[R] EBAM ERROR

[Spencer Graves]

      I haven't seen a reply to this post, so I will offer a couple of 
comments.  Unfortunately, the information provided is not sufficient for 
me to answer your questions.  If you'd still like help from this 
listserve, please provide commented, minimal, self-contained, 
reproducible code, as suggested in the posting guide 
"www.R-project.org/posting-guide.html".  However, have you tried 
"www.bioconductor.org"?  I believe they also have a listserve, and the 
people who follow that list should be more familiar with analysis of 
genetic data than this more general listserve. 

      Also, I suggest you send your email "From" something more 
revealing of who you are.  Some of the most knowledgeable and frequent 
contributors to this listserve rarely if ever answer questions from 
anonymous email addresses like "learningr at gmail.com". 

      Hope this helps. 
      Spencer Graves

Learning R wrote:
> Dear RUsers,
>
> I am new to R. I am learning how to use R. I am a PC user and run R on
> windows. I would appreciate if some one could guide me on a few questions I
> have:
>
> 1) I have 4 cel files (2 replicates for NORM and Disease resp). I have been
> able to run siggenes on this dataset where I have 4 labels in the class file
> groupsnhi.cl  op-> (0,0,1,1) and my data has been read into datrmanhi after
> performing rma. When I run these commands here I receive these errors:
>
>   
>> plot(samnhi.out,seq(0.1,0.6,0.1))
>> identify(samnhi.out,ll=FALSE)
>>     
> warning: no point with 0.25 inches
> warning: no point with 0.25 inches
> warning: no point with 0.25 inches
>
> Why does this happen.
>
> 2) Now I am trying to run EBAM: and when I type I get an error
>
>  > find.out<-find.a0(datrmanhi,groupsnhi.cl,rand=123)
> Loading required package: affy
> Loading required package: affyio
> EBAM Analysis for the two class unpaired case.
>
> Warning: There are 1 genes which have variance Zero or no non-missing
> values.
>          The d-value of these genes is set to NA.
>
>
>         The following object(s) are masked _by_ .GlobalEnv :
>
>          n
>
>
>         The following object(s) are masked from mat.repeat ( position 5 ) :
>
>          center log.bino n p success x1 x2 x3 x4 x5
>
> Error in optim(rep(0, 6), neglogLik.repeat, method = "BFGS") :
>         non-finite finite-difference value [1]
> In addition: Warning message:
> collapsing to unique 'x' values in: approx(Z, Z.norm, z, rule = 2)
>
>
> -------------------------------------------------------------------------------------------------------------------------------------------------------------------------
>
> I have also tried :
>   
>> find.out<-find.a0(exprs2,c(1,1,1,0,0,0),rand=123)
>>     
> EBAM Analysis for the two class unpaired case.
>
> Warning: There are 1 genes which have variance Zero or no non-missing
> values.
>          The d-value of these genes is set to NA.
>
>
>         The following object(s) are masked _by_ .GlobalEnv :
>
>          n
>
>
>         The following object(s) are masked from mat.repeat ( position 3 ) :
>
>          center log.bino n p success x1 x2 x3 x4 x5
>
>
>         The following object(s) are masked from mat.repeat ( position 6 ) :
>
>          center log.bino n p success x1 x2 x3 x4 x5
>
> Error in optim(rep(0, 6), neglogLik.repeat, method = "BFGS") :
>         non-finite finite-difference value [1]
> In addition: Warning message:
> collapsing to unique 'x' values in: approx(Z, Z.norm, z, rule = 2)
>
>
> I would greatly appreciate any solutions and help to solve this problem.
>
> Thank you,
> Appreciate your time.
> Regards,
> Lolita
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>