Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 29, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Biomarker discovery across annotated and unannotated microarray datasets using semi-supervised learning.

Cole Harris¹, Noushin Ghaffari

¹Exagen Diagnostics, Inc, Houston, TX, USA. charris@exagen.com

|October 10, 2008

Summary

This summary is machine-generated.

Related Concept Videos

DNA Microarrays

DNA Microarrays

Microarrays are high-throughput and relatively inexpensive assays that can be automated to analyze large quantities of data at a time. They are used in genome-wide studies to compare gene or protein expression under two varied conditions, such as healthy and diseased states. Microarrays consist of glass or silica slides on which probe molecules are covalently attached through surface functionalization. Most commonly, the slides are prepared through the chemisorption of silanes to silica...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Evaluation of Prenatal Transportation Stress on DNA Methylation (DNAm) and Gene Expression in the Hypothalamic-Pituitary-Adrenal (HPA) Axis Tissues of Mature Brahman Cows.

Genes·2025

Same author

Speeding genomic island discovery through systematic design of reference database composition.

PloS one·2024

Same author

Differential Expression of Circadian Clock Genes in the Bovine Neuroendocrine Adrenal System.

Genes·2023

Same author

Inter-Individual Variation in DNA Methylation Patterns across Two Tissues and Leukocytes in Mature Brahman Cattle.

Biology·2023

Same author

DNA methylation patterns and gene expression from amygdala tissue of mature Brahman cows exposed to prenatal stress.

Frontiers in genetics·2022

Same author

Raw pacific biosciences and illumina sequencing reads and assembled genome data for the cattle ticks <i>Rhipicephalus microplus</i> and <i>Rhipicephalus annulatus</i>.

Data in brief·2021

Same journal

Mild oxidative stress and dietary epigenetic modulators direct DNA methylation remodeling toward stress-resilience pathways.

BMC genomics·2026

Same journal

Integrative ATAC-Seq and RNA-Seq analysis identifies key genes for intramuscular fat content in Laiwu pigs.

BMC genomics·2026

Same journal

A comprehensive long RNA landscape of multi-regional porcine lung-derived small extracellular vesicles.

BMC genomics·2026

Same journal

pGWAS-Portal: a comprehensive online platform for integrative post-genome-wide association study analysis.

BMC genomics·2026

Same journal

Physiological and transcriptomic analyses of Rosa persica in response to drought stress and functional validation of the transcription factor RpERF113-like.

BMC genomics·2026

Same journal

Integrated analysis of chromatin accessibility and transcriptome profiles in granulosa cells of sheep with different FecB genotypes.

BMC genomics·2026

See all related articles

This study introduces GLAD, a novel Semi-Supervised Learning (SSL) method. GLAD enhances DNA microarray analysis by integrating unannotated data to create more robust disease classifiers.

Area of Science:

Bioinformatics
Computational Biology
Genomics

Background:

DNA microarrays generate vast datasets for disease research.
Clinical annotation of microarray data is often limited by patient record access.
Developing robust sample classifiers requires effective data integration strategies.

Purpose of the Study:

To introduce GLAD, a Semi-Supervised Learning (SSL) method.
To combine annotated and unannotated microarray datasets for improved classifier performance.
To identify more robust sample classifiers for molecular disease understanding.

Main Methods:

Developed independent models using gene subsets for annotated and unannotated data.
Utilized a scoring function evaluating classification accuracy and cluster separation.

Related Experiment Videos

Last Updated: Jun 29, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Employed a genetic algorithm for iterative feature selection and model improvement.

Main Results:

The GLAD method successfully integrates independent annotated and unannotated datasets.
Incorporating unannotated data significantly enhances the robustness of sample classifiers.
Iterative model refinement using genetic algorithms improved classifier performance.

Conclusions:

Semi-Supervised Learning (SSL) offers a powerful approach for leveraging diverse microarray data.
GLAD demonstrates the significant benefit of including unannotated data in classifier training.
This method advances the potential of DNA microarray data in understanding the molecular basis of disease.