Analysis of disease association and susceptibility for SNP data using emotional neural networks

The risk of some complex diseases are likely related to single nucleotide polymorphisms (SNPs), which are the most common form of DNA variations. Rapidly developing bioinformatics have made it possible to recognize a group of SNPs as the risk/protective factors of a specific disease, which are related to the possibility of the sample be infected. However, a particular algorithm to consider this kind of tendency information together is still in need. In this paper, inspired form the process that human beings to make a decision, we regard the risk/protect factor in the gene variations as the emotional of our nervous system. In this way, we regard these SNP combination factor as prior knowledge and use the emotional neural networks (ENN) to analysis the disease susceptibility. By sending this kind of information to ENN and using particle swarm optimization with hierarchical structure (PSO_HS) to train the parameters, we get a better result of susceptibility classification. The experimental results about real dataset shows that consider the risk/protect factor by emotional neural networks improve the performance of disease susceptibility analysis.