Advertisement

Classification of Autism Gene Expression Data Using Deep Learning

  • Noura SamyEmail author
  • Radwa Fathalla
  • Nahla A. Belal
  • Osama Badawy
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 38)

Abstract

Gene expression data is used in the prediction of many diseases. Autism spectrum disorder (ASD) is among those diseases, where information on gene expression for selecting and classifying genes are evaluated. The difficulty of selection and identification of the ASD genes remains a major setback in the gene expression analysis of ASD. The objective of this paper is to develop a classification model for ASD subjects. The paper employs: Deep Belief Network (DBN) based on the Gaussian Restricted Boltzmann machine (GRBM). Restricted Boltzmann machine (RBM) is considered a popular graphical model that constructs a latent representation of raw data fed at its input nodes. The model is based on its learning algorithm, namely, contrastive divergence, and information gain (IG) is used as the criterion for gene selection. Our proposed model proves that it can deal with gene expression values efficiently and achieved improvements over classical classification methods. The results show that that the most discriminative genes can be selected and identified with its gene expression values. We report an increase of 8% over the highest achieving algorithm on a standard dataset in terms of accuracy.

Keywords

Restricted Boltzmann machine İnformation gain Feature analysis Gene expression Autism Deep learning 

References

  1. 1.
    Gordon, J.A.: A parent’s guide to autism spectrum disorder: national institute of mental health, USA, pp. 1–27 (2018)Google Scholar
  2. 2.
    Pushpa, M., Swarnamageshwari, M.: Review on feature selection of gene expression data for autism classification: international journal of innovative research in science. Eng. Technol. 5, 3166–3170 (2016)Google Scholar
  3. 3.
    Saengsiri1, P., Na, S., Wichian, U., Meesad, P., Herwig U.: Integrating Feature Selection Methods for Gene Selection: Semantic Scholar, pp. 1–10 (2015)Google Scholar
  4. 4.
    Lai, C.M., Yeh, W.C., Chang, C.Y.: Gene selection using information gain and improved simplified swarm optimization: Neurocomputing, pp. 1–32 (2016)Google Scholar
  5. 5.
    Han, J., Kamber, M., Pei, J.: Data Mining Concepts and Techniques, 3rd edn, pp. 1–740. Elsevier, Hoboken (2012)CrossRefGoogle Scholar
  6. 6.
    Hameed, S.S., Hassan, R., Muhammad, F.F.: Selection and classification of gene expression in autism disorder: use of a combination of statistical filters and a GBPSOSVM algorithm. PLoS ONE 12(11), 1–25 (2017). e0187371CrossRefGoogle Scholar
  7. 7.
    Heinsfelda, A.S., Francob, A.R., Craddockf, R.C., Buchweitzb, A., Meneguzzia, F.: Identification of autism spectrum disorder using deep learning and the ABIDE dataset, pp. 16–23, Elsevier (2017)Google Scholar
  8. 8.
    Latkowski, T., Osowski, S.: Data mining for feature selection in gene expression autism data, pp. 864–872. Elsevier (2015)Google Scholar
  9. 9.
    Tang, J., Alelyani, S., Liu, H.: Feature selection for classification: a review. In: Data Classification: Algorithms and Applications, pp. 37–64 (2014)Google Scholar
  10. 10.
    Rupawon, N.A., Shah, Z.A.: Selection of Informative Gene on Autism Using Statistical and Machine Learning Methods. In: UTM Computing Proceedings Innovations in Computing Technology and Applications vol. 6, pp. 1–8 (2016)Google Scholar
  11. 11.
    Tanaka, M., Okutomi, M.: A novel inference of a restricted boltzmann machine. In: IEEE 22nd International Conference on Pattern Recognition; Tokyo, pp. 1–6 (2014)Google Scholar
  12. 12.
    Gupta, J., Pradhan, I., Ghosh, A.: Classification of gene expression data using gaussian restricted boltzmann machine (GRBM). Int. J. Recent Innov. Trends Comput. Commun. (IJRITCC) 5(6), 56–61 (2017)Google Scholar
  13. 13.
    Hyde, K.K., Novack, M.N., LaHaye, N., Parlett-Pelleriti, C., Anden, R., Dixon, D.R., Linstead, E.: Applications of supervised machine learning in autism spectrum disorder research: a review. Rev. J. Autism Develop. Disord 6, 1–19 (2019)CrossRefGoogle Scholar
  14. 14.
    Gao, L., Ye, M., Lu, X., Huang, D.: Hybrid method based on information gain and support vector machine for gene selection in cancer classification. Genomics Proteomics Bioinf. 15(6), 389–395 (2017)CrossRefGoogle Scholar
  15. 15.
    KajaNisha, R., Sheik Abdullah, A.: Classification of cancer microarray data with feature selection using swarm intelligence techniques. Acta Sci. Med. Sci. 3(7), 82–87 (2019)Google Scholar
  16. 16.
    Bondarenko, A., Borisov, A.R.: Technical university: research on the classification ability of deep belief networks on small and medium datasets. Inf. Technol. Manage. Sci. 6(1), 60–65 (2013)Google Scholar
  17. 17.
    Smolander, J., Dehmer, M., Sterib, F.E.: Comparing deep belief networks with support vector machines for classifying gene expression data from complex disorder. In: Open Bio, pp. 1–26 (2017)Google Scholar
  18. 18.
    Kozio, J.A., Tan, E.M., Dai, L., Ren, P., Zhang, J.Y.: Restricted boltzmann machines for classification of hepatocellular carcinoma. Computat. Biol. J. 2014, 1–5 (2014)Google Scholar
  19. 19.
    Jiang, X., Zhang, H., Duan, F., Quan, X.: Identify Huntington’s disease associated genes based on restricted Boltzmann machine with RNA-seq data. BMC Bioinformatics, pp. 1–13 (2017)Google Scholar
  20. 20.
    Shaltout, N.A., El-Hefnawi, M., Rafea, A., Moustafa, A.: Information gain as a feature selection method for the efficient classification of influenza based on viral hosts. In: Proceedings of the World, London, vo1. I, pp. 1–7 (2014)Google Scholar
  21. 21.
    Ray, S.S., Ganivada, A., Pal, S.K.: A granular self-organizing map for clustering and gene selection in microarray data. In: IEEE, pp. 1–17 (2015)Google Scholar
  22. 22.
    Bolón-Canedo, V., Sánchez Maroño, N., Alonso-Betanzos, A.: Feature Selection for High-Dimensional Data, Artificial Intelligence: Foundations, Theory, and Algorithms, pp. 1–163. Springer (2015)Google Scholar
  23. 23.
    National Center for Biotechnology Information. http://www.ncbi.nlm.nih.gov
  24. 24.
    Chuthapisith, J., Ruangdaraganon, N.: Early detection of autism spectrum disorders. In: Autism Spectrum Disorders: The Role of Genetics in Diagnosis and Treatment, Stephen Deutsch, IntechOpen, 1 August 2011.  https://doi.org/10.5772/17482Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Noura Samy
    • 1
    • 2
    Email author
  • Radwa Fathalla
    • 1
    • 2
  • Nahla A. Belal
    • 1
    • 2
  • Osama Badawy
    • 1
    • 2
  1. 1.Arab Academy for Science and Technology and Maritime TransportAlexandriaEgypt
  2. 2.Collage of Computing and Information TechnologyAlexandriaEgypt

Personalised recommendations