Application of two machine learning algorithms to genetic association studies in the presence of covariates

Nonyane, BA; Foulkes, AS; (2008) Application of two machine learning algorithms to genetic association studies in the presence of covariates. BMC Genet, 9. p. 71. ISSN 1471-2156 DOI:

Text - Published Version

Download (290kB) | Preview


BACKGROUND: Population-based investigations aimed at uncovering genotype-trait associations often involve high-dimensional genetic polymorphism data as well as information on multiple environmental and clinical parameters. Machine learning (ML) algorithms offer a straightforward analytic approach for selecting subsets of these inputs that are most predictive of a pre-defined trait. The performance of these algorithms, however, in the presence of covariates is not well characterized. METHODS AND RESULTS: In this manuscript, we investigate two approaches: Random Forests (RFs) and Multivariate Adaptive Regression Splines (MARS). Through multiple simulation studies, the performance under several underlying models is evaluated. An application to a cohort of HIV-1 infected individuals receiving anti-retroviral therapies is also provided. CONCLUSION: Consistent with more traditional regression modeling theory, our findings highlight the importance of considering the nature of underlying gene-covariate-trait relationships before applying ML algorithms, particularly when there is potential confounding or effect mediation.

Item Type: Article
Keywords: *Algorithms, *Artificial Intelligence, Cholesterol, HDL/blood, Computational Biology, Computer Simulation, *Genetic Predisposition to Disease, Genotype, HIV Infections/blood/drug therapy/ethnology/genetics, Humans, Lipase/genetics, *Models, Statistical, Polymorphism, Single Nucleotide/genetics, Regression Analysis, Algorithms, Artificial Intelligence, Cholesterol, HDL, blood, Computational Biology, Computer Simulation, Genetic Predisposition to Disease, Genotype, HIV Infections, blood, drug therapy, ethnology, genetics, Humans, Lipase, genetics, Models, Statistical, Polymorphism, Single Nucleotide, genetics, Regression Analysis
Faculty and Department: Faculty of Epidemiology and Population Health > Dept of Non-Communicable Disease Epidemiology
PubMed ID: 19014573
Web of Science ID: 262191500001


Download activity - last 12 months
Downloads since deposit
Accesses by country - last 12 months
Accesses by referrer - last 12 months
Impact and interest
Additional statistics for this record are available via IRStats2

Actions (login required)

Edit Item Edit Item