Deep Learning Identification of the Gene-Gene Interactions without the Need of thorough Investigation of Each Genomic Combination

다국어 초록 (Multilingual Abstract)

Genomic association has been measured by various statistics including chi-square, balanced accuracy, and mutual information. When investigating the gene-gene interactions, however, estimating the association measure for all of the possible genomic combination becomes computationally intensive rapidly as the order of interaction increases. We show first that the deep learning neural network can be used to measure the strength of the genomic association with case-control phenotype. Then we demonstrate that the selection of the interacting genotypes is possible without going through all of the interacting combinations. Instead of examining each SNP or SNP combination, as is the conventional way, we start from using all of the available SNPs as the input to the neural network. In that way, the association strength by the whole SNPs’ interaction may be obtained. Then each SNP is excluded in turn from the input and the change in accuracy is measured. A set of SNPs that could cause statistically significant change may be identified. By estimating the accuracy changes when excluding the combinations made of this set, we could successfully identify the causal combination from the used genomic data set.

참고문헌 (Reference)

1 Evans, D. M., "Two-stage two-locus models in genome-wide association" 2 (2): e157-, 2006

2 Hu, J. K., "Testing gene-gene interactions in genome wide association studies" 38 (38): 123-134, 2014

3 황창하, "Support Vector Machine Regression for a Gaussian Fuzzy Model" 한국자료분석학회 6 (6): 431-439, 2004

4 이재용, "Robust Estimation of a Genomic Association against the Imbalance among the Multi-class Phenotypes" 한국자료분석학회 18 (18): 1741-1750, 2016

5 박희창, "Proposition of Modified Balance Cross Entropy in Association Rule Mining" 한국자료분석학회 19 (19): 1733-1741, 2017

6 이희춘, "Prediction Accuracy Increase of Recommender System in Data Scarcity" 한국자료분석학회 12 (12): 1271-1283, 2010

7 Schwarz, D. F., "On safari to random jungle : a fast implementation of random forests for high-dimensional data" 26 (26): 1752-1758, 2010

8 Namkung, J., "New evaluation measures for multifactor dimensionality reduction classifiers in gene-gene interaction analysis" 25 (25): 338-345, 2009

9 Ritchie, M. D., "Multifactor-dimensionality reduction reveals high-order interactions among estrogen-metabolism genes in sporadic breast cancer" 69 : 138-147, 2001

10 Motsinger, A. A., "Multifactor dimensionality reduction: An analysis strategy for modeling and detecting gene-gene interactions in human genetics and pharmacogenomics studies" 2 (2): 318-328, 2006

11 Jing, P. -J., "MACOED: a multi-objective ant colony optimization algorithm for SNP epistasis detection in genome-wide association studies" 31 (31): 634-641, 2015

12 Gyenesei, A., "High-throughput analysis of epistasis in genome-wide association studies with BiForce" 28 (28): 1957-1964, 2012

13 Tuo, S., "FHSA-SED: Two-locus model detection for genome-wide association study with harmony search algorithm" 11 (11): e0150669-, 2016

14 Kam-Thong, T., "EPIBLASTER-fast exhaustive two-locus epistasis detection strategy using graphical processing unit" 19 : 465-471, 2011

15 Li, J., "Detecting gene-gene interactions using a permutation-based random forest method" 9 : 14-, 2016

16 LeCun, Y., "Deep learning" 521 : 436-444, 2015

17 Aflakparast, M., "Cuckoo search epistasis : a new method for exploring significant genetic interactions" 112 : 666-674, 2014

18 Mieth, B., "Combining multiple hypothesis testing with machine learning increases the statistical power of genome-wide association studies" 6 : 36671-, 2016

19 Al-jouie, A., "Chi8 : a GPU program for detecting significant interesting SNPs with the chi-square 8-df test" 8 : 436-, 2015

20 Lee, S., "CARAT-GxG: CUDA-accelerated regression analysis toolkit for large-scale gene-gene interaction with GPU computing system" 13 (13): 27-33, 2014

21 Gola, D., "A roadmap to multifactor dimensionality reduction methods" 17 (17): 293-308, 2016

22 Koo, C. L., "A review for detecting gene-gene interactions using machine learning methods in genetic epidemiology" 432375-, 2013

23 J. Yee, "A modified entropy-based approach for identifying gene-gene interactions in case-control study" 8 (8): e69321-, 2013

24 Li, J., "A fast algorithm for detecting gene-gene interactions in genome-wide association studies" 8 (8): 2292-2318, 2014

25 Uppu, S., "A deep learning approach to detect SNP interactions" 11 (11): 960-975, 2016

26 Velez, D. R., "A balanced accuracy function for epistasis modeling in imbalanced datasets using multifactor dimensionality reduction" 31 : 306-315, 2007