aldex.glm: Calculate glm test statistics using a 'model.matrix'

In ggloor/ALDEx_bioc: Analysis Of Differential Abundance Taking Sample and Scale Variation Into Account

Calculate glm test statistics using a model.matrix

Description

aldex.glm calculates the expected values for each coefficient of a glm model on the data returned by aldex.clr. This function requires the user to define a model with model.matrix.

Usage

aldex.glm(clr, verbose = FALSE, fdr.method = "holm", ...)

Arguments

clr	An ALDEx2 object. The output of aldex.clr.
verbose	A boolean. Toggles whether to print diagnostic information while running. Useful for debugging errors on large datasets. Applies to effect = TRUE.
fdr.method	A string ("BH" or "holm") denoting which method to use to adjust p-values. Default is "holm"
...	Arguments passed to glm.

Value

Returns a data.frame of the average coefficients and their p-values for each feature, with FDR appended as a holm column.

Author(s)

Thom Quinn, Michelle Pistner

References

Please use the citation given by citation(package="ALDEx2").

See Also

aldex, aldex.clr, aldex.ttest, aldex.kw, aldex.glm, aldex.effect, aldex.corr, selex

Examples

data(selex)
#subset for efficiency
selex <- selex[1201:1600,]
covariates <- data.frame("A" = sample(0:1, 14, replace = TRUE),
                         "B" = c(rep(0, 7), rep(1, 7)))
mm <- model.matrix(~ A + B, covariates)
x <- aldex.clr(selex, mm, mc.samples=4, denom="all")
glm.test <- aldex.glm(x)
glm.eff <- aldex.glm.effect(x)
aldex.glm.plot(glm.test, eff=glm.eff, contrast='B', type='MW', post.hoc='holm')

ggloor/ALDEx_bioc documentation built on Oct. 31, 2023, 1:13 a.m.