[BioC] Normalizing data (that is not in microarray "format")

Emmanuel Levy emmanuel.levy at gmail.com
Mon Dec 8 21:32:08 CET 2008

Dear Sean,

Thank you for your reply.

> Reading the help for normalize.loess, it appears that it takes a
> matrix as input.  You do not need an affy object.  Also, note that a

This is actually why I tried to use normalize.loess. Although I get
warnings, it does normalize my data.
The following piece of code generates the error mentioned in my previous email:

> my.mat = matrix(nrow=100, ncol=4, runif(400) )
> my.mat[1,1]=NA
> my.mat.n = normalize.loess(my.mat)

Warning messages:
1: In means[, j] + aux :
  longer object length is not a multiple of shorter object length

I actually figured out that the NormalizeBetweenArray method from the
Limma package does the simple "scaling" normalization I was looking



> sessionInfo()
R version 2.8.0 (2008-10-20)


attached base packages:
[1] splines   tools     stats     graphics  grDevices utils     datasets
[8] methods   base

other attached packages:
 [1] GOstats_2.4.0       Category_2.4.0      genefilter_1.22.0
 [4] survival_2.34-1     RBGL_1.16.0         annotate_1.20.1
 [7] xtable_1.5-4        GO.db_2.2.0         AnnotationDbi_1.2.2
[10] RSQLite_0.6-9       DBI_0.2-4           graph_1.18.0
[13] marray_1.20.0       limma_2.16.3        YEAST_2.0.1
[16] affy_1.20.0         Biobase_2.2.1

loaded via a namespace (and not attached):
[1] affyio_1.10.1        cluster_1.11.11      preprocessCore_1.4.0

> data.frame is not a matrix.  For any of the normalization methods that
> you might choose, it helps to read the help carefully, as that will
> tell you what types of data can be used; most normalization routines
> will take a matrix as input.  If you need more specific help, you will
> need to post some reproducible example code and give the output of
> sessionInfo().
> Sean

More information about the Bioconductor mailing list