Predicting the Survival Time for Bladder Cancer Using an Additive Hazards Model in Microarray Data
,
Abstract
Background: One substantial part of microarray studies is to predict patients’ survival based on their gene expression profile. Variable selection techniques are powerful tools to handle high dimensionality in analysis of microarray data. However, these techniques have not been investigated in competing risks setting. This study aimed to investigate the performance of four sparse variable selection methods in estimating the survival time.
Methods: The data included 1381 gene expression measurements and clinical information from 301 patients with bladder cancer operated in the years 1987 to 2000 in hospitals in Denmark, Sweden, Spain, France, and England. Four methods of the least absolute shrinkage and selection operator, smoothly clipped absolute deviation, the smooth integration of counting and absolute deviation and elastic net were utilized for simultaneous variable selection and estimation under an additive hazards model. The criteria of area under ROC curve, Brier score and c-index were used to compare the methods.
Results: The median follow-up time for all patients was 47 months. The elastic net approach was indicated to outperform other methods. The elastic net had the lowest integrated Brier score (0.137±0.07) and the greatest median of the over-time AUC and C-index (0.803±0.06 and 0.779±0.13, respectively). Five out of 19 selected genes by the elastic net were significant (P<0.05) under an additive hazards model. It was indicated that the expression of RTN4, SON, IGF1R and CDC20 decrease the survival time, while the expression of SMARCAD1 increase it.
Conclusion: The elastic net had higher capability than the other methods for the prediction of survival time in patients with bladder cancer in the presence of competing risks base on additive hazards model.
Counsell N, Douglas J, Tan WS, Feber A, Crabb SJ, Short SC, Freeman A (2014). Loss of expression of the tumour suppressor gene AIMP3 predicts survival following radiotherapy in muscle‐invasive bladder cancer. Int J Cancer, 136(3): 709-720.
Riester M, Taylor JM, Feifer A, Koppie T, Rosenberg JE, Downey RJ, Bochner BH, Michor F (2012). Combination of a novel gene expression signature with a clinical nomogram improves the prediction of survival in high-risk bladder cancer. Clin Cancer Res, 18:1323-1333.
Rosser CJ, Liu L, Sun Y, Villicana P, McCullers M, Porvasnik S, Young PR, Parker AS, Goodison S (2009). Bladder Cancer–Associated Gene Expression Signatures Identified by Profiling of Exfoliated Urothelia. Cancer Epidemiol Biomarkers Prev., 18:444-453.
Meeks JJ, Bellmunt J, Bochner BH, Clarke NW, Daneshmand S, Galsky MD, Hahn NM, Lerner SP, Mason M, Powles T (2012). A systematic review of neoadjuvant and adjuvant chemotherapy for muscle-invasive bladder cancer. Eur Urol, 62:523-533.
Blaveri E, Simko JP, Korkola JE, Brewer JL, Baehner F, Mehta K, DeVries S, Koppie T, Pejavar S, Carroll P (2005). Bladder cancer outcome and subtype classification by gene expression. Clin Cancer Res, 11:4044-4055.
Engler D, Li Y (2009). Survival analysis with high-dimensional covariates: an application in microarray studies. Stat Appl Genet Molec Biol, 8:1-22.
Bøvelstad HM, Nygård S, Størvold HL, Aldrin M, Borgan Ø, Frigessi A, Lingjærde OC (2007). Predicting survival from microarray data—a comparative study. Bioinformatics, 23:2080-2087.
Lin W, Lv J (2013). High-dimensional sparse additive hazards regression. JASA, 108:247-264.
Antoniadis A, Fryzlewicz P, Letué F (2010). The Dantzig selector in Cox's proportional hazards model. Scand J Stat, 37:531-552.
Fan J, Li R (2001). Variable selection via nonconcave penalized likelihood and its oracle properties. JASA, 96:1348-1360.
Efron B, Hastie T, Johnstone I, Tibshirani R (2004). Least angle regression. Ann Stat, 32:407-499.
Lv J, Fan Y (2009). A unified approach to model selection and sparse recovery using regularized least squares. Ann Stat, 37:3498-3528.
Zou H, Hastie T (2005). Regularization and variable selection via the elastic net. J R Stat Soc.: Series B (Statistical Methodology), 67:301-320.
Park MY, Hastie T (2007). L1‐regularization path algorithm for generalized linear models. J R Stat Soc: Series B (Statistical Methodology), 69:659-677.
Tibshirani R (1996). Regression shrinkage and selection via the lasso. J R Stat Soc: Series B (Methodological):267-288.
Lin D, Ying Z (1994). Semiparametric analysis of the additive risk model. Biometrika, 81:61-71.
Xie X, Strickler HD, Xue X (2013). Additive hazard regression models: an application to the natural history of human papillomavirus. Comput Math Methods Med, 2013: 1-7.
Martinussen T, Scheike TH (2009). The additive hazards model with high-dimensional regressors. Lifetime Data Anal, 15:330-342.
Ma S, Huang J (2007). Additive risk survival model with microarray data. BMC Bioinformatics, 8: 192. doi: 10.1186/1471-2105-8-192.
Dyrskjøt L, Zieger K, Real FX, Malats N, Carrato A, Hurst C, Kotwal S, Knowles M, Malmström P-U, de la Torre M (2007). Gene expression signatures predict outcome in non–muscle-invasive bladder carcinoma: a multicenter validation study. Clin Cancer Res, 13:3545-3551.
Binder H, Allignol A, Schumacher M, Beyersmann J (2009). Boosting for high-dimensional time-to-event data with competing risks. Bioinformatics, 25:890-896.
Heagerty PJ, Lumley T, Pepe MS (2000). Time‐dependent ROC curves for censored survival data and a diagnostic marker. Biometrics, 56:337-344.
Wolbers M, Blanche P, Koller MT, Witteman JC, Gerds TA (2014). Concordance for prognostic models with competing risks. Biostatistics:15(3):526-39
Chen C-L, Lai Y-F, Tang P, Chien K-Y, Yu J-S, Tsai C-H, Chen H-W, Wu C-C, Chung T, Hsu C-W (2012). Comparative and targeted proteomic analyses of urinary microparticles from bladder cancer and hernia patients. J Proteome Res, 11:5611-5629.
Zhang K, Bai P, Shi S, Zhou B, Wang Y, Song Y, Rao L, Zhang L (2013). Association of Genetic Variations in RTN4 3’-UTR with Risk of Uterine Leiomyomas. Pathol Oncol Res, 19:475-479.
Hickey CJ, Kim JH, Ahn EYE (2014). New Discoveries of Old SON: A Link Between RNA Splicing and Cancer. J Cell Biochem, 115:224-231.
Ahn E-Y, DeKelver RC, Lo M-C, Nguyen TA, Matsuura S, Boyapati A, Pandit S, Fu X-D, Zhang D-E (2011). SON controls cell-cycle progression by coordinated regulation of RNA splicing. Mol Cell, 42:185-198.
Furukawa T, Tanji E, Kuboki Y, Hatori T, Yamamoto M, Shimizu K, Shibata N, Shiratori K (2012). Targeting of MAPK-associated molecules identifies SON as a prime target to attenuate the proliferation and tumorigenicity of pancreatic cancer cells. Mol Cancer, 11(88):1-10.
Quan H, Tang H, Fang L, Bi J, Liu Y, Li H (2014). IGF1 (CA) 19 and IGFBP-3-202A/C gene polymorphism and cancer risk: a meta-analysis. Cell Biochem Biophys, 69:169-178.
Åhlén J, Wejde J, Brosjö O, von Rosen A, Weng W-H, Girnita L, Larsson O, Larsson C (2005). Insulin-like growth factor type 1 receptor expression correlates to good prognosis in highly malignant soft tissue sarcoma. Clin Cancer Res, 11:206-216.
Moreira A, Meira-Machado L (2012). survivalBIV: Estimation of the Bivariate Distribution Function for Sequentially Ordered Events Under Univariate Censoring. J Stat Softw, 46(13):1-16.
Pineda S, Milne RL, Calle ML, Rothman N, de Maturana EL, Herranz J, Kogevinas M, Chanock SJ, Tardón A, Márquez M (2014). Genetic Variation in the TP53 Pathway and Bladder Cancer Risk. A Comprehensive Analysis. PloS One, 9(5):e89952.
Morrione A, Neill T, Iozzo RV (2013). Dichotomy of decorin activity on the insulin‐like growth factor‐I system. FEBS J, 280:2138-2149.
Metalli D, Lovat F, Tripodi F, Genua M, Xu S-Q, Spinelli M, Alberghina L, Vanoni M, Baffa R, Gomella LG (2010). The insulin-like growth factor receptor I promotes motility and invasion of bladder cancer cells through Akt-and mitogen-activated protein kinase-dependent activation of paxillin. Am J Pathol, 176:2997-3006.
Rochester MA, Patel N, Turney BW, Davies DR, Roberts IS, Crew J, Protheroe A, Macaulay VM (2007). The type 1 insulin‐like growth factor receptor is over‐expressed in bladder cancer. BJU Int, 100:1396-1401.
Dudziec E, Miah S, Choudhry HM, Owen HC, Blizard S, Glover M, Hamdy FC, Catto JW (2011). Hypermethylation of CpG islands and shores around specific microRNAs and mirtrons is associated with the phenotype and presence of bladder cancer. Clin Cancer Res, 17:1287-1296.
Choi J-W, Kim Y, Lee J-H, Kim Y-S (2013). High expression of spindle assembly checkpoint proteins CDC20 and MAD2 is associated with poor prognosis in urothelial bladder cancer. Virchows Arch, 463:681-687.
Lambrou GI, Adamaki M, Delakas D, Spandidos DA, Vlahopoulos S, Zaravinos A (2013). Gene expression is highly correlated on the chromosome level in urinary bladder cancer. Cell Cycle, 12(10):1544-59.
Adra CN, Donato J-L, Badovinac R, Syed F, Kheraj R, Cai H, Moran C, Kolker MT, Turner H, Weremowicz S (2000). SMARCAD1, a novel human helicase family-defining member associated with genetic instability: cloning, expression, and mapping to 4q22–q23, a band rich in breakpoints and deletion mutants involved in several human diseases. Genomics, 69:162-173.
Rowbotham SP, Barki L, Neves-Costa A, Santos F, Dean W, Hawkes N, Choudhary P, Will WR, Webster J, Oxley D (2011). Maintenance of silent chromatin through replication requires SWI/SNF-like chromatin remodeler SMARCAD1. Mole Cell, 42:285-296.
O'Donnell PH, Stark AL, Gamazon ER, Wheeler HE, McIlwee BE, Gorsic L, Im HK, Huang RS, Cox NJ, Dolan ME (2012). Identification of novel germline polymorphisms governing capecitabine sensitivity. Cancer, 118:4063-4073.
Tappenden DM, Hwang HJ, Yang L, Thomas RS, LaPres JJ (2013). The Aryl-Hydrocarbon Receptor Protein Interaction Network (AHR-PIN) as Identified by Tandem Affinity Purification (TAP) and Mass Spectrometry. J Toxicol, 2013:1-12.
Ogutu JO, Schulz-Streeck T, Piepho H-P (2012) Genomic selection using regularized linear regression models: ridge regression, lasso, elastic net and their extensions. BMC proceedings, BioMed Central Ltd, 6: pp. S10.
Hamidi O, Tapak L, Jafarzadeh Kohneloo A, Sadeghifar M (2014). High-Dimensional Additive Hazards Regression for Oral Squamous Cell Carcinoma Using Microarray Data: A Comparative Study. BioMed Res Int, 2014.
Ma S, Kosorok MR, Fine JP (2006). Additive Risk Models for Survival Data with High‐Dimensional Covariates. Biometrics, 62:202-210.
Khoshhali M, Mahjub H, Saidijam M, Poorolajal J, Soltanian AR (2012). Predicting the survival time for diffuse large B-cell lymphoma using microarray data. J Mol Genet Med, 6:287-292.
| Files | ||
| Issue | Vol 45 No 2 (2016) | |
| Section | Original Article(s) | |
| Keywords | ||
| Survival analysis Microarray data Additive hazards model Variable selection Bladder cancer | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
