Dear Matt,
Meanwhile I have investigated your problem with the 'Probe-level
Normalization' step, and there was sadly a minor bug, which did allow
to
scale only the first array, and then caused an error. Interestingly,
only whole genome arrays were affected but not ivt-arrays.
Furthermore,
mas5() was also not affected since it does not include this step.
I have just uploaded version xps-1.24.1 to the BioC servers, so that
you
should be able to download the new version on Monday.
Here is some demo-code using the steps you wanted to do (using
GSE46976):
### new R session: load library xps
library(xps)
### load ROOT scheme file and ROOT data file
scmdir <- "/Volumes/GigaDrive/CRAN/Workspaces/Schemes/na33"
scheme.genome <- root.scheme(file.path(scmdir, "mogene20stv1.root"))
datdir <- "/Volumes/GigaDrive/CRAN/Workspaces/ROOTData"
data.genome <- root.data(scheme.genome,
paste(datdir,"GSE46976_cel.root",sep="/"))
outdir <- getwd()
## Background correct
data_bg_all <- bgcorrect(data.genome, "tmp_Bgrd_All", filedir=outdir,
tmpdir="",
method="sector", select="all",
option="correctbg", params=c(0.02, 4, 4, 0),
exonlevel="all", verbose=TRUE)
## boxplot w/o need to attach data
boxplot(data_bg_all, which="userinfo:fIntenQuant")
## get colnames of bgrd trees
bgrdnames <- colnames(validBgrd(data_bg_all))
bgrdnames
## images for bgrd
image(data_bg_all, bg=TRUE, transfo=NULL, col=heat.colors(12),
names=paste(namePart(bgrdnames[1]),"sbg",sep="."))
image(data_bg_all, bg=TRUE, transfo=log2, col=heat.colors(12),
names=paste(namePart(bgrdnames[1]),"sbg",sep="."))
## attach mask, bgrd and background-corrected intensities
data_bg_all <- attachMask(data_bg_all)
data_bg_all <- attachBgrd(data_bg_all)
data_bg_all <- attachInten(data_bg_all)
# density and boxplot
hist(data_bg_all)
boxplot(data_bg_all)
## to avoid memory comsumption of R remove data:
data_bg_all <- removeMask(data_bg_all)
data_bg_all <- removeBgrd(data_bg_all)
data_bg_all <- removeInten(data_bg_all)
gc()
## Normalization
data_norm <- normalize(data_bg_all, "tmp_Norm_All_mn", filedir=outdir,
tmpdir="", update = FALSE,
select = "all", exonlevel="all",
method="mean",
option = "transcript:all",
logbase = "0", refindex = 0, refmethod =
"mean",
params = list(0.02, 0), verbose=TRUE)
## attach mask and normalized intensities
data_norm <- attachMask(data_norm)
data_norm <- attachInten(data_norm)
# boxplot and density plot
boxplot(data_norm)
hist(data_norm)
## remove
data_norm <- removeMask(data_norm)
data_norm <- removeInten(data_norm)
# Summarization
data_sum <- summarize(data_norm, "tmp_Sum_Norm_mn", filedir=outdir,
tmpdir="", update = FALSE,
select="pmonly", method = "medianpolish",
option
= "transcript",
logbase="log2", params=c(10, 0.01, 1.0),
exonlevel="core+affx", verbose=TRUE)
## boxplot and density plot
boxplot(data_sum)
hist(data_sum)
## get expression data
x<-validData(data_sum)
head(x)
## scatter plot
plot(log2(x[,2]), log2(x[,3]))
Best regards,
Christian
On 7/22/14 12:23 AM, Thornton, Matthew wrote:
> Hello!
>
> I am trying to optimize my data processing with xps. I am getting an
error when using the normalize function. It could be due to improper
switches.
>
> here is the error:
>
>> data_norm <- normalize(data_bkgrd, "Normalize_Step2",
filedir=outdir, tmpdir="", update = FALSE, select = "pmonly",
exonlevel="all", method="mean", option = "transcript:all", logbase =
"0", refindex = 0, refmethod = "mean", params = list(0.02, 0),
verbose=TRUE)
> Opening file </data> in <read>
mode...
> Creating new file
</data>...
> Opening file </data> in
<read> mode...
> Preprocessing data using method <preprocess>...
> Normalizing raw data...
> normalizing data using method <mean>...
> filling array <reference>...
> normalizing <ctr1_mix2_25apr14.int>...
> setting selector mask for typepm <16316>
> normalization <mean>: Scaling factor SF is <0.859736>
> normalizing <ctr2_mix2_25apr14.int>...
> setting selector mask for typepm <16316>
> Error: Length of non-varying units is zero.
> An error has occured: Need to abort current process.
> Error in .local(object, ...) : error in rwrapper function
?Normalize?
>
> Here are the lines in my Rscript for piecewise processing. I am
using the default settings but it would be nice to know more about how
to optimize them.
>
> # Background correct
> data_bkgrd <- bgcorrect(data_raw, "Background_Step1",
filedir=outdir, tmpdir="", method="sector", select="pmonly",
option="correctbg", params=c(0.02, 4, 4, 0), exonlevel="all",
verbose=TRUE)
>
> png(file="Background_Correction_Density_Plot.png", width=600,
height=600)
> par(mar=c(6,3,1,1));
> hist(data_bkgrd, add.legend=TRUE)
> dev.off()
>
> # Normalization
> data_norm <- normalize(data_bkgrd, "Normalize_Step2",
filedir=outdir, tmpdir="", update = FALSE, select = "all",
exonlevel="all", method="mean", option = "transcript:all", logbase =
"0", refindex = 0, refmethod = "mean", params = list(0.02, 0),
verbose=TRUE)
>
> png(file="Normalization_Density_Plot.png", width=600, height=600)
> par(mar=c(6,3,1,1));
> hist(data_norm, add.legend=TRUE)
> dev.off()
>
> # Summarization
> data_sum <- summarize(data_norm, "Summary_Step3", filedir=outdir,
tmpdir="", update = FALSE, select="pmonly", method = "medianpolish",
option = "transcript", exonlevel="core+affx", verbose=TRUE)
>
> png(file="Summary_Density_Plot.png", width=600, height=600)
> par(mar=c(6,3,1,1));
> hist(data_sum, add.legend=TRUE)
> dev.off()
>
> Any comments or advice are greatly appreciated!
>
> Thanks!
>
> Matt
>
>
> matthew.thornton at med.usc.edu
>
> _______________________________________________
> Bioconductor mailing list
> Bioconductor at r-project.org
>
https://stat.ethz.ch/mailman/listinfo/bioconductor
> Search the archives:
http://news.gmane.org/gmane.science.biology.informatics.conductor
>
