Complex diseases cannot generally be explained by Mendelian inheritance because they are influenced by gene-gene and gene-environment interactions. Many common diseases such as asthma, cancer, diabetes, hypertension and obesity are widely accepted and acknowledged to be results of complex interactions between multiple genetic factors. Attempts to identify factors that could be the causes of complex diseases have led to many genome-wide association studies.

From a machine learning viewpoint, the identification of genetic markers that are associated with complex diseases in genome-wide association studies can be treated as an attribute selection problem. The aim of attribute selection is to identify informative attributes necessary for the correct classification of case-control samples. Examples of machine-learning techniques for this bioinformatics application can be found at http://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-10-294 and http://springerplus.springeropen.com/articles/10.1186/2193-1801-2-230.

Linkage Disequilibrium in GWAS

Ref: springerplus.springeropen.com/articles/10.1186/2193-1801-2-230