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 Concept Videos

DNA Microarrays02:34

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

<i>In vitro</i> model reveals structural and metabolic insights into the porcine cecal microbiota in response to β-mannan exposure.

Applied and environmental microbiology·2026
Same author

A Benchmark Evaluation of Chemical Structure Extraction from Patents: Insights and Challenges in Chemical Structure Recognition.

Chemical research in toxicology·2026
Same author

Profiling histone post-translational modifications to identify signatures of epigenetic drug response in T-cell acute lymphoblastic leukemia.

Scientific reports·2026
Same author

OmniCorr: an R-package for visualizing putative host-microbiome interactions using multi-omics data.

Bioinformatics advances·2026
Same author

Patterns of chromosomal instability and epigenetic alterations in colorectal cancer progression: from high-grade dysplasia to liver metastases.

Mutagenesis·2026
Same author

Conservation of the short-day vernalization flowering response pathway in temperate Pooideae grasses.

The New phytologist·2026

Related Experiment Video

Updated: May 28, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Classification of microarrays; synergistic effects between normalization, gene selection and machine learning.

Jenny Önskog1, Eva Freyhult, Mattias Landfors

  • 1Umeå Plant Science Center, Department of Plant Physiology, Umeå University, 901 87 Umeå, Sweden.

BMC Bioinformatics
|October 11, 2011
PubMed
Summary

Machine learning methods for microarray data show improved cancer classification when using normalized data and selecting many genes. Support Vector Machines performed consistently well across datasets.

More Related Videos

Using Microarrays to Interrogate Microenvironmental Impact on Cellular Phenotypes in Cancer
08:20

Using Microarrays to Interrogate Microenvironmental Impact on Cellular Phenotypes in Cancer

Published on: May 21, 2019

DNA Microarrays: Sample Quality Control, Array Hybridization and Scanning
09:27

DNA Microarrays: Sample Quality Control, Array Hybridization and Scanning

Published on: March 15, 2011

Related Experiment Videos

Last Updated: May 28, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Using Microarrays to Interrogate Microenvironmental Impact on Cellular Phenotypes in Cancer
08:20

Using Microarrays to Interrogate Microenvironmental Impact on Cellular Phenotypes in Cancer

Published on: May 21, 2019

DNA Microarrays: Sample Quality Control, Array Hybridization and Scanning
09:27

DNA Microarrays: Sample Quality Control, Array Hybridization and Scanning

Published on: March 15, 2011

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Machine learning (ML) is effective for analyzing microarray data, but performance depends on multiple analysis steps.
  • Previous studies often evaluated ML methods without considering the impact of data normalization and gene selection.

Purpose of the Study:

  • To comprehensively compare the impact of normalization, gene selection, and ML methods on cancer microarray data classification.
  • To identify optimal combinations of methods and understand synergistic effects for improved predictive accuracy.

Main Methods:

  • Utilized seven cancer-related microarray datasets.
  • Evaluated five normalization methods, three gene selection techniques (with 21 gene counts), and eight ML algorithms.
  • Employed a rigorous double cross-validation approach to estimate error rates and compared methods across datasets.

Main Results:

  • Support Vector Machines (SVM) with radial basis, linear, or polynomial kernels demonstrated consistent high performance.
  • A synergistic relationship was observed between SVM, T-test-based gene selection, and a high number of selected genes.
  • Normalized data significantly improved the performance of the evaluated ML methods.

Conclusions:

  • SVM variants are robust choices for cancer classification from microarray data.
  • Combining SVM with specific gene selection strategies and normalization enhances classification accuracy.
  • While normalization is beneficial, definitive conclusions on the best normalization methods remain elusive.