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 robust neural networks approach for spatial and intensity-dependent normalization of cDNA microarray data.

A L Tarca1, J E K Cooke, J Mackay

  • 1Research Center in Forest Biology, Department of Wood and Forest Science, Laval University, Sainte-Foy (QC), Canada G1K-7P4. ltarca@rsvs.ulaval.ca

Bioinformatics (Oxford, England)
|March 31, 2005
PubMed
Summary

This study introduces a novel neural network method to normalize microarray data, effectively correcting for intensity and spatial biases. This approach enhances the reliable identification of biologically significant gene expression changes.

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

Additive and non-additive genetic variance in juvenile Sitka spruce (<i>Picea sitchensis</i> Bong. Carr).

Tree genetics & genomes·2023
Same author

Musculoskeletal radiology training in the UK: a national survey by the British Society of Skeletal Radiologists.

Clinical radiology·2021
Same author

Assessment of quantitative [<sup>18</sup>F]Sodium fluoride PET measures of knee subchondral bone perfusion and mineralization in osteoarthritic and healthy subjects.

Osteoarthritis and cartilage·2021
Same author

Reduced fetal growth velocity precedes antepartum fetal death.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2020
Same author

Prediction of adverse perinatal outcome by fetal biometry: comparison of customized and population-based standards.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2019
Same author

Receptor homodimerization plays a critical role in a novel dominant negative P2RY12 variant identified in a family with severe bleeding.

Journal of thrombosis and haemostasis : JTH·2017

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Microarray experiments are prone to systematic biases from non-biological variations, impacting data accuracy.
  • These biases, including intensity- and spatiality-dependent variations, complicate the identification of true biological differences in gene expression.
  • Effective data normalization is crucial for reliable gene expression analysis.

Purpose of the Study:

  • To develop and present a robust normalization method for cDNA microarray data.
  • To address and correct for both intensity-dependent and spatiality-dependent biases.
  • To improve the accuracy and reliability of identifying differentially expressed genes.

Main Methods:

  • A feed-forward neural network is employed to model the relationship between log-intensity ratio (M), average log-intensity (A), and spatial coordinates (X,Y).

Related Experiment Videos

  • Robustness against outliers is achieved using a weighted approach based on M value deviations and pseudo-spatial coordinates.
  • The method is designed for dual-label (two-color) microarray datasets.

    • Main Results:

    • The neural network method effectively corrects for intensity-dependent bias in microarray data.
    • The method demonstrates significant reduction in spatiality-dependent bias.
    • Comparison with existing methods shows improved bias correction, leading to more reliable gene identification.

    Conclusions:

    • The proposed neural network-based normalization method offers a powerful tool for correcting complex biases in microarray data.
    • This approach enhances the accuracy of identifying truly regulated genes by mitigating systematic variations.
    • The method provides a more reliable foundation for downstream biological interpretation of gene expression profiles.