VARIABLE SELECTION METHOD FOR THE IDENTIFICATION OF EPISTATIC MODELS
Open Access
- 10 November 2014
- conference paper
- Published by World Scientific Pub Co Pte Ltd
- Vol. 20, 195-206
Abstract
Standard analysis methods for genome wide association studies (GWAS) are not robust to complex disease models, such as interactions between variables with small main effects. These types of effects likely contribute to the heritability of complex human traits. Machine learning methods that are capable of identifying interactions, such as Random Forests (RF), are an alternative analysis approach. One caveat to RF is that there is no standardized method of selecting variables so that false positives are reduced while retaining adequate power. To this end, we have developed a novel variable selection method called relative recurrency variable importance metric (r2VIM). This method incorporates recurrency and variance estimation to assist in optimal threshold selection. For this study, we specifically address how this method performs in data with almost completely epistatic effects (i.e. no marginal effects). Our results show that with appropriate parameter settings, r2VIM can identify interaction effects when the marginal effects are virtually nonexistent. It also outperforms logistic regression, which has essentially no power under this type of model when the number of potential features (genetic variants) is large. (All Supplementary Data can be found here: http://research.nhgri.nih.gov/manuscripts/Bailey-Wilson/r2VIM_epi/).Keywords
This publication has 11 references indexed in Scilit:
- Risk estimation using probability machinesBioData Mining, 2014
- The NHGRI GWAS Catalog, a curated resource of SNP-trait associationsNucleic Acids Research, 2013
- Personalizing health care: feasibility and future implicationsBMC Medicine, 2013
- ATHENA: A TOOL FOR META-DIMENSIONAL ANALYSIS APPLIED TO GENOTYPES AND GENE EXPRESSION DATA TO PREDICT HDL CHOLESTEROL LEVELS2012
- Epistasis dominates the genetic architecture of Drosophila quantitative traitsProceedings of the National Academy of Sciences, 2012
- The behaviour of random forest permutation-based variable importance measures under predictor correlationBMC Bioinformatics, 2010
- An introduction to recursive partitioning: Rationale, application, and characteristics of classification and regression trees, bagging, and random forests.Psychological Methods, 2009
- Finding the missing heritability of complex diseasesNature, 2009
- DATA SIMULATION SOFTWARE FOR WHOLE-GENOME ASSOCIATION AND OTHER STUDIES IN HUMAN GENETICS2005
- Role of evolutionary history on haplotype block structure in the human genome: implications for disease mappingCurrent Opinion in Genetics & Development, 2003