Prediction of antimicrobial peptides toxicity based on their physico-chemical properties using machine learning techniques

Abstract Background Antimicrobial peptides are promising tools to fight against ever-growing antibiotic resistance. However, despite many advantages, their toxicity to mammalian cells is a critical obstacle in clinical application and needs to be addressed. Results In this study, by using an up-to-d...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hossein Khabbaz, Mohammad Hossein Karimi-Jafari, Ali Akbar Saboury, Bagher BabaAli
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Antimicrobial peptides Peptide toxicity Machine learning Physico-chemical properties Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/1c0cb3e61e1b44b4b78f6a7e30f8888e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1c0cb3e61e1b44b4b78f6a7e30f8888e
record_format	dspace
spelling	oai:doaj.org-article:1c0cb3e61e1b44b4b78f6a7e30f8888e2021-11-14T12:13:13ZPrediction of antimicrobial peptides toxicity based on their physico-chemical properties using machine learning techniques10.1186/s12859-021-04468-y1471-2105https://doaj.org/article/1c0cb3e61e1b44b4b78f6a7e30f8888e2021-11-01T00:00:00Zhttps://doi.org/10.1186/s12859-021-04468-yhttps://doaj.org/toc/1471-2105Abstract Background Antimicrobial peptides are promising tools to fight against ever-growing antibiotic resistance. However, despite many advantages, their toxicity to mammalian cells is a critical obstacle in clinical application and needs to be addressed. Results In this study, by using an up-to-date dataset, a machine learning model has been trained successfully to predict the toxicity of antimicrobial peptides. The comprehensive set of features of both physico-chemical and linguistic-based with local and global essences have undergone feature selection to identify key properties behind toxicity of antimicrobial peptides. After feature selection, the hybrid model showed the best performance with a recall of 0. 876 and a F1 score of 0. 849. Conclusions The obtained model can be useful in extracting AMPs with low toxicity from AMP libraries in clinical applications. On the other hand, several properties with local nature including positions of strand forming and hydrophobic residues in final selected features show that these properties are critical definer of peptide properties and should be considered in developing models for activity prediction of peptides. The executable code is available at https://git.io/JRZaT .Hossein KhabbazMohammad Hossein Karimi-JafariAli Akbar SabouryBagher BabaAliBMCarticleAntimicrobial peptidesPeptide toxicityMachine learningPhysico-chemical propertiesComputer applications to medicine. Medical informaticsR858-859.7Biology (General)QH301-705.5ENBMC Bioinformatics, Vol 22, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Antimicrobial peptides Peptide toxicity Machine learning Physico-chemical properties Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5
spellingShingle	Antimicrobial peptides Peptide toxicity Machine learning Physico-chemical properties Computer applications to medicine. Medical informatics R858-859.7 Biology (General) QH301-705.5 Hossein Khabbaz Mohammad Hossein Karimi-Jafari Ali Akbar Saboury Bagher BabaAli Prediction of antimicrobial peptides toxicity based on their physico-chemical properties using machine learning techniques
description	Abstract Background Antimicrobial peptides are promising tools to fight against ever-growing antibiotic resistance. However, despite many advantages, their toxicity to mammalian cells is a critical obstacle in clinical application and needs to be addressed. Results In this study, by using an up-to-date dataset, a machine learning model has been trained successfully to predict the toxicity of antimicrobial peptides. The comprehensive set of features of both physico-chemical and linguistic-based with local and global essences have undergone feature selection to identify key properties behind toxicity of antimicrobial peptides. After feature selection, the hybrid model showed the best performance with a recall of 0. 876 and a F1 score of 0. 849. Conclusions The obtained model can be useful in extracting AMPs with low toxicity from AMP libraries in clinical applications. On the other hand, several properties with local nature including positions of strand forming and hydrophobic residues in final selected features show that these properties are critical definer of peptide properties and should be considered in developing models for activity prediction of peptides. The executable code is available at https://git.io/JRZaT .
format	article
author	Hossein Khabbaz Mohammad Hossein Karimi-Jafari Ali Akbar Saboury Bagher BabaAli
author_facet	Hossein Khabbaz Mohammad Hossein Karimi-Jafari Ali Akbar Saboury Bagher BabaAli
author_sort	Hossein Khabbaz
title	Prediction of antimicrobial peptides toxicity based on their physico-chemical properties using machine learning techniques
title_short	Prediction of antimicrobial peptides toxicity based on their physico-chemical properties using machine learning techniques
title_full	Prediction of antimicrobial peptides toxicity based on their physico-chemical properties using machine learning techniques
title_fullStr	Prediction of antimicrobial peptides toxicity based on their physico-chemical properties using machine learning techniques
title_full_unstemmed	Prediction of antimicrobial peptides toxicity based on their physico-chemical properties using machine learning techniques
title_sort	prediction of antimicrobial peptides toxicity based on their physico-chemical properties using machine learning techniques
publisher	BMC
publishDate	2021
url	https://doaj.org/article/1c0cb3e61e1b44b4b78f6a7e30f8888e
work_keys_str_mv	AT hosseinkhabbaz predictionofantimicrobialpeptidestoxicitybasedontheirphysicochemicalpropertiesusingmachinelearningtechniques AT mohammadhosseinkarimijafari predictionofantimicrobialpeptidestoxicitybasedontheirphysicochemicalpropertiesusingmachinelearningtechniques AT aliakbarsaboury predictionofantimicrobialpeptidestoxicitybasedontheirphysicochemicalpropertiesusingmachinelearningtechniques AT bagherbabaali predictionofantimicrobialpeptidestoxicitybasedontheirphysicochemicalpropertiesusingmachinelearningtechniques
_version_	1718429332515323904

Prediction of antimicrobial peptides toxicity based on their physico-chemical properties using machine learning techniques

Ejemplares similares