iPHoP: An integrated machine learning framework to maximize host prediction for metagenome-derived viruses of archaea and bacteria

Simon Roux; Antonio Pedro Camargo; Felipe H Coutinho; Shareef M Dabdoub; Bas E Dutilh; Stephen Nayfach; Andrew Tritt

doi:10.1371/journal.pbio.3002083

Back

iPHoP: An integrated machine learning framework to maximize host prediction for metagenome-derived viruses of archaea and bacteria

Journal article

Open access

Peer reviewed

iPHoP: An integrated machine learning framework to maximize host prediction for metagenome-derived viruses of archaea and bacteria

Simon Roux, Antonio Pedro Camargo, Felipe H Coutinho, Shareef M Dabdoub, Bas E Dutilh, Stephen Nayfach and Andrew Tritt

PLoS biology, Vol.21(4), e3002083

04/21/2023

DOI: 10.1371/journal.pbio.3002083

PMCID: PMC10155999

PMID: 37083735

Files and links (1)

url

https://doi.org/10.1371/journal.pbio.3002083View

Published (Version of record) Open Access

Abstract

The extraordinary diversity of viruses infecting bacteria and archaea is now primarily studied through metagenomics. While metagenomes enable high-throughput exploration of the viral sequence space, metagenome-derived sequences lack key information compared to isolated viruses, in particular host association. Different computational approaches are available to predict the host(s) of uncultivated viruses based on their genome sequences, but thus far individual approaches are limited either in precision or in recall, i.e., for a number of viruses they yield erroneous predictions or no prediction at all. Here, we describe iPHoP, a two-step framework that integrates multiple methods to reliably predict host taxonomy at the genus rank for a broad range of viruses infecting bacteria and archaea, while retaining a low false discovery rate. Based on a large dataset of metagenome-derived virus genomes from the IMG/VR database, we illustrate how iPHoP can provide extensive host prediction and guide further characterization of uncultivated viruses.

Details

Title: Subtitle: iPHoP: An integrated machine learning framework to maximize host prediction for metagenome-derived viruses of archaea and bacteria
Creators: Simon Roux - Lawrence Berkeley National Laboratory
Antonio Pedro Camargo - Lawrence Berkeley National Laboratory
Felipe H Coutinho - Instituto de Ciencias del Mar (ICM-CSIC), Barcelona, Spain
Shareef M Dabdoub - University of Iowa
Bas E Dutilh - Utrecht University
Stephen Nayfach - Lawrence Berkeley National Laboratory
Andrew Tritt - Lawrence Berkeley National Laboratory
Resource Type: Journal article
Publication Details: PLoS biology, Vol.21(4), e3002083
DOI: 10.1371/journal.pbio.3002083
PMID: 37083735
PMCID: PMC10155999
NLM abbreviation: PLoS Biol
ISSN: 1544-9173
eISSN: 1545-7885
Grant note: DOI: 10.13039/501100000781, name: European Research Council, award: 865694; DOI: 10.13039/501100001659, name: Deutsche Forschungsgemeinschaft, award: 390713860; DOI: 10.13039/100005156, name: Alexander von Humboldt-Stiftung; DOI: 10.13039/100018694, name: HORIZON EUROPE Marie Sklodowska-Curie Actions, award: 955974; name: Juan de la Cierva - Incoporacion fellowship, award: IJC2019-039859-I; name: Severo Ochoa Centre of Excellence, award: CEX2019-000928-S; DOI: 10.13039/100006206, name: Biological and Environmental Research, award: DE-AC02-05CH11231
Language: English
Date published: 04/21/2023
Academic Unit: Dental Research; Periodontics
Record Identifier: 9984398208202771

Metrics

24 Record Views

252 Times Cited - Web of Science

See more details