Establishment of a SVM classifier to predict recurrence of ovarian cancer

Zhou,Jinting; Li,Lin; Wang,Liling; Li,Xiaofang; Xing,Hui; Cheng,Li

doi:10.3892/mmr.2018.9362

Establishment of a SVM classifier to predict recurrence of ovarian cancer

Authors:
- Jinting Zhou
- Lin Li
- Liling Wang
- Xiaofang Li
- Hui Xing
- Li Cheng
View Affiliations

Affiliations: Department of Obstetrics and Gynecology, Xiangyang Central Hospital Affiliated to The Hubei University of Arts and Science, Xiangyang, Hubei 441021, P.R. China
Published online on: August 8, 2018 https://doi.org/10.3892/mmr.2018.9362
Pages: 3589-3598
Copyright: © Zhou et al. 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

Gene expression data using retrieved ovarian cancer (OC) samples were used to identify genes of interest and a support vector machine (SVM) classifier was subsequently established to predict the recurrence of OC. Three datasets (GSE17260, GSE44104 and GSE51088) investigating OC gene expression were downloaded from the Gene Expression Omnibus. Differentially expressed genes (DEGs) in samples from patients with non‑recurrent and recurrent OC were revealed via a homogeneity test and quality control analysis. A protein‑protein interaction (PPI) network was subsequently established for the DEGs using data from Biological General Repository for Interaction Datasets, Human Protein Reference Database and Database of Interacting Proteins. Degrees of interaction and betweenness centrality (BC) scores were calculated for each node in the PPI network. The top 100 genes ranked by BC scores were selected to identify feature genes via recursive feature elimination using the GSE17260 dataset. Following this, a SVM classifier was constructed and further validated using the GSE44104 and GSE51088 datasets and independent gene expression data obtained from the Cancer Genome Atlas (TCGA). A total of 639 DEGs were identified from the three gene expression datasets, and a PPI network including 249 nodes and 354 edges was constructed. A SVM classifier consisting of 39 feature genes (including cullin 3, mouse double minute 2 homolog, aurora kinase A, WW domain containing oxidoreducatase, large tumor suppressor kinase 2, sirtuin 6, staphylococcal nuclease and tudor domain containing 1, leucine rich repeats and immunoglobulin like domains 1 and aurora kinase 1 interacting protein 1) was subsequently constructed. The prediction accuracies of the SVM classifier for GSE17260, GSE44104 and GSE51088 datasets as well as data downloaded from TCGA were revealed to be 92.7, 93.3, 96.6 and 90.4%, respectively. Furthermore, the results of the present study revealed that patients with predicted non‑recurrent OC survived significantly longer compared with the patients with predicted recurrent OC (P=6.598x10‑6). A SVM classifier consisting of 39 feature genes was established for predicting the recurrence and prognosis of OC. Therefore, the results of the present study suggested that the 39 feature genes may serve important roles in the development of OC and may represent therapeutic biomarkers of OC.

View Figures

View References

1	Howlader N, Noone AM, Krapcho M, Garshell J, Miller D, Altekruse SF, Kosary CL, Yu M, Ruhl J, Tatalovich Z, et al: SEER Cancer Statistics Review 1975–2012. National Cancer Institute; Bethesda, MD: 2015, https://seer.cancer.gov/archive/csr/1975_2012/November 18–2015
2	Davidson B and Tropé CG: Ovarian cancer: Diagnostic, biological and prognostic aspects. Womens Health (Lond). 10:519–533. 2014. View Article : Google Scholar : PubMed/NCBI
3	Gloss BS and Samimi G: Epigenetic biomarkers in epithelial ovarian cancer. Cancer Lett. 342:257–263. 2014. View Article : Google Scholar : PubMed/NCBI
4	Leung F, Diamandis EP and Kulasingam V: Ovarian cancer biomarkers: Current state and future implications from high-throughput technologies. Adv Clin Chem. 66:25–77. 2014. View Article : Google Scholar : PubMed/NCBI
5	Au KK, Josahkian JA, Francis JA, Squire JA and Koti M: Current state of biomarkers in ovarian cancer prognosis. Future Oncol. 11:3187–3195. 2015. View Article : Google Scholar : PubMed/NCBI
6	Huo J, Hu J, Liu G, Cui Y and Ju Y: Elevated serum interleukin-37 level is a predictive biomarker of poor prognosis in epithelial ovarian cancer patients. Arch Gynecol Obstet. 295:459–465. 2017. View Article : Google Scholar : PubMed/NCBI
7	Masoumi-Moghaddam S, Amini A, Wei AQ, Robertson G and Morris DL: Sprouty 2 protein, but not Sprouty 4, is an independent prognostic biomarker for human epithelial ovarian cancer. Int J Cancer. 137:560–570. 2015. View Article : Google Scholar : PubMed/NCBI
8	Lee JM, Trepel JB, Choyke P, Cao L, Sissung T, Houston N, Yu M, Figg WD, Turkbey IB, Steinberg SM, et al: CECs and IL-8 have prognostic and predictive utility in patients with recurrent platinum-sensitive ovarian cancer: Biomarker correlates from the randomized phase-2 trial of olaparib and cediranib compared with olaparib in recurrent platinum-sensitive ovarian cancer. Front Oncol. 5:1232015. View Article : Google Scholar : PubMed/NCBI
9	Feng Y, He F, Wu H, Huang H, Zhang L, Han X and Liu J: GOLPH3L is a novel prognostic biomarker for epithelial ovarian cancer. J Cancer. 6:893–900. 2015. View Article : Google Scholar : PubMed/NCBI
10	Roque DM, Buza N, Glasgow M, Bellone S, Bortolomai I, Gasparrini S, Cocco E, Ratner E, Silasi DA, Azodi M, et al: Class III β-tubulin overexpression within the tumor microenvironment is a prognostic biomarker for poor overall survival in ovarian cancer patients treated with neoadjuvant carboplatin/paclitaxel. Clin Exp Metastasis. 31:101–110. 2014. View Article : Google Scholar : PubMed/NCBI
11	Penzvalto Z, Lanczky A, Lenart J, Meggyesházi N, Krenács T, Szoboszlai N, Denkert C, Pete I and Győrffy B: MEK1 is associated with carboplatin resistance and is a prognostic biomarker in epithelial ovarian cancer. BMC Cancer. 14:8372014. View Article : Google Scholar : PubMed/NCBI
12	Abdel-Fatah TM, Russell R, Albarakati N, Maloney DJ, Dorjsuren D, Rueda OM, Moseley P, Mohan V, Sun H, Abbotts R, et al: Genomic and protein expression analysis reveals flap endonuclease 1 (FEN1) as a key biomarker in breast and ovarian cancer. Mol Oncol. 8:1326–1338. 2014. View Article : Google Scholar : PubMed/NCBI
13	Wei W, Mok SC, Oliva E, Kim SH, Mohapatra G and Birrer MJ: FGF18 as a prognostic and therapeutic biomarker in ovarian cancer. J Clin Invest. 123:4435–4448. 2013. View Article : Google Scholar : PubMed/NCBI
14	Liu T, Gao H, Chen X, Lou G, Gu L, Yang M, Xia B and Yin H: TNFAIP8 as a predictor of metastasis and a novel prognostic biomarker in patients with epithelial ovarian cancer. Br J Cancer. 109:1685–1692. 2013. View Article : Google Scholar : PubMed/NCBI
15	Yoshihara K, Tajima A, Yahata T, Kodama S, Fujiwara H, Suzuki M, Onishi Y, Hatae M, Sueyoshi K, Fujiwara H, et al: Gene expression profile for predicting survival in advanced-stage serous ovarian cancer across two independent datasets. PLoS One. 5:e96152010. View Article : Google Scholar : PubMed/NCBI
16	Wu YH, Chang TH, Huang YF, Huang HD and Chou CY: COL11A1 promotes tumor progression and predicts poor clinical outcome in ovarian cancer. Oncogene. 33:3432–3440. 2014. View Article : Google Scholar : PubMed/NCBI
17	Karlan BY, Dering J, Walsh C, Orsulic S, Lester J, Anderson LA, Ginther CL, Fejzo M and Slamon D: POSTN/TGFBI-associated stromal signature predicts poor prognosis in serous epithelial ovarian cancer. Gynecol Oncol. 132:334–342. 2014. View Article : Google Scholar : PubMed/NCBI
18	Liu WM, Mei R, Di X, Ryder TB, Hubbell E, Dee S, Webster TA, Harrington CA, Ho MH, Baid J and Smeekens SP: Analysis of high density expression microarrays with signed-rank call algorithms. Bioinformatics. 18:1593–1599. 2002. View Article : Google Scholar : PubMed/NCBI
19	R Development Core Team, . R: a language and environment for statistical computing. the R Foundation for Statistical Computing; Vienna: 2016
20	de Souto MC, Jaskowiak PA and Costa IG: Impact of missing data imputation methods on gene expression clustering and classification. BMC Bioinformatics. 16:642015. View Article : Google Scholar : PubMed/NCBI
21	Affymetrix^® Microarray Suite. User's Guide. Version 5.0. Affymetrix, Inc.; Santa Clara: 2001
22	Kang DD, Sibille E, Kaminski N and Tseng GC: MetaQC: Objective quality control and inclusion/exclusion criteria for genomic meta-analysis. Nucleic Acids Res. 40:e152012. View Article : Google Scholar : PubMed/NCBI
23	Qi C, Hong L, Cheng Z and Yin Q: Identification of metastasis-associated genes in colorectal cancer using metaDE and survival analysis. Oncol Lett. 11:568–574. 2016. View Article : Google Scholar : PubMed/NCBI
24	Shannon PI, Markiel A, Ozier O, Baliga NS, Wang JT, Ramage D, Amin N, Schwikowski B and Ideker T: Cytoscape: A software environment for integrated models of biomolecular interaction networks. Genome Res. 13:2498–2504. 2003. View Article : Google Scholar : PubMed/NCBI
25	Goh KI, Oh E, Jeong H, Kahng B and Kim D: Classification of scale-free networks. Proc Natl Acad Sci USA. 99:pp. 12583–12588. 2002; View Article : Google Scholar : PubMed/NCBI
26	Qureshi MN, Min B, Jo HJ and Lee B: Multiclass classification for the differential diagnosis on the ADHD subtypes using recursive feature elimination and hierarchical extreme learning machine: Structural MRI study. PLoS One. 11:e01606972016. View Article : Google Scholar : PubMed/NCBI
27	Tomczak K, Czerwińska P and Wiznerowicz M: The cancer genome atlas (TCGA): An immeasurable source of knowledge. Contemp Oncol (Pozn). 19:A68–A77. 2015.PubMed/NCBI
28	Sporn MB and Liby KT: NRF2 and cancer: The good, the bad and the importance of context. Nat Rev Cancer. 12:564–571. 2012. View Article : Google Scholar : PubMed/NCBI
29	Liao H, Zhou Q, Zhang Z, Wang Q, Sun Y, Yi X and Feng Y: NRF2 is overexpressed in ovarian epithelial carcinoma and is regulated by gonadotrophin and sex-steroid hormones. Oncol Rep. 27:1918–1924. 2012.PubMed/NCBI
30	Martinez VD, Vucic EA, Thu KL, Pikor LA, Hubaux R and Lam WL: Unique pattern of component gene disruption in the NRF2 inhibitor KEAP1/CUL3/RBX1 E3-ubiquitin ligase complex in serous ovarian cancer. Biomed Res Int. 2014:1594592014. View Article : Google Scholar : PubMed/NCBI
31	Ginath S, Menczer J, Friedmann Y, Aingorn H, Aviv A, Tajima K, Dantes A, Glezerman M, Vlodavsky I and Amsterdam A: Expression of heparanase, Mdm2, and erbB2 in ovarian cancer. Int J Oncol. 18:1133–1144. 2001.PubMed/NCBI
32	Mi RR and Ni H: MDM2 sensitizes a human ovarian cancer cell line. Gynecol Oncol. 90:238–244. 2003. View Article : Google Scholar : PubMed/NCBI
33	Mir R, Tortosa A, Martinez-soler F, Vidal A, Condom E, Pérez-Perarnau A, Ruiz-Larroya T, Gil J and Giménez-Bonafé P: Mdm2 antagonists induce apoptosis and synergize with cisplatin overcoming chemoresistance in TP53 wild-type ovarian cancer cells. Int J Cancer. 132:1525–1536. 2013. View Article : Google Scholar : PubMed/NCBI
34	Yang F, Guo X, Yang G, Rosen DG and Liu J: AURKA and BRCA2 expression highly correlate with prognosis of endometriofid ovarian carcinoma. Mod Pathol. 24:836–845. 2011. View Article : Google Scholar : PubMed/NCBI
35	Do TV, Xiao F, Bickel LE, Klein-Szanto AJ, Pathak HB, Hua X, Howe C, O'Brien SW, Maglaty M, Ecsedy JA, et al: Aurora kinase A mediates epithelial ovarian cancer cell migration and adhesion. Oncogene. 33:539–549. 2014. View Article : Google Scholar : PubMed/NCBI
36	Gourley C, Paige AJW, Taylor KJ, Scott D, Francis NJ, Rush R, Aldaz CM, Smyth JF and Gabra H: WWOX mRNA expression profile in epithelial ovarian cancer supports the role of WWOX variant 1 as a tumour suppressor, although the role of variant 4 remains unclear. Int J Oncol. 26:1681–1689. 2005.PubMed/NCBI
37	Gourley C, Paige AJ, Taylor KJ, Ward C, Kuske B, Zhang J, Sun M, Janczar S, Harrison DJ, Muir M, et al: WWOX gene expression abolishes ovarian cancer tumorigenicity in vivo and decreases attachment to fibronectin via integrin alpha3. Cancer Res. 69:4835–4842. 2009. View Article : Google Scholar : PubMed/NCBI
38	Yan H, Tong J, Lin X, Han Q and Huang H: Effect of the WWOX gene on the regulation of the cell cycle and apoptosis in human ovarian cancer stem cells. Mol Med Rep. 12:1783–1788. 2015. View Article : Google Scholar : PubMed/NCBI
39	Feng S, Pan W, Jin Y and Zheng J: MiR-25 promotes ovarian cancer proliferation and motility by targeting LATS2. Tumour Biol. 35:12339–12344. 2014. View Article : Google Scholar : PubMed/NCBI
40	Xia Y and Gao Y: MicroRNA-181b promotes ovarian cancer cell growth and invasion by targeting LATS2. Biochem Biophys Res Commun. 447:446–451. 2014. View Article : Google Scholar : PubMed/NCBI
41	Zhang J, Yin XJ, Xu CJ, Ning YX, Chen M, Zhang H, Chen SF and Yao LQ: The histone deacetylase SIRT6 inhibits ovarian cancer cell proliferation via down-regulation of Notch 3 expression. Eur Rev Med Pharmacol Sci. 19:818–824. 2015.PubMed/NCBI
42	Zhang G, Liu Z, Qin S and Li K: Decreased expression of SIRT6 promotes tumor cell growth correlates closely with poor prognosis of ovarian cancer. Eur J Gynaecol Oncol. 36:629–632. 2015. View Article : Google Scholar : PubMed/NCBI
43	Lindquist D, Kvarnbrink S, Henriksson R and Hedman H: LRIG and cancer prognosis. Acta Oncol. 53:1135–1142. 2014. View Article : Google Scholar : PubMed/NCBI
44	Yang H, Yao J, Yin J and Wei X: Decreased LRIG1 in human ovarian cancer cell SKOV3 upregulates MRP-1 and contributes to the chemoresistance of VP16. Cancer Biother Radiopharm. 31:125–132. 2016. View Article : Google Scholar : PubMed/NCBI
45	Lim SK and Gopalan G: Aurora-A kinase interacting protein 1 (AURKAIP1) promotes Aurora-A degradation through an alternative ubiquitin-independent pathway. Biochem J. 403:119–127. 2007. View Article : Google Scholar : PubMed/NCBI
46	Yu L, Liu X, Cui K, Di Y, Xin L, Sun X, Zhang W, Yang X, Wei M, Yao Z and Yang J: SND1 acts downstream of TGFβ1 and upstream of Smurf1 to promote breast cancer metastasis. Cancer Res. 75:1275–1286. 2015. View Article : Google Scholar : PubMed/NCBI
47	Wang N, Du X, Zang L, Song N, Yang T, Dong R, Wu T, He X and Lu J: Prognostic impact of metadherin–SND1 interaction in colon cancer. Mol Biol Rep. 39:10497–10504. 2012. View Article : Google Scholar : PubMed/NCBI
48	Cappellari M, Bielli P, Paronetto MP, Ciccosanti F, Fimia GM, Saarikettu J, Silvennoinen O and Sette C: The transcriptional co-activator SND1 is a novel regulator of alternative splicing in prostate cancer cells. Oncogene. 33:3794–3802. 2014. View Article : Google Scholar : PubMed/NCBI