Hi, We have the following design for our twin-sample array analysis: File Cy3 Cy5 Twin 403797 Ref A 1 343724 Ref A 2 343857 Ref A 3 403784 Ref Con 1 343720 Ref Con 2 343960 Ref Con 3 We would like to compare A-Con, so, I have constructed the following design matrix: Intercept T2 T3 A Con 1 0 0 1 0 1 1 0 1 0 1 0 1 1 0 1 0 0 0 1 1 1 0 0 1 1 0 1 0 1 and then constructed the contrast matrix for comparing A-Con: Contrasts Levels AvsCon Intercept 0 T2 0 T3 0 A 1 Con -1 Could you please tell us whether the design and contrast matrices are appropriate for comparing A-Con? Thanks in advance. Kind regards, Sharon [[alternative HTML version deleted]]

Hi Sharon, Your experimental design is almost exactly like the Paired Samples example in the limmaUsersGuide() , section 8.3. The only difference is that you have dual-channel arrays. However, since all your common reference are in the Cy3 channel, all the M-value ratios are already in the direction you want them. You can use the Paired Samples code exactly as if you had single-channel data. HTH, Jenny At 07:18 AM 1/26/2011, Sharon wrote: >Hi, > >We have the following design for our twin-sample array analysis: > >File Cy3 Cy5 Twin >403797 Ref A 1 >343724 Ref A 2 >343857 Ref A 3 >403784 Ref Con 1 >343720 Ref Con 2 >343960 Ref Con 3 > >We would like to compare A-Con, so, I have constructed the following design >matrix: > >Intercept T2 T3 A Con >1 0 0 1 0 >1 1 0 1 0 >1 0 1 1 0 >1 0 0 0 1 >1 1 0 0 1 >1 0 1 0 1 > >and then constructed the contrast matrix for comparing A-Con: > > Contrasts >Levels AvsCon > Intercept 0 > T2 0 > T3 0 > A 1 > Con -1 > >Could you please tell us whether the design and contrast matrices are >appropriate for comparing A-Con? > >Thanks in advance. > >Kind regards, >Sharon > > [[alternative HTML version deleted]] > >_______________________________________________ >Bioconductor mailing list >Bioconductor at r-project.org >https://stat.ethz.ch/mailman/listinfo/bioconductor >Search the archives: >http://news.gmane.org/gmane.science.biology.informatics.conductor

Yes, it is performed on the M-values. You have dual-channel with a common reference, so the stats should be done on the M-values. However, the design matrix will be exactly the same for a dual-channel experiment with common reference all in Cy3 and an Affymetrix data set. Jenny At 09:39 AM 1/26/2011, Sharon wrote: >Hi Jenny, > >Thanks a lot. Does this mean the paired t-test is performed on >M-values but not on the intensity values (as in Affymetrix)? > >Thanks again, >Sharon > >On Wed, Jan 26, 2011 at 2:45 PM, Jenny Drnevich ><<mailto:drnevich@illinois.edu>drnevich@illinois.edu> wrote: >Hi Sharon, > >Your experimental design is almost exactly like the Paired Samples >example in the limmaUsersGuide() , section 8.3. The only difference >is that you have dual-channel arrays. However, since all your common >reference are in the Cy3 channel, all the M-value ratios are already >in the direction you want them. You can use the Paired Samples code >exactly as if you had single-channel data. > >HTH, >Jenny > > >At 07:18 AM 1/26/2011, Sharon wrote: >Hi, > >We have the following design for our twin-sample array analysis: > >File Cy3 Cy5 Twin >403797 Ref A 1 >343724 Ref A 2 >343857 Ref A 3 >403784 Ref Con 1 >343720 Ref Con 2 >343960 Ref Con 3 > >We would like to compare A-Con, so, I have constructed the following design >matrix: > >Intercept T2 T3 A Con >1 0 0 1 0 >1 1 0 1 0 >1 0 1 1 0 >1 0 0 0 1 >1 1 0 0 1 >1 0 1 0 1 > >and then constructed the contrast matrix for comparing A-Con: > > Contrasts >Levels AvsCon > Intercept 0 > T2 0 > T3 0 > A 1 > Con -1 > >Could you please tell us whether the design and contrast matrices are >appropriate for comparing A-Con? > >Thanks in advance. > >Kind regards, >Sharon > > [[alternative HTML version deleted]] > >_______________________________________________ >Bioconductor mailing list ><mailto:bioconductor@r-project.org>Bioconductor@r-project.org >https://stat.ethz.ch/mailman/listinfo/bioconductor >Search the archives: ><http: news.gmane.org="" gmane.science.biology.informatics.conductor="">ht tp://news.gmane.org/gmane.science.biology.informatics.conductor > > [[alternative HTML version deleted]]