Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


case1270577390.pdf (1.24 MB)

ETD Abstract Container

Abstract Header

Detecting Epistasis Effect in Genome-Wide Association Studies Based on Permutation Tests and Ensemble Approaches

Horstman, Benjamin Philip
http://rave.ohiolink.edu/etdc/view?acc_num=case1270577390

Abstract Details

2010, Master of Sciences (Engineering), Case Western Reserve University, EECS - Computer and Information Sciences.
Most complex disease involve multiple genes, their interactions, environmental factors, and gene-environment interactions. Although genome-wide association studies (GWAS) have shown some success for identifying genetic variants underlying complex diseases, most existing studies are based on limited single-locus approaches, which detect SNPs essentially based on their marginal association with the phenotype. In this paper, we propose an ensemble approach based on Boosting to study gene-gene interactions. We extend the basic Adaboost algorithm by incorporating an intuitive importance score based on Gini impurity to select candidate SNPs. Permutation tests are used to control the statistical significance. We perform extensive simulation studies across five models and at realistic GWAS sizes to evaluate the efficacy of our approach and compare it to an existing epistasis algorithm called BEAM. Our results indicate that our approach is valid, efficient for GWAS, and on disease models with epistasis has more power than χ2 genotypic test and BEAM.
Jing Li, PhD (Committee Chair)
Andy Podgurski, PhD (Committee Member)
Robert Elston, PhD (Committee Member)
83 p.
Artificial Intelligence; Genetics
Adaboost; Machine Learning; GWAS; BEAM; SNP; epistasis

Recommended Citations

Citations

  • Horstman, B. P. (2010). Detecting Epistasis Effect in Genome-Wide Association Studies Based on Permutation Tests and Ensemble Approaches [Master's thesis, Case Western Reserve University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=case1270577390

    APA Style (7th edition)

  • Horstman, Benjamin. Detecting Epistasis Effect in Genome-Wide Association Studies Based on Permutation Tests and Ensemble Approaches. 2010. Case Western Reserve University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=case1270577390.

    MLA Style (8th edition)

  • Horstman, Benjamin. "Detecting Epistasis Effect in Genome-Wide Association Studies Based on Permutation Tests and Ensemble Approaches." Master's thesis, Case Western Reserve University, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=case1270577390

    Chicago Manual of Style (17th edition)

case1270577390
1,026
© 2010, all rights reserved.
This open access ETD is published by Case Western Reserve University School of Graduate Studies and OhioLINK.