Synthetic antimicrobial peptides generation using recurrent neural networks
Abstract The antimicrobial peptides (AMPs) have taken importance in the development of new antibiotics because of their role as an inhibitor, not only of bacteria but also of viruses, fungi and parasites, among others. Since the discovery of AMPs, thousands have been reported, however, many of them are not suitable for therapeutic applications due to their long amino acid sequences, low antimicrobial potency and high production costs. In this work, we propose to use recurrent neural networks (RNN) with LSTM cells in order to generate more potent and economical peptides. We perform different experiments generating synthetic AMPs between 12 and 20 amino acids. The results show that we can use RNN and improve the generation process compared with the template method.
Main Authors: | , , , |
---|---|
Format: | Digital revista |
Language: | English |
Published: |
Universidad Nacional de Colombia
2021
|
Online Access: | http://www.scielo.org.co/scielo.php?script=sci_arttext&pid=S0012-73532021000100210 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
oai:scielo:S0012-73532021000100210 |
---|---|
record_format |
ojs |
spelling |
oai:scielo:S0012-735320210001002102021-06-03Synthetic antimicrobial peptides generation using recurrent neural networksVélez,AndrésMera,CarlosOrduz,SergioBranch,John W. antimicrobial resistance synthetic peptides virtual screening deep learning Abstract The antimicrobial peptides (AMPs) have taken importance in the development of new antibiotics because of their role as an inhibitor, not only of bacteria but also of viruses, fungi and parasites, among others. Since the discovery of AMPs, thousands have been reported, however, many of them are not suitable for therapeutic applications due to their long amino acid sequences, low antimicrobial potency and high production costs. In this work, we propose to use recurrent neural networks (RNN) with LSTM cells in order to generate more potent and economical peptides. We perform different experiments generating synthetic AMPs between 12 and 20 amino acids. The results show that we can use RNN and improve the generation process compared with the template method.info:eu-repo/semantics/openAccessUniversidad Nacional de ColombiaDYNA v.88 n.216 20212021-03-01info:eu-repo/semantics/articletext/htmlhttp://www.scielo.org.co/scielo.php?script=sci_arttext&pid=S0012-73532021000100210en10.15446/dyna.v88n216.88799 |
institution |
SCIELO |
collection |
OJS |
country |
Colombia |
countrycode |
CO |
component |
Revista |
access |
En linea |
databasecode |
rev-scielo-co |
tag |
revista |
region |
America del Sur |
libraryname |
SciELO |
language |
English |
format |
Digital |
author |
Vélez,Andrés Mera,Carlos Orduz,Sergio Branch,John W. |
spellingShingle |
Vélez,Andrés Mera,Carlos Orduz,Sergio Branch,John W. Synthetic antimicrobial peptides generation using recurrent neural networks |
author_facet |
Vélez,Andrés Mera,Carlos Orduz,Sergio Branch,John W. |
author_sort |
Vélez,Andrés |
title |
Synthetic antimicrobial peptides generation using recurrent neural networks |
title_short |
Synthetic antimicrobial peptides generation using recurrent neural networks |
title_full |
Synthetic antimicrobial peptides generation using recurrent neural networks |
title_fullStr |
Synthetic antimicrobial peptides generation using recurrent neural networks |
title_full_unstemmed |
Synthetic antimicrobial peptides generation using recurrent neural networks |
title_sort |
synthetic antimicrobial peptides generation using recurrent neural networks |
description |
Abstract The antimicrobial peptides (AMPs) have taken importance in the development of new antibiotics because of their role as an inhibitor, not only of bacteria but also of viruses, fungi and parasites, among others. Since the discovery of AMPs, thousands have been reported, however, many of them are not suitable for therapeutic applications due to their long amino acid sequences, low antimicrobial potency and high production costs. In this work, we propose to use recurrent neural networks (RNN) with LSTM cells in order to generate more potent and economical peptides. We perform different experiments generating synthetic AMPs between 12 and 20 amino acids. The results show that we can use RNN and improve the generation process compared with the template method. |
publisher |
Universidad Nacional de Colombia |
publishDate |
2021 |
url |
http://www.scielo.org.co/scielo.php?script=sci_arttext&pid=S0012-73532021000100210 |
work_keys_str_mv |
AT velezandres syntheticantimicrobialpeptidesgenerationusingrecurrentneuralnetworks AT meracarlos syntheticantimicrobialpeptidesgenerationusingrecurrentneuralnetworks AT orduzsergio syntheticantimicrobialpeptidesgenerationusingrecurrentneuralnetworks AT branchjohnw syntheticantimicrobialpeptidesgenerationusingrecurrentneuralnetworks |
_version_ |
1755932763810168832 |