ATHENA: The analysis tool for heritable and environmental network associations

Emily R. Holzinger, Scott M. Dudek, Alex T. Frase, Sarah A. Pendergrass, Marylyn D. Ritchie

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Motivation: Advancements in high-throughput technology have allowed researchers to examine the genetic etiology of complex human traits in a robust fashion. Although genome-wide association studies have identified many novel variants associated with hundreds of traits, a large proportion of the estimated trait heritability remains unexplained. One hypothesis is that the commonly used statistical techniques and study designs are not robust to the complex etiology that may underlie these human traits. This etiology could include non-linear gene × gene or gene × environment interactions. Additionally, other levels of biological regulation may play a large role in trait variability.Results: To address the need for computational tools that can explore enormous datasets to detect complex susceptibility models, we have developed a software package called the Analysis Tool for Heritable and Environmental Network Associations (ATHENA). ATHENA combines various variable filtering methods with machine learning techniques to analyze high-throughput categorical (i.e. single nucleotide polymorphisms) and quantitative (i.e. gene expression levels) predictor variables to generate multivariable models that predict either a categorical (i.e. disease status) or quantitative (i.e. cholesterol levels) outcomes. The goal of this article is to demonstrate the utility of ATHENA using simulated and biological datasets that consist of both single nucleotide polymorphisms and gene expression variables to identify complex prediction models. Importantly, this method is flexible and can be expanded to include other types of high-throughput data (i.e. RNA-seq data and biomarker measurements).

Original languageEnglish (US)
Pages (from-to)698-705
Number of pages8
JournalBioinformatics
Volume30
Issue number5
DOIs
StatePublished - Mar 1 2014

Fingerprint

Single Nucleotide Polymorphism
Genes
High Throughput
Gene Expression
Gene-Environment Interaction
Single nucleotide Polymorphism
Genome-Wide Association Study
Throughput
Nucleotides
Polymorphism
Gene expression
Categorical
Software
Biomarkers
Cholesterol
Gene-environment Interaction
Research Personnel
RNA
Gene
Technology

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computational Mathematics

Cite this

Holzinger, E. R., Dudek, S. M., Frase, A. T., Pendergrass, S. A., & Ritchie, M. D. (2014). ATHENA: The analysis tool for heritable and environmental network associations. Bioinformatics, 30(5), 698-705. https://doi.org/10.1093/bioinformatics/btt572
Holzinger, Emily R. ; Dudek, Scott M. ; Frase, Alex T. ; Pendergrass, Sarah A. ; Ritchie, Marylyn D. / ATHENA : The analysis tool for heritable and environmental network associations. In: Bioinformatics. 2014 ; Vol. 30, No. 5. pp. 698-705.
@article{743fdbe228e34e5594bc084455acc0e8,
title = "ATHENA: The analysis tool for heritable and environmental network associations",
abstract = "Motivation: Advancements in high-throughput technology have allowed researchers to examine the genetic etiology of complex human traits in a robust fashion. Although genome-wide association studies have identified many novel variants associated with hundreds of traits, a large proportion of the estimated trait heritability remains unexplained. One hypothesis is that the commonly used statistical techniques and study designs are not robust to the complex etiology that may underlie these human traits. This etiology could include non-linear gene × gene or gene × environment interactions. Additionally, other levels of biological regulation may play a large role in trait variability.Results: To address the need for computational tools that can explore enormous datasets to detect complex susceptibility models, we have developed a software package called the Analysis Tool for Heritable and Environmental Network Associations (ATHENA). ATHENA combines various variable filtering methods with machine learning techniques to analyze high-throughput categorical (i.e. single nucleotide polymorphisms) and quantitative (i.e. gene expression levels) predictor variables to generate multivariable models that predict either a categorical (i.e. disease status) or quantitative (i.e. cholesterol levels) outcomes. The goal of this article is to demonstrate the utility of ATHENA using simulated and biological datasets that consist of both single nucleotide polymorphisms and gene expression variables to identify complex prediction models. Importantly, this method is flexible and can be expanded to include other types of high-throughput data (i.e. RNA-seq data and biomarker measurements).",
author = "Holzinger, {Emily R.} and Dudek, {Scott M.} and Frase, {Alex T.} and Pendergrass, {Sarah A.} and Ritchie, {Marylyn D.}",
year = "2014",
month = "3",
day = "1",
doi = "10.1093/bioinformatics/btt572",
language = "English (US)",
volume = "30",
pages = "698--705",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "5",

}

Holzinger, ER, Dudek, SM, Frase, AT, Pendergrass, SA & Ritchie, MD 2014, 'ATHENA: The analysis tool for heritable and environmental network associations', Bioinformatics, vol. 30, no. 5, pp. 698-705. https://doi.org/10.1093/bioinformatics/btt572

ATHENA : The analysis tool for heritable and environmental network associations. / Holzinger, Emily R.; Dudek, Scott M.; Frase, Alex T.; Pendergrass, Sarah A.; Ritchie, Marylyn D.

In: Bioinformatics, Vol. 30, No. 5, 01.03.2014, p. 698-705.

Research output: Contribution to journalArticle

TY - JOUR

T1 - ATHENA

T2 - The analysis tool for heritable and environmental network associations

AU - Holzinger, Emily R.

AU - Dudek, Scott M.

AU - Frase, Alex T.

AU - Pendergrass, Sarah A.

AU - Ritchie, Marylyn D.

PY - 2014/3/1

Y1 - 2014/3/1

N2 - Motivation: Advancements in high-throughput technology have allowed researchers to examine the genetic etiology of complex human traits in a robust fashion. Although genome-wide association studies have identified many novel variants associated with hundreds of traits, a large proportion of the estimated trait heritability remains unexplained. One hypothesis is that the commonly used statistical techniques and study designs are not robust to the complex etiology that may underlie these human traits. This etiology could include non-linear gene × gene or gene × environment interactions. Additionally, other levels of biological regulation may play a large role in trait variability.Results: To address the need for computational tools that can explore enormous datasets to detect complex susceptibility models, we have developed a software package called the Analysis Tool for Heritable and Environmental Network Associations (ATHENA). ATHENA combines various variable filtering methods with machine learning techniques to analyze high-throughput categorical (i.e. single nucleotide polymorphisms) and quantitative (i.e. gene expression levels) predictor variables to generate multivariable models that predict either a categorical (i.e. disease status) or quantitative (i.e. cholesterol levels) outcomes. The goal of this article is to demonstrate the utility of ATHENA using simulated and biological datasets that consist of both single nucleotide polymorphisms and gene expression variables to identify complex prediction models. Importantly, this method is flexible and can be expanded to include other types of high-throughput data (i.e. RNA-seq data and biomarker measurements).

AB - Motivation: Advancements in high-throughput technology have allowed researchers to examine the genetic etiology of complex human traits in a robust fashion. Although genome-wide association studies have identified many novel variants associated with hundreds of traits, a large proportion of the estimated trait heritability remains unexplained. One hypothesis is that the commonly used statistical techniques and study designs are not robust to the complex etiology that may underlie these human traits. This etiology could include non-linear gene × gene or gene × environment interactions. Additionally, other levels of biological regulation may play a large role in trait variability.Results: To address the need for computational tools that can explore enormous datasets to detect complex susceptibility models, we have developed a software package called the Analysis Tool for Heritable and Environmental Network Associations (ATHENA). ATHENA combines various variable filtering methods with machine learning techniques to analyze high-throughput categorical (i.e. single nucleotide polymorphisms) and quantitative (i.e. gene expression levels) predictor variables to generate multivariable models that predict either a categorical (i.e. disease status) or quantitative (i.e. cholesterol levels) outcomes. The goal of this article is to demonstrate the utility of ATHENA using simulated and biological datasets that consist of both single nucleotide polymorphisms and gene expression variables to identify complex prediction models. Importantly, this method is flexible and can be expanded to include other types of high-throughput data (i.e. RNA-seq data and biomarker measurements).

UR - http://www.scopus.com/inward/record.url?scp=84897711239&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897711239&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/btt572

DO - 10.1093/bioinformatics/btt572

M3 - Article

C2 - 24149050

AN - SCOPUS:84897711239

VL - 30

SP - 698

EP - 705

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 5

ER -

Holzinger ER, Dudek SM, Frase AT, Pendergrass SA, Ritchie MD. ATHENA: The analysis tool for heritable and environmental network associations. Bioinformatics. 2014 Mar 1;30(5):698-705. https://doi.org/10.1093/bioinformatics/btt572