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

An SVM-based system for predicting protein subnuclear localizations.

Zhengdeng Lei1, Yang Dai

  • 1Department of Bioengineering (MC063), University of Illinois at Chicago, 851 South Morgan Street, Chicago IL 60607, USA. zlei2@uic.edu

BMC Bioinformatics
|December 13, 2005
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

Patient-derived organoids reveal ductal dysfunction and CFTR-modulator responses in chronic pancreatitis.

Cell stem cell·2026
Same author

Case Report: Ultrasound-guided percutaneous splenic biopsy as a lifesaving diagnostic modality in B-cell lymphoma presenting as hemophagocytic lymphohistiocytosis: a report of two cases.

Frontiers in oncology·2026
Same author

HDAC inhibition sensitizes pancreatic tumors to DNA damage by global redistribution of the transcriptional machinery.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Case Report: A diagnostic chameleon of EBV-associated immune dysregulation: HLH unmasking multiple myeloma with subsequent emergence of aggressive B-cell lymphoma.

Frontiers in immunology·2026
Same author

A novel monocyte-derived antigen presenting cell-T regulatory cell axis contributes to skin wound healing and is impaired in diabetic mice.

Journal of immunology (Baltimore, Md. : 1950)·2026
Same author

Case Report: Hemophagocytic lymphohistiocytosis masquerading as drug-induced liver injury: successful treatment with low-dose ruxolitinib and glucocorticoids.

Frontiers in immunology·2026
Same journal

OpenIMC: an open-source platform for analyzing single-cell and spatial proteomics by imaging mass cytometry.

BMC bioinformatics·2026
Same journal

NAP: an open source pipeline for cross-domain microbiome profiling using Nanopore sequencing-derived amplicon data.

BMC bioinformatics·2026
Same journal

SurvGME: an R package for survival analysis with graphical and measurement error models.

BMC bioinformatics·2026
Same journal

SimMapNet: a Bayesian framework for gene regulatory network inference using gene ontology similarities as external hint.

BMC bioinformatics·2026
Same journal

Dual channel drug-drug interactions extraction based on cross attention.

BMC bioinformatics·2026
Same journal

FeSseqdb: a curated sequence-level database and interpretable machine learning framework for identifying iron-sulfur proteins.

BMC bioinformatics·2026
See all related articles

A new computational tool predicts protein subnuclear localization using support vector machine (SVM) learning. This method accurately identifies protein locations, aiding in understanding protein function and biological pathways.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Proteomics

Background:

  • A significant gap exists between known protein sequences and functionally characterized proteins.
  • Predicting protein localization is crucial for understanding molecular function and biological pathways.
  • Existing tools primarily focus on subcellular localization, with limited options for subnuclear prediction.

Purpose of the Study:

  • To develop a fast, broadly applicable computational tool for predicting subnuclear and subcellular protein localizations.
  • To extract subtle sequence signals for discriminating between proteins with different subnuclear localizations.
  • To establish the first multi-class classification system for protein subnuclear localization prediction.

Main Methods:

  • Utilized support vector machine (SVM) learning models with novel kernel functions for sequence similarity measurement.

Related Experiment Videos

  • Employed k-peptide vectors mapped by high-scored k-peptide pairs (BLOSUM62 scores).
  • Integrated multiple encoding methods to create a multi-class classification system.

    • Main Results:

    • Achieved approximately 50% prediction accuracy for 6 subnuclear localizations (vs. 16.7% random chance) on single-localization proteins.
    • Demonstrated 65% accuracy on an independent set of multi-localization proteins.
    • Developed an integrated system accessible at http://array.bioengr.uic.edu/subnuclear.htm.

    Conclusions:

    • The integrated system's performance is enhanced by combining predictions from multiple SVMs using selected encoding methods.
    • The predictive accuracy is expected to increase with the availability of more proteins with known subnuclear localizations.
    • This tool provides a valuable resource for functional genomics and understanding protein behavior within the cell.