Using distance covariance for improved variable selection with application to learning genetic risk models

Statistics in Medicine

Volumn 34, Issue 10, 2015, Pages 1708-1720

  Kong, Jing ^a   Wang, Sijian ^a,b   Wahba, Grace ^a,b  

^a University of Wisconsin   (United States)

^b UNIVERSITY OF WISCONSIN SCHOOL OF MEDICINE AND PUBLIC HEALTH   (United States)

Author keywords

Distance correlation; Penalized Bernoulli likelihood; SVM with reject option; TCGA ovarian cancer data; Variable selection

Indexed keywords

CISPLATIN; CYCLIC AMP; FIBROBLAST GROWTH FACTOR RECEPTOR 2; MITOGEN ACTIVATED PROTEIN KINASE 4; SECRETED FRIZZLED RELATED PROTEIN 5; SOMATOMEDIN BINDING PROTEIN 5; SOMATOMEDIN C; ANTINEOPLASTIC AGENT;

ANALYSIS OF COVARIANCE; ANALYTIC METHOD; ANIMAL EXPERIMENT; ANIMAL MODEL; ARTICLE; BURKITT LYMPHOMA; CONTROLLED STUDY; CORRELATION ANALYSIS; CORRELATION COEFFICIENT; DISTANCE CORRELATION SURE INDEPENDENCE SCREENING; DISTANCE COVARIANCE; EWING SARCOMA; FEMALE; GENETIC RISK; HUMAN; LEARNING GENETIC RISK MODEL; MAJOR CLINICAL STUDY; MATHEMATICAL ANALYSIS; MATHEMATICAL MODEL; NEUROBLASTOMA; NONHODGKIN LYMPHOMA; NONHUMAN; OVARY CANCER; PROBABILITY; PROTEIN EXPRESSION; RANDOM FOREST; REGRESSION ANALYSIS; RHABDOMYOSARCOMA; SIGNAL TRANSDUCTION; SUPPORT VECTOR MACHINE; TUMOR VASCULARIZATION; VALIDATION PROCESS; WNT SIGNALING PATHWAY; ANALYSIS OF VARIANCE; BINOMIAL DISTRIBUTION; BIOLOGICAL MODEL; DIFFERENTIAL DIAGNOSIS; DRUG EFFECTS; GENETIC PREDISPOSITION; GENETIC SCREENING; GENETICS; OVARIAN NEOPLASMS; PATHOLOGY; PHARMACOGENETICS; PROCEDURES; RISK ASSESSMENT; STATISTICS AND NUMERICAL DATA; TUMOR GENE;

ANALYSIS OF VARIANCE; ANTINEOPLASTIC AGENTS; BINOMIAL DISTRIBUTION; DIAGNOSIS, DIFFERENTIAL; FEMALE; GENES, NEOPLASM; GENETIC PREDISPOSITION TO DISEASE; GENETIC TESTING; HUMANS; MODELS, GENETIC; OVARIAN NEOPLASMS; PHARMACOGENETICS; RISK ASSESSMENT;

EID: 84926355097     PISSN: 02776715     EISSN: 10970258     Source Type: Journal    
DOI: 10.1002/sim.6441     Document Type: Article

References (22)

1. Fan J, Lv J. Sure independence screening for ultrahigh dimensional feature space. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 2008; 70(5):849-911.
2. Székely GJ, Rizzo ML, Bakirov NK. Measuring and testing dependence by correlation of distances. The Annals of Statistics 2008; 35(6):2769-2794.
3. Li R, Zhong W, Zhu L. Feature screening via distance correlation. Journal of the American Statistical Association 2012;107(499):1129-1139.
4. Kong J, Klein BEK, Klein R, Lee KE, Wahba G. Using distance correlation and SS-ANOVA to assess associations of familial relationships, lifestyle factors, diseases, and mortality. Proceedings of the National Academy of Sciences 2012; 109(50):20352-20357.
5. Kosorok MR. Discussion of brownian distance covariance. The Annals of Applied Statistics 2009; 3(4):1270-1278.
6. Khan J, Wei JS, Ringnér M, Saal LH, Ladanyi M, Westermann F, Berthold F, Schwab M, Antonescu CR, Peterson C, Meltzer PS. Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks. Nature Medicine 2001; 7(6):673-679.
7. Lee Y, Lin Y, Wahba G. Multicategory support vector machines: theory and application to the classification of microarray data and satellite radiance data. Journal of the American Statistical Association 2004; 99(465):67-81.
8. National Cancer Institute website. http://www.cancer.gov/cancertopics/types/ovarian [Accessed on 28 August 2013].
9. Network Cancer Genome Atlas Research and others. Integrated genomic analyses of ovarian carcinoma. Nature 2011; 474(7353):609-615.
10. Selvanayagam ZE, Cheung TH, Wei N, Vittal R, Lo KW, Yeo W, Kita T, Ravatn R, Chung TK, Wong YF, Chin KV. Prediction of chemotherapeutic response in ovarian cancer with DNA microarray expression profiling. Cancer Genetics and Cytogenetics 2004; 154(1):63-66.
11. Rho SB, Dong SM, Kang S, Seo SS, Yoo CW, Lee DO, Woo JS, Park SY. Insulin-like growth factor-binding protein-5 (IGFBP-5) acts as a tumor suppressor by inhibiting angiogenesis. Carcinogenesis 2008; 29(11):2106-2111.
12. Mehlmann LM, Saeki Y, Tanaka S, Brennan TJ, Evsikov AV, Pendola FL, Knowles BB, Eppig JJ, Jaffe LA. The GS-linked receptor GPR3 maintains meiotic arrest in mammalian oocytes. Science 2004; 306(5703):1947-1950.
13. Ledent C, Demeestere I, Blum D, Petermans J, Hämäläinen T, Smits G, Vassart G. Premature ovarian aging in mice deficient for GPS3. Proceedings of the National Academy of Sciences of the United States of America 2005; 102(25):8922-8926.
14. Basu S, Harfouche R, Soni S, Chimote G, Mashelkar RA, Sengupta S. Nanoparticle-mediated targeting of MAPK signaling predisposes tumor to chemotherapy. Proceedings of the National Academy of Sciences 2009; 106(19):7957-7961.
15. Bast RC, Mills GB. Personalizing therapy for ovarian cancer. BRCAness and beyond. Journal of Clinical Oncology 2010; 28 (22):3545-3548.
16. Thiele S, Rauner M, Goettsch C, Rachner TD, Benad P, Fuessel S, Erdmann K, Hamann C, Baretton GB, Wirth MP, Jakob F, Hofbauer LC. Expression profile of WNT molecules in prostate cancer and its regulation by aminobisphosphonates. Journal of Cellular Biochemistry 2011; 112(6):1593-1600.
17. Bitler BG, Nicodemus JP, Li H, Cai Q, Wu H, Hua X, Li T, Birrer MJ, Godwin AK, Cairns P, Zhang R. Wnt5a suppresses epithelial ovarian cancer by promoting cellular senescence. Cancer Research 2011; 71(19):6184-6194.
18. Cole C, Lau S, Backen A, Clamp A, Rushton G, Dive C, Hodgkinson C, McVey R, Kitchener H, Jayson GC. Inhibition of FGFR2 and FGFR1 increases cisplatin sensitivity in ovarian cancer. Cancer Biology & Therapy 2010; 10(5):495-504.
19. Yin J, Lu K, Lin J, Wu L, Hildebrandt MAT, Chang DW, Meyer L, Wu X, Liang D. Genetic variants in TGF-β pathway are associated with ovarian cancer risk. PloS One 2011; 6(9):e25559.
20. Gu C. gss: general smoothing splines. R package version 2.1-2, 2007.
21. Wegkamp M, Yuan M. Support vector machines with a reject option. Bernoulli 2011; 17(4):1368-1385.
22. Bartlett PL, Wegkamp MH. Classification with a reject option using a hinge loss. The Journal of Machine Learning Research 2008; 91823-1840.