Year 2021, Volume 9 , Issue 1, Pages 23 - 32 2021-01-30

Sequential Feature Maps with LSTM Recurrent Neural Networks for Robust Tumor Classification

Canan BATUR ŞAHİN [1] , Banu DİRİ [2]


In the field of biomedicine, applications of the identification of biomarkers require a robust gene selection mechanism. For identifying the characteristic marker of an observed event, the selection of attributes becomes important. The robustness of gene selection methods affects detecting biologically meaningful genes in tumor diagnosis. For mapping, sequential features Long-short-term memory (LSTM) was used with Artificial Immune Recognition Systems (AIRS) to remember gene sequences and effectively recall of learned sequential patterns. An attempt was made to improve AIRS with LSTM which is a type of RNNs to produce discriminative gene subsets for finding biologically meaningful genes in tumor diagnosis. The algorithms were evaluated using six common cancer microarray datasets. By converging to the intrinsic information of the microarray datasets, specific groups like functions of the co-regulated groups were observed. The results showed that the LSTM based AIRS model can successfully identify biologically significant genes from the microarray datasets. Also the predictive genes for biological sequences areimportant in gene expression microarrays.This study confirms that different genes can be found in the same pathways. It was also found that the gene subsets selected by the algorithms were involved in important biological pathways.In this work we try an LSTM on our learning problem. We suspected that recurrent neural networks would be a good architecture for making predictions.The results show that the optimal gene subsets were based on the suggested framework, so they should have rich biomedical interpretability.

Artificial immune system, Biomarker discovery, Robustness, Tumor Classification, Optimization
  • Loscalzo S., YU L., Ding C., “Consensus Group Stable Feature Selection”, June28–July1, Paris,France, 2009.
  • Loscalzo S., YU L., Ding C., “Stable Feature Selection via Dense Feature Groups”, August 24–27, Las Vegas, Nevada, USA, 2008.
  • Farhan M., Mohsin M., HamdanA.,Bakar A.A., “An evaluation of feature selection technique for dentrite cell algorithm”, IEEE, 2014.
  • Schmidhuber, J., Wierstra, D., and Gomez, F. J. Evolino: “Hybrid neuroevolution/optimal linear search for sequence prediction”. In Proceedings of the 19th International Joint Conference on Artificial Intelligence (IJCAI), pp. 853–858, 2005
  • Rubvurm M., Körner M., “Temporal vegetation modelling using long short-term memory networks for crop identification from medium-resolution multi-spectral satellite images”, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), USA, 2017.
  • Dasgupta D., Nino L.F., Immunological computation: theory and applications .2009 by Taylor & Francis Group, LLC. Book, 2009.
  • Chung Y., et al., “Emprical evaluation of gated recurrent neural networks on sequence modeling”, Neural ComputAppl arxiv:1412.3555v1, 2014.
  • Luque-Baena R.M., Urda D., Gonzalo Claros M., Franco L., and Jerez J.M., “Robust genesignatustes from microarray data using genetic algorithms encriched with biological pathway keywords”, Journal of Biomedical Informatics, http://dx.doi.org/10.1016/j.jbi.2014.01.006, 2014.
  • https://machinelearning-blog.com/2018/02/21/recurrent-neural-networks/
  • https://www.cs.waikato.ac.nz/ml/weka/
  • https://worldwidescience.org/topicpages/i/immunity-related+gtpase+irgml.html
  • https://www.genecards.org/cgiin/carddisp.pl?gene=PCBP4
  • http://www.bionewsonline.com/
  • Ferreira A.j. (2014), “Feature selection and discretization for high-dimensional data”, Phd Thesis.
  • Mazel J. (2011), “ Unsupervised network anomaly detection”, Phd Thesis.
  • Polat K., Güneş S., Sahan S., Kodaz H., (2005), “A New Classification Method for Breast Cancer Diagnosis: Feature Selection Artificial Immune Recognition System (FS-AIRS)”, Berlin.
  • Menon A. edited by. (2004).Frontiers of Evolutionary Computation, Kluwer academic Publishers, Pittsburgh, USA.
  • Oh S. , Lee J.S., Moon B.R.(2004).Hybrid Genetic Algorithms for Feature Selection .Vol. 26, No.11, November.
  • Brownlee J. (2005). “Clonal Selection Theory &Clonalg the Clonal Selectıon Classıfıcatıon Algorıthm (CSCA), Technical Report.
  • Dudek G. (2012). “An Artificial System for Classification with Local Feature Selection”,IEEE Transaction on Evolutionary Computation. December 2012,Czestochowa.
  • Wang K., Chen K.,Adrian A., (2014), “An improved artificial immune recognition system with the opposite sign test for feature selection”, Knowledge-Based Systems ,Taiwan.
  • Daga M., Lakhwani K., (2013),” A Novel Content Based Image Retrieval Implemented ByNsa of Aıs”, Internatıonal Journal of Scıentıfıc & Technology Research.
  • Farhan M., Mohsin M., HamdanA.,Bakar A.A., (2014),” An Evaluation of Feature Selection Technique for Dendrite Cell Algorithm”,IEEE.
  • Gu F., Greensmith J., Aickelin U., (2008),” Further Exploration of the Dendritic Cell Algorithm: Antigen Multiplier and Time Windows”, ICARIS 2008.
  • Wollmer M., Eyben F., Rigoll G., (2008),” Combining Long Short-Term Memory and Dynamic Bayesian Networks for Incremental Emotion-Sensitive Artificial Listening”, Journal of Selected Topıcs in Signal Processing.
  • Daga M., Lakhwani K., (2013), “A Novel Content Based Image Retrieval Implemented By NSA Of AIS”, International journal of scientific & technology research
  • Kalousis A., Prados J. and Hilario M., (2007),“Stability of Feature Selection Algorithms: a study on high-dimensional spaces”, Knowladge and Information Systems.
  • Saeys Y., Abeel T., and Peer Y.V. (2008),”Robust Feature Selection Using Ensemble Feature Selection Techniques”. In Proceedings of the ECML Conference, pages 313-325.
Primary Language en
Subjects Computer Science, Artifical Intelligence
Published Date January 2021
Journal Section Araştırma Articlessi
Authors

Orcid: 0000-0002-2131-6368
Author: Canan BATUR ŞAHİN (Primary Author)
Institution: SIIRT UNIVERSITY
Country: Turkey


Orcid: 0000-0002-2131-6368
Author: Banu DİRİ
Institution: Yildiz Technical University
Country: Turkey


Dates

Publication Date : January 30, 2021

Bibtex @research article { bajece604885, journal = {Balkan Journal of Electrical and Computer Engineering}, issn = {2147-284X}, address = {}, publisher = {Balkan Yayın}, year = {2021}, volume = {9}, pages = {23 - 32}, doi = {10.17694/bajece.604885}, title = {Sequential Feature Maps with LSTM Recurrent Neural Networks for Robust Tumor Classification}, key = {cite}, author = {Batur Şahin, Canan and Diri, Banu} }
APA Batur Şahin, C , Diri, B . (2021). Sequential Feature Maps with LSTM Recurrent Neural Networks for Robust Tumor Classification . Balkan Journal of Electrical and Computer Engineering , 9 (1) , 23-32 . DOI: 10.17694/bajece.604885
MLA Batur Şahin, C , Diri, B . "Sequential Feature Maps with LSTM Recurrent Neural Networks for Robust Tumor Classification" . Balkan Journal of Electrical and Computer Engineering 9 (2021 ): 23-32 <https://dergipark.org.tr/en/pub/bajece/issue/60125/604885>
Chicago Batur Şahin, C , Diri, B . "Sequential Feature Maps with LSTM Recurrent Neural Networks for Robust Tumor Classification". Balkan Journal of Electrical and Computer Engineering 9 (2021 ): 23-32
RIS TY - JOUR T1 - Sequential Feature Maps with LSTM Recurrent Neural Networks for Robust Tumor Classification AU - Canan Batur Şahin , Banu Diri Y1 - 2021 PY - 2021 N1 - doi: 10.17694/bajece.604885 DO - 10.17694/bajece.604885 T2 - Balkan Journal of Electrical and Computer Engineering JF - Journal JO - JOR SP - 23 EP - 32 VL - 9 IS - 1 SN - 2147-284X- M3 - doi: 10.17694/bajece.604885 UR - https://doi.org/10.17694/bajece.604885 Y2 - 2020 ER -
EndNote %0 Balkan Journal of Electrical and Computer Engineering Sequential Feature Maps with LSTM Recurrent Neural Networks for Robust Tumor Classification %A Canan Batur Şahin , Banu Diri %T Sequential Feature Maps with LSTM Recurrent Neural Networks for Robust Tumor Classification %D 2021 %J Balkan Journal of Electrical and Computer Engineering %P 2147-284X- %V 9 %N 1 %R doi: 10.17694/bajece.604885 %U 10.17694/bajece.604885
ISNAD Batur Şahin, Canan , Diri, Banu . "Sequential Feature Maps with LSTM Recurrent Neural Networks for Robust Tumor Classification". Balkan Journal of Electrical and Computer Engineering 9 / 1 (January 2021): 23-32 . https://doi.org/10.17694/bajece.604885
AMA Batur Şahin C , Diri B . Sequential Feature Maps with LSTM Recurrent Neural Networks for Robust Tumor Classification. Balkan Journal of Electrical and Computer Engineering. 2021; 9(1): 23-32.
Vancouver Batur Şahin C , Diri B . Sequential Feature Maps with LSTM Recurrent Neural Networks for Robust Tumor Classification. Balkan Journal of Electrical and Computer Engineering. 2021; 9(1): 23-32.
IEEE C. Batur Şahin and B. Diri , "Sequential Feature Maps with LSTM Recurrent Neural Networks for Robust Tumor Classification", Balkan Journal of Electrical and Computer Engineering, vol. 9, no. 1, pp. 23-32, Jan. 2021, doi:10.17694/bajece.604885