Graves' disease,the production of thyroid-stimulating hormone receptor-stimulating antibodies leading to hyperthyroidism,is one of the most common forms of human autoimmune disease.It is widely agreed that complex diseases are not controlled simply by an individual gene or DNA variation but by their combination.Single nucleotide polymorphisms(SNPs),which are the most common form of DNA variation,have great potential as a medical diagnostic tool.In this paper,the P-value is used as a SNP pre-selection criterion,and a wrapper algorithm with binary particle swarm optimization is used to find the rule for discriminating between affected and control subjects.We analyzed the association between combinations of SNPs and Graves' disease by investigating 108 SNPs in 384 cases and 652 controls.We evaluated our method by differentiating between cases and controls in a five-fold cross validation test,and it achieved a 72.9% prediction accuracy with a combination of 17 SNPs.The experimental results showed that SNPs,even those with a high P-value,have a greater effect on Graves' disease when acting in a combination.
The risks of developing complex diseases are likely to be determined by single nucleotide polymorphisms (SNPs), which are the most common form of DNA variations. Rapidly developing genotyping technologies have made it possible to assess the influence of SNPs on a particular disease. The aim of this paper is to identify the risk/protective factors of a disease, which are modeled as a subset of SNPs (with specified alleles) with the maximum odds ratio. On the basis of risk/protective factor and the relationship between nucleotides and amino acids, two novel risk/protective factors (called k-relaxed risk/protective factors and weighted-relaxed risk/protective factors) are proposed to consider more complex disease-associated SNPs. However, the enormous amount of possible SNPs interactions presents a mathematical and computational challenge. In this paper, we use the Bayesian Optimization Algorithm (BOA) to search for the risk/protective factors of a particular disease. Determining the Bayesian network (BN) structure is NP-hard; therefore, the binary particle swarm optimization was used to determine the BN structure. The proposed algorithm was tested on four datasets. Experimental results showed that the algorithm proposed in this paper is a promising method for discovering SNPs interactions that cause/prevent diseases.