MWAS_stats: Metabolome-Wide Associations

In MWASTools: MWASTools: an integrated pipeline to perform metabolome-wide association studies

Description

This function tests for association between individual metabolites and a disease phenotype.

Usage

MWAS_stats (metabo_SE, disease_id, confounder_ids = NULL, assoc_method, mt_method = "BH",
            output = "pvalues", CV_metabo = NULL)

Arguments

metabo_SE	SummarizedExperiment object. See "MWAS_SummarizedExperiment()".
disease_id	character vector corresponding to the ID of the response to be modeled.
confounder_ids	optional character vector corresponding to the IDs of the covariates to be included in the model (e.g. age or gender).
assoc_method	character constant indicating the association method that will be used. Possible values for assoc_method are: "pearson" (Pearson correlation), "spearman" (Spearman correlation), "kendall" (Kendall correlation), "linear" (linear regression) or "logistic" (logistic regression).
mt_method	character constant indicating the multiple-testing correction method that will be used. Possible values for mt_method are: "BH" (Benjamini and Hochberg), "bonferroni", "holm", "hochberg", "hommel", "BY" (Benjamini and Yekutieli), "qvalues", or "none".
output	character constant indicating the output of the function. If output = "pvalues", p-values and estimates for each metabolic variable will be returned as a matrix. If output = "models", detailed information about the statistical model fitted for each metabolic variable will be returned.
CV_metabo	optional numeric vector containing the coefficients of variation of the metabolic variables. This vector will be added as an additional column of the output matrix.

Value

By default, a matrix where each row contains the model coefficient estimate and the p-value obtained for each metabolic variable. When output = "models", the function returns a list, each list element containing detailed information about the statistic model fitted for each metabolic variable.

References

Benjamini Y, Hochberg Y. (1995). Controlling the false discovery rate: a practical and powerful approach to multiple testing. Journal of the Royal Statistical Society Series B, 57, 289–300.

Benjamini Y, Yekutieli D. (2001). The control of the false discovery rate in multiple testing under dependency. Annals of Statistics, 29, 1165–1188.

Dobson AJ. (1990). An Introduction to Generalized Linear Models. London: Chapman and Hall.

Kim, S. (2015). ppcor: An R Package for a Fast Calculation to Semi-partial Correlation Coefficients. Communications for Statistical Applications and Methods, 22, 665-674.

Holm S. (1979). A simple sequentially rejective multiple test procedure. Scandinavian Journal of Statistics, 6, 65–70.

Hommel G. (1988). A stagewise rejective multiple test procedure based on a modified Bonferroni test. Biometrika, 75, 383–386.

Hochberg Y. (1988). A sharper Bonferroni procedure for multiple tests of significance. Biometrika, 75, 800–803.

Shaffer JP. (1995). Multiple hypothesis testing. Annual Review of Psychology, 46, 561–576.

Storey JD. (2002). A direct approach to false discovery rates. Journal of the Royal Statistical Society, Series B, 64: 479-498.

Venables WN, Ripley BD. (2002). Modern Applied Statistics with S. New York: Springer.

Examples

## Load data
data(metabo_SE)
data(targetMetabo_SE)

## Test for association between BMI and metabolic_data
BMI_model <- MWAS_stats (metabo_SE, disease_id = "BMI", assoc_method = "spearman",
                         mt_method = "BH", output = "pvalues")

## Test for association between diabetes and target_metabolites (age-gender adjusted)
T2D_model <- MWAS_stats (targetMetabo_SE, disease_id = "T2D",
                         confounder_ids = c("Age", "Gender"),
                         assoc_method = "logistic", mt_method = "BY",
                         output = "pvalues")

MWASTools documentation built on Nov. 8, 2020, 5:07 p.m.