Paul Haake

Abstract:
The genetic causes of many monogenic diseases have already been discovered. However, most common diseases are actually the result of complex nonlinear interactions between multiple genetic and environmental components. There is thus a pressing need for new computational methods capable of detecting nonlinearly interacting single nucleotide polymorphism (SNPs) that are associated with disease, from amidst up to hundreds of thousands of candidate SNPs. Recently, some progress has been made using feature selection algorithms based on weights from the ReliefF data mining algorithm on sets of up to 1500 SNPs. However, the accuracy of ReliefF does not scale up to the sizes needed for truly large genome-scale SNP association studies. We propose a population-based variant dubbed VLSReliefF, which mitigates this performance drop by stochastically applying ReliefF to SNP subsets, and then assigning each SNP the maximum ReliefF weight it achieved in any subset. A heuristic method is proposed for determining the optimal subset size as a function of heritability, sample size, and order of interactions. The method is validated using a variety of computational experiments on synthetic datasets of up to 100,000 SNPs.

Abstract:
A hybrid evolutionary approach is proposed for the combined problem of feature selection (using a genetic algorithm with Intersection/Union recombination and a fitness function based on a counter-propagation artificial neural network) and subsequent classifier construction (using strongly-typed genetic programming), for use in nonlinear association studies with relatively large potential feature sets and noisy class data. The method was tested using synthetic data with various degrees of injected noise, based on a proposed mental health database.allResults show the algorithm has good potential for feature selection, classification and function characterization.