Bioinformatics Advance Access originally published online on July 16, 2009
Bioinformatics 2009 25(19):2478-2485; doi:10.1093/bioinformatics/btp435
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
An algorithm for learning maximum entropy probability models of disease risk that efficiently searches and sparingly encodes multilocus genomic interactions
1Department of Electrical Engineering, The Pennsylvania State University, 2Department of Electrical and Computer Engineering, The Virginia Polytechnic Institute and State University, 3Department of Internal Medicine, 4Division of Public Health Sciences, Department of Biostatistical Sciences and 5Division of Public Health Sciences, Department of Epidemiology and Prevention, Wake Forest University
*To whom correspondence should be addressed.
 |
Abstract |
|---|
Motivation: In both genome-wide association studies (GWAS) and pathway analysis, the modest sample size relative to the number of genetic markers presents formidable computational, statistical and methodological challenges for accurately identifying markers/interactions and for building phenotype-predictive models.
Results: We address these objectives via maximum entropy conditional probability modeling (MECPM), coupled with a novel model structure search. Unlike neural networks and support vector machines (SVMs), MECPM makes explicit and is determined by the interactions that confer phenotype-predictive power. Our method identifies both a marker subset and the multiple k-way interactions between these markers. Additional key aspects are: (i) evaluation of a select subset of up to five-way interactions while retaining relatively low complexity; (ii) flexible single nucleotide polymorphism (SNP) coding (dominant, recessive) within each interaction; (iii) no mathematical interaction form assumed; (iv) model structure and order selection based on the Bayesian Information Criterion, which fairly compares interactions at different orders and automatically sets the experiment-wide significance level; (v) MECPM directly yields a phenotype-predictive model. MECPM was compared with a panel of methods on datasets with up to 1000 SNPs and up to eight embedded penetrance function (i.e. ground-truth) interactions, including a five-way, involving less than 20 SNPs. MECPM achieved improved sensitivity and specificity for detecting both ground-truth markers and interactions, compared with previous methods.
Availability: http://www.cbil.ece.vt.edu/ResearchOngoingSNP.htm
Contact: djmiller{at}engr.psu.edu
Supplementary information:Supplementary data are available at Bioinformatics online.
Associate Editor: Alfonso Valencia
Received on April 3, 2009; revised on June 24, 2009; accepted on July 13, 2009
CiteULike 
Connotea 
Del.icio.us What's this?