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

Prediction of biologically significant components from microarray data: Independently Consistent Expression

Rahul Bijlani1, Yinhe Cheng, David A Pearce

  • 1Department of Computer Science, University of Rochester School of Medicine and Dentistry, NY 14642, USA.

Bioinformatics (Oxford, England)
|December 25, 2002
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

Modeling Dyadic Interdependence in Endocrine Functioning: A Multilevel Machine Learning Study of Adults with Cancer and Their Caregivers.

IEEE transactions on bio-medical engineering·2026
Same author

Machine Learning Risk Stratification Approach Using Patient-Reported Outcomes for Forecasting Unplanned Health Care Use and Symptom Burden in Cancer Survivors.

JCO clinical cancer informatics·2026
Same author

Diagnostic uncertainty as a public health imperative: a call for R69 code adoption.

Diagnosis (Berlin, Germany)·2026
Same author

Diversity of DNA viruses in the atmosphere of sub-Antarctic South Georgia.

Frontiers in microbiology·2026
Same author

Digital health technology use in clinical trials of rare diseases: a systematic review.

Communications medicine·2025
Same author

What Matters Ethically About How the UDN Has Changed Since Its Inception?

AMA journal of ethics·2025
Same journal

Probabilistic RNA designability via interpretable ensemble approximation and dynamic decomposition.

Bioinformatics (Oxford, England)·2026
Same journal

Quantifying domain-specific relevance of computational biology Wikipedia articles using TF-IDF and cosine similarity.

Bioinformatics (Oxford, England)·2026
Same journal

GATSBI: improving context-aware protein embeddings through biologically motivated data splits.

Bioinformatics (Oxford, England)·2026
Same journal

BiMba: using Vision Mamba to predict protein sites that bind other proteins.

Bioinformatics (Oxford, England)·2026
Same journal

ProMeta: a meta-learning framework for robust disease diagnosis and prediction from plasma proteomics.

Bioinformatics (Oxford, England)·2026
Same journal

Is a Win-Win possible? Achieving pareto-optimal privacy-utility balance in fine-tuned genome language model embeddings against embedding reconstruction attacks.

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

The Independent Consistent Expression Discriminator (ICED) method accurately identifies disease-predicting genes from gene expression data, even with small sample sizes. This approach aids in diagnosing diseases and finding new therapeutic targets.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Supervised learning is key for analyzing high-throughput gene expression data.
  • Identifying predictor genes aids in disease diagnosis and developing scientific approaches.
  • Gene expression variability is inherent in biological states and requires specialized analysis.

Purpose of the Study:

  • To introduce the Independent Consistent Expression Discriminator (ICED) for biologically relevant predictor gene selection.
  • To develop a novel approach for accurate predictor selection from limited microarray samples.
  • To embrace gene expression variability for improved disease state discrimination.

Main Methods:

  • ICED normalizes raw data and assigns weights to genes from both classes.

Related Experiment Videos

  • It counts votes to determine the optimal number of predictor genes.
  • It calculates prediction strengths for classification and identifies genes with consistent or variable expression patterns between classes.

    • Main Results:

    • ICED was applied to large AML/ALL and a small Batten disease dataset.
    • The method correctly predicted biologically relevant perturbations for disease classification, regardless of sample size.
    • Candidate proteins were identified for further study in disease mechanisms and therapeutic development.

    Conclusions:

    • ICED offers a novel approach to select biologically relevant predictors of differential disease states.
    • The method accurately classifies diseases even with limited sample sizes.
    • Identified candidate proteins may serve as future therapeutic targets.