Optimization of neural network architecture using genetic programming improves detection and modeling of gene-gene interactions in studies of human diseases

Public Deposited
Analytics

Downloadable Content

Download PDF
Request Version for Screen Reader
Creator
  • Ritchie, Marylyn D
    • Other Affiliation: Program in Human Genetics and Department of Molecular Physiology and Biophysics, Vanderbilt University Medical School
  • White, Bill C
    • Other Affiliation: Program in Human Genetics and Department of Molecular Physiology and Biophysics, Vanderbilt University Medical School
  • Parker, Joel S
    • Affiliation: University of North Carolina at Chapel Hill
    • Other Affiliation: Program in Human Genetics and Department of Molecular Physiology and Biophysics, Vanderbilt University Medical School
  • Hahn, Lance W
    • Other Affiliation: Program in Human Genetics and Department of Molecular Physiology and Biophysics, Vanderbilt University Medical School
  • Moore, Jason H
    • Other Affiliation: Program in Human Genetics and Department of Molecular Physiology and Biophysics, Vanderbilt University Medical School
Abstract
  • Background Appropriate definition of neural network architecture prior to data analysis is crucial for successful data mining. This can be challenging when the underlying model of the data is unknown. The goal of this study was to determine whether optimizing neural network architecture using genetic programming as a machine learning strategy would improve the ability of neural networks to model and detect nonlinear interactions among genes in studies of common human diseases. Results Using simulated data, we show that a genetic programming optimized neural network approach is able to model gene-gene interactions as well as a traditional back propagation neural network. Furthermore, the genetic programming optimized neural network is better than the traditional back propagation neural network approach in terms of predictive ability and power to detect gene-gene interactions when non-functional polymorphisms are present. Conclusion This study suggests that a machine learning strategy for optimizing neural network architecture may be preferable to traditional trial-and-error approaches for the identification and characterization of gene-gene interactions in common, complex human diseases.
Date of publication
DOI
Identifier
Resource type
  • Article
Rights statement
  • In Copyright
Rights holder
  • Marylyn D Ritchie et al.; licensee BioMed Central Ltd.
Journal title
  • BMC Bioinformatics
Journal volume
  • 4
Journal issue
  • 1
Page start
  • 28
Language
  • English
Is the article or chapter peer-reviewed?
  • Yes
ISSN
  • 1471-2105
Bibliographic citation
  • BMC Bioinformatics. 2003 Jul 07;4(1):28
Publisher
  • BioMed Central Ltd
Access right
  • Open Access
Date uploaded
  • September 5, 2012

Relations

Parents:

This work has no parents.

Items

Thumbnail Title Date Uploaded Visibility Actions
file details 1471-2105-4-28.pdf 2019-05-06 Public Download
file details 1471-2105-4-28.xml 2019-05-06 Public Download