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

Implicit motif distribution based hybrid computational kernel for sequence classification.

Volkan Atalay1, Rengul Cetin-Atalay

  • 1Virginia Bioinformatics Institute, Virginia Polytechnic Institute and State University, Blacksburg, VA 24061, USA.

Bioinformatics (Oxford, England)
|December 16, 2004
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

On the state of protein function prediction: a report on the fourth CAFA challenge.

bioRxiv : the preprint server for biology·2026
Same author

Molecular contrastive learning with graph attention network (MoCL-GAT) for enhanced molecular representation.

BMC bioinformatics·2026
Same author

Mitochondrial one-carbon metabolism is required for TGF-β-induced glycine synthesis and fibrotic responses.

Nature communications·2025
Same author

Arginine promotes the activation of human lung fibroblasts independent of its metabolism.

The Biochemical journal·2025
Same author

HIF-1 regulates mitochondrial function in bone marrow-derived macrophages but not in tissue-resident alveolar macrophages.

Scientific reports·2025
Same author

mTOR signaling regulates multiple metabolic pathways in human lung fibroblasts after TGF-β and in pulmonary fibrosis.

American journal of physiology. Lung cellular and molecular physiology·2025

We developed P2SL, a computational system for protein subcellular targeting prediction. It uses implicit motif distributions and machine learning to classify protein locations with 81% accuracy.

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Machine Learning

Background:

  • Classification problems often require motif extraction from sequences.
  • Searching for explicit motifs can be computationally prohibitive.
  • Implicit motif distribution offers an alternative for sequence analysis.

Purpose of the Study:

  • To develop a general computational kernel for classification problems involving sequence motif extraction.
  • To create a system for predicting protein subcellular localization.
  • To model targeting-signals using implicit motif distributions.

Main Methods:

  • Designed a computational kernel for implicit motif distribution.
  • Developed the P2SL system using self-organizing maps and support vector machines.

Related Experiment Videos

  • Modeled targeting-signals by the distribution of subsequence occurrences.

    • Main Results:

    • P2SL achieved approximately 81% prediction accuracy for ER, cytosolic, mitochondrial, and nuclear protein localization.
    • The system models targeting-signals via implicit motif distribution.
    • P2SL provides distribution potential for proteins, crucial for shuttling proteins.

    Conclusions:

    • The implicit motif distribution approach is effective for sequence-based classification.
    • P2SL accurately predicts protein subcellular localization.
    • The system is valuable for analyzing proteins with dynamic localization.