Abstract
BackgroundAppropriate 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.ResultsUsing 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.ConclusionThis 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.
Highlights
Appropriate definition of neural network architecture prior to data analysis is crucial for successful data mining
The ability to detect and model gene-gene interactions was investigated for both the back propagation NN (BPNN) and Genetic Programming Neural Network (GPNN)
The results of this study demonstrate that Genetic programming (GP) is an excellent way of automating Neural networks (NN) architecture design
Summary
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. The detection and characterization of genes associated with common, complex diseases is a difficult challenge in human genetics. That is, when interactions among genes are considered, the data becomes too sparse to estimate the genetic effects To deal with this issue, one can collect a very large sample size. The alternative is to develop new statistical methods that have improved power to identify gene-gene interactions in relatively small sample sizes
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
