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

A learned comparative expression measure for affymetrix genechip DNA microarrays.

Will Sheffler1, Eli Upfal, John Sedivy

  • 1Dept. of Genome Sciences, University of Washington, USA. wsheffle@u.washington.edu

Proceedings. IEEE Computational Systems Bioinformatics Conference
|February 2, 2006
PubMed
Summary

We developed a new method, learned comparative expression measure (LCEM), to detect gene expression changes between biological conditions. LCEM outperforms existing methods like MAS5 and RMA, especially for small microarray studies.

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

Prioritizing peptides for targeted mass spectrometry experiments using deep learning.

bioRxiv : the preprint server for biology·2026
Same author

Embryo-scale Visual Cell Sorting reveals a conserved transcriptomic signature of nucleolar size linked to proteostasis.

bioRxiv : the preprint server for biology·2026
Same author

Prediction and functional interpretation of inter-chromosomal genome architecture from DNA sequence with TwinC.

Nature communications·2026
Same author

Benchmarking Hi-C scaffolders using reference genomes and de novo assemblies.

Genome biology·2026
Same author

Unified imputation of missing data modalities and features in multi-omic data via shared representation learning.

bioRxiv : the preprint server for biology·2026
Same author

Improvements to Casanovo, a Deep Learning <i>De Novo</i> Peptide Sequencer.

Journal of proteome research·2025

Area of Science:

  • Genomics
  • Bioinformatics
  • Molecular Biology

Background:

  • Microarray studies commonly aim to identify genes with altered expression between biological conditions.
  • Current methods often rely on static models or indirect estimation of absolute expression levels before comparison.

Purpose of the Study:

  • To introduce a novel method for detecting differential gene expression between samples using Affymetrix GeneChip data.
  • To develop a learned comparative expression measure (LCEM) that directly assesses expression changes.

Main Methods:

  • Utilized a large dataset of known differential expression cases (>200,000) to train the LCEM.
  • Employed classification of probe-level data patterns to identify changes.
  • Focused on perfect match probe data, finding mismatch probe data less useful.

Related Experiment Videos

Main Results:

  • LCEM demonstrated a lower false discovery rate compared to MAS5 and single-chip RMA at typical microarray analysis selectivity levels.
  • LCEM showed superior performance over RMA when multiple chips were available for RMA, excelling in two out of three datasets.
  • The MAS5 log ratio statistic exhibited poor performance across all tested datasets.

Conclusions:

  • LCEM is a powerful method for detecting gene expression changes, particularly effective for small microarray studies where other methods may not generalize.
  • LCEM offers improved accuracy and reduced false discovery rates compared to established methods like MAS5 and RMA.