Display options
Share it on

Asian Pac J Cancer Prev. 2017 May 01;18(5):1453-1457. doi: 10.22034/APJCP.2017.18.5.1453.

Classification of Bladder Cancer Patients via Penalized Linear Discriminant Analysis.

Asian Pacific journal of cancer prevention : APJCP

Hadi Raeisi Shahraki, Peyman Bemani, Maryam Jalali

Affiliations

  1. Department of Biostatistics, School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran. Email: [email protected]

PMID: 28612601 PMCID: PMC5555561 DOI: 10.22034/APJCP.2017.18.5.1453

Abstract

Objectives: In order to identify genes with the greatest contribution to bladder cancer, we proposed a sparse model making the best discrimination from other patients. Methods: In a cross-sectional study, 22 genes with a key role in most cancers were considered in 21 bladder cancer patients and 14 participants of the same age (± 3 years) without bladder cancer in Shiraz city, Southern Iran. Real time-PCR was carried out using SYBR Green and for each of the 22 target genes 2-Δct as a quantitative index of gene expression was reported. We determined the most affective genes for the discriminant vector by applying penalized linear discriminant analysis using LASSO penalties. All the analyses were performed using SPSS version 18 and the penalized LDA package in R.3.1.3 software. Results: Using penalized linear discriminant analysis led to elimination of 13 less important genes. Considering the simultaneous effects of 22 genes with important influence on many cancers, it was found that TGFβ, IL12A, Her2, MDM2, CTLA-4 and IL-23 genes had the greatest contribution in classifying bladder cancer patients with the penalized linear discriminant vector. The receiver operating characteristic (ROC) curve revealed that the proposed vector had good performance with minimal (only 3) mis- classification. The area under the curve (AUC) of our proposed test was 96% (95% CI: 83%- 100%) and sensitivity, specificity, positive and negative predictive values were 90.5%, 85.7%, 90.5% and 85.7%, respectively. Conclusions: The penalized discriminant method can be considered as appropriate for classifying bladder cancer cases and searching for important biomarkers.

Creative Commons Attribution License

Keywords: Bladder cancer; classification; gene expression; discriminant analysis; penalized method

References

  1. MedGenMed. 2007 Nov 13;9(4):34 - PubMed
  2. Mol Cell Proteomics. 2011 Oct;10(10):M111.007922 - PubMed
  3. Asian Pac J Cancer Prev. 2015;16(15):6773-7 - PubMed
  4. Eur Urol. 2011 Aug;60(2):350-7 - PubMed
  5. Semin Oncol. 2012 Oct;39(5):524-33 - PubMed
  6. J Natl Cancer Inst. 1994 Sep 7;86(17 ):1325-30 - PubMed
  7. Urol Oncol. 2013 Apr;31(3):372-8 - PubMed
  8. Nat Rev Urol. 2016 Jul;13(7):369 - PubMed
  9. Anticancer Res. 2007 Sep-Oct;27(5A):3051-8 - PubMed
  10. J Clin Oncol. 2001 Jun 1;19(11):2856-64 - PubMed
  11. Hum Genet. 2009 Jun;125(5-6):527-39 - PubMed
  12. J Cell Physiol. 2013 Jan;228(1):30-5 - PubMed
  13. Clin Biochem. 2005 Feb;38(2):142-8 - PubMed
  14. Cancer Lett. 2008 Jun 28;265(1):27-38 - PubMed
  15. Bioinformatics. 2006 Aug 1;22(15):1855-62 - PubMed
  16. Arab J Urol. 2015 Jun;13(2):146-52 - PubMed
  17. BJU Int. 2011 Nov;108(10):1672-8 - PubMed
  18. Pathol Res Pract. 2003;199(5):323-8 - PubMed
  19. Clin Cancer Res. 2014 Mar 15;20(6):1531-41 - PubMed
  20. J Environ Public Health. 2016;2016:7620157 - PubMed
  21. IEEE/ACM Trans Comput Biol Bioinform. 2004 Oct-Dec;1(4):181-90 - PubMed
  22. J R Stat Soc Series B Stat Methodol. 2011 Nov;73(5):753-772 - PubMed

Publication Types