Dear all, Newbie. I have an expression matrix with ~760 genes, 40 samples and each sample has 4 replicates (=160 columns). May I use Matrix= impute.knn (My.matrix) Or should I detremine some parameters? Thanks in advance.

yes, but you will want to call the function as imputedMatrix = impute.knn(myMatrix)$data for example, using a synthetic matrix with random NAs: library(impute) set.seed(123) # create a 760*160 matrix w/random NAs baz <- matrix(rnorm(760*160), ncol=160) is.na(baz) <- rbinom(760*160, 1, 0.01) anyMissing(baz) # [1] TRUE mean(baz, na.rm=TRUE) # [1] 0.00251371 # now impute it, with the default k=10 neighbors qux <- impute.knn(baz)$data anyMissing(qux) # [1] FALSE mean(qux) # [1] 0.002513383 More parameters are of course documented under ?impute.knn Hope this helps; impute is a real workhorse package. --t On Sat, Mar 3, 2012 at 7:16 AM, Ali Mohammadian <nrcgeb@gmail.com> wrote: > Dear all, > Newbie. > I have an expression matrix with ~760 genes, 40 samples and each > sample has 4 replicates (=160 columns). May I use > Matrix= impute.knn (My.matrix) > > Or should I detremine some parameters? Thanks in advance. > > _______________________________________________ > Bioconductor mailing list > Bioconductor@r-project.org > https://stat.ethz.ch/mailman/listinfo/bioconductor > Search the archives: > http://news.gmane.org/gmane.science.biology.informatics.conductor > -- *A model is a lie that helps you see the truth.* * * Howard Skipper<http: cancerres.aacrjournals.org="" content="" 31="" 9="" 1173.full.pdf=""> [[alternative HTML version deleted]]