Journal
BIOINFORMATION
Volume 10, Issue 5, Pages 246-250Publisher
BIOMEDICAL INFORMATICS
DOI: 10.6026/97320630010246
Keywords
miRNA; Gastric Cancer; Artificial Neural Network; Bioinformatics; Risk Biomarker
Categories
Funding
- CAPES/Biologia Computacional
- FAPESPA
- Conselho Nacional de Desenvolvimento Cientifico e Tecnologico - CNPq
- Coordenacao de Aperfeicoamento de Pessoal de Nivel Superior - CAPES
- Governo do Para/SEDECT/FAPESPA, PROPESP/UFPA-FADESP
- IESAM
- CESUPA
- CNPq/Brazil [162605/2011- 0]
- CNPq/Produtividade
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available