Towards Identify Selective Antibacterial Peptides Based on Abstracts MeaningReportar como inadecuado

Towards Identify Selective Antibacterial Peptides Based on Abstracts Meaning - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Computational and Mathematical Methods in Medicine - Volume 2016 2016, Article ID 1505261, 11 pages -

Research Article

University of Guadalajara, Guadalajara, JAL, Mexico

Technical and Industrial Teaching Center, Guadalajara, JAL, Mexico

The College of the South Border ECOSUR, Tapachula, CHIS, Mexico

Received 12 February 2016; Revised 21 April 2016; Accepted 21 April 2016

Academic Editor: Emil Alexov

Copyright © 2016 Liliana I. Barbosa-Santillán et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


We present an Identify Selective Antibacterial Peptides ISAP approach based on abstracts meaning. Laboratories and researchers have significantly increased the report of their discoveries related to antibacterial peptides in primary publications. It is important to find antibacterial peptides that have been reported in primary publications because they can produce antibiotics of different generations that attack and destroy the bacteria. Unfortunately, researchers used heterogeneous forms of natural language to describe their discoveries sometimes without the sequence of the peptides. Thus, we propose that learning the words meaning instead of the antibacterial peptides sequence is possible to identify and predict antibacterial peptides reported in the PubMed engine. The ISAP approach consists of two stages: training and discovering. ISAP founds that the 35% of the abstracts sample had antibacterial peptides and we tested in the updated Antimicrobial Peptide Database 2 APD2. ISAP predicted that 45% of the abstracts had antibacterial peptides. That is, ISAP found that 810 antibacterial peptides were not classified like that, so they are not reported in APD2. As a result, this new search tool would complement the APD2 with a set of peptides that are candidates to be antibacterial. Finally, 20% of the abstracts were not semantic related to APD2.

Autor: Liliana I. Barbosa-Santillán, Juan J. Sánchez-Escobar, M. Angeles Calixto-Romo, and Luis F. Barbosa-Santillán



Documentos relacionados