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

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.

Figure 1

Binary expression tree example of a GP solution. This figure is an example of a possible computer program generated by GP. While the program can take virtually any form, we are using a binary expression tree representation, thus we have shown this type as an example.

Figure 2

GP crossover. This figure shows a crossover event in GP between two binary expression trees. Here, the left sub-tree of parent 1 is swapped with the left sub-tree of parent 2 to create 2 new trees.

Figure 3

GPNN representation of a NN. This figure is an example of one NN optimized by GPNN. The O is the output node, S indicates the activation function, W indicates a weight, and X₁-X₄ are the NN inputs.

Figure 4

Feed-forward BPNN representation of the GPNN in Figure 3. To generate this NN, each weight in Figure 3 was computed to produce a single value.

Figure 5

Optimal architecture from BPNN trial and error optimization. This figure shows the result of the BPNN trial and error procedure on one data set from each epistasis model. This shows the NN architecture for the best classification error selected from Table 1.