A computationally fast measure of epistasis for 2 SNPs and a categorical phenotype.

Complex diseases may be caused by interactions or combined effects between multiple genetic and environmental factors. One of the main limitations of testing for interaction between genetic loci in large whole genome studies is the high computational cost of performing such analyses. In this study a new methodology for interaction testing (commonly referred to in genetics as the epistatic effect) between two single nucleotide polymorphisms (SNPs) and a categorical phenotype is presented. It is shown that it provides reasonable approximations with a significantly shorter run time. The proposed measure based on the Pearson's chi-square additive property is compared to fitting a logistic regression model on a randomly selected subset of 218 SNP loci from a study that included 550,000 SNPs). For each possible pair of SNPs a chi-square test for the epistatic effect on case-control status is estimated by fitting a logistic regression model, and compared to the results of the proposed method. Results indicate strong agreement (Pearson's correlation r>0.95) while the proposed method is found to be 20 times faster. This provides a significant pragmatic advantage for the proposed method since the number of tests for epistasis can now be increased by a factor of 20 while the computational cost remains the same.

Classification capacity of a modular neural network implementing neurally inspired architecture and training rules.

A three-layer neural network (NN) with novel adaptive architecture has been developed. The hidden layer of the network consists of slabs of single neuron models, where neurons within a slab--but not between slabs--have the same type of activation function. The network activation functions in all three layers have adaptable parameters. The network was trained using a biologically inspired, guided-annealing learning rule on a variety of medical data. Good training/testing classification performance was obtained on all data sets tested. The performance achieved was comparable to that of SVM classifiers. It was shown that the adaptive network architecture, inspired from the modular organization often encountered in the mammalian cerebral cortex, can benefit classification performance.