Predicting cell-penetrating peptides using machine learning algorithms and navigating in their chemical space

Abstract Cell-penetrating peptides (CPPs) are naturally able to cross the lipid bilayer membrane that protects cells. These peptides share common structural and physicochemical properties and show different pharmaceutical applications, among which drug delivery is the most important. Due to their ab...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ewerton Cristhian Lima de Oliveira, Kauê Santana, Luiz Josino, Anderson Henrique Lima e Lima, Claudomiro de Souza de Sales Júnior
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/008fb2a4424c40229b36420953d305c0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:008fb2a4424c40229b36420953d305c0
record_format	dspace
spelling	oai:doaj.org-article:008fb2a4424c40229b36420953d305c02021-12-02T14:37:08ZPredicting cell-penetrating peptides using machine learning algorithms and navigating in their chemical space10.1038/s41598-021-87134-w2045-2322https://doaj.org/article/008fb2a4424c40229b36420953d305c02021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87134-whttps://doaj.org/toc/2045-2322Abstract Cell-penetrating peptides (CPPs) are naturally able to cross the lipid bilayer membrane that protects cells. These peptides share common structural and physicochemical properties and show different pharmaceutical applications, among which drug delivery is the most important. Due to their ability to cross the membranes by pulling high-molecular-weight polar molecules, they are termed Trojan horses. In this study, we proposed a machine learning (ML)-based framework named BChemRF-CPPred (b eyond chem ical r ules-based f ramework for CPP pred iction) that uses an artificial neural network, a support vector machine, and a Gaussian process classifier to differentiate CPPs from non-CPPs, using structure- and sequence-based descriptors extracted from PDB and FASTA formats. The performance of our algorithm was evaluated by tenfold cross-validation and compared with those of previously reported prediction tools using an independent dataset. The BChemRF-CPPred satisfactorily identified CPP-like structures using natural and synthetic modified peptide libraries and also obtained better performance than those of previously reported ML-based algorithms, reaching the independent test accuracy of 90.66% (AUC = 0.9365) for PDB, and an accuracy of 86.5% (AUC = 0.9216) for FASTA input. Moreover, our analyses of the CPP chemical space demonstrated that these peptides break some molecular rules related to the prediction of permeability of therapeutic molecules in cell membranes. This is the first comprehensive analysis to predict synthetic and natural CPP structures and to evaluate their chemical space using an ML-based framework. Our algorithm is freely available for academic use at http://comptools.linc.ufpa.br/BChemRF-CPPred .Ewerton Cristhian Lima de OliveiraKauê SantanaLuiz JosinoAnderson Henrique Lima e LimaClaudomiro de Souza de Sales JúniorNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Ewerton Cristhian Lima de Oliveira Kauê Santana Luiz Josino Anderson Henrique Lima e Lima Claudomiro de Souza de Sales Júnior Predicting cell-penetrating peptides using machine learning algorithms and navigating in their chemical space
description	Abstract Cell-penetrating peptides (CPPs) are naturally able to cross the lipid bilayer membrane that protects cells. These peptides share common structural and physicochemical properties and show different pharmaceutical applications, among which drug delivery is the most important. Due to their ability to cross the membranes by pulling high-molecular-weight polar molecules, they are termed Trojan horses. In this study, we proposed a machine learning (ML)-based framework named BChemRF-CPPred (b eyond chem ical r ules-based f ramework for CPP pred iction) that uses an artificial neural network, a support vector machine, and a Gaussian process classifier to differentiate CPPs from non-CPPs, using structure- and sequence-based descriptors extracted from PDB and FASTA formats. The performance of our algorithm was evaluated by tenfold cross-validation and compared with those of previously reported prediction tools using an independent dataset. The BChemRF-CPPred satisfactorily identified CPP-like structures using natural and synthetic modified peptide libraries and also obtained better performance than those of previously reported ML-based algorithms, reaching the independent test accuracy of 90.66% (AUC = 0.9365) for PDB, and an accuracy of 86.5% (AUC = 0.9216) for FASTA input. Moreover, our analyses of the CPP chemical space demonstrated that these peptides break some molecular rules related to the prediction of permeability of therapeutic molecules in cell membranes. This is the first comprehensive analysis to predict synthetic and natural CPP structures and to evaluate their chemical space using an ML-based framework. Our algorithm is freely available for academic use at http://comptools.linc.ufpa.br/BChemRF-CPPred .
format	article
author	Ewerton Cristhian Lima de Oliveira Kauê Santana Luiz Josino Anderson Henrique Lima e Lima Claudomiro de Souza de Sales Júnior
author_facet	Ewerton Cristhian Lima de Oliveira Kauê Santana Luiz Josino Anderson Henrique Lima e Lima Claudomiro de Souza de Sales Júnior
author_sort	Ewerton Cristhian Lima de Oliveira
title	Predicting cell-penetrating peptides using machine learning algorithms and navigating in their chemical space
title_short	Predicting cell-penetrating peptides using machine learning algorithms and navigating in their chemical space
title_full	Predicting cell-penetrating peptides using machine learning algorithms and navigating in their chemical space
title_fullStr	Predicting cell-penetrating peptides using machine learning algorithms and navigating in their chemical space
title_full_unstemmed	Predicting cell-penetrating peptides using machine learning algorithms and navigating in their chemical space
title_sort	predicting cell-penetrating peptides using machine learning algorithms and navigating in their chemical space
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/008fb2a4424c40229b36420953d305c0
work_keys_str_mv	AT ewertoncristhianlimadeoliveira predictingcellpenetratingpeptidesusingmachinelearningalgorithmsandnavigatingintheirchemicalspace AT kauesantana predictingcellpenetratingpeptidesusingmachinelearningalgorithmsandnavigatingintheirchemicalspace AT luizjosino predictingcellpenetratingpeptidesusingmachinelearningalgorithmsandnavigatingintheirchemicalspace AT andersonhenriquelimaelima predictingcellpenetratingpeptidesusingmachinelearningalgorithmsandnavigatingintheirchemicalspace AT claudomirodesouzadesalesjunior predictingcellpenetratingpeptidesusingmachinelearningalgorithmsandnavigatingintheirchemicalspace
_version_	1718390990560034816

Predicting cell-penetrating peptides using machine learning algorithms and navigating in their chemical space

Ejemplares similares