May I ask you a question about output of the function lumiT ? I am using this function to do variance stabilization on some data from an Ilumina BeadStudio output file using the VST method. Because of the standard format of this file, I have 4 values for each probe, AVG_Signal, BEAD_STDERR,Avd_NBEADS and Detection_Pvalue which of course are the inputs for the lumiT function. Applying the VST method, the 3 parameters c1,c2 and c3 are calculated. Since the input file does not explicitily provide the bead-level values for each probe, but only their statistical characteristics, I do not understand exactly how the final value for each probe outputed by the lumiT function is calculated and if it represents the mean of the transformed bead-level values. To be more precise I would like to ask if the final output is calculated with the formula:h=1/c1*arcsinh???(c2/???c3+(c1*m)/???c3), where m represents the mean of the beads values of the probe and h represents the output of lumiT for that probe. Thank you very much for your kindness. -- output of sessionInfo(): R version 3.0.2 (2013-09-25) Platform: x86_64-w64-mingw32/x64 (64-bit) locale: [1] LC_COLLATE=Romanian_Romania.1250 LC_CTYPE=Romanian_Romania.1250 [3] LC_MONETARY=Romanian_Romania.1250 LC_NUMERIC=C [5] LC_TIME=Romanian_Romania.1250 attached base packages: [1] stats graphics grDevices utils datasets methods base -- Sent via the guest posting facility at bioconductor.org.

Hi Neagu You are correct: in formula:h=1/c1*arcsinh⁡(c2/√c3+(c1*m)/√c3), where m represents the mean of the beads values of the probe and h represents the output of lumiT for that probe. For more details, please check the method paper: http://nar.oxfordjournals.org/content/36/2/e11.long Pan On Sat, Jan 4, 2014 at 8:05 AM, Neagu Matei Stefan [guest] < guest@bioconductor.org> wrote: > > May I ask you a question about output of the function lumiT ? > I am using this function to do variance stabilization on some data from an > Ilumina BeadStudio output file using the VST method. Because of the > standard format of this file, I have 4 values for each probe, AVG_Signal, > BEAD_STDERR,Avd_NBEADS and Detection_Pvalue which of course are the inputs > for the lumiT function. Applying the VST method, the 3 parameters c1,c2 and > c3 are calculated. Since the input file does not explicitily provide the > bead-level values for each probe, but only their statistical > characteristics, I do not understand exactly how the final value for each > probe outputed by the lumiT function is calculated and if it represents the > mean of the transformed bead-level values. > To be more precise I would like to ask if the final output is calculated > with the formula:h=1/c1*arcsinh⁡(c2/√c3+(c1*m)/√c3), where m represents the > mean of the beads values of the probe and h represents the output of lumiT > for that probe. > Thank you very much for your kindness. > > -- output of sessionInfo(): > > R version 3.0.2 (2013-09-25) > Platform: x86_64-w64-mingw32/x64 (64-bit) > > locale: > [1] LC_COLLATE=Romanian_Romania.1250 LC_CTYPE=Romanian_Romania.1250 > [3] LC_MONETARY=Romanian_Romania.1250 LC_NUMERIC=C > [5] LC_TIME=Romanian_Romania.1250 > > attached base packages: > [1] stats graphics grDevices utils datasets methods base > > -- > Sent via the guest posting facility at bioconductor.org. > [[alternative HTML version deleted]]