Identification of influential observations in high-dimensional cancer survival data through the rank product test
Tóm tắt
Survival analysis is a statistical technique widely used in many fields of science, in particular in the medical area, and which studies the time until an event of interest occurs. Outlier detection in this context has gained great importance due to the fact that the identification of long or short-term survivors may lead to the detection of new prognostic factors. However, the results obtained using different outlier detection methods and residuals are seldom the same and are strongly dependent of the specific Cox proportional hazards model selected. In particular, when the inherent data have a high number of covariates, dimensionality reduction becomes a key challenge, usually addressed through regularized optimization, e.g. using Lasso, Ridge or Elastic Net regression. In the case of transcriptomics studies, this is an ubiquitous problem, since each observation has a very high number of associated covariates (genes). In order to solve this issue, we propose to use the Rank Product test, a non-parametric technique, as a method to identify discrepant observations independently of the selection method and deviance considered. An example based on the The Cancer Genome Atlas (TCGA) ovarian cancer dataset is presented, where the covariates are patients’ gene expressions. Three sub-models were considered, and, for each one, different outliers were obtained. Additionally, a resampling strategy was conducted to demonstrate the methods’ consistency and robustness. The Rank Product worked as a consensus method to identify observations that can be influential under survival models, thus potential outliers in the high-dimensional space. The proposed technique allows us to combine the different results obtained by each sub-model and find which observations are systematically ranked as putative outliers to be explored further from a clinical point of view.
Tài liệu tham khảo
Cox DR. Regression models and life-tables. J R Stat Soc Ser B (Methodol). 1972; 34(2):187–220.
Kalbeisch JD, Prentice RL. The Statistical Analysis of Failure Time Data, 2nd edn. Hoboken: Wiley; 2002.
Bednarski T. Robust estimation in cox’s regression model. Scand J Stat. 1993; 20(3):213–25.
Heritier S, Cantoni E, Copt S, Victoria-Feser MP. Robust Methods in Biostatistics. New York: Wiley; 2009.
Nardi A, Schemper M. New residuals for cox regression and their application to outlier screening. Biometrics. 1999; 55(2):523–9.
Therneau TM, Grambsch PM, Fleming TR. Martingale-based residuals for survival models. Biometrika. 1990; 77(1):147–60.
Bhlmann P, van de Geer S. Statistics for High-Dimensional Data: Methods, Theory and Applications, 1st edn. Berlin: Springer; 2011.
Tibshirani R. Regression shrinkage and selection via the lasso. J R Stat Soc Ser B. 1994; 58:267–88.
Zou H, Hastie T. Regularization and variable selection via the elastic net. J R Stat Soc Ser B (Stat Methodol). 2005; 67(2):301–20. https://doi.org/10.1111/j.1467-9868.2005.00503.x.
Eo SH, Hong SM, Cho H. Identification of outlying observations with quantile regression for censored data. Comput Stat. 2014;:1–17. http://arxiv.org/abs/1404.7710v1.
Pinto JD, Carvalho AM, Vinga S. Outlier Detection in Survival Analysis Based on the Concordance C-index. In: Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms (BIOSTEC 2015): 2015. p. 75–82. https://doi.org/10.5220/0005225300750082.
Breitling R, Armengaud P, Amtmann A, Herzyk P. Rank products: a simple, yet powerful, new method to detect differentially regulated genes in replicated microarray experiments. FEBS Lett. 2004; 573(1-3):83–92. https://doi.org/10.1016/j.febslet.2004.07.055.
Caldas J, Vinga S. Global meta-analysis of transcriptomics studies. Plos ONE 2014;9(2). https://doi.org/10.1371/journal.pone.0089318.
Koziol JA. Comments on the rank product method for analyzing replicated experiments. FEBS Lett. 2010; 584(5):941–4. https://doi.org/10.1016/j.febslet.2010.01.031.
Eisinga R, Breitling R, Heskes T. The exact probability distribution of the rank product statistics for replicated experiments. FEBS Lett. 2013; 587(6):677–82. https://doi.org/10.1016/j.febslet.2013.01.037.
Heskes T, Eisinga R, Breitling R. A fast algorithm for determining bounds and accurate approximate p-values of the rank product statistic for replicate experiments. BMC Bioinformatics. 2014; 15:367.
Storey JD. A direct approach to false discovery rates. J R Stat Soc Ser B (Stat Methodol). 2002; 64(3):479–98. https://doi.org/10.1111/1467-9868.00346.
Tibshirani R. The lasso method for variable selection in the cox model. Stat Med. 1997; 16(4):385–95. https://doi.org/10.1002/(SICI)1097-0258(19970228)16:4%3C385::AID-SIM380%3E3.0.CO;2-3.
Zhang W, Ota T, Shridhar V, Chien J, Wu B, Kuang R. Network-based survival analysis reveals subnetwork signatures for predicting outcomes of ovarian cancer treatment. PLoS Comput Biol 2013;9(3).
R Core Team. R: A Language and Environment for Statistical Computing. Vienna: R Foundation for Statistical Computing; 2012. R Foundation for Statistical Computing. http://www.R-project.org/.
Smith PJ. Analysis of Failure and Survival Data. Chapman and Hall/CRC, United States of America, USA. 2002.
Volkmann J, Reuning U, Rudelius M, Haefner N, Schuster T, Rose ABV, Weimer J, Hilpert F, Kiechle M, Duerst M, Arnold N, Schmalfeldt B, Meindl A, Ramser J. High expression of crystallin b represents an independent molecular marker for unfavourable ovarian cancer patient outcome and impairs trail- and cisplatin-induced apoptosis in human ovarian cancer cells. Int J Cancer. 2013; 132(12):2820–32. https://doi.org/10.1002/ijc.27975.
Chen J, Wang M, Xi B, Xue J, He D, Zhang J, Zhao Y. Sparc is a key regulator of proliferation, apoptosis and invasion in human ovarian cancer. PLoS ONE. 2012; 7(8):1–15. https://doi.org/10.1371/journal.pone.0042413.
Feng J, Tang L. Sparc in tumor pathophysiology and as a potential therapeutic target. Curr Pharm Des. 2014; 20(39):6182–90. https://doi.org/10.2174/1381612820666140619123255.
Pal T, Permuth-Wey J, Betts JA, Krischer JP, Fiorica J, Arango H, LaPolla J, Hoffman M, Martino MA, Wakeley K, Wilbanks G, Nicosia S, Cantor A, Sutphen R. Brca1 and brca2 mutations account for a large proportion of ovarian carcinoma cases. Cancer. 2005; 104(12):2807–16. https://doi.org/10.1002/cncr.21536.
Southey MC, Winship I, Nguyen-Dumont T. Palb2: research reaching to clinical outcomes for women with breast cancer. Hereditary Cancer Clin Pract. 2016; 14(1):9. https://doi.org/10.1186/s13053-016-0049-2.