fit_models: fit_models

In Malindrie/scShapes: A Statistical Framework for Modeling and Identifying Differential Distributions in Single-cell RNA-sequencing Data

fit_models

Description

This function is used to fit genes with GLM

Usage

fit_models(counts, cexpr, lib.size, formula = NULL, model = NULL, BPPARAM)

Arguments

counts	A non-negative integer matrix of scRNA-seq filtered read counts containing genes belonging to the family of ZINB distributions selected from ks_test.
cexpr	A dataframe that contains the covariate values. The rows of the dataframe are the corresponding samples/cells from the counts matrix from filter_counts. The cells of the dataframe are the covariates to be included in the GLM.
lib.size	A numeric vector that contains the total number of counts per cell from the counts matrix from filter_counts.
formula	A regression formula to fit the covariates in the ZINB GLM.
model	A specific model to fit (1:P, 2:NB, 3:ZIP, 4:ZINB, NULL:All)
BPPARAM	configuration parameter related to the method of parallel execution. For further information on how to set-up parallel execution refer to BiocParallel vignette.

Value

A list of models fitted by 'glm'

Examples

data(scData)

# apply the fit_models function to subset genes belonging to the
# family of ZINB distributions, selceted from ks_test function.

library(BiocParallel)
scData_models <- fit_models(counts=scData$counts, cexpr=scData$covariates,
lib.size=scData$lib_size, BPPARAM=bpparam())

Malindrie/scShapes documentation built on Nov. 21, 2022, 8:58 a.m.