Function for normalizing the mean and variance (or just the variance) of single replicate log ratios

Description

This performs a robust loess normalization of the variance of the log ratios in a single replicate experiment by regressing the absolute (mean normalized) log ratios on the log intensities and using the fitted values to scale the (mean normalized) log ratio for each gene.

Usage

1
norm1b(logratio, logintensity, span1 = 0.6, span2 = 0.2, mean.norm=TRUE)

Arguments

logratio

A vector or single-column matrix of log (base 2) ratios of gene expressions in two samples, if mean.norm is FALSE the log ratios should be already mean normalized.

logintensity

A vector or single-column matrix of log (base 2) total intensities (defined as the product) of gene expressions in the two samples.

span1

Proportion of data used to fit the loess regression of the log ratios on the log intensities for the mean normalization.

span2

Proportion of data used to fit the loess regression of the absolute (mean normalized) log ratios on the log intensities for the variance normalization.

mean.norm

A logical value indicating whether or not a mean normalization should be performed prior to the variance normalization.

Value

A vector or single-column matrix of mean and variance normalized log (base 2) ratios of gene expressions in two samples.

Author(s)

N. Dean and A. E. Raftery

References

N. Dean and A. E. Raftery (2005). Normal uniform mixture differential gene expression detection for cDNA microarrays. BMC Bioinformatics. 6, 173-186.

http://www.biomedcentral.com/1471-2105/6/173

See Also

norm1a,norm1c,norm1d,norm2c,norm2d

Examples

1
2
3
4
5
data(like)
lR<-log(like[,1],2)-log(like[,2],2)
lI<-log(like[,1],2)+log(like[,2],2)

lRnorm<-norm1b(lR,lI,mean.norm=TRUE)