- author = "Robin Nunkesser and Thorsten Bernholt and Holger Schwender and Katja Ickstadt and Ingo Wegener",
- title = "Detecting high-order interactions of single nucleotide polymorphisms using genetic programming",
- journal = "Bioinformatics",
- year = "2007",
- volume = "23",
- number = "24",
- pages = "3280--3288",
- month = "15 " # dec,
- email = "robin.nunkesser@uni-dortmund.de",
- keywords = "genetic algorithms, genetic programming, SNP",
- ISSN = "1460-2059",
- language = "en",
- oai = "oai:CiteSeerX.psu:10.1.1.618.7444",
-
URL = "
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.618.7444",
-
URL = "
http://bioinformatics.oxfordjournals.org/content/23/24/3280.full.pdf",
-
DOI = "
doi:10.1093/bioinformatics/btm522",
- size = "9 pages",
-
abstract = "Motivation: Not individual single nucleotide
polymorphisms (SNPs), but high-order interactions of
SNPs are assumed to be responsible for complex diseases
such as cancer. Therefore, one of the major goals of
genetic association studies concerned with such
genotype data is the identification of these high-order
interactions. This search is additionally impeded by
the fact that these interactions often are only
explanatory for a relatively small subgroup of
patients. Most of the feature selection methods
proposed in the literature, unfortunately, fail at this
task, since they can either only identify individual
variables or interactions of a low order, or try to
find rules that are explanatory for a high percentage
of the observations. In this article, we present a
procedure based on genetic programming and multi-valued
logic that enables the identification of high-order
interactions of categorical variables such as SNPs.
This method called GPAS cannot only be used for feature
selection, but can also be employed for
discrimination.
Results: In an application to the genotype data from the GENICA study, an association study concerned with sporadic breast cancer, GPAS is able to identify high-order interactions of SNPs leading to a considerably increased breast cancer risk for different subsets of patients that are not found by other feature selection methods. As an application to a subset of the HapMap data shows, GPAS is not restricted to association studies comprising several 10 SNPs, but can also be employed to analyse whole-genome data.",
-
notes = "Software can be downloaded from
http://ls2-www.cs.uni-dortmund.de/~nunkesser/#Software
Preliminary Version: Technical Report 24/2007, SFB 475, Universitat Dortmund, Germany. http://hdl.handle.net/2003/25875 http://dx.doi.org/10.17877/DE290R-14226
Disjunctive Normal Form (bit set fast implementation). Variable population size (those which are not dominated) Pareto (3 objectives: size TP, TN). No fitness sharing? Non-standard selection. crossover. 5 DNF specific mutations.
GPAS better than Logic regression, CART, Bagging, Random Forests on GENICA HapMap and (Random) Simulated data.",
