Modeling association in microbial communities with clique loglinear models

Adrian Dobra, Camilo Valdes, Dragana Ajdic, Bertrand Clarke, Jennifer L Clarke

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

There is a growing awareness of the important roles that microbial communities play in complex biological processes. Modern investigation of these often uses next generation sequencing of metagenomic samples to determine community composition. We propose a statistical technique based on clique loglinear models and Bayes model averaging to identify microbial components in a metagenomic sample at various taxonomic levels that have significant associations. We describe the model class, a stochastic search technique for model selection, and the calculation of estimates of posterior probabilities of interest. We demonstrate our approach using data from the Human Microbiome Project and from a study of the skin microbiome in chronic wound healing. Our technique also identifies significant dependencies among microbial components as evidence of possible microbial syntrophy.

Original languageEnglish (US)
Pages (from-to)931-957
Number of pages27
JournalAnnals of Applied Statistics
Volume13
Issue number2
DOIs
StatePublished - Jan 1 2019

Fingerprint

Log-linear Models
Clique
Association reactions
Modeling
Wound Healing
Model Averaging
Stochastic Search
Posterior Probability
Bayes
Model Selection
Skin
Sequencing
Estimate
Demonstrate
Community
Log-linear models
Chemical analysis
Model

Keywords

  • Contingency tables
  • Graphical models
  • Microbiome
  • Model selection
  • Next generation sequencing

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation
  • Statistics, Probability and Uncertainty

Cite this

Modeling association in microbial communities with clique loglinear models. / Dobra, Adrian; Valdes, Camilo; Ajdic, Dragana; Clarke, Bertrand; Clarke, Jennifer L.

In: Annals of Applied Statistics, Vol. 13, No. 2, 01.01.2019, p. 931-957.

Research output: Contribution to journalArticle

Dobra, Adrian ; Valdes, Camilo ; Ajdic, Dragana ; Clarke, Bertrand ; Clarke, Jennifer L. / Modeling association in microbial communities with clique loglinear models. In: Annals of Applied Statistics. 2019 ; Vol. 13, No. 2. pp. 931-957.
@article{4f8ad0760adf4c74bf2a44fb2a0450e2,
title = "Modeling association in microbial communities with clique loglinear models",
abstract = "There is a growing awareness of the important roles that microbial communities play in complex biological processes. Modern investigation of these often uses next generation sequencing of metagenomic samples to determine community composition. We propose a statistical technique based on clique loglinear models and Bayes model averaging to identify microbial components in a metagenomic sample at various taxonomic levels that have significant associations. We describe the model class, a stochastic search technique for model selection, and the calculation of estimates of posterior probabilities of interest. We demonstrate our approach using data from the Human Microbiome Project and from a study of the skin microbiome in chronic wound healing. Our technique also identifies significant dependencies among microbial components as evidence of possible microbial syntrophy.",
keywords = "Contingency tables, Graphical models, Microbiome, Model selection, Next generation sequencing",
author = "Adrian Dobra and Camilo Valdes and Dragana Ajdic and Bertrand Clarke and Clarke, {Jennifer L}",
year = "2019",
month = "1",
day = "1",
doi = "10.1214/18-AOAS1229",
language = "English (US)",
volume = "13",
pages = "931--957",
journal = "Annals of Applied Statistics",
issn = "1932-6157",
publisher = "Institute of Mathematical Statistics",
number = "2",

}

TY - JOUR

T1 - Modeling association in microbial communities with clique loglinear models

AU - Dobra, Adrian

AU - Valdes, Camilo

AU - Ajdic, Dragana

AU - Clarke, Bertrand

AU - Clarke, Jennifer L

PY - 2019/1/1

Y1 - 2019/1/1

N2 - There is a growing awareness of the important roles that microbial communities play in complex biological processes. Modern investigation of these often uses next generation sequencing of metagenomic samples to determine community composition. We propose a statistical technique based on clique loglinear models and Bayes model averaging to identify microbial components in a metagenomic sample at various taxonomic levels that have significant associations. We describe the model class, a stochastic search technique for model selection, and the calculation of estimates of posterior probabilities of interest. We demonstrate our approach using data from the Human Microbiome Project and from a study of the skin microbiome in chronic wound healing. Our technique also identifies significant dependencies among microbial components as evidence of possible microbial syntrophy.

AB - There is a growing awareness of the important roles that microbial communities play in complex biological processes. Modern investigation of these often uses next generation sequencing of metagenomic samples to determine community composition. We propose a statistical technique based on clique loglinear models and Bayes model averaging to identify microbial components in a metagenomic sample at various taxonomic levels that have significant associations. We describe the model class, a stochastic search technique for model selection, and the calculation of estimates of posterior probabilities of interest. We demonstrate our approach using data from the Human Microbiome Project and from a study of the skin microbiome in chronic wound healing. Our technique also identifies significant dependencies among microbial components as evidence of possible microbial syntrophy.

KW - Contingency tables

KW - Graphical models

KW - Microbiome

KW - Model selection

KW - Next generation sequencing

UR - http://www.scopus.com/inward/record.url?scp=85068691242&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068691242&partnerID=8YFLogxK

U2 - 10.1214/18-AOAS1229

DO - 10.1214/18-AOAS1229

M3 - Article

VL - 13

SP - 931

EP - 957

JO - Annals of Applied Statistics

JF - Annals of Applied Statistics

SN - 1932-6157

IS - 2

ER -