Please use this identifier to cite or link to this item:
http://hdl.handle.net/1843/44899
Type: | Artigo de Periódico |
Title: | Immune/neural approach to characterize salivary gland neoplasms (SGN) |
Authors: | Carlos Rafael Lima Monção Eloa Mangabeira Santos Thiago Silva Prates Alfredo Maurício Batista de Paula Cláudio Marcelo Cardoso Lucyana Conceição Farias Sérgio Henrique Sousa Santos Marcos Flávio Silveira Vasconcelos D’Angelo André Luiz Sena Guimarães |
Abstract: | The purpose of the current study was to use immune-inspired algorithm ClonALG whose performance is increased by using the Kohonen neural network training algorithm (Immune/Neural approach), to characterize the nature of salivary gland neoplasms (SGNs). The leader gene approach in order to identify biomarkers for SGNs. Extensive data were obtained for each of the 35 types of neoplasms. The gene leaders for each type of SGN were identified in a table and then divided according to the two different methods: K-means clustering and Immune/Neural approach. Genes related to SGNs were identified using PubMed, OMIM and Genecards databases. A bioinformatics algorithm was then applied, and the STRING database was employed to build networks of protein–protein interactions for each nature of an SGNs. The weighted number of links (WNL) and total interactions score (TIS) values were then obtained. Finally, the genes were clustered, and the gene leaders were identified using the K-means clustering method and the Immune/Neural approach. |
Subject: | Tumores Glândulas salivares Bioinformática |
language: | eng |
metadata.dc.publisher.country: | Brasil |
Publisher: | Universidade Federal de Minas Gerais |
Publisher Initials: | UFMG |
metadata.dc.publisher.department: | ICA - INSTITUTO DE CIÊNCIAS AGRÁRIAS |
Rights: | Acesso Restrito |
metadata.dc.identifier.doi: | https://doi.org/10.1016/j.asoc.2019.105877 |
URI: | http://hdl.handle.net/1843/44899 |
Issue Date: | Mar-2020 |
metadata.dc.url.externa: | https://www.sciencedirect.com/science/article/pii/S1568494619306581 |
metadata.dc.relation.ispartof: | Applied Soft Computing |
Appears in Collections: | Artigo de Periódico |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.