A flexible computational framework for detecting, characterizing, and interpreting statistical patterns of epistasis in genetic studies of human disease susceptibility
Journal
Journal of Theoretical Biology
Journal Volume
241
Journal Issue
2
Pages
252-261
Date Issued
2006
Author(s)
Abstract
Detecting, characterizing, and interpreting gene-gene interactions or epistasis in studies of human disease susceptibility is both a mathematical and a computational challenge. To address this problem, we have previously developed a multifactor dimensionality reduction (MDR) method for collapsing high-dimensional genetic data into a single dimension (i.e. constructive induction) thus permitting interactions to be detected in relatively small sample sizes. In this paper, we describe a comprehensive and flexible framework for detecting and interpreting gene-gene interactions that utilizes advances in information theory for selecting interesting single-nucleotide polymorphisms (SNPs), MDR for constructive induction, machine learning methods for classification, and finally graphical models for interpretation. We illustrate the usefulness of this strategy using artificial datasets simulated from several different two-locus and three-locus epistasis models. We show that the accuracy, sensitivity, specificity, and precision of a na?ve Bayes classifier are significantly improved when SNPs are selected based on their information gain (i.e. class entropy removed) and reduced to a single attribute using MDR. We then apply this strategy to detecting, characterizing, and interpreting epistatic models in a genetic study (n = 5 0 0) of atrial fibrillation and show that both classification and model interpretation are significantly improved. ? 2005 Elsevier Ltd. All rights reserved.
SDGs
Other Subjects
data mining; disease resistance; epistasis; genetic engineering; learning; polymorphism; accuracy; article; Bayes theorem; disease classification; disease predisposition; entropy; epistasis; gene interaction; gene locus; genetic analysis; genetic epistasis; heart atrium fibrillation; human; information processing; information science; mathematical analysis; mathematical computing; priority journal; sensitivity analysis; sensitivity and specificity; single nucleotide polymorphism; statistical analysis; Atrial Fibrillation; Computational Biology; Computer Simulation; Entropy; Epistasis, Genetic; Genetic Predisposition to Disease; Humans; Models, Genetic; Polymorphism, Single Nucleotide
Type
journal article