Identification of subtype‑specific prognostic signatures using Cox models with redundant gene elimination

Tian,Suyan

doi:10.3892/ol.2018.8418

Identification of subtype‑specific prognostic signatures using Cox models with redundant gene elimination

Authors:
- Suyan Tian
View Affiliations

Affiliations: Division of Clinical Research, The First Hospital of Jilin University, Changchun, Jilin 130021, P.R. China
Published online on: April 4, 2018 https://doi.org/10.3892/ol.2018.8418
Pages: 8545-8555
Copyright: © Tian . This is an open access article distributed under the terms of Creative Commons Attribution License.

Metrics: Total Views: 0 (Spandidos Publications: | PMC Statistics: )

Metrics: Total PDF Downloads: 0 (Spandidos Publications: | PMC Statistics: )

Cited By (CrossRef): 0 citations Loading Articles...

Abstract

Lung cancer (LC) is a leading cause of cancer‑associated mortalities worldwide. Adenocarcinoma (AC) and squamous cell carcinoma (SCC) account for ~70% of all cases of LC. Since AC and SCC are two distinct diseases, their corresponding prognostic genes associated with patient survival time are expected to be different. To date, only a few studies have distinguished patients with good prognosis from those with poor prognosis for each specific subtype. In the present study, the Cox filter model, a feature selection algorithm that identifies subtype‑specific prognostic genes to incorporate pathway information and eliminate redundant genes, was adopted. By applying the proposed model to data on non‑small cell lung cancer (NSCLC), it was demonstrated that both redundant gene elimination and search space restriction can improve the predictive capacity and the model stability of resulting prognostic gene signatures. To conclude, a pre‑filtering procedure that incorporates pathway information for screening likely irrelevant genes prior to complex downstream analysis is recommended. Furthermore, a feature selection algorithm that considers redundant gene elimination may be preferable to one without such a consideration.

View Figures

View References

1	Lemjabbar-Alaoui H, Hassan OU, Yang YW and Buchanan P: Lung cancer: Biology and treatment options. Biochim Biophys Acta. 1856:189–210. 2015.PubMed/NCBI
2	Lu C, Onn A and Vaporciyan A: Cancer of the lungHolland-Frei Cancer Medicine. Kufe DW, Pollock RE, Weichselbaum RR, Bast RC, Gansler TS, Holland JF and Frei E: 8th edition. People's Medical Publishing House; Shelton, CT: 2010
3	Pikor LA, Ramnarine VR, Lam S and Lam WL: Genetic alterations defining NSCLC subtypes and their therapeutic implications. Lung Cancer. 82:179–189. 2013. View Article : Google Scholar : PubMed/NCBI
4	Siegel R, Naishadham D and Jemal A: Cancer statistics, 2012. CA Cancer J Clin. 62:10–29. 2012. View Article : Google Scholar : PubMed/NCBI
5	Saeys Y, Inza I and Larrañaga P: A review of feature selection techniques in bioinformatics. Bioinformatics. 23:2507–2517. 2007. View Article : Google Scholar : PubMed/NCBI
6	Hira ZM and Gillies DF: A review of feature selection and feature extraction methods applied on microarray data. Adv Bioinformatics. 2015:1983632015. View Article : Google Scholar : PubMed/NCBI
7	Ben-Hamo R, Boue S, Martin F, Talikka M and Efroni S: Classification of lung adenocarcinoma and squamous cell carcinoma samples based on their gene expression profile in the sbv IMPROVER Diagnostic Signature Challenge. Syst Biom. 1:83–92. 2013.
8	Tian S and Suárez-fariñas M: Hierarchical-TGDR: Combining biological hierarchy with a regularization method for multi-class classification of lung cancer samples via high-throughput gene-expression data. Syst Biom. 1:93–102. 2013.
9	Tian S and Suárez-Fariñas M: Multi-TGDR: A regularization method for multi-class classification in microarray experiments. PLoS One. 8:e783022013. View Article : Google Scholar : PubMed/NCBI
10	Zhu CQ, Ding K, Strumpf D, Weir BA, Meyerson M, Pennell N, Thomas RK, Naoki K, Ladd-Acosta C, Liu N, et al: Prognostic and predictive gene signature for adjuvant chemotherapy in resected non-small-cell lung cancer. J Clin Oncol. 28:4417–4424. 2010. View Article : Google Scholar : PubMed/NCBI
11	Der SD, Sykes J, Pintilie M, Zhu CQ, Strumpf D, Liu N, Jurisica I, Shepherd FA and Tsao MS: Validation of a histology-independent prognostic gene signature for early-stage, non-small-cell lung cancer including stage IA patients. J Thorac Oncol. 9:59–64. 2014. View Article : Google Scholar : PubMed/NCBI
12	Zhao Q, Shi X, Xie Y, Huang J, Shia B and Ma S: Combining multidimensional genomic measurements for predicting cancer prognosis: Observations from TCGA. Brief Bioinform. 16:291–303. 2014. View Article : Google Scholar : PubMed/NCBI
13	Zhao SD, Parmigiani G, Huttenhower C and Waldron L: Más-o-menos: A simple sign averaging method for discrimination in genomic data analysis. Bioinformatics. 30:3062–3069. 2014. View Article : Google Scholar : PubMed/NCBI
14	Tian S: Classification and survial prediction for early-stage lung adenocarcinoma and squamous cell carcinoma patients. Oncol Lett. 14:5464–5470. 2017.PubMed/NCBI
15	Tian S: Identification of subtype-specific prognostic genes for early-stage lung adenocarcinoma and squamous cell carcinoma patients using an embedded feature selection algorithm. PLoS One. 10:e01346302015. View Article : Google Scholar : PubMed/NCBI
16	Tian S, Wang C and An MW: Test on existence of histology subtype-specific prognostic signatures among early stage lung adenocarcinoma and squamous cell carcinoma patients using a Cox-model based filter. Biol Direct. 10:152015. View Article : Google Scholar : PubMed/NCBI
17	Cox DR: Regression models and life-tables. J R Stat Soc B. 34:187–220. 1972.
18	Wang S, Nan B, Zhou N and Zhu J: Hierarchically penalized Cox regression with grouped variables. Biometrika. 96:307–322. 2009. View Article : Google Scholar
19	Breheny P and Hunag J: Penalized methods for bi-level variable selection. Stat Interface. 2:369–380. 2009. View Article : Google Scholar : PubMed/NCBI
20	Tian S, Wang C, Chang HH and Sun G: Identification of prognostic genes and gene sets for early-stage non-small cell lung cancer using bi-level selection methods. Sci Rep. 7:461642017. View Article : Google Scholar : PubMed/NCBI
21	Tian S, Chang HH and Wang C: Weighted-SAMGSR: Combining significance analysis of microarray-gene set reduction algorithm with pathway topology-based weights to select relevant genes. Biol Direct. 11:502016. View Article : Google Scholar : PubMed/NCBI
22	Johannes M, Brase JC, Fröhlich H, Gade S, Gehrmann M, Fälth M, Sültmann H and Beissbarth T: Integration of pathway knowledge into a reweighted recursive feature elimination approach for risk stratification of cancer patients. Bioinformatics. 26:2136–2144. 2010. View Article : Google Scholar : PubMed/NCBI
23	Chen L, Xuan J, Riggins RB, Clarke R and Wang Y: Identifying cancer biomarkers by network-constrained support vector machines. BMC Syst Biol. 5:1612011. View Article : Google Scholar : PubMed/NCBI
24	Sun H, Lin W, Feng R and Li H: Network-regularized high-dimensional Cox regression for analysis of genomic data. Stat Sin. 24:1433–1459. 2014.PubMed/NCBI
25	Sokolov A, Carlin DE, Paull EO, Baertsch R and Stuart JM: Pathway-based genomics prediction using generalized elastic net. PLoS Comput Biol. 12:e10047902016. View Article : Google Scholar : PubMed/NCBI
26	Morrison JL, Breitling R, Higham DJ and Gilbert DR: GeneRank: Using search engine technology for the analysis of microarray experiments. BMC Bioinformatics. 6:2332005. View Article : Google Scholar : PubMed/NCBI
27	McCall MN, Bolstad BM and Irizarry RA: Frozen robust multiarray analysis (fRMA). Biostatistics. 11:242–253. 2010. View Article : Google Scholar : PubMed/NCBI
28	Johnson WE, Li C and Rabinovic A: Adjusting batch effects in microarray expression data using empirical bayes methods. Biostatistics. 8:118–127. 2007. View Article : Google Scholar : PubMed/NCBI
29	Law CW, Chen Y, Shi W and Smyth GK: Voom: Precision weights unlock linear model analysis tools for RNA-seq read counts. Genome Biol. 15:R292014. View Article : Google Scholar : PubMed/NCBI
30	Smyth GK: Limma: Linear Models for Microarray Data. In Bioinformatics and Computational Biology Solutions Using R and Bioconductor. 397–420. 2005. View Article : Google Scholar
31	Gu J, Lu Y, Liu C and Lu H: Multiclass classification of sarcomas using pathway based feature selection method. J Theor Biol. 362:3–8. 2014. View Article : Google Scholar : PubMed/NCBI
32	Eng KH, Wang S, Bradley WH, Rader JS and Kendziorski C: Pathway-index models for construction of patient-specific risk profiles. Stat Med. 32:1524–1535. 2013. View Article : Google Scholar : PubMed/NCBI
33	Uno H, Cai T, Pencina MJ, D'Agostino RB and Wei LJ: On the C-statistics for evaluating overall adequacy of risk prediction procedures with censored survival data. Stat Med. 30:1105–1117. 2011.PubMed/NCBI
34	Laimighofer M, Krumsiek J, Buettner F and Theis FJ: Unbiased prediction and feature selection in high-dimensional survival regression. J Comput Biol. 23:279–290. 2016. View Article : Google Scholar : PubMed/NCBI
35	Tibshirani R: Regression shrinkage and selection via the Lasso. J Royal Statistical Society Series B (Methodological). 58:267–288. 1996.
36	Hoffman P, Grinstein G, Marx K, Grosse I and Stanley E: DNA visual and analytic data mining. Proceedings Vis'97. (cat no. 97CB36155). 1997.
37	Ge R, Zhou M, Luo Y, Meng Q, Mai G, Ma D, Wang G and Zhou F: McTwo: A two-step feature selection algorithm based on maximal information coefficient. BMC Bioinformatics. 17:1422016. View Article : Google Scholar : PubMed/NCBI
38	Chu W, Li R and Reimherr M: Feature screening fo time-varying coefficient models with ultrahigh dimensional longitudinal data. Ann Appl Stat. 10:596–617. 2016. View Article : Google Scholar : PubMed/NCBI
39	Yang G, Yu Y, Li R and Buu A: Feature screening in ultrahigh dimensional Cox's model. Stat Sin. 26:881–901. 2016.PubMed/NCBI