Hi all, I have an experiment with several control and several experimental replicate chips, and the chips are not actual biological replicates, but rather represent replicate hybridizations or amplifications. In terms of the data to be input into a clustering algorithm such as kmeans, would it be better for me to calculate a single average value for the control side and one for the experimental side than it would be to input all of the replicate chip data? It seems that using all of the replicate data points from non-biological replicates would only help partition non-biological aspects of the data and not help answer questions regarding what is happening biologically between the control and experimental cases. Thanks in advance, Ken

I agree with your approach. --Naomi At 05:47 PM 4/13/2005, Ken Termiso wrote: >Hi all, > >I have an experiment with several control and several experimental >replicate chips, and the chips are not actual biological replicates, but >rather represent replicate hybridizations or amplifications. In terms of >the data to be input into a clustering algorithm such as kmeans, would it >be better for me to calculate a single average value for the control side >and one for the experimental side than it would be to input all of the >replicate chip data? It seems that using all of the replicate data points >from non-biological replicates would only help partition non- biological >aspects of the data and not help answer questions regarding what is >happening biologically between the control and experimental cases. > >Thanks in advance, >Ken > >_______________________________________________ >Bioconductor mailing list >Bioconductor@stat.math.ethz.ch >https://stat.ethz.ch/mailman/listinfo/bioconductor Naomi S. Altman 814-865-3791 (voice) Associate Professor Bioinformatics Consulting Center Dept. of Statistics 814-863-7114 (fax) Penn State University 814-865-1348 (Statistics) University Park, PA 16802-2111