity·2024
Same author

Changes in the continuous leaping performance of Finnish adolescents between 1979 and 2020.

Journal of sports sciences·2022
Same author

Longitudinal associations among cardiorespiratory and muscular fitness, motor competence and objectively measured physical activity.

Journal of science and medicine in sport·2019
Same author

Influence of MP 29-02 on ciliary beat frequency in human epithelial cells in vitro.

European archives of oto-rhino-laryngology : official journal of the European Federation of Oto-Rhino-Laryngological Societies (EUFOS) : affiliated with the German Society for Oto-Rhino-Laryngology - Head and Neck Surgery·2018
Same author

Fundamental movement skills in adolescents: Secular trends from 2003 to 2010 and associations with physical activity and BMI.

Scandinavian journal of medicine & science in sports·2017
Same author

Motivational climate, goal orientation, perceived sport ability, and enjoyment within Finnish junior ice hockey players.

Scandinavian journal of medicine & science in sports·2015

Area of Science:

  • Computational biology
  • Bioinformatics
  • Machine learning in biology

Background:

  • Detecting remote protein homology is crucial for understanding protein function and evolution.
  • Existing methods may struggle with distant evolutionary relationships.
  • Accurate classification of protein domains is essential for biological databases.

Purpose of the Study:

  • To introduce a new method, the Fisher kernel method, for enhanced remote protein homology detection.
  • To evaluate the performance of this method in classifying protein domains.
  • To explore the potential of combining generative and discriminative models in biosequence analysis.

Main Methods:

  • Development of the Fisher kernel method, a variant of support vector machines.

Related Experiment Videos

  • Derivation of a novel kernel function from a hidden Markov model (HMM).
  • Application of the method to classify protein domains by SCOP superfamily.

    • Main Results:

    • The Fisher kernel method demonstrates strong performance in classifying protein domains.
    • The method successfully identifies remote protein homologies.
    • The approach shows promise for classifying protein domains across different superfamilies.

    Conclusions:

    • The Fisher kernel method offers a powerful new tool for remote protein homology detection.
    • Combining generative models (HMMs) with discriminative methods (SVMs) is a viable strategy for biosequence analysis.
    • This approach has potential applications beyond protein domain classification.