Identifying FCN2 as a Potential Biomarker for Hepatocellular Carcinoma Using a Novel Supervised Classification Method

Authors

  • Nuttachat Wisittipanit Mae Fah Luang University
  • Ekachai Chukeatirote Mae Fah Luang University

DOI:

https://doi.org/10.14456/gag.2019.3

Keywords:

hepatocellular carcinoma, gene expression, machine learning, attribute selection, genetic marker

Abstract

Hepatocellular Carcinoma (HCC) is the most prevalent form of liver cancers of which most patients show no symptoms of the condition until the ailment is beyond the curable stage. Computational analysis using data mining methods were employed to analyze gene expression profiles on microarray chips from 511 samples (268 HCC tissues and 243 adjacent non-HCC tissues) to identify highly differentially expressed genes. Of 23,000 genes available in the platform, 500 genes (~2%) were preliminary identified by Relief algorithm based on the high ranking scores of their expression levels between HCC-infected tissues and normal tissues. Then, the intensive search for differentially expressed genes were performed by machine learning methods; namely Support Vector Machines (SVM), K-Nearest Neighbour (KNN) and Naïve Bayes Classification (NBC) algorithm, by attribute pool sweep process. Results showed that several highly differentially expressed genes were detected having relatively high classification accuracy with Ficolin-2 acting as a common discovered gene.

References

Anand P, Ajaikumar BK, Chitra S, Kuzhuvelil BH, Tharakan ST, Lai OS, Sung B, Aggarwal BB (2008) Cancer is preventable disease that requires major lifestyle changes. Pharmaceutical Research 25: 2097-2116.

Boser BE, Guyon IM, Vapnik VN (1992) A training algorithm for optimal margin classifiers. Proceedings 5th Annual Conference Workshop on Computational learning theory 144-152.

Chen T, Hu Y, Ding Q, Yu J, Wang F, Luo F, Zhang XL (2015) Serum ficolin-2 concentrations are significantly changed in patients with hepatitis B virus infection and liver diseases. Virologica Sinica 30: 249-260. doi:10.1007/s12250-015-3605-4.

Foster R, Jahroudi N, Varshney U, Gedamu L (1988) Structure and expression of the human metallothionein-1G gene. Differential promoter activity of two linked metallothionein-1 genes in response to heavy metals. Journal of Biological Chemistry 263: 1528-1535.

Gebo KA, Chander G, Jenckes MW, Ghanem KG, Herlong HF, Torbenson MS, El-Kamary SS, Bass EB (2002) Screening Tests for Hepatocellular Carcinoma in Patients With Chronic Hepatitis C: A Systematic Review. Hepatology 36: 84-92.

Gyorgy B, Elizabeth MB, Stephen HC (2011) Hepatocellular carcinoma in non-alcoholic fatty liver disease: An emerging menace. Journal of Hepatology 56: 1384-1391.

Hromas R, Broxmeyer HE, Kim C, Nakshatri H, Christopherson K, Azam M, Hou YH (1999) Cloning of BRAK, a novel divergent CXC chemokine preferentially expressed in normal versus malignant cells. Biochemistry Biophysics Research Communication 255: 703-706.

Jemal A, Bray F, Center MM, Ferlay J, Ward E, Forman D (2011) Global cancer statistics. CA Cancer Journal for Clinicians 61: 69-90.

Kilpatrick DC, Mclintock LA, Allan EK, Copland M, Fujita T, Jordanides NE, Koch C, Matsushita M, Shiraki H, Stewart K, et al. (2003) No strong relationship between mannan binding lectin or plasma ficolins and chemotherapy-related infections. Clinical and Experimental Immunology 134: 279-284.

Kira K, Rendell L (1992) A practical approach to feature selection. Proceedings of the 9th International Conference on Machine Learning 249-255.

Lamb JR, Zhang C, Xie T, Wang K, Zhang B, Hao K, Chudin E, Fraser HB, Millstein J, Ferguson M, et al. (2011) Predictive Genes in Adjacent Normal Tissue Are Preferentially Altered by sCNV during Tumorigenesis in Liver Cancer and May Rate Limiting. PLoS ONE Doi:10.1371/journal.pone.0020090.

Maass T, Sfakianakis I, Staib F, Krupp M, Galle PR, Teufel A (2010) Microarray-Based Gene Expression Analysis of Hepatocellular Carcinoma. Current Genomics 11: 261-268.

Matsushita M, Endo Y, Fujita T (2000) Cutting Edge: Complement-Activating Complex of Ficolin and Mannose-Binding Lectin-Associated Serine Protease. The Journal of Immunology 164: 2281-2284.

Maton A, Jean H, Charles WM, Susan J (1993) Human Biology and Health, Englewood Cliffs, New Jersey.

Pedro D (1997) On the Optimality of the Simple Bayesian Classifier under Zero-One Loss. Machine Learning 29: 103-130.

Pollack JR, Perou CM, Alizadeh AA, Eisen MB, Pergamenschikov A, Williams CF, Jeffrey SS, Botstein D, Brown PO (1999) Genome-wide analysis of DNA copy number changes using cDNA microarrays. Nature Genetics 23: 41-46.

Rebecca S (2014) Cancer statistics. A Cancer Journal for Clinicians 64: 9-29.

Skawran B, Steinemann D, Weigmann A, Flemming P, Becker T, Flik J, Kreipe H, Schlegelberger B, Wilkens L (2008) Gene Expression profiling of Hepatocellular Carcinoma: Upregulation of genes in Amplified Chromosome Regions. Modern Pathology 21: 505-516.

Szala A, Sawicki S, Swierzko AS, Szemraj J, Sniadecki M, Michalski M, Kaluzynski A, Lukasiewicz J, Maciejewska A, Wydra D, et al. (2013) Ficolin-2 and ficolin-3 in women with malignant and benign ovarian tumours. Cancer Immunology Immunotherapy 62: 1411-1419.

Timmermann A, Kuster A, Kurth I, Heinrich PC (2002) A functional role of the membrane-proximal extracellular domains of the signal transducer gp130 in heterodimerization with the leukemia inhibitory factor receptor. European Journal of Biochemistry 269: 2716-2726.

Tung EK, Mak CK, Fatima S, Lo RC, Zhao H, Zhang C, Dai H, Poon RT, Yuen MF, Lai CL (2011) Clinicopathological and prognostic significance of serum and tissue Dickkopf-1 levels in human hepatocellular carcinoma. Liver International 31: 1494-1504.

Ueda T, Honda M, Horimoto K, Aburatani S (2013) Gene Expression profiling of hepatitis B- and hepatitis C-related hepatocellular carcinoma using graphical Gaussian modelling. Genomics 101: 238-248.

Valerio B, Debora D, Alessandro U, Giorgio S (2013) Hepatocellular Carcinoma – Future Outlook. INTECH, pp.197-215.

Van de Steeg E, Stranecky V, Hartmannova H (2012) Complete OATP1B1 and OATP1B3 deficiency causes human Rotor syndrome by interrupting conjugated bilirubin reuptake into the liver. Journal of Clinical Investigation 122: 519-528.

Wang W, Peng JX, Yang JQ, Yang LY (2009) Identification of Gene Expression Profiling in Hepatocellular Carcinoma Using cDNA Microarrays. Digestive Diseases and Science 54: 2729-2735.

Zakim D, Thomas D (2002) Hepatology: A Textbook of Liver Disease, 4th ed., Saunders, Pennsylvania.

Downloads

Published

2019-07-22

Issue

Section

Research Articles