臺灣博碩士論文加值系統

基因上位(epistasis)的交互作用是一個重要的分析工具，以應對複雜的疾病。藉由病例對照研究(case-control study)使用單一核苷酸多型性 (single nucleotide polymorphism, SNP)資料集可以幫助了解基因上位的交互作用。然而，從高維度的單一核苷酸多型性資料集(high-dimensional SNP data)中，辨識基因上位的交互作用仍然是一項挑戰以及重要的議題。目前存在的病例對照研究方法雖然能辨識基因上位的交互作用，但是這些方法仍然受限於樣本數的大小、演算法的效能以及評估測量工具的選擇。本論文提出一個基因上位交互作用辨識方法，方法利用分類技巧(classification)植基於多重維度降低技巧(multifactor-dimensionality reduction, MDR)，取名為CMDR，可以從樣本數較小的資料中辨識與疾病有關連的基因上位性交互作用。CMDR利用分類技巧將交差驗證(cross-validation, CV)的每一個子資料集之case與control樣本調整至平衡，並且使用多重維度降低技巧訓練(training)一個常模(model)以辨識有統計意義(significant)的基因上位交互作用。此外，本論文利用差分演算法(differential evolution, DE)以提升CMDR之執行效能，取名為DECMDR，幫助CMDR能從全基因組資料集(genome-wide data)中辨識高階層的基因上位交互作用。最後本論文提出一個多目標方法(multi-objective approach)植基於差分演算法，取名為MODECMDR，能同時使用多種評估測量工具從不同的統計觀點辨識出更有意義的基因上位交互作用。本論文使用多個被設計的基因上位性模組，包含主要影響(Marginal effect)與無主要影響(Without marginal effect)，並且利用多種不同的參數設定，包含遺傳率(Heritability)與最小等位基因频率(minor allele frequencies)，產生多個維度高的模擬資料集(simulation data)。在模擬資料集測試中，結果顯示CMDR、DECMDR以及MODECMDR皆比其他已存在的方法，例如MDR、BEAM以及SNPRuler，更有效的辨識出基因上位交互作用，尤其在樣本數較低的實驗中更為有效。最後，本論文使用一個大型真實資料集Wellcome Trust Case Control Consortium (WTCCC)測試CMDR、DECMDR以及MODECMDR是否能辨識有意義的基因上位交互作用。實驗結果顯示CMDR、DECMDR以及MODECMDR能有效的辨識出有意義的基因上位交互作用。在執行效能方面，DECMDR與MODECMDR成功的降低CMDR的執行時間，指示DECMDR與MODECMDR能有效的被使用於全基因組資料集。在評估測量工具方面，MODECMDR成功將CMDR從單一目標轉換至多目標辨識，所有測試結果皆顯示MODECMDR能較CMDR與DECMDR辨識出更多有意義的基因上位交互作用。

Epistasis interaction is an important analysis tool to tackling complex disease. In case-control studies, detecting epistatic interactions in single nucleotide polymorphism (SNP) data is a challenging and important issue, particularly in terms of high-order SNP–SNP interactions in high-dimensional data. Although existing case-control study approaches can successfully detect epistatic interactions in case-control studies, they are limited by processing smaller samples, the amount of time required for highly time-consuming processing and the evaluation function selections. This dissertation proposes an epistatic interaction detection method which uses a classification technique based on the Multifactor-Dimensionality Reduction technique (CMDR) to find disease-associated epistatic interactions in data sets with small sample sizes. CMDR uses a classification technique to adjust the unbalanced distribution between cases and controls and uses fundamental principles of MDR to train a model to detect significant epistatic interactions. Furthermore, a differential evolution is combined with CMDR (DECMDR) to handle high-order SNP–SNP interactions in large genome-wide data sets. Finally, the multi-objective approach based on DECMDR (MODECMDR) is proposed to detect the more significant epistatic interactions by considering multiple evaluation measures. Several epistatic models both with and without marginal effects under different parameter settings (heritability h2 and minor allele frequencies MAF) are used to generate high-dimensional simulation data sets with small samples. Comparison of results for simulation data show that CMDR, DECMDR and MODECMDR are significantly more powerful than existing methods such as MDR, BEAM and SNPRuler, especially for small sample sizes. A large real data set was obtained from the Wellcome Trust Case Control Consortium (WTCCC) and used to test whether CMDR, DECMDR and MODECMDR can detect the significant epistatic interactions. Results indicate the three methods can effectively detect significant epistatic interactions. In terms of running time, DECMDR and MODECMDR successfully reduce the CMDR running time, indicating that DECMDR and MODECMDR can effectively handle genome-wide data sets. For evaluation measure selection, MODECMDR is successfully integrated with multi-objective detection in DECMDR. All testing results indicate that MODECMDR is better than CMDR or DECMDR in detecting more significant epistatic interactions.

ABSTRACT IN CHINESE.............................................................................................i
ABSTRACT........................................................................................................iii
ACKNOWLEDGEMENT.................................................................................................v
TABLE OF CONTENT................................................................................................vi
List of Figures.................................................................................................viii
List of Tables..................................................................................................x
Abbreviations...................................................................................................xi
Chapter 1. Introduction.........................................................................................1
1.1 Background and Literature Review............................................................................1
1.2 Problem Definition and Motivation...........................................................................6
1.2.1 Problem Definition........................................................................................6
1.2.2 Purpose and Specific Aims.................................................................................9
1.2.3 Research Hypothesis.......................................................................................10
1.2.4 Significance..............................................................................................11
1.2.5 Organization of Dissertation..............................................................................12
Chapter 2. Materials and Methods................................................................................13
2.1 Classification and Multifactor-Dimensionality Reduction (CMDR)..............................................13
2.1.1 Multifactor-Dimensionality Reduction (MDR)................................................................13
2.1.2 Classification Adjustment.................................................................................15
2.1.3 Design of Classification and Multifactor-Dimensionality Reduction.........................................16
2.2.1 Differential Evolution Algorithm..........................................................................21
2.2.2 Design of Differential Evolution Algorithm Based on CMDR..................................................23
2.3 Multi-objective DECMDR (MODECMDR)...........................................................................31
2.3.1 Multi-objective Optimization..............................................................................31
2.3.2 Design of Multi-objective DECMDR..........................................................................32
2.4 Parameter settings..........................................................................................44
Chapter 3. Experimental Results.................................................................................45
3.1 Experiments on Simulation Data..............................................................................45
3.1.1 Comparison of CMDR, DECMDR and MODECMDR with Existing Methods on Disease Loci with Marginal Effects.......45
3.1.2 Comparison of CMDR, DECMDR and MODECMDR with Existing Methods on Disease Loci without Marginal Effects....48
3.2 Experiments on Real Data....................................................................................61
3.2.1 Results on WTCCC Data.....................................................................................61
3.2.2 Comparison of CMDR, DECMDR and MODECMDR on CAD data with WTCCC............................................65
Chapter 4. Discussion...........................................................................................106
4.1 Relationship between Our Proposed Methods and Existing Methods..............................................106
4.2 The Effect of Difference between Cases and Controls in Each CV-subset.......................................108
4.3 The Effects of TP, FP, FN and TN Values in Small Data Sets..................................................110
4.4 Models Selected by Minimum Prediction Error Rate versus Model Selected by Cross-Validation Consistency......112
4.5 Comparison of CMDR, DECMDR and MODECMDR with Existing Methods on Computation Time...........................116
4.6 Comparison of CMDR, DECMDR and MODECMDR on Performance of Evaluation Measures...............................118
4.7 Advantages of CMDR, DECMDR and MODECMDR.....................................................................119
4.8 The Limitations of CMDR, DECMDR and MODECMDR................................................................122
Chapter 5. Conclusions and Future Work..........................................................................124
5.1 Conclusions.................................................................................................124
5.2 Future Works................................................................................................125
References......................................................................................................129
Appendix A: Example of CMDR procedures..........................................................................137
Appendix B: Example of DECMDR procedures........................................................................146
Appendix C: Example of MODECMDR procedures......................................................................158
Appendix D: List of Publications................................................................................174

[1]A. D Roses, A. M. Saunders, Y. Huang, J. Strum, K. H. Weisgraber, and R. W. Mahley, "Complex disease-associated pharmacogenetics: drug efficacy, drug safety, and confirmation of a pathogenetic hypothesis (Alzheimer's disease)," Pharmacogenomics Journal, vol. 7, pp. 10-28, Feb 2007.
[2]J. Li, K. Humphreys, H. Darabi, G. Rosin, U. Hannelius, T. Heikkinen, et al., "A genome-wide association scan on estrogen receptor-negative breast cancer," Breast Cancer Res, vol. 12, pp. R93, Nov 2010.
[3]J. Shan, W. Mahfoudh, S. P. Dsouza, E. Hassen, N. Bouaouina, S. Abdelhak, et al., "Genome-Wide Association Studies (GWAS) breast cancer susceptibility loci in Arabs: susceptibility and prognostic implications in Tunisians," Breast Cancer Res Treat, vol. 135, pp. 715-24, Oct 2012.
[4]N. Orr, A. Lemnrau, R. Cooke, O. Fletcher, K. Tomczyk, M. Jones, et al., "Genome-wide association study identifies a common variant in RAD51B associated with male breast cancer risk," Nat Genet, vol. 44, pp. 1182-4, Nov 2012.
[5]R. Hein, M. Maranian, J. L. Hopper, M. K. Kapuscinski, M. C. Southey, D. J. Park, et al., "Comparison of 6q25 breast cancer hits from Asian and European Genome Wide Association Studies in the Breast Cancer Association Consortium (BCAC)," PLoS ONE, vol. 7, pp. e42380, Aug 2012.
[6]F. Chen, G. K. Chen, D. O. Stram, R. C. Millikan, C. B. Ambrosone, E. M. John, et al., "A genome-wide association study of breast cancer in women of African ancestry," Hum Genet, vol. 132, pp. 39-48, Jan 2013.
[7]H. J. Cordell, "Detecting gene-gene interactions that underlie human diseases," Nature Reviews Genetics, vol. 10, pp. 392-404, Jun 2009.
[8]H. Y. Lane, G. E. Tsai, and E. Lin, "Assessing gene-gene interactions in pharmacogenomics," Mol Diagn Ther, vol. 16, pp. 15-27, Feb 2012.
[9]K. V. Steen, "Travelling the world of gene-gene interactions," Brief Bioinform, vol. 13, pp. 1-19, Jan 2012.
[10]C. C. M. Chen, H. Schwender, J. Keith, R. Nunkesser, K. Mengersen, and P. Macrossan, "Methods for identifying SNP interactions: A review on variations of Logic Regression, Random Forest and Bayesian logistic regression," IEEE-ACM Transactions on Computational Biology and Bioinformatics, vol. 8, pp. 1580-91, Nov-Dec 2011.
[11]H. Schwender and K. Ickstadt, "Identification of SNP interactions using logic regression," Biostatistics, vol. 9, pp. 187-198, Jan 2008.
[12]L. E. Mechanic, B. T. Luke, J. E. Goodman, S. J. Chanock, and C. C. Harris, "Polymorphism Interaction Analysis(PIA): A method for investigating complex gene-gene interactions," BMC Bioinformatics, vol. 9, pp. 146, Mar 2008.
[13]L. Y. Chuang, Y. D. Lin, H. W. Chang, and C. H. Yang, "An improved PSO algorithm for generating protective SNP barcodes in breast cancer," PLoS ONE, vol. 7, May 2012.
[14]C. H. Yang, L. Y. Chuang, Y. H. Cheng, Y. D. Lin, C. L. Wang, C. H. Wen, et al., "Single nucleotide polymorphism barcoding to evaluate oral cancer risk using odds ratio-based genetic algorithms," Kaohsiung Journal of Medical Sciences, vol. 28, pp. 362-368, Jul 2012.
[15]C. H. Yang, Y. D. Lin, L. Y. Chuang, and H. W. Chang, "Evaluation of breast cancer susceptibility using improved genetic algorithms to generate genotype SNP barcodes," IEEE-ACM Transactions on Computational Biology and Bioinformatics, vol. 10, pp. 361-371, Mar-Apr 2013.
[16]M. T. Hagan, H. B. Demuth, and M. H. Beale, Neural network design: Pws Pub. Boston, 1996.
[17]N. Matchenko-Shimko and M.-P. Dube, "Gene-gene interaction tests using SVM and neural network modeling," in IEEE Symposium on Computational Intelligence and Bioinformatics and Computational Biology (CIBCB'07), pp. 90-97, Apr 2007.
[18]L. Breiman, "Random forests," Machine learning, vol. 45, pp. 5-32, Oct 2001.
[19]K. L. Lunetta, L. B. Hayward, J. Segal, and P. Van Eerdewegh, "Screening large-scale association study data: exploiting interactions using random forests," BMC Genetics, vol. 5, pp. 32, Dec 2004.
[20]G. J. Upton, "Fisher's exact test," Journal of the Royal Statistical Society. Series A (Statistics in Society), vol. 155, pp. 395-402, Feb 1992.
[21]J. H. Moore, "A global view of epistasis," Nature Genetics, vol. 37, pp. 13-14, Jan 2005.
[22]C. L. Koo, M. J. Liew, M. S. Mohamad, and A. H. M. Salleh, "A review for detecting gene-gene interactions using machine learning methods in genetic epidemiology," Biomed Research International, vol. 2013, pp. 432375, Oct 2013.
[23]W. Bateson and G. Mendel, Mendel's principles of heredity: Courier Dover Publications, 2013.
[24]M. D. Ritchie, L. W. Hahn, N. Roodi, L. R. Bailey, W. D. Dupont, F. F. Parl, et al., "Multifactor-dimensionality reduction reveals high-order interactions among estrogen-metabolism genes in sporadic breast cancer," American Journal of Human Genetics, vol. 69, pp. 138-147, Jul 2001.
[25]Y. Zhang and J. S. Liu, "Bayesian inference of epistatic interactions in case-control studies," Nature Genetics, vol. 39, pp. 1167-1173, Sep 2007.
[26]X. Wan, C. Yang, Q. Yang, H. Xue, N. L. S. Tang, and W. C. Yu, "Predictive rule inference for epistatic interaction detection in genome-wide association studies," Bioinformatics, vol. 26, pp. 30-37, Jan 2010.
[27]L. W. Hahn, M. D. Ritchie, and J. H. Moore, "Multifactor dimensionality reduction software for detecting gene-gene and gene-environment interactions," Bioinformatics, vol. 19, pp. 376-382, Feb 2003.
[28]J. Zhang, T. J. Hou, W. Wang, and J. S. Liu, "Detecting and understanding combinatorial mutation patterns responsible for HIV drug resistance," Proceedings of the National Academy of Sciences of the United States of America, vol. 107, pp. 1321-1326, Jan 2010.
[29]S. D. Turner, S. M. Dudek, and M. D. Ritchie, "ATHENA: A knowledge-based hybrid backpropagation-grammatical evolution neural network algorithm for discovering epistasis among quantitative trait Loci," BioData Mining, vol. 3, pp. 5, Sep 2010.
[30]F. Gunther, N. Wawro, and K. Bammann, "Neural networks for modeling gene-gene interactions in association studies," BMC Genetics, vol. 10, pp. 87, Dec 2009.
[31]A. A. Motsinger, T. J. Fanelli, and M. D. Ritchie, "Power of grammatical evolution neural networks to detect gene-gene interactions in the presence of error common to genetic epidemiological studies," Genetic Epidemiology, vol. 31, pp. 491-491, Jul 2007.
[32]M. D. Ritchie, A. A. Motsinger, W. S. Bush, C. S. Coffey, and J. H. Moore, "Genetic programming neural networks: A powerful bioinformatics tool for human genetics," Applied Soft Computing, vol. 7, pp. 471-479, Jan 2007.
[33]A. A. Motsinger, S. L. Lee, G. Mellick, and M. D. Ritchie, "GPNN: Power studies and applications of a neural network method for detecting gene-gene interactions in studies of human disease," BMC Bioinformatics, vol. 7, pp. 39, Jan 2006.
[34]Y. Tomita, S. Tomida, Y. Hasegawa, Y. Suzuki, T. Shirakawa, T. Kobayashi, et al., "Artificial neural network approach for selection of susceptible single nucleotide polymorphisms and construction of prediction model on childhood allergic asthma," BMC Bioinformatics, vol. 5, pp. 120, Sep 2004.
[35]M. D. Ritchie, B. C. White, J. S. Parker, L. W. Hahn, and J. H. Moore, "Optimization of neural network architecture using genetic programming improves detection and modeling of gene-gene interactions in studies of human diseases," BMC Bioinformatics, vol. 4, pp. 28, Jul 2003.
[36]S. H. Chen, J. Sun, L. Dimitrov, A. R. Turner, T. S. Adams, D. A. Meyers, et al., "A support vector machine approach for detecting gene-gene interaction," Genetic Epidemiology, vol. 32, pp. 152-167, Feb 2008.
[37]D. F. Schwarz, I. R. Konig, and A. Ziegler, "On safari to Random Jungle: a fast implementation of Random Forests for high-dimensional data," Bioinformatics, vol. 27, pp. 439-439, Feb 2011.
[38]R. Jiang, W. Tang, X. Wu, and W. Fu, "A random forest approach to the detection of epistatic interactions in case-control studies," BMC Bioinformatics, vol. 10, pp. S65, Jan 2009.
[39]S. J. Winham, C. L. Colby, R. R. Freimuth, X. Wang, M. de Andrade, M. Huebner, et al., "SNP interaction detection with Random Forests in high-dimensional genetic data," BMC Bioinformatics, vol. 13, pp. 164, Jul 2012.
[40]C. Kooperberg and I. Ruczinski, "Identifying interacting SNPs using Monte Carlo logic regression," Genetic Epidemiology, vol. 28, pp. 157-170, Feb 2005.
[41]M. Calle, V. Urrea, G. Vellalta, N. Malats, and K. Van Steen, "Model-based multifactor dimensionality reduction for detecting interactions in high-dimensional genomic data," European Journal of Human Genetics, vol. 19, pp. 696-703, Jun 2011.
[42]M. L. Calle, V. Urrea, G. Vellalta, N. Malats, and K. V. Steen, "Improving strategies for detecting genetic patterns of disease susceptibility in association studies," Statistics in Medicine, vol. 27, pp. 6532-6546, Dec 2008.
[43]X. Y. Lou, G. B. Chen, L. Yan, J. Z. Ma, J. Zhu, R. C. Elston, et al., "A generalized combinatorial approach for detecting gene-by-gene and gene-by-environment interactions with application to nicotine dependence," American Journal of Human Genetics, vol. 80, pp. 1125-1137, Jun 2007.
[44]Y. J. Chung, S. Y. Lee, R. C. Elston, and T. Park, "Odds ratio based multifactor-dimensionality reduction method for detecting gene-gene interactions," Bioinformatics, vol. 23, pp. 71-76, Jan 2007.
[45]S. Y. Lee, Y. Chung, R. C. Elston, Y. Kim, and T. Park, "Log-linear model-based multifactor dimensionality reduction method to detect gene-gene interactions," Bioinformatics, vol. 23, pp. 2589-2595, Oct 2007.
[46]C. F. Li, F. T. Luo, Y. X. Zeng, and W. H. Jia, "Weighted risk score-based multifactor dimensionality reduction to detect gene-gene interactions in nasopharyngeal carcinoma," International Journal of Molecular Sciences, vol. 15, pp. 10724-10737, Jun 2014.
[47]J. H. Moore, J. C. Gilbert, C. T. Tsai, F. T. Chiang, T. Holden, N. Barney, et al., "A flexible computational framework for detecting, characterizing, and interpreting statistical patterns of epistasis in genetic studies of human disease susceptibility," Journal of Theoretical Biology, vol. 241, pp. 252-261, Jul 2006.
[48]W. S. Bush, S. M. Dudek, and M. D. Ritchie, "Parallel multifactor dimensionality reduction: a tool for the large-scale analysis of gene-gene interactions," Bioinformatics, vol. 22, pp. 2173-2174, Sep 2006.
[49]C. S. Greene, N. A. Sinnott-Armstrong, D. S. Himmelstein, P. J. Park, J. H. Moore, and B. T. Harris, "Multifactor dimensionality reduction for graphics processing units enables genome-wide testing of epistasis in sporadic ALS," Bioinformatics, vol. 26, pp. 694-695, Jan 2010.
[50]D. R. Velez, B. C. White, A. A. Motsinger, W. S. Bush, M. D. Ritchie, S. M. Williams, et al., "A balanced accuracy function for epistasis modeling in imbalanced datasets using multifactor dimensionality reduction," Genetic Epidemiology, vol. 31, pp. 306-315, May 2007.
[51]C. H. Yang, Y. D. Lin, L. Y. Chuang, J. B. Chen, and H. W. Chang, "MDR-ER: balancing functions for adjusting the ratio in risk classes and classification errors for imbalanced cases and controls using multifactor-dimensionality reduction," PLoS ONE, vol. 8, pp. e79387, Nov 2013.
[52]W. Bateson, Mendel's principles of heredity: Cosimo, Inc., 2007.
[53]R. A. Fisher, "XV.—The Correlation between Relatives on the Supposition of Mendelian Inheritance," Transactions of the Royal Society of Edinburgh, vol. 52, pp. 399-433, Jan 1919.
[54]J. H. Moore and S. M. Williams, "Traversing the conceptual divide between biological and statistical epistasis: systems biology and a more modern synthesis," Bioessays, vol. 27, pp. 637-646, Jun 2005.
[55]F. W. Asselbergs, J. H. Moore, M. P. van den Berg, E. B. Rimm, R. A. de Boer, R. P. Dullaart, et al., "A role for CETP TaqIB polymorphism in determining susceptibility to atrial fibrillation: a nested case control study," BMC Medical Genetics, vol. 7, pp. 39, Apr 2006.
[56]C. H. Yang, Y. D. Lin, C. Y. Yen, L. Y. Chuang, and H. W. Chang, "A systematic gene-gene and gene-environment interaction analysis of DNA repair genes XRCC1, XRCC2, XRCC3, XRCC4, and oral cancer risk," OMICS: a Journal of Integrative Biology, vol. 19, pp. 238-247, Apr 2015.
[57]C. H. Yang, Y. D. Lin, S. J. Wu, L. Y. Chuang, and H. W. Chang, "High order gene-gene interactions in eight single nucleotide polymorphisms of renin-angiotensin system genes for hypertension association study." Biomed Research International, vol. 2015, pp. 454091, Apr 2015.
[58]W. S. Bush, T. L. Edwards, S. M. Dudek, B. A. McKinney, and M. D. Ritchie, "Alternative contingency table measures improve the power and detection of multifactor dimensionality reduction," BMC Bioinformatics, vol. 9, pp. 238, May 2008.
[59]J. Namkung, K. Kim, S. Yi, W. Chung, M. S. Kwon, and T. Park, "New evaluation measures for multifactor dimensionality reduction classifiers in gene-gene interaction analysis," Bioinformatics, vol. 25, pp. 338-345, Feb 2009.
[60]K. Ye, "Experiments: Planning, analysis, and parameter design optimization.," Interfaces, vol. 33, pp. 96-98, Sep-Oct 2003.
[61]R. Storn and K. Price, "Differential evolution - simple and efficient heuristic for global optimization over continuous spaces," Journal of Global Optimization, vol. 11, pp. 341-359, Dec 1997.
[62]A. K. Qin, V. L. Huang, and P. N. Suganthan, "Differential evolution algorithm with strategy adaptation for global numerical optimization," IEEE Transactions on Evolutionary Computation, vol. 13, pp. 398-417, Apr 2009.
[63]S. Das and P. N. Suganthan, "Differential evolution: A survey of the state-of-the-art," IEEE Transactions on Evolutionary Computation, vol. 15, pp. 27-54, Feb 2011.
[64]K. Deb, Multi-objective optimization using evolutionary algorithms vol. 16: John Wiley & Sons, 2001.
[65]K. Price, R. M. Storn, and J. A. Lampinen, Differential evolution: a practical approach to global optimization: Springer, 2006.
[66]M. D. Ritchie, L. W. Hahn, and J. H. Moore, "Power of multifactor dimensionality reduction for detecting gene-gene interactions in the presence of genotyping error, missing data, phenocopy, and genetic heterogeneity," Genetic Epidemiology, vol. 24, pp. 150-157, Feb 2003.
[67]J. L. Shang, J. Y. Zhang, X. J. Lei, W. Y. Zhao, and Y. F. Dong, "EpiSIM: simulation of multiple epistasis, linkage disequilibrium patterns and haplotype blocks for genome-wide interaction analysis," Genes & Genomics, vol. 35, pp. 305-316, Jun 2013.
[68]R. J. Urbanowicz, J. Kiralis, N. A. Sinnott-Armstrong, T. Heberling, J. M. Fisher, and J. H. Moore, "GAMETES: a fast, direct algorithm for generating pure, strict, epistatic models with random architectures," BioData Mining, vol. 5, pp. 16, Oct 2012.
[69]P. R. Burton, D. G. Clayton, L. R. Cardon, N. Craddock, P. Deloukas, A. Duncanson, et al., "Genome-wide association study of 14,000 cases of seven common diseases and 3,000 shared controls," Nature, vol. 447, pp. 661-678, Jun 2007.
[70]P. Libby and P. Theroux, "Pathophysiology of coronary artery disease," Circulation, vol. 111, pp. 3481-3488, Jun 2005.
[71]C. S. Coffey, P. R. Hebert, M. D. Ritchie, H. M. Krumholz, J. M. Gaziano, P. M. Ridker, et al., "An application of conditional logistic regression and multifactor dimensionality reduction for detecting gene-gene interactions on risk of myocardial infarction: The importance of model validation," BMC Bioinformatics, vol. 5, pp. 49, Apr 2004.
[72]C. T. Tsai, J. J. Hwang, M. D. Ritchie, J. H. Moore, F. T. Chiang, L. P. Lai, et al., "Renin-angiotensin system gene polymorphisms and coronary artery disease in a large angiographic cohort: Detection of high order gene-gene interaction," Atherosclerosis, vol. 195, pp. 172-180, Nov 2007.
[73]M. Agirbasli, A. I. Guney, H. S. Ozturhan, D. Agirbasli, K. Ulucan, D. Sevinc, et al., "Multifactor dimensionality reduction analysis of MTHFR, PAI-1, ACE, PON1, and eNOS gene polymorphisms in patients with early onset coronary artery disease," European Journal of Cardiovascular Prevention & Rehabilitation, vol. 18, pp. 803-809, Dec 2011.
[74]H. Sanada, J. Yatabe, S. Midorikawa, S. Hashimoto, T. Watanabe, J. H. Moore, et al., "Single-nucleotide polymorphisms for diagnosis of salt-sensitive hypertension," Clinical Chemistry, vol. 52, pp. 352-360, Mar 2006.
[75]J. Gui, A. S. Andrew, P. Andrews, H. M. Nelson, K. T. Kelsey, M. R. Karagas, et al., "A robust multifactor dimensionality reduction method for detecting gene–gene interactions with application to the genetic analysis of bladder cancer susceptibility," Annals of human genetics, vol. 75, pp. 20-28, Jan 2011.
[76]A. M. Coutinho, I. Sousa, M. Martins, C. Correia, T. Morgadinho, C. Bento, et al., "Evidence for epistasis between SLC6A4 and ITGB3 in autism etiology and in the determination of platelet serotonin levels," Human Genetics, vol. 121, pp. 243-256, Apr 2007.
[77]T. L. Edwards, K. Lewis, D. R. Velez, S. Dudek, and M. D. Ritchie, "Exploring the performance of multifactor dimensionality reduction in large scale SNP studies and in the presence of genetic heterogeneity among epistatic disease models," Human Heredity, vol. 67, pp. 183-192, Dec 2009.
[78]A. A. Motsinger and M. D. Ritchie, "The effect of reduction in cross-validation intervals on the performance of multifactor dimensionality reduction," Genetic Epidemiology, vol. 30, pp. 546-555, Sep 2006.
[79]A. M. Molinaro, R. Simon, and R. M. Pfeiffer, "Prediction error estimation: a comparison of resampling methods," Bioinformatics, vol. 21, pp. 3301-3307, Aug 2005.
[80]Y. H. Yang, "Consistency of cross validation for comparing regression procedures," Annals of Statistics, vol. 35, pp. 2450-2473, Dec 2007.