Skip to content

edgeR: design matrix setup

2 messages · rmje, Martin Morgan

rmje
# 
I have a data frame like this:

                       T0h T0.25h T0.5h  T1h  T2h  T3h  T6h T12h T24h T48h 
C0h C0.25h C0.5h  C1h  C2h  C3h  C6h C12h C24h C48h
NM_001001130   68     95    56   43   66   62   68   90   63   89   65    
85    58   49 81   49   76   73   48   77
NM_001001152   79    129    52   50   24   45  130  154  112  147   56    
85    67   33 52   31   93   77   65  109
...
...
...


It has about 29000 rows and 20 columns (incl col.name).
How would you set this up in edgeR if you want to compare the 10 first with
the 10 last?


--
View this message in context: http://r.789695.n4.nabble.com/edgeR-design-matrix-setup-tp4631094.html
Sent from the R help mailing list archive at Nabble.com.
Martin Morgan
#
On 05/23/2012 07:24 AM, rmje wrote:
Please ask questions about Bioconductor packages on the Bioconductor 
mailing list

   http://bioconductor.org/help/mailing-list/

There have been recent time-course questions on the mailing list, so 
it's good to browse recents posts. Remember to include sessionInfo(). 
Have you looked at the extensive vignette for this package

   http://bioconductor.org/packages/2.10/bioc/html/edgeR.html

and limma, and taken a stab at answering your own question? It helps to 
see where you're coming from...; for this particular question and if 
you're statistically naive it might help to have a conversation with 
someone local who is a little versed in statistics.

Martin