A Genome-Based Model to Predict the Virulence of Pseudomonas aeruginosa Isolates
Pseudomonas aeruginosa is a clinically important Gram-negative opportunistic pathogen. P. aeruginosa shows a large degree of genomic heterogeneity both through variation in sequences found throughout the species (core genome) and through the presence or absence of sequences in different isolates (ac...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
American Society for Microbiology
2020-08-01
|
Series: | mBio |
Subjects: | |
Online Access: | https://doi.org/10.1128/mBio.01527-20 |
id |
doaj-18477388e9ed43e0974f539ffcaf0a4f |
---|---|
record_format |
Article |
spelling |
doaj-18477388e9ed43e0974f539ffcaf0a4f2021-07-02T10:26:55ZengAmerican Society for MicrobiologymBio2150-75112020-08-01114e01527-2010.1128/mBio.01527-20A Genome-Based Model to Predict the Virulence of Pseudomonas aeruginosa IsolatesNathan B. PincusEgon A. OzerJonathan P. AllenMarcus NguyenJames J. DavisDeborah R. WinterChih-Hsien ChuangCheng-Hsun ChiuLaura ZamoranoAntonio OliverAlan R. HauserPseudomonas aeruginosa is a clinically important Gram-negative opportunistic pathogen. P. aeruginosa shows a large degree of genomic heterogeneity both through variation in sequences found throughout the species (core genome) and through the presence or absence of sequences in different isolates (accessory genome). P. aeruginosa isolates also differ markedly in their ability to cause disease. In this study, we used machine learning to predict the virulence level of P. aeruginosa isolates in a mouse bacteremia model based on genomic content. We show that both the accessory and core genomes are predictive of virulence. This study provides a machine learning framework to investigate relationships between bacterial genomes and complex phenotypes such as virulence.Variation in the genome of Pseudomonas aeruginosa, an important pathogen, can have dramatic impacts on the bacterium’s ability to cause disease. We therefore asked whether it was possible to predict the virulence of P. aeruginosa isolates based on their genomic content. We applied a machine learning approach to a genetically and phenotypically diverse collection of 115 clinical P. aeruginosa isolates using genomic information and corresponding virulence phenotypes in a mouse model of bacteremia. We defined the accessory genome of these isolates through the presence or absence of accessory genomic elements (AGEs), sequences present in some strains but not others. Machine learning models trained using AGEs were predictive of virulence, with a mean nested cross-validation accuracy of 75% using the random forest algorithm. However, individual AGEs did not have a large influence on the algorithm’s performance, suggesting instead that virulence predictions are derived from a diffuse genomic signature. These results were validated with an independent test set of 25 P. aeruginosa isolates whose virulence was predicted with 72% accuracy. Machine learning models trained using core genome single-nucleotide variants and whole-genome k-mers also predicted virulence. Our findings are a proof of concept for the use of bacterial genomes to predict pathogenicity in P. aeruginosa and highlight the potential of this approach for predicting patient outcomes.https://doi.org/10.1128/mBio.01527-20pseudomonas aeruginosagenome analysismachine learningmodelingpredictionvirulence |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Nathan B. Pincus Egon A. Ozer Jonathan P. Allen Marcus Nguyen James J. Davis Deborah R. Winter Chih-Hsien Chuang Cheng-Hsun Chiu Laura Zamorano Antonio Oliver Alan R. Hauser |
spellingShingle |
Nathan B. Pincus Egon A. Ozer Jonathan P. Allen Marcus Nguyen James J. Davis Deborah R. Winter Chih-Hsien Chuang Cheng-Hsun Chiu Laura Zamorano Antonio Oliver Alan R. Hauser A Genome-Based Model to Predict the Virulence of Pseudomonas aeruginosa Isolates mBio pseudomonas aeruginosa genome analysis machine learning modeling prediction virulence |
author_facet |
Nathan B. Pincus Egon A. Ozer Jonathan P. Allen Marcus Nguyen James J. Davis Deborah R. Winter Chih-Hsien Chuang Cheng-Hsun Chiu Laura Zamorano Antonio Oliver Alan R. Hauser |
author_sort |
Nathan B. Pincus |
title |
A Genome-Based Model to Predict the Virulence of Pseudomonas aeruginosa Isolates |
title_short |
A Genome-Based Model to Predict the Virulence of Pseudomonas aeruginosa Isolates |
title_full |
A Genome-Based Model to Predict the Virulence of Pseudomonas aeruginosa Isolates |
title_fullStr |
A Genome-Based Model to Predict the Virulence of Pseudomonas aeruginosa Isolates |
title_full_unstemmed |
A Genome-Based Model to Predict the Virulence of Pseudomonas aeruginosa Isolates |
title_sort |
genome-based model to predict the virulence of pseudomonas aeruginosa isolates |
publisher |
American Society for Microbiology |
series |
mBio |
issn |
2150-7511 |
publishDate |
2020-08-01 |
description |
Pseudomonas aeruginosa is a clinically important Gram-negative opportunistic pathogen. P. aeruginosa shows a large degree of genomic heterogeneity both through variation in sequences found throughout the species (core genome) and through the presence or absence of sequences in different isolates (accessory genome). P. aeruginosa isolates also differ markedly in their ability to cause disease. In this study, we used machine learning to predict the virulence level of P. aeruginosa isolates in a mouse bacteremia model based on genomic content. We show that both the accessory and core genomes are predictive of virulence. This study provides a machine learning framework to investigate relationships between bacterial genomes and complex phenotypes such as virulence.Variation in the genome of Pseudomonas aeruginosa, an important pathogen, can have dramatic impacts on the bacterium’s ability to cause disease. We therefore asked whether it was possible to predict the virulence of P. aeruginosa isolates based on their genomic content. We applied a machine learning approach to a genetically and phenotypically diverse collection of 115 clinical P. aeruginosa isolates using genomic information and corresponding virulence phenotypes in a mouse model of bacteremia. We defined the accessory genome of these isolates through the presence or absence of accessory genomic elements (AGEs), sequences present in some strains but not others. Machine learning models trained using AGEs were predictive of virulence, with a mean nested cross-validation accuracy of 75% using the random forest algorithm. However, individual AGEs did not have a large influence on the algorithm’s performance, suggesting instead that virulence predictions are derived from a diffuse genomic signature. These results were validated with an independent test set of 25 P. aeruginosa isolates whose virulence was predicted with 72% accuracy. Machine learning models trained using core genome single-nucleotide variants and whole-genome k-mers also predicted virulence. Our findings are a proof of concept for the use of bacterial genomes to predict pathogenicity in P. aeruginosa and highlight the potential of this approach for predicting patient outcomes. |
topic |
pseudomonas aeruginosa genome analysis machine learning modeling prediction virulence |
url |
https://doi.org/10.1128/mBio.01527-20 |
work_keys_str_mv |
AT nathanbpincus agenomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT egonaozer agenomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT jonathanpallen agenomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT marcusnguyen agenomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT jamesjdavis agenomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT deborahrwinter agenomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT chihhsienchuang agenomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT chenghsunchiu agenomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT laurazamorano agenomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT antoniooliver agenomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT alanrhauser agenomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT nathanbpincus genomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT egonaozer genomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT jonathanpallen genomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT marcusnguyen genomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT jamesjdavis genomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT deborahrwinter genomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT chihhsienchuang genomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT chenghsunchiu genomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT laurazamorano genomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT antoniooliver genomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates AT alanrhauser genomebasedmodeltopredictthevirulenceofpseudomonasaeruginosaisolates |
_version_ |
1721331970330329088 |