- author = "Alison A Motsinger and Stephen L Lee and George Mellick and Marylyn D Ritchie",
- title = "{GPNN}: Power studies and applications of a neural network method for detecting gene-gene interactions in studies of human disease",
- journal = "BMC bioinformatics [electronic resource]",
- publisher = "BioMed Central Ltd.",
- year = "2006",
- volume = "7",
- number = "1",
- pages = "39--39",
- month = jan # "~25",
- keywords = "genetic algorithms, genetic programming",
- ISSN = "1471-2105",
- bibsource = "OAI-PMH server at www.biomedcentral.com",
- language = "en",
- oai = "oai:biomedcentral.com:1471-2105-7-39",
- rights = "Copyright 2006 Motsinger et al; licensee BioMed Central Ltd.",
-
URL = "
http://www.biomedcentral.com/1471-2105/7/39",
-
URL = "
http://www.biomedcentral.com/content/pdf/1471-2105-7-39.pdf",
-
DOI = "
doi:10.1186/1471-2105-7-39",
- size = "10 pages",
-
abstract = "Background
The identification and characterisation of genes that influence the risk of common, complex multifactorial disease primarily through interactions with other genes and environmental factors remains a statistical and computational challenge in genetic epidemiology. We have previously introduced a genetic programming optimised neural network (GPNN) as a method for optimising the architecture of a neural network to improve the identification of gene combinations associated with disease risk. The goal of this study was to evaluate the power of GPNN for identifying high-order gene-gene interactions. We were also interested in applying GPNN to a real data analysis in Parkinson's disease.
Results
We show that GPNN has high power to detect even relatively small genetic effects (2-3per cent heritability) in simulated data models involving two and three locus interactions. The limits of detection were reached under conditions with very small heritability (<1per cent) or when interactions involved more than three loci. We tested GPNN on a real dataset comprised of Parkinson's disease cases and controls and found a two locus interaction between the DLST gene and sex.
Conclusion
These results indicate that GPNN may be a useful pattern recognition approach for detecting gene-gene and gene-environment interactions.",
