R: Fit a generalized linear model (GLM) for each gene.

fitNbinomGLMs {DESeq}

R Documentation

Fit a generalized linear model (GLM) for each gene.

Description

Use this function to estimate coefficients and calculate deviance from a GLM for each gene. The GLM uses the nbkd.sf family, with the dispersion estimate according to getVarianceFunction(cds). Note that this requires that the variance functions were estimated with method "pooled" or "blind".

Usage

fitNbinomGLMs( cds, modelFormula, glmControl=list() )

Arguments

`cds`	a CountDataSet
`modelFormula`	a formula. The left hand side must be 'count' (not 'counts'!), the right hand side can involve any column of `pData(cds)`, i.e., `pData(cds)` is used as the model frame. If you have passed just a single factor to the 'conditions' argument of `newCountDataSet`, it can be referred to as 'condition' in the formula. If you have passed a data frame to 'conditions', all columns of this data frame will be available.
`glmControl`	list of additional parameters to be passed to `glm.control`

Value

A data frame with one row for each gene and columns as follows:

one column for each estimated coefficient, on a log2 scale (i.e., the natural log reported by glm is rescaled to base 2)
a column 'deviance', with the deviance of the fit
a boolean column 'converged', indicating whether the fit converged

Furthermore, the data frame has a scalar attribute 'df.residual' that contains the number of residual degrees of freedom.

Author(s)

Simon Anders (sanders@fs.tum.de)

Examples

   # see nbinomGLMTest for an example

[Package DESeq version 1.36.0 Index]