Identification of miRNAs Expression Profile in Gastric Cancer Using Self-Organizing Maps (SOM)

BACK TO CONTENTS | PDF | NEXT

Title	Identification of miRNAs Expression Profile in Gastric Cancer Using Self-Organizing Maps (SOM)
Authors	Larissa Luz Gomes^{1, 2}, Fabiano Cordeiro Moreira^{1, 3}, Igor Guerreiro Hamoy^{1, 4}, Sidney Santos^{1, 5}, Paulo Assumpçăo^{5, 6}, Ádamo L. Santana⁷ & Ândrea Ribeiro-dos-Santos^{1, 5}*
Affiliation	¹Laboratório de Genética Humana e Médica, Universidade Federal do Pará, Belém, Pará, Brasil; ²Instituto de Estudos Superiores da Amazônia, Belém, Pará, Brasil; ³Centro Universitário do Estado do Pará, Belém, Pará, Brasil; ⁴Universidade Federal Rural da Amazônia, Campus de Capanema, Pará, Brasil; ⁵Núcleo de Pesquisa em Oncologia, Universidade Federal do Pará, Belém, Pará, Brasil; ⁶Hospital Universitário Joăo de Barros Barreto, Universidade Federal do Pará, Belém, PA, Brazil; 7Laboratory of High Performance Networks Planning, Federal University of Pará, Belém, Pará, Brazil
Email	akely@ufpa.br/akelyufpa@gmail.com; *Corresponding author
Article Type	Hypothesis
Date	Received April 04, 2014; Accepted April 15, 2014; Published May 20, 2014
Abstract	In this paper, an unsupervised artificial neural network was implemented to identify the patters of specific signatures. The network was based on the differential expression of miRNAs (under or over expression) found in healthy or cancerous gastric tissues. Among the tissues analyzes, the neural network evaluated 514 miRNAs of gastric tissue that exhibited significant differential expression. The result suggested a specific expression signature nine miRNAs (hsa-mir-21, hsa-mir-29a, hsa-mir-29c, hsa-mir-148a, hsa-mir-141, hsa-let-7b, hsa-mir-31, hsa-mir-451, and hsa-mir-192), all with significant values (p-value < 0.01 and fold change > 5) that clustered the samples into two groups: healthy tissue and gastric cancer tissue. The results obtained “in silico” must be validated in a molecular biology laboratory; if confirmed, this method may be used in the future as a risk marker for gastric cancer development.
Keywords	miRNA, Gastric Cancer, Artificial Neural Network, Bioinformatics, Risk Biomarker.
Citation	*Gomes et al.* Bioinformation 10(5): 246-250 (2014)
Edited by	P Kangueane
ISSN	0973-2063
Publisher	Biomedical Informatics
License	This is an Open Access article which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. This is distributed under the terms of the Creative Commons Attribution License.