Predicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning

Abstract Background Prokaryotic viruses, which infect bacteria and archaea, are the most abundant and diverse biological entities in the biosphere. To understand their regulatory roles in various ecosystems and to harness the potential of bacteriophages for use in therapy, more knowledge of viral-ho...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jiayu Shang, Yanni Sun
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Prediction of virus-host interactions Deep learning Graph convolutional neural network Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/cb95452b3ffb461eb7c9d39846bf9ffb
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cb95452b3ffb461eb7c9d39846bf9ffb
record_format	dspace
spelling	oai:doaj.org-article:cb95452b3ffb461eb7c9d39846bf9ffb2021-11-28T12:41:11ZPredicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning10.1186/s12915-021-01180-41741-7007https://doaj.org/article/cb95452b3ffb461eb7c9d39846bf9ffb2021-11-01T00:00:00Zhttps://doi.org/10.1186/s12915-021-01180-4https://doaj.org/toc/1741-7007Abstract Background Prokaryotic viruses, which infect bacteria and archaea, are the most abundant and diverse biological entities in the biosphere. To understand their regulatory roles in various ecosystems and to harness the potential of bacteriophages for use in therapy, more knowledge of viral-host relationships is required. High-throughput sequencing and its application to the microbiome have offered new opportunities for computational approaches for predicting which hosts particular viruses can infect. However, there are two main challenges for computational host prediction. First, the empirically known virus-host relationships are very limited. Second, although sequence similarity between viruses and their prokaryote hosts have been used as a major feature for host prediction, the alignment is either missing or ambiguous in many cases. Thus, there is still a need to improve the accuracy of host prediction. Results In this work, we present a semi-supervised learning model, named HostG, to conduct host prediction for novel viruses. We construct a knowledge graph by utilizing both virus-virus protein similarity and virus-host DNA sequence similarity. Then graph convolutional network (GCN) is adopted to exploit viruses with or without known hosts in training to enhance the learning ability. During the GCN training, we minimize the expected calibrated error (ECE) to ensure the confidence of the predictions. We tested HostG on both simulated and real sequencing data and compared its performance with other state-of-the-art methods specifically designed for virus host classification (VHM-net, WIsH, PHP, HoPhage, RaFAH, vHULK, and VPF-Class). Conclusion HostG outperforms other popular methods, demonstrating the efficacy of using a GCN-based semi-supervised learning approach. A particular advantage of HostG is its ability to predict hosts from new taxa.Jiayu ShangYanni SunBMCarticlePrediction of virus-host interactionsDeep learningGraph convolutional neural networkBiology (General)QH301-705.5ENBMC Biology, Vol 19, Iss 1, Pp 1-15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Prediction of virus-host interactions Deep learning Graph convolutional neural network Biology (General) QH301-705.5
spellingShingle	Prediction of virus-host interactions Deep learning Graph convolutional neural network Biology (General) QH301-705.5 Jiayu Shang Yanni Sun Predicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning
description	Abstract Background Prokaryotic viruses, which infect bacteria and archaea, are the most abundant and diverse biological entities in the biosphere. To understand their regulatory roles in various ecosystems and to harness the potential of bacteriophages for use in therapy, more knowledge of viral-host relationships is required. High-throughput sequencing and its application to the microbiome have offered new opportunities for computational approaches for predicting which hosts particular viruses can infect. However, there are two main challenges for computational host prediction. First, the empirically known virus-host relationships are very limited. Second, although sequence similarity between viruses and their prokaryote hosts have been used as a major feature for host prediction, the alignment is either missing or ambiguous in many cases. Thus, there is still a need to improve the accuracy of host prediction. Results In this work, we present a semi-supervised learning model, named HostG, to conduct host prediction for novel viruses. We construct a knowledge graph by utilizing both virus-virus protein similarity and virus-host DNA sequence similarity. Then graph convolutional network (GCN) is adopted to exploit viruses with or without known hosts in training to enhance the learning ability. During the GCN training, we minimize the expected calibrated error (ECE) to ensure the confidence of the predictions. We tested HostG on both simulated and real sequencing data and compared its performance with other state-of-the-art methods specifically designed for virus host classification (VHM-net, WIsH, PHP, HoPhage, RaFAH, vHULK, and VPF-Class). Conclusion HostG outperforms other popular methods, demonstrating the efficacy of using a GCN-based semi-supervised learning approach. A particular advantage of HostG is its ability to predict hosts from new taxa.
format	article
author	Jiayu Shang Yanni Sun
author_facet	Jiayu Shang Yanni Sun
author_sort	Jiayu Shang
title	Predicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning
title_short	Predicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning
title_full	Predicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning
title_fullStr	Predicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning
title_full_unstemmed	Predicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning
title_sort	predicting the hosts of prokaryotic viruses using gcn-based semi-supervised learning
publisher	BMC
publishDate	2021
url	https://doaj.org/article/cb95452b3ffb461eb7c9d39846bf9ffb
work_keys_str_mv	AT jiayushang predictingthehostsofprokaryoticvirusesusinggcnbasedsemisupervisedlearning AT yannisun predictingthehostsofprokaryoticvirusesusinggcnbasedsemisupervisedlearning
_version_	1718407859002146816

Predicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning

Ejemplares similares