A model for predicting prognosis in patients with esophageal squamous cell carcinoma based on joint representation learning

Yu,Jun; Wu,Xiaoliu; Lv,Min; Zhang,Yuanying; Zhang,Xiaomei; Li,Jintian; Zhu,Ming; Huang,Jianfeng; Zhang,Qin

doi:10.3892/ol.2020.12250

A model for predicting prognosis in patients with esophageal squamous cell carcinoma based on joint representation learning

Authors:
- Jun Yu
- Xiaoliu Wu
- Min Lv
- Yuanying Zhang
- Xiaomei Zhang
- Jintian Li
- Ming Zhu
- Jianfeng Huang
- Qin Zhang
View Affiliations

Affiliations: Department of Molecular Biology, Jiangsu Cancer Hospital and Jiangsu Institute of Cancer Research and The Affiliated Cancer Hospital of Nanjing Medical University, Xuanwu, Nanjing 210009, P.R. China, Department of Pathology, Jiangsu Cancer Hospital and Jiangsu Institute of Cancer Research and The Affiliated Cancer Hospital of Nanjing Medical University, Xuanwu, Nanjing 210009, P.R. China, Department of Thoracic Surgery, Jiangsu Cancer Hospital and Jiangsu Institute of Cancer Research and The Affiliated Cancer Hospital of Nanjing Medical University, Xuanwu, Nanjing 210009, P.R. China
Published online on: October 29, 2020 https://doi.org/10.3892/ol.2020.12250
Article Number: 387
Copyright: © Yu 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

Esophageal squamous cell carcinoma (ESCC) is one of the deadliest cancer types with a poor prognosis due to the lack of symptoms in the early stages and a delayed diagnosis. The present study aimed to identify the risk factors significantly associated with prognosis and to search for novel effective diagnostic modalities for patients with early‑stage ESCC. mRNA and methylation data of patients with ESCC and the corresponding clinical information were downloaded from The Cancer Genome Atlas (TCGA) database, and the representation features were screened using deep learning autoencoder. The univariate Cox regression model was used to select the prognosis‑related features from the representation features. K‑means clustering was used to cluster the TCGA samples. Support vector machine classifier was constructed based on the top 75 features mostly associated with the risk subgroups obtained from K‑means clustering. Two ArrayExpress datasets were used to verify the reliability of the obtained risk subgroups. The differentially expressed genes and methylation genes (DEGs and DMGs) between the risk subgroups were analyzed, and pathway enrichment analysis was performed. A total of 500 representation features were produced. Using K‑means clustering, the TCGA samples were clustered into two risk subgroups with significantly different overall survival rates. Joint multimodal representation strategy, which showed a good model fitness (C‑index=0.760), outperformed early‑fusion autoencoder strategy. The joint representation learning‑based classification model had good robustness. A total of 1,107 DEGs and 199 DMGs were screened out between the two risk subgroups. The DEGs were involved in 70 pathways, the majority of which were correlated with metastasis and proliferation of various cancer types, including cytokine‑cytokine receptor interaction, cell adhesion molecules PPAR signaling pathway, pathways in cancer, transcriptional misregulation in cancer and ECM‑receptor interaction pathways. The two survival subgroups obtained via the joint representation learning‑based model had good robustness, and had prognostic significance for patients with ESCC.

View Figures

View References

1	Lin DC, Wang MR and Koeffler HP: Genomic and epigenomic aberrations in esophageal squamous cell carcinoma and implications for patients. Gastroenterology. 154:374–389. 2018. View Article : Google Scholar : PubMed/NCBI
2	Zhao J, He YT, Zheng RS, Zhang SW and Chen WQ: Analysis of esophageal cancer time trends in China, 1989–2008. Asian Pac J Cancer Prev. 13:4613–4617. 2012. View Article : Google Scholar : PubMed/NCBI
3	Liang H, Fan JH and Qiao YL: Epidemiology, etiology, and prevention of esophageal squamous cell carcinoma in China. Cancer Biol Med. 14:33–41. 2017. View Article : Google Scholar : PubMed/NCBI
4	Wang GQ, Jiao GG, Chang FB, Fang WH, Song JX, Lu N, Lin DM, Xie YQ and Yang L: Long-term results of operation for 420 patients with early squamous cell esophageal carcinoma discovered by screening. Ann Thorac Surg. 77:1740–1744. 2004. View Article : Google Scholar : PubMed/NCBI
5	Abnet CC, Arnold M and Wei WQ: Epidemiology of esophageal squamous cell carcinoma. Gastroenterology. 154:360–373. 2018. View Article : Google Scholar : PubMed/NCBI
6	Gao YB, Chen ZL, Li JG, Hu XD, Shi XJ, Sun ZM, Zhang F, Zhao ZR, Li ZT, Liu ZY, et al: Genetic landscape of esophageal squamous cell carcinoma. Nat Genet. 46:1097–1102. 2014. View Article : Google Scholar : PubMed/NCBI
7	Baylin SB: DNA methylation and gene silencing in cancer. Nat Clin Pract Oncol. 2 (Suppl 1):S4–S11. 2005. View Article : Google Scholar : PubMed/NCBI
8	Yamada N, Yasui K, Dohi O, Gen Y, Tomie A, Kitaichi T, Iwai N, Mitsuyoshi H, Sumida Y, Moriguchi M, et al: Genome-wide DNA methylation analysis in hepatocellular carcinoma. Oncol Rep. 35:2228–2236. 2016. View Article : Google Scholar : PubMed/NCBI
9	Riley RD, Hayden JA, Steyerberg EW, Moons KG, Abrams K, Kyzas PA, Malats N, Briggs A, Schroter S, Altman DG, et al: Prognosis research strategy (PROGRESS) 2: Prognostic factor research. PLoS Med. 10:e10013802013. View Article : Google Scholar : PubMed/NCBI
10	Iida M, Ikeda F, Hata J, Hirakawa Y, Ohara T, Mukai N, Yoshida D, Yonemoto K, Esaki M, Kitazono T, et al: Development and validation of a risk assessment tool for gastric cancer in a general Japanese population. Gastric Cancer. 21:383–390. 2018. View Article : Google Scholar : PubMed/NCBI
11	Pavlou M, Ambler G, Seaman SR, Guttmann O, Elliott P, King M and Omar RZ: How to develop a more accurate risk prediction model when there are few events. BMJ. 351:h38682015. View Article : Google Scholar : PubMed/NCBI
12	Hoffman MM, Ernst J, Wilder SP, Kundaje A, Harris RS, Libbrecht M, Giardine B, Ellenbogen PM, Bilmes JA, Birney E, et al: Integrative annotation of chromatin elements from ENCODE data. Nucleic Acids Res. 41:827–841. 2013. View Article : Google Scholar : PubMed/NCBI
13	Bengio Y: Learning Deep Architectures for AI. Foundations and Trends^® in Machine Learning, 2009. simplehttps://doi.org/10.1561/2200000006
14	Papazafeiropoulos G, Vu QV, Truong VH, Luong MC and Pham VT: Prediction of buckling coefficient of stiffened plate girders using deep learning algorithm. CIGOS 2019, Innovation for Sustainable Infrastructure Springer. Ha-Minh C, Dao D, Benboudjema F, Derrible S, Huynh D and Tang A: Lecture Notes in Civil Engineering. Vol 54. Springer; Singapore: simplehttps://doi.org/10.1007/978-981-15-0802-8_183
15	Chaudhary K, Poirion OB, Lu L and Garmire LX: Deep learning-based multi-omics integration robustly predicts survival in liver cancer. Clin Cancer Res. 24:1248–1259. 2018. View Article : Google Scholar : PubMed/NCBI
16	Poirion OB, Chaudhary K, Huang S and Garmire LX: Multi-omics-based pan-cancer prognosis prediction using an ensemble of deep-learning and machine-learning models. medRxiv. doi: https://doi.org/10.1101/19010082.
17	Xie G, Dong C, Kong Y, Zhong JF, Li M and Wang K: Group lasso regularized deep learning for cancer prognosis from multi-omics and clinical features. Genes (Basel). 10:2402019. View Article : Google Scholar
18	Lu T, Chen D, Wang Y, Sun X, Li S, Miao S, Wo Y, Dong Y, Leng X, Du W and Jiao W: Identification of DNA methylation-driven genes in esophageal squamous cell carcinoma: A study based on the cancer genome atlas. Cancer Cell Int. 19:522019. View Article : Google Scholar : PubMed/NCBI
19	Hansen KD: IlluminaHumanMethylation450kanno. ilmn12. hg19: Annotation for illumina's 450k methylation arrays. R package version 0.2 12016. doi: 10.18129/B9.bioc.IlluminaHumanMethylation450kanno.ilmn12.hg19.
20	Hastie T, Tibshirani R, Narasimhan B and Chu G: Impute: Impute: Imputation for microarray data. R package version. 2019.
21	Malika C, Ghazzali N, Boiteau V and Niknafs A: NbClust: An R package for determining the relevant number of clusters in a data set. J Stat Software. 61:1–36. 2014.
22	Schröder MS, Culhane AC, Quackenbush J and Haibe-Kains B: Survcomp: An R/Bioconductor package for performance assessment and comparison of survival models. Bioinformatics. 27:3206–3208. 2011. View Article : Google Scholar : PubMed/NCBI
23	Becker N, Werft W, Toedt G, Lichter P and Benner A: PenalizedSVM: A R-package for feature selection SVM classification. Bioinformatics. 25:1711–1712. 2009. View Article : Google Scholar : PubMed/NCBI
24	Love MI, Huber W and Anders S: Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2. Genome Biol. 15:5502014. View Article : Google Scholar : PubMed/NCBI
25	Ritchie ME, Phipson B, Wu D, Hu Y, Law CW, Shi W and Smyth GK: limma powers differential expression analyses for RNA-sequencing and microarray studies. Nucleic Acids Res. 43:e472015. View Article : Google Scholar : PubMed/NCBI
26	Brembilla-Perrot B, de la Chaise Terrier A, Skeik L, Cherrier F and Pernot C: Factors predicting the response to an antiarrhythmic during an electrophysiologic study for ventricular tachycardia. Arch Mal Coeur Vaiss. 80:1497–1503. 1987.(In French). PubMed/NCBI
27	Chen J, Kwong DL, Cao T, Hu Q, Zhang L, Ming X, Chen J, Fu L and Guan X: Esophageal squamous cell carcinoma (ESCC): Advance in genomics and molecular genetics. Dis Esophagus. 28:84–89. 2015. View Article : Google Scholar : PubMed/NCBI
28	Song G, Xu J, He L, Sun X, Xiong R, Luo Y, Hu X, Zhang R, Yue Q, Liu K and Feng G: Systematic profiling identifies PDLIM2 as a novel prognostic predictor for oesophageal squamous cell carcinoma (ESCC). J Cell Mol Med. 23:5751–5761. 2019. View Article : Google Scholar : PubMed/NCBI
29	Wang Y, Yao H and Zhao S: Auto-encoder based dimensionality reduction. Neurocomputing. 184:232–242. 2016. View Article : Google Scholar
30	Xiao Y, Wu J, Lin Z and Zhao X: A semi-supervised deep learning method based on stacked sparse auto-encoder for cancer prediction using RNA-seq data. Comput Methods Programs Biomed. 166:99–105. 2018. View Article : Google Scholar : PubMed/NCBI
31	Qiao Y, Luo X, Li C, Tian H and Ma J: Heterogeneous graph-based joint representation learning for users and POIs in location-based social network. Information Processing Management. 57:1021512020. View Article : Google Scholar
32	Wang F, Yan Z, Lv J, Xin J, Dang Y, Sun X, An Y, Qi Y, Jiang Q, Zhu W, et al: Gene expression profiling reveals distinct molecular subtypes of esophageal squamous cell carcinoma in Asian populations. Neoplasia. 21:571–581. 2019. View Article : Google Scholar : PubMed/NCBI
33	Cancer Genome Atlas Research Network; Analysis Working Group: Asan University; BC Cancer Agency; Brigham and Women's Hospital; Broad Institute; Brown University; Case Western Reserve University; Dana-Farber Cancer Institute; Duke University, et al, . Integrated genomic characterization of oesophageal carcinoma. Nature. 541:169–174. 2017. View Article : Google Scholar : PubMed/NCBI
34	Liu W, Snell JM, Jeck WR, Hoadley KA, Wilkerson MD, Parker JS, Patel N, Mlombe YB, Mulima G, Liomba NG, et al: Subtyping sub-saharan esophageal squamous cell carcinoma by comprehensive molecular analysis. JCI Insight. 1:e887552016. View Article : Google Scholar : PubMed/NCBI
35	Albelda S: Role of integrins and other cell adhesion molecules in tumor progression and metastasis. Lab Invest. 68:4–17. 1993.PubMed/NCBI
36	Chen YZ, Xue JY, Chen CM, Yang BL, Xu QH, Wu F, Liu F, Ye X, Meng X, Liu GY, et al: PPAR signaling pathway may be an important predictor of breast cancer response to neoadjuvant chemotherapy. Cancer Chemother Pharmacol. 70:637–644. 2012. View Article : Google Scholar : PubMed/NCBI
37	Dong C, Wang X, Xu H, Zhan X, Ren H, Liu Z, Liu G and Liu L: Identification of a cytokine-cytokine receptor interaction gene signature for predicting clinical outcomes in patients with colorectal cancer. Int J Clin Exp Med. 10:9009–9018. 2017.
38	Ertel A, Verghese A, Byers SW, Ochs M and Tozeren A: Pathway-specific differences between tumor cell lines and normal and tumor tissue cells. Mol Cancer. 5:552006. View Article : Google Scholar : PubMed/NCBI