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

Hierarchical Bayesian neural network for gene expression temporal patterns.

Yulan Liang1, Arpad G Kelemen

  • 1Department of Biostatistics, University at Buffalo. yliang@buffalo.edu

Statistical Applications in Genetics and Molecular Biology
|May 2, 2006
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

An Integrated Immunometabolic Signature Predicts Prognosis and Immunotherapy Response in ccRCC and Identifies <i>UCN</i>-Mediated Immune Evasion as a Therapeutic Vulnerability: Evidence from In Vitro and In Vivo Studies.

Cancers·2026
Same author

Telehealth interventions for alcohol use disorder: A systematic review.

Liver research (Beijing, China)·2025
Same author

Event-triggered affine formation of second-order multi-agent systems via complex-valued Laplacian.

ISA transactions·2024
Same author

Unraveling the Degradation and Air-Induced Healing Mechanisms of Halide Perovskites under Proton Irradiation.

ACS applied materials & interfaces·2024
Same author

Use of Smartphone Apps for Improving Physical Function Capacity in Cardiac Patient Rehabilitation: Systematic Review.

JMIRx med·2023
Same author

A Physical Activity Mobile Game for Hematopoietic Stem Cell Transplant Patients: App Design, Development, and Evaluation.

JMIRx med·2023

This study introduces a Hierarchical Bayesian Neural Network to analyze noisy gene expression temporal patterns. The model effectively captures complex dynamics in time course gene array data, outperforming other machine learning methods.

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Systems Biology

Background:

  • Analyzing gene expression temporal patterns presents challenges due to data correlation, high noise levels, and heterogeneous dynamic patterns.
  • Existing methods struggle to accurately model the complex nature of time course gene array data.

Purpose of the Study:

  • To propose a novel Hierarchical Bayesian Neural Network (HBNN) model for accurate analysis of gene expression temporal patterns.
  • To address the challenges of input correlations, variations, and noise in time course gene expression data.

Main Methods:

  • Developed a Hierarchical Bayesian Neural Network model to capture correlations in time course gene array data.
  • Utilized a hierarchical Bayesian framework to estimate variations and noise.

Related Experiment Videos

  • Employed Monte Carlo Markov Chain (MCMC) simulation for simultaneous optimization of network parameters and hyperparameters.

    • Main Results:

    • The HBNN model successfully captured dynamic features of gene expression temporal patterns, even with high noise and correlated inputs.
    • Demonstrated robust performance on yeast cell cycle temporal data.
    • Outperformed popular machine learning methods like Nearest Neighbor, Support Vector Machine, and Self-Organized Map.

    Conclusions:

    • The proposed HBNN model offers a powerful approach for analyzing complex gene expression temporal patterns.
    • The model's ability to handle noise and correlations makes it suitable for diverse microarray data applications.
    • This method provides a significant advancement in understanding gene regulatory dynamics.