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

Evaluation of normalization methods for cDNA microarray data by k-NN classification.

Wei Wu1, Eric P Xing, Connie Myers

  • 1Life Sciences Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA. wuw2@upmc.edu

BMC Bioinformatics
|July 28, 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

A foundation model for continuous glucose monitoring data.

Nature·2026
Same author

Deep phenotyping of health-disease continuum in the Human Phenotype Project.

Nature medicine·2025
Same author

Causal Representation Learning from Multi-modal Biomedical Observations.

ArXiv·2025
Same author

Scaling Structure Aware Virtual Screening to Billions of Molecules with SPRINT.

ArXiv·2025
Same author

Interpretable adenylation domain specificity prediction using protein language models.

bioRxiv : the preprint server for biology·2025
Same author

A foundation model of transcription across human cell types.

Nature·2025
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

Double-bias removal normalization strategies effectively reduce dye biases in cDNA microarray data, improving classification accuracy. These methods, particularly IGLOESS-SLFILTERW7, ISTSPLINE-SLLOESS, and IGLOESS-SLLOESS, outperform others in removing spatial and intensity effects for better analysis.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Non-biological factors introduce variations in cDNA microarray data.
  • Existing normalization methods aim to remove these variations.
  • Few studies systematically evaluate normalization for dye bias removal in classification tasks.

Purpose of the Study:

  • To systematically evaluate normalization methods for removing dye biases in cDNA microarray data.
  • To assess the impact of normalization on downstream classification tasks.
  • To identify optimal normalization strategies for improving classification accuracy.

Main Methods:

  • Applied ten location and three scale normalization methods to five cancer-related cDNA microarray datasets.
  • Utilized leave-one-out cross-validation (LOOCV) classification error with k-nearest neighbor (k-NN) as the endpoint.

Related Experiment Videos

  • Compared single-bias, double-bias, and scale normalization techniques.

    • Main Results:

    • k-NN classifiers are sensitive to dye biases.
    • Double-bias removal techniques (spatial and intensity effects) significantly reduced LOOCV classification errors compared to single-bias methods.
    • Three specific two-step strategies (IGLOESS-SLFILTERW7, ISTSPLINE-SLLOESS, IGLOESS-SLLOESS) showed the best performance.
    • Scale normalization methods did not reduce LOOCV classification error.

    Conclusions:

    • Double-bias removal normalization strategies are superior for removing spatial and intensity dye biases in cDNA microarray data.
    • The evaluated strategies IGLOESS-SLFILTERW7, ISTSPLINE-SLLOESS, and IGLOESS-SLLOESS consistently improved classification accuracy.
    • k-NN LOOCV error is a sensitive and informative metric for evaluating normalization methods.