Bulletin of Mathematical Biology

, Volume 80, Issue 8, pp 2124–2136 | Cite as

Sparse Representation-Based Patient-Specific Diagnosis and Treatment for Esophageal Squamous Cell Carcinoma

  • Bin Huang
  • Ning Zhong
  • Lili Xia
  • Guiping Yu
  • Hongbao Cao
Original Article


Precision medicine and personalized treatment have attracted attention in recent years. However, most genetic medicines mainly target one genetic site, while complex diseases like esophageal squamous cell carcinoma (ESCC) usually present heterogeneity that involves variations of many genetic markers. Here, we seek an approach to leverage genetic data and ESCC knowledge data to forward personalized diagnosis and treatment for ESCC. First, 851 ESCC-related gene markers and their druggability were studied through a comprehensive literature analysis. Then, a sparse representation-based variable selection (SRVS) was employed for patient-specific genetic marker selection using gene expression datasets. Results showed that the SRVS method could identify a unique gene vector for each patient group, leading to significantly higher classification accuracies compared to randomly selected genes (100, 97.17, 100, 100%; permutation p values: 0.0032, 0.0008, 0.0004, and 0.0008). The SRVS also outperformed an ANOVA-based gene selection method in terms of the classification ratio. The patient-specific gene markers are targets of ESCC effective drugs, providing specific guidance for medicine selection. Our results suggest the effectiveness of integrating previous database utilizing SRVS in assisting personalized medicine selection and treatment for ESCC.


Esophageal squamous cell carcinoma Sparse representation Gene selection 



We would like to thank Rachel Amey from University of Delaware for her contribution to the English writing of the manuscript. This study is partly supported by non-small cell lung cancer research funding, Jiangsu Provincial Planning Commission; by clinical diagnosis and treatment of small lung lesions and normative research, Wuxi City Health Planning Commission, MS201625; and by 2017 Fifth Provincial ‘333 Project’ Research Project.

Compliance with Ethical Standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. Abu-Farsakh S, Wu T, Lalonde A et al (2017) High expression of Claudin-2 in esophageal carcinoma and precancerous lesions is significantly associated with the bile salt receptors VDR and TGR5. BMC Gastroenterol 17(1):33CrossRefGoogle Scholar
  2. Ando T, Ishiguro H, Kuwabara Y et al (2008) Relationship between expression of 5-fluorouracil metabolic enzymes and 5-fluorouracil sensitivity in esophageal carcinoma cell lines. Dis Esophagus 21(1):15–20CrossRefGoogle Scholar
  3. Cao H, Duan J, Lin D et al (2014) Sparse representation based biomarker selection for schizophrenia with integrated analysis of fMRI and SNPs. Neuroimage 102:220–228CrossRefGoogle Scholar
  4. Chen X, Huang L (2017) LRSSLMDA: Laplacian regularized sparse subspace learning for MiRNA–disease association prediction. PLoS Comput Biol 13(12):e1005912. CrossRefGoogle Scholar
  5. Chen X, Yan GY (2013) Novel human lncRNA–disease association inference based on lncRNA expression profiles. Bioinformatics 29(20):2617–2624. CrossRefGoogle Scholar
  6. Chen X, Xie D, Zhao Q, You ZH (2017a) MicroRNAs and complex diseases: from experimental results to computational models. Brief Bioinform. Google Scholar
  7. Chen X, Yan CC, Zhang X, You ZH (2017b) Long non-coding RNAs and complex diseases: from experimental results to computational models. Brief Bioinform 18(4):558–576. Google Scholar
  8. Chen YB, Liao XY, Zhang JB et al (2017c) ADAR2 functions as a tumor suppressor via editing IGFBP7 in esophageal squamous cell carcinoma. Int J Oncol 50(2):622–630CrossRefGoogle Scholar
  9. Chen X, Huang L, Xie D, Zhao Q (2018) EGBMMDA: extreme gradient boosting machine for MiRNA–disease association prediction. Cell Death Dis 9(1):3. CrossRefGoogle Scholar
  10. Davis G, Mallat S, Avellaneda M (1997) Greedy adaptive approximation. J Constr Approx 13(1):57–98CrossRefzbMATHGoogle Scholar
  11. Donoho DL, Tsaig Y (2008) Fast solution of L1-norm minimization problems when the solution may be sparse. IEEE Trans Inf Theory 54:4789–4812CrossRefzbMATHGoogle Scholar
  12. Fu L, Qin YR, Xie D, Chow HY, Ngai SM, Kwong DL, Li Y, Guan XY (2007) Identification of alpha-actinin 4 and 67 kDa laminin receptor as stage-specific markers in esophageal cancer via proteomic approaches. Cancer 110(12):2672–2681CrossRefGoogle Scholar
  13. Gan SY, Zhong XY, Xie SM et al (2010) Expression and significance of tumor drug resistance related proteins and beta-catenin in esophageal squamous cell carcinoma. Chin J Cancer 29(3):300–305CrossRefGoogle Scholar
  14. Gao Y, Hu N, Han XY et al (2011) Risk factors for esophageal and gastric cancers in Shanxi Province, China: a case-control study. Cancer Epidemiol 35(6):e91-9CrossRefGoogle Scholar
  15. Hara H, Tahara M, Daiko H et al (2013) Phase II feasibility study of preoperative chemotherapy with docetaxel, cisplatin, and fluorouracil for esophageal squamous cell carcinoma. Cancer Sci 104(11):1455–1460CrossRefGoogle Scholar
  16. Hiratsuka J, Kodama A, Imajo Y et al (1988) A case of triple cancer–gastric, esophageal and hepatocellular carcinoma. Gan No Rinsho 34(6):807–813Google Scholar
  17. Kaneko K, Yano T, Minashi K et al (2013) Treatment strategy for superficial pharyngeal squamous cell carcinoma synchronously combined with esophageal cancer. Oncology 84(1):57–64CrossRefGoogle Scholar
  18. Lam KY, Tsao SW, Zhang D et al (1997) Prevalence and predictive value of p53 mutation in patients with esophageal squamous cell carcinomas: a prospective clinico-pathological study and survival analysis of 70 patients. Int J Cancer 74:212–219CrossRefGoogle Scholar
  19. Law SY, Fok M, Cheng SW, Wong J (1992) A comparison of outcome after resection for squamous cell carcinomas and adenocarcinomas of the esophagus and cardia. Surg Gynecol Obstet 175:107–112Google Scholar
  20. Lawrence MS, Stojanov P, Polak P et al (2013) Mutational heterogeneity in cancer and the search for new cancer-associated genes. Nature. 499(7457):214–218. CrossRefGoogle Scholar
  21. Li JQ, Rong ZH, Chen X, Yan GY, You ZH (2017) MCMDA: matrix completion for MiRNA–disease association prediction. Oncotarget 8(13):21187–21199. Google Scholar
  22. Lorenzi PL, Claerhout S, Mills GB, Weinstein JN (2014) A curated census of autophagy-modulating proteins and small molecules: candidate targets for cancer therapy. Autophagy 10(7):1316–1326CrossRefGoogle Scholar
  23. Lu YF, Goldstein DB, Angrist M, Cavalleri G (2014) Personalized medicine and human genetic diversity. Cold Spring Harb Perspect Med 4(9):a008581CrossRefGoogle Scholar
  24. Nakakubo Y, Hida Y, Miyamoto M, Hashida H, Oshikiri T, Kato K, Suzuoki M, Hiraoka K, Ito T, Morikawa T, Okushiba S, Kondo S, Katoh H (2002) The prognostic significance of RCAS1 expression in squamous cell carcinoma of the oesophagus. Cancer Lett 177(1):101–105CrossRefGoogle Scholar
  25. Narita M, Kanda T, Abe T et al (2015) Immune responses in patients with esophageal cancer treated with SART1 peptide-pulsed dendritic cell vaccine. Int J Oncol 46(4):1699–1709CrossRefGoogle Scholar
  26. Ohashi S, Miyamoto S, Kikuchi O, Goto T, Amanuma Y, Muto M (2015) Recent advances from basic and clinical studies of esophageal squamous cell carcinoma. Gastroenterology 149(7):1700–1715CrossRefGoogle Scholar
  27. Rosenfeld MR, Malats N, Schramm L et al (1997) Serum anti-p53 antibodies and prognosis of patients with small-cell lung cancer. J Natl Cancer Inst 89(5):381–385CrossRefGoogle Scholar
  28. Roth MJ, Liu SF, Dawsey SM et al (1997) Cytologic detection of esophageal squamous cell carcinoma and precursor lesions using balloon and sponge samplers in asymptomatic adults in Linxian, China. Cancer 80:2047–2059CrossRefGoogle Scholar
  29. Shi H, Lv F, Zhu S et al (2011) Dual inhibition of 5-LOX and COX-2 suppresses esophageal squamous cell carcinoma. Cancer Lett 309(1):19–26CrossRefGoogle Scholar
  30. Shi Z, Tang Y, Li K, Fan Q (2015) TKTL1 expression and its downregulation is implicated in cell proliferation inhibition and cell cycle arrest in esophageal squamous cell carcinoma. Tumour Biol 36(11):8519–8529CrossRefGoogle Scholar
  31. Stilgenbauer S, Schnaiter A, Paschka P et al (2014) Gene mutations and treatment outcome in chronic lymphocytic leukemia: results from the CLL8 trial. Blood 123(21):3247–3254CrossRefGoogle Scholar
  32. Sun Y, Shi N, Lu H et al (2014) ABCC4 copy number variation is associated with susceptibility to esophageal squamous cell carcinoma. Carcinogenesis 35(9):1941–1950CrossRefGoogle Scholar
  33. Takikita M, Hu N, Shou JZ et al (2009) Biomarkers of apoptosis and survival in esophageal squamous cell carcinoma. BMC Cancer 9:310CrossRefGoogle Scholar
  34. Wang Q, Zhu H, Xiao Z et al (2013) Expression of epidermal growth factor receptor is an independent prognostic factor for esophageal squamous cell carcinoma. World J Surg Oncol 11:278CrossRefGoogle Scholar
  35. Wang X, Wang J, Jia Y et al (2017) Methylation decreases the Bin1 tumor suppressor in ESCC and restoration by decitabine inhibits the epithelial mesenchymal transition. Oncotarget. Google Scholar
  36. Yang ZT, Yeo SY, Yin YX et al (2016) Tenascin-C, a prognostic determinant of esophageal squamous cell carcinoma. PLoS ONE 11(1):e0145807CrossRefGoogle Scholar
  37. You ZH, Huang ZA, Zhu Z, Yan GY, Li ZW, Wen Z, Chen X (2017) PBMDA: a novel and effective path-based computational model for miRNA–disease association prediction. PLoS Comput Biol 13(3):e1005455. CrossRefGoogle Scholar
  38. Zhang W, Zhu H, Liu X et al (2014) Epidermal growth factor receptor is a prognosis predictor in patients with esophageal squamous cell carcinoma. Ann Thorac Surg 98(2):513–519CrossRefGoogle Scholar

Copyright information

© Society for Mathematical Biology 2018

Authors and Affiliations

  1. 1.Department of Cardiothoracic SurgeryThe Affiliated Jiangyin Hospital of Southeast University Medical CollegeJiangyinChina
  2. 2.Department of Cardiothoracic SurgeryThe First People’s Hospital of KunshanKunshanChina
  3. 3.Department of UltrasoundThe People’s Hospital of TonglingTonglingChina
  4. 4.Department of Genomics Research, R&D SolutionsElsevier Inc.RockvilleUSA
  5. 5.Unit on Statistical GenomicsNational Institute of Health (NIH)BethesdaUSA

Personalised recommendations