Hi Sean, Thank you so much for your help and guidance in this. Your solution sounds good...I will try my best to code this one out..!! Thank you again, Saurin --- On Wed, 11/3/10, Sean Davis <sdavis2@mail.nih.gov> wrote: From: Sean Davis <sdavis2@mail.nih.gov> Subject: Re: [BioC] heatmap Clustering help, two class (Control vs Exp) Experiments, To: saurin_jani@yahoo.com Cc: "Steve Lianoglou" <mailinglist.honeypot@gmail.com>, "Bioconductor Bioconductor" <bioconductor@stat.math.ethz.ch> Date: Wednesday, November 3, 2010, 2:30 PM On Wed, Nov 3, 2010 at 2:07 PM, Saurin D. Jani <saurin_jani@yahoo.com> wrote: Hi Steve, May be something like this: �d �d �u � | u � u �d n geneY �u �u �d � | u � u �d n geneX ---------------------- c1 c5 c10 �| e1 e4 e8 e2 where: d = down, u = up, n = normal , c= control , e = exprimental original expression set has this order: c1,c2,c3...c10 e1,e2,e3..e10 Thank you so much, Saurin Hi, Saurin. You're going to need to write some code to do this, I think. �I would suggest clustering your two sample groups, c and e, using hclust. �Grab the order from that for each of the two groups, combine them in whatever way you like, figuring out the appropriate indexes for ALL the samples based on the separate hclust results, and then feeding that custom ordering to the heatmap function. �I don't think this is as common a use case as you might think, so I doubt there is a simple canned solution. Sean � --- On Wed, 11/3/10, Steve Lianoglou <mailinglist.honeypot@gmail.com> wrote: > From: Steve Lianoglou <mailinglist.honeypot@gmail.com> > Subject: Re: [BioC] heatmap Clustering help, two class (Control vs Exp) Experiments, > To: saurin_jani@yahoo.com > Cc: "Bioconductor Bioconductor" <bioconductor@stat.math.ethz.ch> > Date: Wednesday, November 3, 2010, 12:56 PM > Hi Saurin, > > On Wed, Nov 3, 2010 at 12:43 PM, Saurin D. Jani <saurin_jani@yahoo.com> > wrote: > > Hi, > > > > You are right but When I do this: > > > > > heatmap.2(FeatureX,col=gmpalette,Colv=as.dendrogram(hclust(col.dist, method="average")), > Rowv=as.dendrogram(hclust(row.dist,method="average")),scale="row",ke y=TRUE,keysize=0.60,symkey=FALSE,density.info="none",trace="none",marg ins=c(5,MapMargin),cexRow=1,cexCol=1,cex.sub=1); > > > > my control and exp. samples get mixed up..!! is there > anyway I can pass a parameter ..not to do that just cluster > samples on control and then exp. so, sorted view will be > there. > > But why would you cluster the samples to begin with, if you > just want > to reorder them in some (your) arbitrary way? > > Assuming your data is properly nomralised, etc. and > clustering your > samples "mixes them up," then the heatmap is showing you > visually that > your treatment examples aren't "strikingly different" than > your > controls. Your data is trying to tell you that (apparently) > all of > these experiments kind of look (expression wise) like each > other. > > Maybe that's telling you something about the quality of > your data, or > its annotation? > > Maybe you can try the plotPCA function in the affycoretools > package as > another way to see how your experiments "cluster > together". > > I'm not sure that it would change things, but what happens > if you > remove all probes w/ low variance across your entire > dataset and > re-cluster them? > > > May be something like this: cluster control samples > then exp. samples and then cluster based on Signal > Intensity. so, I keep the order ctrl1,ctrl5,ctrl6,ctrl2,... > and then Exp1,Exp5,Ex2,Exp10 ....so on... > > But then this is kind of misrepresenting what one would > expect to see > in such a plot .. you could, of course, plot and save > heatmaps over > just your control data, then again with just your > experiment, then > photoshop them together, but ... what's the point? > > I guess the question is: what are you trying to show in the > heatmap > you are trying to� produce? > > Given that, people might be able to then suggest things you > could try. > > -- > Steve Lianoglou > Graduate Student: Computational Systems Biology > �| Memorial Sloan-Kettering Cancer Center > �| Weill Medical College of Cornell University > Contact Info: http://cbio.mskcc.org/~lianos/contact > _______________________________________________ Bioconductor mailing list Bioconductor@stat.math.ethz.ch https://stat.ethz.ch/mailman/listinfo/bioconductor Search the archives: http://news.gmane.org/gmane.science.biology.informatics.conductor [[alternative HTML version deleted]]

Hi, heatmap clustering two class ..Solved:  Thanks Sean,Thoma, Steve...for your help. For Thread info. here is code:  FeatureX <- esetSub2X; # DE genes Exp. set   eR <- nrow(FeatureX);   eC <- ncol(FeatureX);   #HSET <- matrix(data = 0, nrow = eR, ncol = eC);    HSET <- numeric();    Hcols <- character();   #row.dist <- as.dist(1 - cor(t(FeatureX)));   row.dist <- as.dist(1 - cor(t(FeatureX)));   col.dist <- as.dist(1 - cor(FeatureX)); ############### building custom Heatmap set   clust_col <- hclust(col.dist,method="average");   cORD <- as.numeric(clust_col$order);   smps <- colnames(FeatureX);   n_smps <- smps[w:x];   t_smps <- smps[y:z]; #----------------------------------------------------------- # build Normal samples  for(f in 1:cORD)   {      ns = colnames(FeatureX)[cORD[f]];     if(is.element(ns,n_smps))        {         HSET <- cbind(HSET,FeatureX[,ns]);         Hcols <- c(Hcols,ns);        }    } # build Tumor samples  for(f in 1:cORD)   {      ts = colnames(FeatureX)[cORD[f]];     if(is.element(ts,t_smps))        {         HSET <- cbind(HSET,FeatureX[,ts]);         Hcols <- c(Hcols,ts);        }    } colnames(HSET) <- Hcols; FeatureX <- HSET; heatmap.2(FeatureX); #----------------------------------------------------------- On Wed, Nov 3, 2010 at 2:07 PM, Saurin D. Jani <saurin_jani@yahoo.com> wrote: Hi Steve, May be something like this:  d  d  u   | u   u  d n geneY  u  u  d   | u   u  d n geneX ---------------------- c1 c5 c10  | e1 e4 e8 e2 where: d = down, u = up, n = normal , c= control , e = exprimental original expression set has this order: c1,c2,c3...c10 e1,e2,e3..e10 Thank you so much, Saurin Hi, Saurin. You're going to need to write some code to do this, I think.  I would suggest clustering your two sample groups, c and e, using hclust. Grab the order from that for each of the two groups, combine them in whatever way you like, figuring out the appropriate indexes for ALL the samples based on the separate hclust results, and then feeding that custom ordering to the heatmap function.  I don't think this is as common a use case as you might think, so I doubt there is a simple canned solution. Sean --- On Wed, 11/3/10, Steve Lianoglou <mailinglist.honeypot@gmail.com> wrote: > From: Steve Lianoglou <mailinglist.honeypot@gmail.com> > Subject: Re: [BioC] heatmap Clustering help, two class (Control vs Exp) Experiments, > To: saurin_jani@yahoo.com > Cc: "Bioconductor Bioconductor" <bioconductor@stat.math.ethz.ch> > Date: Wednesday, November 3, 2010, 12:56 PM > Hi Saurin, > > On Wed, Nov 3, 2010 at 12:43 PM, Saurin D. Jani <saurin_jani@yahoo.com> > wrote: > > Hi, > > > > You are right but When I do this: > > > > > heatmap.2(FeatureX,col=gmpalette,Colv=as.dendrogram(hclust(col.dist, method="average")), > Rowv=as.dendrogram(hclust(row.dist,method="average")),scale="row",ke y=TRUE,keysize=0.60,symkey=FALSE,density.info="none",trace="none",marg ins=c(5,MapMargin),cexRow=1,cexCol=1,cex.sub=1); > > > > my control and exp. samples get mixed up..!! is there > anyway I can pass a parameter ..not to do that just cluster > samples on control and then exp. so, sorted view will be > there. > > But why would you cluster the samples to begin with, if you > just want > to reorder them in some (your) arbitrary way? > > Assuming your data is properly nomralised, etc. and > clustering your > samples "mixes them up," then the heatmap is showing you > visually that > your treatment examples aren't "strikingly different" than > your > controls. Your data is trying to tell you that (apparently) > all of > these experiments kind of look (expression wise) like each > other. > > Maybe that's telling you something about the quality of > your data, or > its annotation? > > Maybe you can try the plotPCA function in the affycoretools > package as > another way to see how your experiments "cluster > together". > > I'm not sure that it would change things, but what happens > if you > remove all probes w/ low variance across your entire > dataset and > re-cluster them? > > > May be something like this: cluster control samples > then exp. samples and then cluster based on Signal > Intensity. so, I keep the order ctrl1,ctrl5,ctrl6,ctrl2,... > and then Exp1,Exp5,Ex2,Exp10 ....so on... > > But then this is kind of misrepresenting what one would > expect to see > in such a plot .. you could, of course, plot and save > heatmaps over > just your control data, then again with just your > experiment, then > photoshop them together, but ... what's the point? > > I guess the question is: what are you trying to show in the > heatmap > you are trying to  produce? > > Given that, people might be able to then suggest things you > could try. > > -- > Steve Lianoglou > Graduate Student: Computational Systems Biology >  | Memorial Sloan-Kettering Cancer Center >  | Weill Medical College of Cornell University > Contact Info: http://cbio.mskcc.org/~lianos/contact > _______________________________________________ Bioconductor mailing list Bioconductor@stat.math.ethz.ch https://stat.ethz.ch/mailman/listinfo/bioconductor Search the archives: http://news.gmane.org/gmane.science.biology.informatics.conductor [[alternative HTML version deleted]]