ruv_mixed_model: Remove unwanted variation using mixed model

In jhsiao999/Humanzee: Tools for statistical analysis of genomics data

Description

This function is a modified version of limma gls.series function. We changed to gls.series function to include model residuals that are computed after removing variation due to the random effect component. Otherwise, no changes was made to the gls.series algorithm.

Usage

ruv_mixed_model(M, design = NULL, per_gene = FALSE, ndups = 1,
  spacing = 1, block = NULL, correlation = NULL, weights = NULL)

Arguments

M	Data matrix of genes by samples.
design	Design matrix of the model fixed effects.
block	A vector that uniquely identifies levels of each random effect.
correlation	Consensus correlation coefficient describing the average correlation between biological replicates. This is usually computed via the duplicateCorrelation() function in the limma package.

Examples

ruv_mixed_model()

jhsiao999/Humanzee documentation built on May 19, 2019, 9:28 a.m.