This is a test version of Biostars. For the public version, visit https://www.biostars.org.
Error of Groups in R 
> fit = lmFit(gse50397eset, design_gse50397)

Error in lmFit(gse50397eset, design_gse50397) : 
 row dimension of design doesn't match column dimension of data object.

Can anyone please help me out of this error.

affy limma oligo bioconductor r
• 4,000 views • link
updated by Biostar Biostar • written by 12021560-040 12021560-040

Can you check and post:

dim(gse50397eset)
dim(design_gse50397)
• 1 views • link
written by WouterDeCoster WouterDeCoster

dim(gse50397eset) [1] 33297 89 dim(design_gse50397) [1] 77 2 I run these commands but did not find anything useful.. :(

• 1 views • link
written by 12021560-040 12021560-040

dim(gse50397eset) [1] 33297 89 dim(design_gse50397) [1] 77 2 I run these commands but did not find anything useful.. :(

• 1 views • link
written by 12021560-040 12021560-040

dim tells you the sizes of your objects. And indeed, these do not match. You should check if you properly created those objects.

• 1 views • link
written by WouterDeCoster WouterDeCoster

which objects aren't created properly?? and how can I make them proper match?

• 1 views • link
written by 786 786

please tell according to my script that which objects are not properly defined?

• 1 views • link
written by 12021560-040 12021560-040

shouldn't this be fit = lm(gse50397eset, design_gse50397)?

Then you get fit$fitted.values

• 1 views • link
written by MAPK MAPK 
Please help me and pinpoint the error specifically If you can I am not getting any help from the above responses.. Please help me get out of this error i will be very thankful to you.
gse50397dat = getGEO('GSE50397')
gse50397raw= getGEOSuppFiles("GSE50397")
tarfile <- grep("\\.tar$", rownames(gse50397raw), value = TRUE)
list.files("GSE50397")
untar("GSE50397/GSE50397_RAW.tar", exdir = "GSE50397/CEL")
list.files("GSE50397/CEL")
celfiles <- list.files("GSE50397/CEL", full = TRUE)
rawData <- read.celfiles(celfiles)
rawData
normData <- rma(rawData)
gse50397eset= exprs(normData)
groups = pData(phenoData(gse50397dat[[1]]))$Hba1c
groups=as.character(groups)
groups=sort(groups)
groups[c(11)]="diabetic"
groups[c(17)]="diabetic"
groups[c(25)]="diabetic"
groups[c(27)]="diabetic"
groups[c(29)]="diabetic"
groups[c(32)]="diabetic"
groups[c(35)]="diabetic"
groups[c(38)]="diabetic"
groups[c(42:43)]="diabetic"
groups[c(46)]="diabetic"
groups[c(48)]="diabetic"
groups[c(51)]="diabetic"
groups[c(53:56)]="diabetic"
groups[c(61)]="diabetic"
groups[c(65)]="diabetic"
groups[c(76:78)]="diabetic"
groups[c(82:84)]="diabetic"
groups[c(87)]="diabetic"
groups[c(13:16)]="control"
groups[c(23:24)]="control"
groups[c(30:31)]="control"
groups[c(57:60)]="control"
groups[c(62:64)]="control"
groups[c(66:75)]="control"
groups[c(80:81)]="control"
groups[c(88:89)]="control"
f = factor(groups, levels=c("control","diabetic"))
design_gse50397 = model.matrix(~0+f)
colnames(design_gse50397) = levels(f)
cont.matrix = makeContrasts(T2D-diabetic, levels=design_gse50397)
fit = lmFit(gse50397eset, design_gse50397)
Error in lmFit(gse50397eset, design_gse50397) : 
  row dimension of design doesn't match column dimension of data object
• 1 views • link
written by 12021560-040 12021560-040

What an absurd way of creating your trait data object, I would like to suggest you first follow a proper introduction to R before you try to do research. I'd suggest http://swirlstats.com/

• 1 views • link
written by WouterDeCoster WouterDeCoster

0 answers

No answers yet.

Log in to answer this question.

More posts like this