|
BioData Mining 2010
Grammatical evolution decision trees for detecting gene-gene interactionsAbstract: Decision trees are a highly successful, easily interpretable data-mining method that are typically optimized with a hierarchical model building approach, which limits their potential to identify interacting effects. To overcome this limitation, we utilize evolutionary computation, specifically grammatical evolution, to build decision trees to detect and model gene-gene interactions. In the current study, we introduce the Grammatical Evolution Decision Trees (GEDT) method and software and evaluate this approach on simulated data representing gene-gene interaction models of a range of effect sizes. We compare the performance of the method to a traditional decision tree algorithm and a random search approach and demonstrate the improved performance of the method to detect purely epistatic interactions.The results of our simulations demonstrate that GEDT has high power to detect even very moderate genetic risk models. GEDT has high power to detect interactions with and without main effects.GEDT, while still in its initial stages of development, is a promising new approach for identifying gene-gene interactions in genetic association studies.In the last decade, the field of human genetics has experienced an unprecedented burst in technological advancement, allowing for exciting opportunities to unravel the genetic etiology of common, complex diseases [1]. As genotyping has become more reliable and cost-effective, genome-wide association studies (GWAS) have become more commonplace tools for gene mapping, allowing hundreds of thousands or millions of genetic variants to be tested for association with disease outcomes [1]. Typically, traditional statistical approaches (i.e. χ2 tests of association, regression analysis, etc.) are used to test for univariate associations, and then those associations are evaluated for replication and validation in independent patient cohorts [2]. This traditional approach has been very successful in identifying strong single gene effects in ma
|