The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Feature selection and prediction modeling of drug responsiveness in Pharmacogenomics

약물유전체학에서 약물반응 예측모형과 변수선택 방법

  • Kim, Kyuhwan (Department of Statistics, Chung-Ang University) ;
  • Kim, Wonkuk (Department of Applied Statistics, Chung-Ang University)
  • 김규환 (중앙대학교 통계학과) ;
  • 김원국 (중앙대학교 응용통계학과)
  • Received : 2020.11.17
  • Accepted : 2021.02.01
  • Published : 2021.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

A main goal of pharmacogenomics studies is to predict individual's drug responsiveness based on high dimensional genetic variables. Due to a large number of variables, feature selection is required in order to reduce the number of variables. The selected features are used to construct a predictive model using machine learning algorithms. In the present study, we applied several hybrid feature selection methods such as combinations of logistic regression, ReliefF, TurF, random forest, and LASSO to a next generation sequencing data set of 400 epilepsy patients. We then applied the selected features to machine learning methods including random forest, gradient boosting, and support vector machine as well as a stacking ensemble method. Our results showed that the stacking model with a hybrid feature selection of random forest and ReliefF performs better than with other combinations of approaches. Based on a 5-fold cross validation partition, the mean test accuracy value of the best model was 0.727 and the mean test AUC value of the best model was 0.761. It also appeared that the stacking models outperform than single machine learning predictive models when using the same selected features.

약물유전체학 연구의 주요 목표는 고차원의 유전 변수를 기반으로 개인의 약물 반응성을 예측하는 것이다. 변수의 개수가 많기 때문에 변수의 개수를 줄이기 위해서는 변수 선택이 필요하며, 선택된 변수들은 머신러닝 알고리즘을 사용하여 예측 모델을 구축하는데 사용된다. 본 연구에서는 400명의 뇌전증 환자의 차세대 염기서열 분석 데이터에 로지스틱 회귀, ReliefF, TurF, 랜덤 포레스트, LASSO의 조합과 같은 여러 가지 혼합 변수 선택 방법을 적용하였다. 선택된 변수들에 랜덤포레스트, 그래디언트 부스팅, 서포트벡터머신을 포함한 머신러닝 방법들을 적용했고 스태킹을 통해 앙상블 모형을 구축하였다. 본 연구의 결과는 랜덤포레스트와 ReliefF의 혼합 변수 선택 방법을 이용한 스태킹 모형이 다른 모형보다 더 좋은 성능을 보인다는 것을 보여주었다. 5-폴드 교차 검증을 기반으로 하여 적합한 최적 모형의 평균 검증 정확도는 0.727이고 평균 검증 AUC 값은 0.761로 나타났다. 또한, 동일한 변수를 사용할 때 스태킹 모델이 단일 머신러닝 예측 모델보다 성능이 우수한 것으로 나타났다.

Keywords

Acknowledgement

이 논문은 2019년도 중앙대학교 CAU GRS 지원에 의하여 작성되었음. 이 논문은 2018년도 정부(교육부)의 재원으로 한국연구재단의 지원을 받아 수행된 기초연구사업임 (NRF-2018R1D1A1B07050012).

References

  1. Abraham G, Tye-Din JA, Bhalala OG, Kowalczyk A, Zobel J, and Inouye M (2014). Accurate and robust genomic prediction of celiac disease using statistical learning, PLoS Genetics, 10, e1004137. https://doi.org/10.1371/journal.pgen.1004137
  2. Austin PC, Tu JV, Ho JE, Levy D, and Lee DS (2013). Using methods from the data-mining and machinelearning literature for disease classification and prediction: a case study examining classification of heart failure subtypes, Journal of Clinical Epidemiology, 66, 398-407. https://doi.org/10.1016/j.jclinepi.2012.11.008
  3. Boulesteix AL, Janitza S, Kruppa J, and Konig IR (2012). Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics, Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2, 493-507. https://doi.org/10.1002/widm.1072
  4. Bommert A, Sun X, Bischl B, Rahnenfuhrer J, and Lang M (2020). Benchmark for filter methods for feature selection in high-dimensional classification data, Computational Statistics and Data Analysis, 143, 106839. https://doi.org/10.1016/j.csda.2019.106839
  5. Breiman L (1996). Stacked regressions, Machine Learning, 24, 49-64. https://doi.org/10.1007/BF00117832
  6. Breiman L (2001). Random forests, Machine Learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324
  7. Chen X and Ishwaran H (2012). Random forests for genomic data analysis, Genomics, 99, 323-329. https://doi.org/10.1016/j.ygeno.2012.04.003
  8. D'iaz-Uriarte R (2007). GeneSrF and varSelRF: a web-based tool and R package for gene selection and classification using random forest, BMC Bioinformatics, 8, 328. https://doi.org/10.1186/1471-2105-8-328
  9. Fisher RS, Acevedo C, Arzimanoglou A, et al (2014). Ilae official report: a practical clinical definition of epilepsy, Epilepsia, 55, 475-482. https://doi.org/10.1111/epi.12550
  10. Genuer R, Poggi JM, and Tuleau-Malot C (2015). VSURF: an R package for variable selection using random forests, The R Journal, 7, 19-33. https://doi.org/10.32614/RJ-2015-018
  11. Ho DSW, Schierding W, Wake M, Saffery R, and O'Sullivan J (2019). Machine learning SNP based prediction for precision medicine, Frontiers in genetics, 10, 267. https://doi.org/10.3389/fgene.2019.00267
  12. Jovic A, Brkic K, and Bogunovic N (2015). A review of feature selection methods with applications, ' In 2015 38th international convention on information and communication technology, electronics and microelectronics (MIPRO), 1200-1205.
  13. Kang KW, Kim W, Cho YW, et al (2019). Genetic characteristics of non-familial epilepsy, PeerJ, 7, e8278. https://doi.org/10.7717/peerj.8278
  14. Kim MK, Moore JH, Kim, and Shin MH (2011). Evidence for epistatic interactions in antiepileptic drug resistance, Journal of Human Genetics, 56, 71-76. https://doi.org/10.1038/jhg.2010.151
  15. Kira K, and Rendell LA (1992). The feature selection problem: Traditional methods and a new algorithm. In Aaai Press.
  16. Kononenko I (1994). Estimating attributes: analysis and extensions of RELIEF. In European conference on machine learning, 171-182, Springer, Berlin, Heidelberg.
  17. Lee JY, Kim MK, and Kim W (2020). Robust linear trend test for low-coverage next-generation sequence data controlling for covariates, Mathematics, 8, 217. https://doi.org/10.3390/math8020217
  18. Li J, Cheng K, Wang S, Morstatter F, Trevino RP, Tang J, and Liu H (2017). Feature selection: a data perspective, ACM Computing Surveys (CSUR), 50, 1-45.
  19. Lopez B, Torrent-Fontbona F, Vin as R, and Ferna ndez-Real JM (2017). Single nucleotide polymorphism relevance learning with random forests for type 2 diabetes risk prediction, Artificial Intelligence in Medicine, 85, 43-49. https://doi.org/10.1016/j.artmed.2017.09.005
  20. Mieth B, Kloft M, Rodr'iguez JA, et al (2016). Combining multiple hypothesis testing with machine learning increases the statistical power of genome-wide association studies, Scientific Reports, 6, 36671. https://doi.org/10.1038/srep36671
  21. Montanez CAC, Fergus P, Montaez AC, Hussain A, Al-Jumeily D, and Chalmers C (2018). Deep learning classification of polygenic obesity using genome wide association study snps, In 2018 International Joint Conference on Neural Networks (IJCNN), IEEE.
  22. Moore JH and White BC (2007). Tuning relieff for genome-wide genetic analysis. In European Conference on Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics, Springer.
  23. Mustra M, Grgic M, and Delac K (2012). Breast density classification using multiple feature selection, Automatika, 53, 1289-1305.
  24. Nguyen TT, Huang JZ, Wu Q, Nguyen TT, and Li MJ (2015). Genome-wide association data classification and snps selection using two-stage quality-based random forests, BMC Genomics, Springer.
  25. Romagnoni A, J egou S, Van Steen K, Wainrib G, and Hugot JP (2019). Comparative performances of machine learning methods for classifying crohn disease patients using genome-wide genotyping data, Scientific Reports, 9, 1-18. https://doi.org/10.1038/s41598-018-37186-2
  26. Tibshirani R (1996). Regression shrinkage and selection via the lasso, Journal of the Royal Statistical Society: Series B (Methodological), 58, 267-288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
  27. Van der Laan MJ, Polley EC, and Hubbard AE (2007). Super learner, Journal of Clinical Epidemiology, 6.
  28. Wei Z, Wang W, Bradfield J, et al (2013). Large sample size, wide variant spectrum, and advanced machinelearning technique boost risk prediction for inflammatory bowel disease, The American Journal of Human Genetics, 92, 1008-1012. https://doi.org/10.1016/j.ajhg.2013.05.002
  29. Wolpert DH (1992). Stacked generalization, Neural Networks, 5, 241-259. https://doi.org/10.1016/S0893-6080(05)80023-1
  30. Zou H and Hastie T (2005). Regularization and variable selection via the elastic net, Journal of the Royal Statistical Society: Series B (Statistical Methodology), 67, 301-320. https://doi.org/10.1111/j.1467-9868.2005.00503.x