Unravelling gene interactions to find the cause of artherosclerosis, a multigenic disease, using an artificial neural network

To understand the etiology of multigenic disease like atherosclerosis a polymerase chain reaction based gene array containing 65 single nucleotide polymorphisms (SNP) was analyzed. To assess the possibilities of pattern recognition techniques in detecting unfavorable genetic combinations two approaches were analyzed. A selection of these 65 single nucleotide polymorphisms formed the input to both binary logistic regression models and to self-learning artificial neural networks. Repeated analysis showed that both methods performed equal. Further research to improve the differentiating power of both methods should focus first on decreasing the number of otherwise indeterminable polymorphisms.