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

Predicting protein subcellular location by fusing multiple classifiers.

Kuo-Chen Chou1, Hong-Bin Shen

  • 1Gordon Life Science Institute, 13784 Torrey Del Mar, San Diego, California 92130, USA. kchou@san.rr.com

Journal of Cellular Biochemistry
|April 28, 2006
PubMed
Summary

Accurately predicting protein subcellular localization is crucial for understanding cellular functions. A new ensemble classifier, trained on amphiphilic pseudo amino acid composition, significantly improves prediction accuracy for 14 cellular compartments.

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

BindRNAgen: Protein-binding RNA sequence generation using latent diffusion models.

Journal of molecular biology·2026
Same author

DrugDL: dual-modal deep learning framework for multi-property drug prediction and targeted therapy discovery.

Bioinformatics (Oxford, England)·2026
Same author

Reconstructing cell-cell interaction network in single-cell spatial transcriptomics via directed heterogeneous graph autoencoder.

Bioinformatics (Oxford, England)·2026
Same author

SMENET: A Multi-View Semantic Model for Multi-Level Enzyme Function Prediction.

IEEE transactions on computational biology and bioinformatics·2025
Same author

Ab-initio amino acid sequence design from protein text description with ProtDAT.

Nature communications·2025
Same author

Simultaneously infer cell pseudotime, velocity field, and gene interaction from multi-branch scRNA-seq data with scPN.

NAR genomics and bioinformatics·2025

Area of Science:

  • Cell Biology
  • Proteomics
  • Bioinformatics

Background:

  • Identifying protein functions relies heavily on understanding their subcellular localization within cellular compartments.
  • Experimental determination of protein localization is time-consuming and costly, hindering research in the post-genomic era.
  • Automated methods are needed to rapidly and reliably predict subcellular locations for basic research and drug discovery.

Purpose of the Study:

  • To develop an automated, accurate, and fast method for predicting protein subcellular localization using sequence information.
  • To create an ensemble classifier by fusing multiple basic classifiers trained on different aspects of protein sequence composition.

Main Methods:

  • An ensemble classifier was developed by fusing individual classifiers using a voting system.

Related Experiment Videos

  • Each basic classifier was trained on a different dimension of the amphiphilic pseudo amino acid composition.
  • Predictions were validated across 14 distinct subcellular localizations using resubstitution, jackknife, and independent dataset tests.

    • Main Results:

    • The developed fusion ensemble classifier demonstrated significantly higher success rates compared to existing methods.
    • The method achieved high accuracy in predicting protein locations among the 14 tested cellular compartments.
    • Validation across multiple testing strategies confirmed the robustness and effectiveness of the ensemble approach.

    Conclusions:

    • The novel ensemble classifier provides a fast and reliable automated method for predicting protein subcellular localization.
    • This approach can accelerate basic biological research and aid in drug discovery by enabling timely functional annotation of proteins.
    • The classifier has potential applications in predicting other protein attributes, such as membrane protein type and enzyme families.