{"title":"Unsupervised Classification of DNA Barcodes Species Using Multi-Library Wavelet Networks","authors":"Abdesselem Dakhli, Wajdi Bellil, Chokri Ben Amar","volume":100,"journal":"International Journal of Computer and Information Engineering","pagesStart":1016,"pagesEnd":1023,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/10002066","abstract":"DNA Barcode provides good sources of needed\r\ninformation to classify living species. The classification problem has\r\nto be supported with reliable methods and algorithms. To analyze\r\nspecies regions or entire genomes, it becomes necessary to use the\r\nsimilarity sequence methods. A large set of sequences can be\r\nsimultaneously compared using Multiple Sequence Alignment which\r\nis known to be NP-complete. However, all the used methods are still\r\ncomputationally very expensive and require significant computational\r\ninfrastructure. Our goal is to build predictive models that are highly\r\naccurate and interpretable. In fact, our method permits to avoid the\r\ncomplex problem of form and structure in different classes of\r\norganisms. The empirical data and their classification performances\r\nare compared with other methods. Evenly, in this study, we present\r\nour system which is consisted of three phases. The first one, is called\r\ntransformation, is composed of three sub steps; Electron-Ion\r\nInteraction Pseudopotential (EIIP) for the codification of DNA\r\nBarcodes, Fourier Transform and Power Spectrum Signal Processing.\r\nMoreover, the second phase step is an approximation; it is\r\nempowered by the use of Multi Library Wavelet Neural Networks\r\n(MLWNN). Finally, the third one, is called the classification of DNA\r\nBarcodes, is realized by applying the algorithm of hierarchical\r\nclassification.","references":"[1] P. D. N. Hebert, A. Cywinska, S. L. Ball and JR. DeWaard, \u201cBiological\r\nidentifications through DNA barcodes\u201d. Proc R Soc, 2003, pp. 313-321.\r\n[2] E. Weitschek, G. Fiscon and G. Felici, \u201cSupervised DNA Barcodes\r\nspecies classification: analysis, comparisons and results\u201d, BioData\r\nMining, vol. 7:4 2014, pp.2-18.\r\n[3] M. Moftah, S. H. Abdel Aziz, S. Elramah and A. Favereaux,\r\n\u201cClassification of Sharks in the Egyptian Mediterranean Waters Using\r\nMorphological and DNA Barcodes Approaches\u201d, PLoS ONE, vol. 6,\r\n2011, pp. 1-7.\r\n[4] Ch. Lei, Ch. Yu-Mei, C. Ding-Cheng and S. Xiao-Wen, \u201cDNA Barcodes\r\nand species and subspecies classification within genus Carassius\u201d,\r\nZoological Research,vol.33, 2012, pp. 463-472.\r\n[5] R. Sandberg, G. Winberg, CI Br\u00e4nden, A. Kaske, I ErnbergI and J.\r\nC\u00f6ster, \u201cCapturing Whole - Genome characteristics in short sequences\r\nusing a naive Bayesian classifer\u201d, Genome Res, vol.11, 2001, pp. 1404-\r\n1409.\r\n[6] F. Zanoguera and M. Francesco, \u201cProtein classification into domains of\r\nlife using Markov chain models\u201d, Proceedings of the 2004 IEEE\r\nComputational Systems Bioinformatics Conference, 2004, 0-7695-2194-\r\n0\/04\r\n[7] C. Wu, M. Berry, Y.-S Fung and J. McLarty, \u201cNeural Networks for\r\nMolecular Sequence Classification\u201d, Proc Int Conf Intell Syst Mol Biol.,\r\n1993, pp. 429-437.\r\n[8] S. Kumar Subramanian and D. N, \u201cArtificial Neural Network Based\r\nMethod for Classification of Gene Expression Data of Human Diseases\r\nalong with Privacy Preserving\u201d, International Journal of Computers &\r\nTechnology, vol.4, 2013, pp. 722-730.\r\n[9] S. bai Arniker and H. Keung Kwan, \u201cAdvanced Numerical\r\nRepresentation of DNA Sequences\u201d, International Conference on\r\nBioscience, Biochemistry and Bioinformatics IPCBEE, vol.31, 2012,\r\npp.1-5.\r\n[10] W. Bellil, C. Ben Amar and M. Adel Alimi, \u201cBeta Wavelet Based Image\r\nCompression\u201d, International Conference on Signal, System and Design,\r\nSSD03, Tunisia, vol.1, 2003, pp.77-82.\r\n[11] W. Bellil, C. Ben Amar and Mohamed AA: Synthesis of wavelet filters\r\nusing wavelet neural networks\u201d, Transactions on Engineering,\r\nComputation and Technology 2006, vol.13, pp. 108-111.\r\n[12] C. Ben Amar, M. Zied and M. Adel Alimi, \u201cBeta wavelets. Synthesis\r\nand application to lossy image compression\u201d, Journal of Advances in\r\nEngineering Software, Elsevier Edition, vol.36, 2005, pp. 459 \u2013 474.\r\n[13] W. Bellil, C. Ben Amar and M. Adel Alimi,\u201dSynthesis of wavelet filters\r\nusing wavelet neural networks\u201d, Transactions on Engineering,\r\nComputation and Technology, vol.13, 2006, pp. 108-111.\r\n[14] C. Ben Amar, W. Bellil and M. Adel Alimi, \u201cBeta Function and its\r\nDerivatives: A New Wavelet Family\u201d, Transactions on Systems, Signals\r\nand Devices, vol.1, 2006, pp. 275-293.\r\n[15] W. Bellil, C. Ben Amar and M. Adel Alimi, \u201cBeta wavelets networks for\r\nfunction approximation\u201d, International Conference on Adaptative and\r\nNatural Computing Algorithms, ICANNGA05, Coimbra Portugal,\r\nSpringer Wien NewYork, 2005, pp. 18-21.\r\n[16] M. Zaied, O. Jemai and C. Ben Amar, \u201cTraining of the Beta wavelet\r\nnetworks by the frames theory: Application to face recognition\u201d,\r\nieeexplore.ieee.org, Image Processing Theory, Tools & Applications,\r\n2008, 978-1-4244-3322-3\/08\/.\r\n[17] M. Zaied, C. Ben Amar and M. Adel Alimi, \u201cBeta wavelet Networks for\r\nFace recognition\u201d, Journal of decision systems, vol.14, 2005, pp.109-\r\n122.\r\n[18] dmb.asi.cnr.it\/supbarcodes.php.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 100, 2015"}