Tumor Classification Using Gene Expression and Machine Learning Models

  • Kubra TuncalEmail author
  • Cagri OzkanEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1095)


Cancer is the most fatal cause of death and determination of the reasons, making early diagnosis and correct treatment reduces the loss of lives but humans are still far away to produce a complete and permanent solutions to this problem. Nowadays, RNA and gene researches try make this solutions step by step more effective to defect cancer and to improve these researches. However, the number of the genes and complexity of the data makes analysis and experiments more challenging for humans thus, computerized solutions such as machine learning models are needed. This paper presents preliminary results of five types of tumor classification on RNA-Seq. Three machine learning models, Support Vector Machine, Backpropagation neural network and Decision Tree is implemented and various experiments are performed for this task. Obtained results show that machine learning models can effectively be used for tumor classification using gene information and Support Vector Machine achieved superior results than other considered models.


RNA-Seq Backpropagation Support Vector Machine Decision Tree 


  1. 1.
    Erdemir, F., Gülzade, U.: Genetik, genomik bilimi ve hemşirelik. Dokuz Eylül Üniversitesi Hemşirelik Yüksekokulu Elektronik Dergisi 3(2), 96–101 (2010). (in Turkish)Google Scholar
  2. 2.
    Xiao, Y., Wu, J., Lin, Z.: A semi-supervised deep learning method based on stacked sparse auto-encoder for cancer prediction using RNA-seq data. Comput. Meth. Programs Biomed. 166, 99–105 (2018)CrossRefGoogle Scholar
  3. 3.
    Weinstein, J.N., et al.: The cancer genome atlas pan-cancer analysis project. Nat. Genet. 45(10), 1113–1120 (2013)CrossRefGoogle Scholar
  4. 4.
    Danaee, P., Ghaeini, R., Hendrix, D.: A deep learning approach for cancer detection and relevant gene identification. Pacific Symp. Biocomput. 2017, 219–229 (2017)Google Scholar
  5. 5.
    Tarek, S., Abd Elwahab, R., Shoman, M.: Gene expression based cancer classification. Egypt. Inf. J. 18, 151–159 (2017)CrossRefGoogle Scholar
  6. 6.
    Huang, S., et al.: Applications of support vector machine (SVM) learning in cancer genomics. Cancer Genomics Proteomics 15, 41–51 (2018)Google Scholar
  7. 7.
    Khashman, A., Sekeroglu, B.: Global binarization of document images using a neural network. In: Third International IEEE Conference on Signal-Image Technologies and Internet-Based System, pp. 665–672, Shanghai (2007)Google Scholar
  8. 8.
    Dougherty, G.: Pattern recognition and classification. Springer, New York (2013). Scholar
  9. 9.
    Tong, S., Koller, D.: Support vector machine active learning with applications to text classification. J. Mach. Learn. Res. 2, 45–66 (2001)zbMATHGoogle Scholar
  10. 10.
    Senturk, Z.K., Senturk, A.: Yapay sinir agları ile gögüs kanseri tahmini. El-Cezeri J. Sci. Eng. 3(2), 345–350 (2016). (in Turkish)Google Scholar
  11. 11.
    Yuan, Z., Wang, C.: An improved network traffic classification algorithm based on Hadoop decision tree. In: 2016 IEEE International Conference of Online Analysis and Computing Science (ICOACS), Chongqing, pp. 53–56 (2016)Google Scholar
  12. 12.
    Ge L, Shi, J., Zhu, P.: Melt index prediction by support vector regression. In: 2016 International Conference on Control, Automation and Information Sciences (ICCAIS), Ansan, pp. 60–63 (2016)Google Scholar
  13. 13.
    Polaka, I., Igar, T., Borisov, A.: Decision tree classifiers in bioinformatics. J. Riga Tech. Univ. (42), 118–123 (2010)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Information Systems EngineeringNear East UniversityNicosiaTurkey

Personalised recommendations