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 novel Mixture Model Method for identification of differentially expressed genes from DNA microarray data.

Kayvan Najarian1, Maryam Zaheri, Ali A Rad

  • 1Computer Science Department, University of North Carolina Charlotte, University City Blvd, Charlotte, NC, USA. knajaria@uncc.edu

BMC Bioinformatics
|December 18, 2004
PubMed
Summary

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

EMBC Special Issue: Modeling Early Oxygenation Trajectory in PARDS from High-Frequency Mechanical Ventilation Signals Using Deep Sequence Architectures.

IEEE transactions on bio-medical engineering·2026
Same author

Multi-dimensional MRI representation and privileged learning approaches to functional outcome prediction for ischemic stroke patients.

NPJ digital medicine·2026
Same author

A Novel, Interpretable Machine Learning Model Predicts Furosemide Dosing After Congenital Cardiac Surgery.

Pediatric cardiology·2026
Same author

The impact of data source on real-world medication adherence and exposure measures: From prescription to sold.

Journal of managed care & specialty pharmacy·2026
Same author

LoRA-based methods on Unet for transfer learning in aneurysmal subarachnoid hematoma segmentation.

BMC medical imaging·2025
Same author

The legacy and future of recurrent neural networks in personalized medicine: A reflection on the 2024 Nobel Physics Prize.

Biomedical journal·2025

A new Mixture Model Method (MMM) ensures repeatable gene expression analysis with small sample sizes. This enhanced method improves accuracy in identifying disease-related genes compared to traditional MMM.

Area of Science:

  • Bioinformatics
  • Statistical Genetics
  • Computational Biology

Background:

  • Microarray data analysis aims to identify differentially expressed genes.
  • Traditional Mixture Model Method (MMM) can over-fit data with few replicates, leading to non-repeatable results.
  • Existing methods lack robustness when dealing with limited sample sizes.

Purpose of the Study:

  • To develop a novel Mixture Model Method (MMM) for robust and repeatable microarray data analysis.
  • To reduce the sensitivity of gene expression analysis results to parameter choices.
  • To improve the accuracy of identifying differentially expressed genes, especially with small numbers of replicates.

Main Methods:

  • A modified Mixture Model Method (MMM) was developed to enhance repeatability and parameter independence.

Related Experiment Videos

  • The proposed algorithm was applied to two distinct biological datasets: Leukaemia and a mouse model for phosphate deficiency.
  • Gene selection performance was evaluated against established biological information and compared with the standard MMM.

    • Main Results:

    • The enhanced MMM demonstrated 100% repeatability across multiple runs.
    • The method showed minimal sensitivity to parameter variations.
    • On the Leukaemia dataset, the proposed algorithm achieved a 12% improvement over standard MMM in identifying known expressed genes.

    Conclusions:

    • The novel MMM provides a highly repeatable and robust approach for gene expression analysis.
    • The algorithm effectively identifies biologically relevant genes, aiding in disease pathogenesis studies.
    • This method offers significant advantages for comparative evaluation of treatment strategies using gene expression data.