Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2011 Jan;75(1):122-32.
doi: 10.1111/j.1469-1809.2010.00623.x. Epub 2010 Nov 30.

Importance Measures for Epistatic Interactions in Case-Parent Trios

Affiliations
Free PMC article

Importance Measures for Epistatic Interactions in Case-Parent Trios

Holger Schwender et al. Ann Hum Genet. .
Free PMC article

Abstract

Ensemble methods (such as Bagging and Random Forests) take advantage of unstable base learners (such as decision trees) to improve predictions, and offer measures of variable importance useful for variable selection. LogicFS has been proposed as such an ensemble learner for case-control studies when interactions of single nucleotide polymorphisms (SNPs) are of particular interest. LogicFS uses bootstrap samples of the data and employs the Boolean trees derived in logic regression as base learners to create ensembles of models that allow for the quantification of the contributions of epistatic interactions to the disease risk. In this article, we propose an extension of logicFS suitable for case-parent trio data, and derive an additional importance measure that is much less influenced by linkage disequilibrium between SNPs than the measure originally used in logicFS. We illustrate the performance of the novel procedure in simulation studies and in a case study of 461 case-parent trios with autistic children.

Figures

Figure 1
Figure 1
Scatter plot for the values of VIMTrio and VIMAdj for the interaction term S3DS7D, derived from the applications of trioFS to 10 simulated data sets where disease risk is determined by said interaction. The values for importance measure VIMTrio are always smaller than the corresponding values for VIMAdj, illustrating the benefit of accounting for potentially over-fitted interactions. Since SNPs were not in linkage disequilibrium, the values for the importance measure VIMLD are the same as the ones for VIMTrio, and are omitted from the plot.

Similar articles

See all similar articles

Cited by 4 articles

Publication types

Feedback