R help - Mar 2008 - Statistical Questions: finding differentially expressed

>Date: Thu, 6 Mar 2008 06:46:07 -0800 (PST)
>From: Keizer_71 <christophe.lo@gmail.com>
>Subject: [R] Statistical Questions: finding differentially expressed
 >genes
>To: r-help@r-project.org
>Message-ID: <15873163.post@talk.nabble.com>
>Content-Type: text/plain; charset=us-ascii
>Hi Everyone,
>I am trying to find a way to do this in excel to tell me which genes
>are the most differentially expressed. Sorry, i couldn't find excel
forum
>section in nabble. However, if it is in R it is fine. This is a microarray
data,
>and it has been normalized. According to Dov Stekel in Microarray, i will
need
 >to calculate log ratio (control-treatment). Once you have the log
ratio,
> calculate using paired t-test. Once you calculate the paired t-test,
> you will find the p-value and the t-test. Is there a way in excel to
 > calculate the confidence level that is significant. For example, it will
be under
>1% for all the genes to be differentially expressed. 
>The book did not explained how log ratio will help me determine the
>significant value. 
>GeneID   treatment control treatment control treatment control 
>Gene1        2.1   1 2     2.2     1.1    0.7      2.7 
>Gene2        1.5   1.4   1.7    2.2   1.3     1.2 
>Gene3      1.4   1.7   1.8    2.7   1.6      1.5 
>Gene4       2.2   2.4    2.1    2.3     2.1      1.9 
>Gene5       2.6   3.4    2.1    1.3   2.6     2.9 
>Objective: find genes who are differentially epxressed.

  I'm not sure what you are asking, but to find whether one of your genes is
significantly expressed is relatively straightforward in R or excel, and you
have already outlined the procedure yourself. Have you tried to perform a paired
t test or log transform in either software yet, and if so, what is the stumbling
block?
  Read and follow the examples given in Dov Stekel's excellent book. There
is no better microarray statistics primer IMHO, and reasons for log transforms
and an example of exactly the analysis you require are clearly explained.
  I 

       
---------------------------------

	[[alternative HTML version deleted]]