A genome-by-environment interaction classifier for precision medicine: Personal transcriptome response to rhinovirus identifies children prone to asthma exacerbations

Vincent Gardeux, Joanne Berghout, Ikbel Achour, A. Grant Schissler, Qike Li, Colleen Kenost, Jianrong Li, Yuan Shang, Anthony Bosco, Donald Saner, Marilyn J. Halonen, Daniel J. Jackson, Haiquan Li, Fernando D. Martinez, Yves A. Lussier

Research output: Research - peer-reviewArticle

Abstract

Objective: To introduce a disease prognosis framework enabled by a robust classification scheme derived from patient-specific transcriptomic response to stimulation. Materials and Methods: Within an illustrative case study to predict asthma exacerbation, we designed a stimulation assay that reveals individualized transcriptomic response to human rhinovirus. Gene expression from peripheral blood mononuclear cells was quantified from 23 pediatric asthmatic patients and stimulated in vitro with human rhinovirus. Responses were obtained via the single-subject gene set testing methodology "N-of-1- pathways." The classifier was trained on a related independent training dataset (n=19). Novel visualizations of personal transcriptomic responses are provided. Results: Of the 23 pediatric asthmatic patients, 12 experienced recurrent exacerbations. Our classifier, using individualized responses and trained on an independent dataset, obtained 74% accuracy (area under the receiver operating curve of 71%; 2-sided P=.039). Conventional classifiers using messenger RNA (mRNA) expression within the viralexposed samples were unsuccessful (all patients predicted to have recurrent exacerbations; accuracy of 52%). Discussion: Prognosis based on single time point, static mRNA expression alone neglects the importance of dynamic genome-by-environment interplay in phenotypic presentation. Individualized transcriptomic response quantified at the pathway (gene sets) level reveals interpretable signals related to clinical outcomes. Conclusion: The proposed framework provides an innovative approach to precision medicine. We show that quantifying personal pathway-level transcriptomic response to a disease-relevant environmental challenge predicts disease progression. This genome-by-environment interaction assay offers a noninvasive opportunity to translate omics data to clinical practice by improving the ability to predict disease exacerbation and increasing the potential to produce more effective treatment decisions.

LanguageEnglish (US)
Pages1116-1126
Number of pages11
JournalJournal of the American Medical Informatics Association
Volume24
Issue number6
DOIs
StatePublished - Nov 1 2017

Fingerprint

Rhinovirus
Precision Medicine
Transcriptome
Asthma
Genome
Disease Progression
Pediatrics
Messenger RNA
Genes
Datasets
Blood Cells
Gene Expression
Therapeutics
In Vitro Techniques

Keywords

  • Asthma
  • Dynamic expression
  • Gene-by-environment
  • Genomic classifier
  • HRV stimulation
  • Pathways
  • PBMC stimulated
  • Personal transcriptome
  • Precision medicine
  • Prognostic
  • Virogram

ASJC Scopus subject areas

  • Health Informatics

Cite this

A genome-by-environment interaction classifier for precision medicine : Personal transcriptome response to rhinovirus identifies children prone to asthma exacerbations. / Gardeux, Vincent; Berghout, Joanne; Achour, Ikbel; Schissler, A. Grant; Li, Qike; Kenost, Colleen; Li, Jianrong; Shang, Yuan; Bosco, Anthony; Saner, Donald; Halonen, Marilyn J.; Jackson, Daniel J.; Li, Haiquan; Martinez, Fernando D.; Lussier, Yves A.

In: Journal of the American Medical Informatics Association, Vol. 24, No. 6, 01.11.2017, p. 1116-1126.

Research output: Research - peer-reviewArticle

Gardeux, Vincent ; Berghout, Joanne ; Achour, Ikbel ; Schissler, A. Grant ; Li, Qike ; Kenost, Colleen ; Li, Jianrong ; Shang, Yuan ; Bosco, Anthony ; Saner, Donald ; Halonen, Marilyn J. ; Jackson, Daniel J. ; Li, Haiquan ; Martinez, Fernando D. ; Lussier, Yves A./ A genome-by-environment interaction classifier for precision medicine : Personal transcriptome response to rhinovirus identifies children prone to asthma exacerbations. In: Journal of the American Medical Informatics Association. 2017 ; Vol. 24, No. 6. pp. 1116-1126
@article{dc139c48fe5f4d80813ad7e0249fd4cf,
title = "A genome-by-environment interaction classifier for precision medicine: Personal transcriptome response to rhinovirus identifies children prone to asthma exacerbations",
abstract = "Objective: To introduce a disease prognosis framework enabled by a robust classification scheme derived from patient-specific transcriptomic response to stimulation. Materials and Methods: Within an illustrative case study to predict asthma exacerbation, we designed a stimulation assay that reveals individualized transcriptomic response to human rhinovirus. Gene expression from peripheral blood mononuclear cells was quantified from 23 pediatric asthmatic patients and stimulated in vitro with human rhinovirus. Responses were obtained via the single-subject gene set testing methodology {"}N-of-1- pathways.{"} The classifier was trained on a related independent training dataset (n=19). Novel visualizations of personal transcriptomic responses are provided. Results: Of the 23 pediatric asthmatic patients, 12 experienced recurrent exacerbations. Our classifier, using individualized responses and trained on an independent dataset, obtained 74% accuracy (area under the receiver operating curve of 71%; 2-sided P=.039). Conventional classifiers using messenger RNA (mRNA) expression within the viralexposed samples were unsuccessful (all patients predicted to have recurrent exacerbations; accuracy of 52%). Discussion: Prognosis based on single time point, static mRNA expression alone neglects the importance of dynamic genome-by-environment interplay in phenotypic presentation. Individualized transcriptomic response quantified at the pathway (gene sets) level reveals interpretable signals related to clinical outcomes. Conclusion: The proposed framework provides an innovative approach to precision medicine. We show that quantifying personal pathway-level transcriptomic response to a disease-relevant environmental challenge predicts disease progression. This genome-by-environment interaction assay offers a noninvasive opportunity to translate omics data to clinical practice by improving the ability to predict disease exacerbation and increasing the potential to produce more effective treatment decisions.",
keywords = "Asthma, Dynamic expression, Gene-by-environment, Genomic classifier, HRV stimulation, Pathways, PBMC stimulated, Personal transcriptome, Precision medicine, Prognostic, Virogram",
author = "Vincent Gardeux and Joanne Berghout and Ikbel Achour and Schissler, {A. Grant} and Qike Li and Colleen Kenost and Jianrong Li and Yuan Shang and Anthony Bosco and Donald Saner and Halonen, {Marilyn J.} and Jackson, {Daniel J.} and Haiquan Li and Martinez, {Fernando D.} and Lussier, {Yves A.}",
year = "2017",
month = "11",
doi = "10.1093/jamia/ocx069",
volume = "24",
pages = "1116--1126",
journal = "Journal of the American Medical Informatics Association : JAMIA",
issn = "1067-5027",
publisher = "Oxford University Press",
number = "6",

}

TY - JOUR

T1 - A genome-by-environment interaction classifier for precision medicine

T2 - Journal of the American Medical Informatics Association : JAMIA

AU - Gardeux,Vincent

AU - Berghout,Joanne

AU - Achour,Ikbel

AU - Schissler,A. Grant

AU - Li,Qike

AU - Kenost,Colleen

AU - Li,Jianrong

AU - Shang,Yuan

AU - Bosco,Anthony

AU - Saner,Donald

AU - Halonen,Marilyn J.

AU - Jackson,Daniel J.

AU - Li,Haiquan

AU - Martinez,Fernando D.

AU - Lussier,Yves A.

PY - 2017/11/1

Y1 - 2017/11/1

N2 - Objective: To introduce a disease prognosis framework enabled by a robust classification scheme derived from patient-specific transcriptomic response to stimulation. Materials and Methods: Within an illustrative case study to predict asthma exacerbation, we designed a stimulation assay that reveals individualized transcriptomic response to human rhinovirus. Gene expression from peripheral blood mononuclear cells was quantified from 23 pediatric asthmatic patients and stimulated in vitro with human rhinovirus. Responses were obtained via the single-subject gene set testing methodology "N-of-1- pathways." The classifier was trained on a related independent training dataset (n=19). Novel visualizations of personal transcriptomic responses are provided. Results: Of the 23 pediatric asthmatic patients, 12 experienced recurrent exacerbations. Our classifier, using individualized responses and trained on an independent dataset, obtained 74% accuracy (area under the receiver operating curve of 71%; 2-sided P=.039). Conventional classifiers using messenger RNA (mRNA) expression within the viralexposed samples were unsuccessful (all patients predicted to have recurrent exacerbations; accuracy of 52%). Discussion: Prognosis based on single time point, static mRNA expression alone neglects the importance of dynamic genome-by-environment interplay in phenotypic presentation. Individualized transcriptomic response quantified at the pathway (gene sets) level reveals interpretable signals related to clinical outcomes. Conclusion: The proposed framework provides an innovative approach to precision medicine. We show that quantifying personal pathway-level transcriptomic response to a disease-relevant environmental challenge predicts disease progression. This genome-by-environment interaction assay offers a noninvasive opportunity to translate omics data to clinical practice by improving the ability to predict disease exacerbation and increasing the potential to produce more effective treatment decisions.

AB - Objective: To introduce a disease prognosis framework enabled by a robust classification scheme derived from patient-specific transcriptomic response to stimulation. Materials and Methods: Within an illustrative case study to predict asthma exacerbation, we designed a stimulation assay that reveals individualized transcriptomic response to human rhinovirus. Gene expression from peripheral blood mononuclear cells was quantified from 23 pediatric asthmatic patients and stimulated in vitro with human rhinovirus. Responses were obtained via the single-subject gene set testing methodology "N-of-1- pathways." The classifier was trained on a related independent training dataset (n=19). Novel visualizations of personal transcriptomic responses are provided. Results: Of the 23 pediatric asthmatic patients, 12 experienced recurrent exacerbations. Our classifier, using individualized responses and trained on an independent dataset, obtained 74% accuracy (area under the receiver operating curve of 71%; 2-sided P=.039). Conventional classifiers using messenger RNA (mRNA) expression within the viralexposed samples were unsuccessful (all patients predicted to have recurrent exacerbations; accuracy of 52%). Discussion: Prognosis based on single time point, static mRNA expression alone neglects the importance of dynamic genome-by-environment interplay in phenotypic presentation. Individualized transcriptomic response quantified at the pathway (gene sets) level reveals interpretable signals related to clinical outcomes. Conclusion: The proposed framework provides an innovative approach to precision medicine. We show that quantifying personal pathway-level transcriptomic response to a disease-relevant environmental challenge predicts disease progression. This genome-by-environment interaction assay offers a noninvasive opportunity to translate omics data to clinical practice by improving the ability to predict disease exacerbation and increasing the potential to produce more effective treatment decisions.

KW - Asthma

KW - Dynamic expression

KW - Gene-by-environment

KW - Genomic classifier

KW - HRV stimulation

KW - Pathways

KW - PBMC stimulated

KW - Personal transcriptome

KW - Precision medicine

KW - Prognostic

KW - Virogram

UR - http://www.scopus.com/inward/record.url?scp=85032901492&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032901492&partnerID=8YFLogxK

U2 - 10.1093/jamia/ocx069

DO - 10.1093/jamia/ocx069

M3 - Article

VL - 24

SP - 1116

EP - 1126

JO - Journal of the American Medical Informatics Association : JAMIA

JF - Journal of the American Medical Informatics Association : JAMIA

SN - 1067-5027

IS - 6

ER -