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

Ritchie MD, White BC, Parker JS, Hahn LW, Moore JH - BMC Bioinformatics (2003)

Bottom Line: Appropriate definition of neural network architecture prior to data analysis is crucial for successful data mining.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.

View Article: PubMed Central - HTML - PubMed

Affiliation: Program in Human Genetics and Department of Molecular Physiology and Biophysics, Vanderbilt University Medical School, Nashville, TN, 37232-0700, USA. ritchie@phg.mc.vanderbilt.edu

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.

Show MeSH
GPNN representation of a NN. This figure is an exampleof one NN optimized by GPNN. The O is the output node, S indicatesthe activation function, W indicates a weight, and X1-X4 arethe NN inputs.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC183838&req=5

Figure 3: GPNN representation of a NN. This figure is an exampleof one NN optimized by GPNN. The O is the output node, S indicatesthe activation function, W indicates a weight, and X1-X4 arethe NN inputs.

Mentions: The use of binary expression trees allow for the flexibility ofthe GP to evolve a tree-like structure that adheres to the componentsof a NN. Figure 3 shows an exampleof a binary expression tree representation of a NN generated byGPNN. Figure 4 shows the sameNN that has been reduced from the binary expression tree form tolook more like a common feed-forward NN. The GP is constrained insuch a way that it uses standard GP operators but retains the typicalstructure of a feed-forward NN. A set of rules is defined priorto network evolution to ensure that the GP tree maintains a structurethat represents a NN. The rules used for this GPNN implementationare consistent with those described by Koza and Rice [14]. The flexibility of the GPNN allowsoptimal network architectures to be generated that contain the appropriate inputs,connections, and weights for a given data set.


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

Ritchie MD, White BC, Parker JS, Hahn LW, Moore JH - BMC Bioinformatics (2003)

GPNN representation of a NN. This figure is an exampleof one NN optimized by GPNN. The O is the output node, S indicatesthe activation function, W indicates a weight, and X1-X4 arethe NN inputs.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC183838&req=5

Figure 3: GPNN representation of a NN. This figure is an exampleof one NN optimized by GPNN. The O is the output node, S indicatesthe activation function, W indicates a weight, and X1-X4 arethe NN inputs.
Mentions: The use of binary expression trees allow for the flexibility ofthe GP to evolve a tree-like structure that adheres to the componentsof a NN. Figure 3 shows an exampleof a binary expression tree representation of a NN generated byGPNN. Figure 4 shows the sameNN that has been reduced from the binary expression tree form tolook more like a common feed-forward NN. The GP is constrained insuch a way that it uses standard GP operators but retains the typicalstructure of a feed-forward NN. A set of rules is defined priorto network evolution to ensure that the GP tree maintains a structurethat represents a NN. The rules used for this GPNN implementationare consistent with those described by Koza and Rice [14]. The flexibility of the GPNN allowsoptimal network architectures to be generated that contain the appropriate inputs,connections, and weights for a given data set.

Bottom Line: Appropriate definition of neural network architecture prior to data analysis is crucial for successful data mining.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.

View Article: PubMed Central - HTML - PubMed

Affiliation: Program in Human Genetics and Department of Molecular Physiology and Biophysics, Vanderbilt University Medical School, Nashville, TN, 37232-0700, USA. ritchie@phg.mc.vanderbilt.edu

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.

Show MeSH