Evaluation of a Bayesian model-based approach in GA studies
Proceedings of the third International Workshop on Machine Learning in Systems Biology, PMLR 8:30-43, 2009.
In a typical Genetic Association Study (GAS) several hundreds to millions of genomic variables are measured and tested for association with a given set of a phenotypic variables (e.g., a given disease state or a complete expression profile), with the aim of identifying the genetic background of complex, multifactorial diseases. These highly varying requirements resulted in a number of different statistical tools applying different approaches either bayesian or non-bayesian, model-based or conditional. In this paper we evaluate dedicated GAS tools and general purpose feature subset selection (FSS) tools including a Bayesian model-based tool BMLA in a GAS context. In the evaluation we used an artificial data set generated from a reference model with 113 genotypic variables that was based on a real-world genotype data.