Improved Prediction of Bacterial Genotype-Phenotype Associations Using Interpretable Pangenome-Spanning Regressions

ABSTRACT Discovery of genetic variants underlying bacterial phenotypes and the prediction of phenotypes such as antibiotic resistance are fundamental tasks in bacterial genomics. Genome-wide association study (GWAS) methods have been applied to study these relations, but the plastic nature of bacter...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	John A. Lees, T. Tien Mai, Marco Galardini, Nicole E. Wheeler, Samuel T. Horsfield, Julian Parkhill, Jukka Corander
Formato:	article
Lenguaje:	EN
Publicado:	American Society for Microbiology 2020
Materias:	elastic net pangenome phenotype prediction Microbiology QR1-502
Acceso en línea:	https://doaj.org/article/39a9c15c29234af282ab753ee02f2acb
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:39a9c15c29234af282ab753ee02f2acb
record_format	dspace
spelling	oai:doaj.org-article:39a9c15c29234af282ab753ee02f2acb2021-11-15T15:56:44ZImproved Prediction of Bacterial Genotype-Phenotype Associations Using Interpretable Pangenome-Spanning Regressions10.1128/mBio.01344-202150-7511https://doaj.org/article/39a9c15c29234af282ab753ee02f2acb2020-08-01T00:00:00Zhttps://journals.asm.org/doi/10.1128/mBio.01344-20https://doaj.org/toc/2150-7511ABSTRACT Discovery of genetic variants underlying bacterial phenotypes and the prediction of phenotypes such as antibiotic resistance are fundamental tasks in bacterial genomics. Genome-wide association study (GWAS) methods have been applied to study these relations, but the plastic nature of bacterial genomes and the clonal structure of bacterial populations creates challenges. We introduce an alignment-free method which finds sets of loci associated with bacterial phenotypes, quantifies the total effect of genetics on the phenotype, and allows accurate phenotype prediction, all within a single computationally scalable joint modeling framework. Genetic variants covering the entire pangenome are compactly represented by extended DNA sequence words known as unitigs, and model fitting is achieved using elastic net penalization, an extension of standard multiple regression. Using an extensive set of state-of-the-art bacterial population genomic data sets, we demonstrate that our approach performs accurate phenotype prediction, comparable to popular machine learning methods, while retaining both interpretability and computational efficiency. Compared to those of previous approaches, which test each genotype-phenotype association separately for each variant and apply a significance threshold, the variants selected by our joint modeling approach overlap substantially. IMPORTANCE Being able to identify the genetic variants responsible for specific bacterial phenotypes has been the goal of bacterial genetics since its inception and is fundamental to our current level of understanding of bacteria. This identification has been based primarily on painstaking experimentation, but the availability of large data sets of whole genomes with associated phenotype metadata promises to revolutionize this approach, not least for important clinical phenotypes that are not amenable to laboratory analysis. These models of phenotype-genotype association can in the future be used for rapid prediction of clinically important phenotypes such as antibiotic resistance and virulence by rapid-turnaround or point-of-care tests. However, despite much effort being put into adapting genome-wide association study (GWAS) approaches to cope with bacterium-specific problems, such as strong population structure and horizontal gene exchange, current approaches are not yet optimal. We describe a method that advances methodology for both association and generation of portable prediction models.John A. LeesT. Tien MaiMarco GalardiniNicole E. WheelerSamuel T. HorsfieldJulian ParkhillJukka CoranderAmerican Society for Microbiologyarticleelastic netpangenomephenotype predictionMicrobiologyQR1-502ENmBio, Vol 11, Iss 4 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	elastic net pangenome phenotype prediction Microbiology QR1-502
spellingShingle	elastic net pangenome phenotype prediction Microbiology QR1-502 John A. Lees T. Tien Mai Marco Galardini Nicole E. Wheeler Samuel T. Horsfield Julian Parkhill Jukka Corander Improved Prediction of Bacterial Genotype-Phenotype Associations Using Interpretable Pangenome-Spanning Regressions
description	ABSTRACT Discovery of genetic variants underlying bacterial phenotypes and the prediction of phenotypes such as antibiotic resistance are fundamental tasks in bacterial genomics. Genome-wide association study (GWAS) methods have been applied to study these relations, but the plastic nature of bacterial genomes and the clonal structure of bacterial populations creates challenges. We introduce an alignment-free method which finds sets of loci associated with bacterial phenotypes, quantifies the total effect of genetics on the phenotype, and allows accurate phenotype prediction, all within a single computationally scalable joint modeling framework. Genetic variants covering the entire pangenome are compactly represented by extended DNA sequence words known as unitigs, and model fitting is achieved using elastic net penalization, an extension of standard multiple regression. Using an extensive set of state-of-the-art bacterial population genomic data sets, we demonstrate that our approach performs accurate phenotype prediction, comparable to popular machine learning methods, while retaining both interpretability and computational efficiency. Compared to those of previous approaches, which test each genotype-phenotype association separately for each variant and apply a significance threshold, the variants selected by our joint modeling approach overlap substantially. IMPORTANCE Being able to identify the genetic variants responsible for specific bacterial phenotypes has been the goal of bacterial genetics since its inception and is fundamental to our current level of understanding of bacteria. This identification has been based primarily on painstaking experimentation, but the availability of large data sets of whole genomes with associated phenotype metadata promises to revolutionize this approach, not least for important clinical phenotypes that are not amenable to laboratory analysis. These models of phenotype-genotype association can in the future be used for rapid prediction of clinically important phenotypes such as antibiotic resistance and virulence by rapid-turnaround or point-of-care tests. However, despite much effort being put into adapting genome-wide association study (GWAS) approaches to cope with bacterium-specific problems, such as strong population structure and horizontal gene exchange, current approaches are not yet optimal. We describe a method that advances methodology for both association and generation of portable prediction models.
format	article
author	John A. Lees T. Tien Mai Marco Galardini Nicole E. Wheeler Samuel T. Horsfield Julian Parkhill Jukka Corander
author_facet	John A. Lees T. Tien Mai Marco Galardini Nicole E. Wheeler Samuel T. Horsfield Julian Parkhill Jukka Corander
author_sort	John A. Lees
title	Improved Prediction of Bacterial Genotype-Phenotype Associations Using Interpretable Pangenome-Spanning Regressions
title_short	Improved Prediction of Bacterial Genotype-Phenotype Associations Using Interpretable Pangenome-Spanning Regressions
title_full	Improved Prediction of Bacterial Genotype-Phenotype Associations Using Interpretable Pangenome-Spanning Regressions
title_fullStr	Improved Prediction of Bacterial Genotype-Phenotype Associations Using Interpretable Pangenome-Spanning Regressions
title_full_unstemmed	Improved Prediction of Bacterial Genotype-Phenotype Associations Using Interpretable Pangenome-Spanning Regressions
title_sort	improved prediction of bacterial genotype-phenotype associations using interpretable pangenome-spanning regressions
publisher	American Society for Microbiology
publishDate	2020
url	https://doaj.org/article/39a9c15c29234af282ab753ee02f2acb
work_keys_str_mv	AT johnalees improvedpredictionofbacterialgenotypephenotypeassociationsusinginterpretablepangenomespanningregressions AT ttienmai improvedpredictionofbacterialgenotypephenotypeassociationsusinginterpretablepangenomespanningregressions AT marcogalardini improvedpredictionofbacterialgenotypephenotypeassociationsusinginterpretablepangenomespanningregressions AT nicoleewheeler improvedpredictionofbacterialgenotypephenotypeassociationsusinginterpretablepangenomespanningregressions AT samuelthorsfield improvedpredictionofbacterialgenotypephenotypeassociationsusinginterpretablepangenomespanningregressions AT julianparkhill improvedpredictionofbacterialgenotypephenotypeassociationsusinginterpretablepangenomespanningregressions AT jukkacorander improvedpredictionofbacterialgenotypephenotypeassociationsusinginterpretablepangenomespanningregressions
_version_	1718427081028665344

Improved Prediction of Bacterial Genotype-Phenotype Associations Using Interpretable Pangenome-Spanning Regressions

Ejemplares similares