Predicting bacteriophage hosts based on sequences of annotated receptor-binding proteins

Abstract Nowadays, bacteriophages are increasingly considered as an alternative treatment for a variety of bacterial infections in cases where classical antibiotics have become ineffective. However, characterizing the host specificity of phages remains a labor- and time-intensive process. In order t...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Dimitri Boeckaerts, Michiel Stock, Bjorn Criel, Hans Gerstmans, Bernard De Baets, Yves Briers
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/e50571a47871445980ba53df088626f8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e50571a47871445980ba53df088626f8
record_format	dspace
spelling	oai:doaj.org-article:e50571a47871445980ba53df088626f82021-12-02T14:12:07ZPredicting bacteriophage hosts based on sequences of annotated receptor-binding proteins10.1038/s41598-021-81063-42045-2322https://doaj.org/article/e50571a47871445980ba53df088626f82021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-81063-4https://doaj.org/toc/2045-2322Abstract Nowadays, bacteriophages are increasingly considered as an alternative treatment for a variety of bacterial infections in cases where classical antibiotics have become ineffective. However, characterizing the host specificity of phages remains a labor- and time-intensive process. In order to alleviate this burden, we have developed a new machine-learning-based pipeline to predict bacteriophage hosts based on annotated receptor-binding protein (RBP) sequence data. We focus on predicting bacterial hosts from the ESKAPE group, Escherichia coli, Salmonella enterica and Clostridium difficile. We compare the performance of our predictive model with that of the widely used Basic Local Alignment Search Tool (BLAST). Our best-performing predictive model reaches Precision-Recall Area Under the Curve (PR-AUC) scores between 73.6 and 93.8% for different levels of sequence similarity in the collected data. Our model reaches a performance comparable to that of BLASTp when sequence similarity in the data is high and starts outperforming BLASTp when sequence similarity drops below 75%. Therefore, our machine learning methods can be especially useful in settings in which sequence similarity to other known sequences is low. Predicting the hosts of novel metagenomic RBP sequences could extend our toolbox to tune the host spectrum of phages or phage tail-like bacteriocins by swapping RBPs.Dimitri BoeckaertsMichiel StockBjorn CrielHans GerstmansBernard De BaetsYves BriersNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Dimitri Boeckaerts Michiel Stock Bjorn Criel Hans Gerstmans Bernard De Baets Yves Briers Predicting bacteriophage hosts based on sequences of annotated receptor-binding proteins
description	Abstract Nowadays, bacteriophages are increasingly considered as an alternative treatment for a variety of bacterial infections in cases where classical antibiotics have become ineffective. However, characterizing the host specificity of phages remains a labor- and time-intensive process. In order to alleviate this burden, we have developed a new machine-learning-based pipeline to predict bacteriophage hosts based on annotated receptor-binding protein (RBP) sequence data. We focus on predicting bacterial hosts from the ESKAPE group, Escherichia coli, Salmonella enterica and Clostridium difficile. We compare the performance of our predictive model with that of the widely used Basic Local Alignment Search Tool (BLAST). Our best-performing predictive model reaches Precision-Recall Area Under the Curve (PR-AUC) scores between 73.6 and 93.8% for different levels of sequence similarity in the collected data. Our model reaches a performance comparable to that of BLASTp when sequence similarity in the data is high and starts outperforming BLASTp when sequence similarity drops below 75%. Therefore, our machine learning methods can be especially useful in settings in which sequence similarity to other known sequences is low. Predicting the hosts of novel metagenomic RBP sequences could extend our toolbox to tune the host spectrum of phages or phage tail-like bacteriocins by swapping RBPs.
format	article
author	Dimitri Boeckaerts Michiel Stock Bjorn Criel Hans Gerstmans Bernard De Baets Yves Briers
author_facet	Dimitri Boeckaerts Michiel Stock Bjorn Criel Hans Gerstmans Bernard De Baets Yves Briers
author_sort	Dimitri Boeckaerts
title	Predicting bacteriophage hosts based on sequences of annotated receptor-binding proteins
title_short	Predicting bacteriophage hosts based on sequences of annotated receptor-binding proteins
title_full	Predicting bacteriophage hosts based on sequences of annotated receptor-binding proteins
title_fullStr	Predicting bacteriophage hosts based on sequences of annotated receptor-binding proteins
title_full_unstemmed	Predicting bacteriophage hosts based on sequences of annotated receptor-binding proteins
title_sort	predicting bacteriophage hosts based on sequences of annotated receptor-binding proteins
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/e50571a47871445980ba53df088626f8
work_keys_str_mv	AT dimitriboeckaerts predictingbacteriophagehostsbasedonsequencesofannotatedreceptorbindingproteins AT michielstock predictingbacteriophagehostsbasedonsequencesofannotatedreceptorbindingproteins AT bjorncriel predictingbacteriophagehostsbasedonsequencesofannotatedreceptorbindingproteins AT hansgerstmans predictingbacteriophagehostsbasedonsequencesofannotatedreceptorbindingproteins AT bernarddebaets predictingbacteriophagehostsbasedonsequencesofannotatedreceptorbindingproteins AT yvesbriers predictingbacteriophagehostsbasedonsequencesofannotatedreceptorbindingproteins
_version_	1718391876307910656

Predicting bacteriophage hosts based on sequences of annotated receptor-binding proteins

Ejemplares similares