Exact variance component tests for longitudinal microbiome studies

Jing Zhai, Kenneth Knox, Homer Twigg, Hua Zhou, Jin J. Zhou

Research output: Contribution to journalArticle

Abstract

In metagenomic studies, testing the association between microbiome composition and clinical outcomes translates to testing the nullity of variance components. Motivated by a lung human immunodeficiency virus (HIV) microbiome project, we study longitudinal microbiome data by using variance component models with more than two variance components. Current testing strategies only apply to models with exactly two variance components and when sample sizes are large. Therefore, they are not applicable to longitudinal microbiome studies. In this paper, we propose exact tests (score test, likelihood ratio test, and restricted likelihood ratio test) to (a) test the association of the overall microbiome composition in a longitudinal design and (b) detect the association of one specific microbiome cluster while adjusting for the effects from related clusters. Our approach combines the exact tests for null hypothesis with a single variance component with a strategy of reducing multiple variance components to a single one. Simulation studies demonstrate that our method has a correct type I error rate and superior power compared to existing methods at small sample sizes and weak signals. Finally, we apply our method to a longitudinal pulmonary microbiome study of HIV-infected patients and reveal two interesting genera Prevotella and Veillonella associated with forced vital capacity. Our findings shed light on the impact of the lung microbiome on HIV complexities. The method is implemented in the open-source, high-performance computing language Julia and is freely available at https://github.com/JingZhai63/VCmicrobiome.

Original languageEnglish (US)
JournalGenetic Epidemiology
DOIs
StateAccepted/In press - Jan 1 2019

Fingerprint

Microbiota
Longitudinal Studies
Sample Size
Computing Methodologies
Veillonella
HIV
Prevotella
Metagenomics
Lung
Vital Capacity
Language
Viruses

Keywords

  • human immunodeficiency virus
  • linear mixed effects models
  • longitudinal pulmonary microbiome
  • variance component models

ASJC Scopus subject areas

  • Epidemiology
  • Genetics(clinical)

Cite this

Exact variance component tests for longitudinal microbiome studies. / Zhai, Jing; Knox, Kenneth; Twigg, Homer; Zhou, Hua; Zhou, Jin J.

In: Genetic Epidemiology, 01.01.2019.

Research output: Contribution to journalArticle

Zhai, Jing ; Knox, Kenneth ; Twigg, Homer ; Zhou, Hua ; Zhou, Jin J. / Exact variance component tests for longitudinal microbiome studies. In: Genetic Epidemiology. 2019.
@article{1d4360e655d24caa88ced63c06145195,
title = "Exact variance component tests for longitudinal microbiome studies",
abstract = "In metagenomic studies, testing the association between microbiome composition and clinical outcomes translates to testing the nullity of variance components. Motivated by a lung human immunodeficiency virus (HIV) microbiome project, we study longitudinal microbiome data by using variance component models with more than two variance components. Current testing strategies only apply to models with exactly two variance components and when sample sizes are large. Therefore, they are not applicable to longitudinal microbiome studies. In this paper, we propose exact tests (score test, likelihood ratio test, and restricted likelihood ratio test) to (a) test the association of the overall microbiome composition in a longitudinal design and (b) detect the association of one specific microbiome cluster while adjusting for the effects from related clusters. Our approach combines the exact tests for null hypothesis with a single variance component with a strategy of reducing multiple variance components to a single one. Simulation studies demonstrate that our method has a correct type I error rate and superior power compared to existing methods at small sample sizes and weak signals. Finally, we apply our method to a longitudinal pulmonary microbiome study of HIV-infected patients and reveal two interesting genera Prevotella and Veillonella associated with forced vital capacity. Our findings shed light on the impact of the lung microbiome on HIV complexities. The method is implemented in the open-source, high-performance computing language Julia and is freely available at https://github.com/JingZhai63/VCmicrobiome.",
keywords = "human immunodeficiency virus, linear mixed effects models, longitudinal pulmonary microbiome, variance component models",
author = "Jing Zhai and Kenneth Knox and Homer Twigg and Hua Zhou and Zhou, {Jin J.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1002/gepi.22185",
language = "English (US)",
journal = "Genetic Epidemiology",
issn = "0741-0395",
publisher = "Wiley-Liss Inc.",

}

TY - JOUR

T1 - Exact variance component tests for longitudinal microbiome studies

AU - Zhai, Jing

AU - Knox, Kenneth

AU - Twigg, Homer

AU - Zhou, Hua

AU - Zhou, Jin J.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In metagenomic studies, testing the association between microbiome composition and clinical outcomes translates to testing the nullity of variance components. Motivated by a lung human immunodeficiency virus (HIV) microbiome project, we study longitudinal microbiome data by using variance component models with more than two variance components. Current testing strategies only apply to models with exactly two variance components and when sample sizes are large. Therefore, they are not applicable to longitudinal microbiome studies. In this paper, we propose exact tests (score test, likelihood ratio test, and restricted likelihood ratio test) to (a) test the association of the overall microbiome composition in a longitudinal design and (b) detect the association of one specific microbiome cluster while adjusting for the effects from related clusters. Our approach combines the exact tests for null hypothesis with a single variance component with a strategy of reducing multiple variance components to a single one. Simulation studies demonstrate that our method has a correct type I error rate and superior power compared to existing methods at small sample sizes and weak signals. Finally, we apply our method to a longitudinal pulmonary microbiome study of HIV-infected patients and reveal two interesting genera Prevotella and Veillonella associated with forced vital capacity. Our findings shed light on the impact of the lung microbiome on HIV complexities. The method is implemented in the open-source, high-performance computing language Julia and is freely available at https://github.com/JingZhai63/VCmicrobiome.

AB - In metagenomic studies, testing the association between microbiome composition and clinical outcomes translates to testing the nullity of variance components. Motivated by a lung human immunodeficiency virus (HIV) microbiome project, we study longitudinal microbiome data by using variance component models with more than two variance components. Current testing strategies only apply to models with exactly two variance components and when sample sizes are large. Therefore, they are not applicable to longitudinal microbiome studies. In this paper, we propose exact tests (score test, likelihood ratio test, and restricted likelihood ratio test) to (a) test the association of the overall microbiome composition in a longitudinal design and (b) detect the association of one specific microbiome cluster while adjusting for the effects from related clusters. Our approach combines the exact tests for null hypothesis with a single variance component with a strategy of reducing multiple variance components to a single one. Simulation studies demonstrate that our method has a correct type I error rate and superior power compared to existing methods at small sample sizes and weak signals. Finally, we apply our method to a longitudinal pulmonary microbiome study of HIV-infected patients and reveal two interesting genera Prevotella and Veillonella associated with forced vital capacity. Our findings shed light on the impact of the lung microbiome on HIV complexities. The method is implemented in the open-source, high-performance computing language Julia and is freely available at https://github.com/JingZhai63/VCmicrobiome.

KW - human immunodeficiency virus

KW - linear mixed effects models

KW - longitudinal pulmonary microbiome

KW - variance component models

UR - http://www.scopus.com/inward/record.url?scp=85059669061&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059669061&partnerID=8YFLogxK

U2 - 10.1002/gepi.22185

DO - 10.1002/gepi.22185

M3 - Article

C2 - 30623484

AN - SCOPUS:85059669061

JO - Genetic Epidemiology

JF - Genetic Epidemiology

SN - 0741-0395

ER -