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

Biological sequence classification utilizing positive and unlabeled data.

Yuanyuan Xiao1, Mark R Segal

  • 1Department of Epidemiology and Biostatistics, Center for Bioinformatics and Molecular Biostatistics, University of California, San Francisco, CA 94107, USA.

Bioinformatics (Oxford, England)
|March 18, 2008
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

Ethnic differences in health outcomes of Chinese children and adolescents: A comparative meta-analysis.

iScience·2026
Same author

Single-nucleus transcriptomics identifies SPON1 as a candidate mediator of the anti-fibrotic effect of <i>Abelmoschus manihot</i> (L.) in diabetic kidney disease.

American journal of translational research·2026
Same author

A knowledge-driven unified framework for plant disease classification and severity grading via domain adaptation.

Plant phenomics (Washington, D.C.)·2026
Same author

Machine learning algorithms in jointly developing prediction models for subsequent school bullying victimization in Chinese children and adolescents.

Psychiatry research·2026
Same author

School bullying associated morbidity and hospital consultation among Chinese children and adolescents: Evidence from the MHSCAY cohort.

Public health·2026
Same author

A multi-omics study reveals pathway-level insights and predictive biomarkers in pediatric TB.

Clinical proteomics·2026
Same journal

3DICE: Interpretable 3D Cross-Modal Learning for Drug-Target Interaction Prediction and Large-Scale Drug Discovery.

Bioinformatics (Oxford, England)·2026
Same journal

KASSPer: Kinase Active Site Structure Prediction using Protein and Ligand Language Models and Its Application to Virtual Screening.

Bioinformatics (Oxford, England)·2026
Same journal

IDR searcher: a search engine solution for public image resources.

Bioinformatics (Oxford, England)·2026
Same journal

KCFtools: Rapid alignment-free method for introgression screening and GWAS using k-mer profiles.

Bioinformatics (Oxford, England)·2026
Same journal

Meta2DB: Curated shotgun metagenomic feature sets and metadata for health state prediction.

Bioinformatics (Oxford, England)·2026
Same journal

conMItion: an R package adjusting confounding factors for associations in multi-omics.

Bioinformatics (Oxford, England)·2026
See all related articles

This study introduces a new method for genomics, likely positive-iterative classification (LP-IC), to identify specific sequences within large unlabeled datasets. LP-IC outperforms existing methods in accuracy and predictive performance for biological sequence analysis.

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Genomic data often features a small number of sequences with a specific property (positive instances) amidst numerous unlabeled sequences.
  • Traditional two-class classification methods are inadequate for this imbalanced data configuration common in genomics.

Purpose of the Study:

  • To develop a novel classification method, likely positive-iterative classification (LP-IC), tailored for genomics data with imbalanced classes.
  • To evaluate LP-IC's performance against existing methods, particularly those from text classification.

Main Methods:

  • Developed likely positive-iterative classification (LP-IC), an iterative classification scheme.
  • Incorporated a class dispersion measure from unsupervised clustering for model selection.

Related Experiment Videos

  • Applied LP-IC to two case studies: HLA binding prediction and human-mouse alternative splicing conservation.

    • Main Results:

    • LP-IC demonstrated superior performance compared to existing methodologies.
    • Achieved higher combined accuracy and precision in identifying positive instances from unlabeled data.
    • Showcased improved predictive performance of classifiers on independent test datasets.

    Conclusions:

    • LP-IC offers a more effective approach for classification tasks involving imbalanced genomic datasets.
    • The method shows promise for applications such as predicting HLA binding and analyzing cross-species splicing conservation.