Hi all. I have a microarry gene expression data in the form of a matrix, where rows represent genes and columns represent conditions. plotDensity in "affy" package can draw a density distribution curve for each column and put them in a single plot. I wanna draw a density distribution curve for each colomn, put them each in a seperate plot, and put all these plots in a single page. What should I do? Thanks to all!

There must be more elegant way of doing this but here is my solution my.plotDensity <- function (mat, ylab = "density", xlab = "x", type = "l", col = 1:6, ...){ x.density <- apply(mat, 2, density) all.x <- do.call("cbind", lapply(x.density, function(x) x$x)) all.y <- do.call("cbind", lapply(x.density, function(x) x$y)) for(i in 1:ncol(mat)){ plot( all.x[ ,i], all.y[ ,i], xlim=range(all.x), ylim=range(all.y), main=colnames(mat)[i], ylab=ylab, xlab=xlab, type=type, col=col, ... ) } invisible(list(all.x = all.x, all.y = all.y)) } # Usage m <- matrix( rnorm(1000*6)^2, nc=6 ) # simulate m[,5] <- 5 + m[,5] # make array 5 an outlier colnames(m) <- paste("Array", 1:6) par(mfrow=c(2,3)) my.plotDensity(m) Regards, Adai On Mon, 2005-03-07 at 07:33 +0000, zhihua li wrote: > Hi all. > I have a microarry gene expression data in the form of a matrix, where rows > represent genes and columns represent conditions. plotDensity in "affy" > package can draw a density distribution curve for each column and put them > in a single plot. I wanna draw a density distribution curve for each > colomn, put them each in a seperate plot, and put all these plots in a > single page. What should I do? > Thanks to all! > > _______________________________________________ > Bioconductor mailing list > Bioconductor@stat.math.ethz.ch > https://stat.ethz.ch/mailman/listinfo/bioconductor >

I'd suggest using densityplot() in `lattice'; e.g.: > m <- matrix(rnorm(6e3), 1e3, 6) > colnames(m) <- paste("cond", 1:6) > library(lattice) > densityplot(~ m | factor(rep(colnames(m), each=nrow(m)))) HTH, Andy > From: Adaikalavan Ramasamy > > There must be more elegant way of doing this but here is my solution > > my.plotDensity <- function (mat, ylab = "density", xlab = "x", type = > "l", col = 1:6, ...){ > > x.density <- apply(mat, 2, density) > all.x <- do.call("cbind", lapply(x.density, function(x) x$x)) > all.y <- do.call("cbind", lapply(x.density, function(x) x$y)) > > for(i in 1:ncol(mat)){ > > plot( all.x[ ,i], all.y[ ,i], > xlim=range(all.x), ylim=range(all.y), > main=colnames(mat)[i], > ylab=ylab, xlab=xlab, type=type, col=col, ... ) > } > > invisible(list(all.x = all.x, all.y = all.y)) > } > > > # Usage > > m <- matrix( rnorm(1000*6)^2, nc=6 ) # simulate > m[,5] <- 5 + m[,5] # make array 5 an outlier > colnames(m) <- paste("Array", 1:6) > > par(mfrow=c(2,3)) > my.plotDensity(m) > > > Regards, Adai > > > On Mon, 2005-03-07 at 07:33 +0000, zhihua li wrote: > > Hi all. > > I have a microarry gene expression data in the form of a > matrix, where rows > > represent genes and columns represent conditions. > plotDensity in "affy" > > package can draw a density distribution curve for each > column and put them > > in a single plot. I wanna draw a density distribution curve > for each > > colomn, put them each in a seperate plot, and put all these > plots in a > > single page. What should I do? > > Thanks to all! > > > > _______________________________________________ > > Bioconductor mailing list > > Bioconductor@stat.math.ethz.ch > > https://stat.ethz.ch/mailman/listinfo/bioconductor > > > > _______________________________________________ > Bioconductor mailing list > Bioconductor@stat.math.ethz.ch > https://stat.ethz.ch/mailman/listinfo/bioconductor > > >