fitZINB: fitZINB

In mcalgaro93/benchdamic: Benchmark of differential abundance methods on microbiome data

fitZINB

Description

Fit a Zero-Inflated Negative Binomial (ZINB) distribution for each taxon of the countdata. The ZINB estimation procedure is performed by zinbwave zinbFit function with commondispersion = FALSE, regularization parameter epsilon = 1e10, and not assuming the presence of any group in the samples (design matrix equal to a column of ones.)

Usage

fitZINB(object, assay_name = "counts", verbose = TRUE)

Arguments

object	a phyloseq object, a TreeSummarizedExperiment object, or a matrix of counts.
assay_name	the name of the assay to extract from the TreeSummarizedExperiment object (default assayName = "counts"). Not used if the input object is a phyloseq.
verbose	an optional logical value. If TRUE information on the steps of the algorithm is printed. Default verbose = TRUE.

Value

A data frame containing the continuity corrected logarithms of the average fitted values for each row of the matrix of counts in the Y column, and the estimated probability to observe a zero in the Y0 column.

Examples

# Generate some random counts
counts = matrix(rnbinom(n = 60, size = 3, prob = 0.5), nrow = 10, ncol = 6)

# Fit model on the counts matrix
ZINB <- fitZINB(counts)
head(ZINB)

mcalgaro93/benchdamic documentation built on Nov. 28, 2024, 2:16 p.m.