[BioC] limma - genas: unexpected warnings

Gordon K Smyth smyth at wehi.EDU.AU
Mon Dec 2 06:31:04 CET 2013


Dear Guido,

Thanks for the reminder.  A bug fix for genas() has been included in limma 
3.18.4, so that genas() now handles vector df.prior in a graceful manner.

Best wishes
Gordon

> Date: Wed, 27 Nov 2013 14:30:08 +0000
> From: "Hooiveld, Guido" <guido.hooiveld at wur.nl>
> To: "bioconductor at r-project.org" <bioconductor at r-project.org>
> Subject: [BioC] limma - genas: unexpected warnings
>
> Hi Gordon,

> I am using the function genas() on a model that has been fitted with the 
> option robust=TRUE. Unexpectedly cryptic warnings are thrown, that are 
> absent when robust=FALSE. Although this is not an error, I thought you 
> may want to know. I checked that it is not dependent on my specific 
> dataset.
>
> Regards,
> Guido
>
> Using the code from the genas() help page:
> ...
> ...
> # fit a linear model
> fit <- lmFit(y,design)
> fit2 <- eBayes(fit)
>
>> genas(fit2, coef=c(2,3), plot=TRUE, subset="F")
> $technical.correlation
> [1] 0.5
>
> $covariance.matrix
>          [,1]      [,2]
> [1,]  4.516257 -3.770552
> [2,] -3.770552  4.446184
>
> $biological.correlation
> [1] -0.8414376
>
> $deviance
> [1] 114.4627
>
> $p.value
> [1] 1.031906e-26
>
> $n
> [1] 210
>
> There were 50 or more warnings (use warnings() to see the first 50)
>> warnings()
> Warning messages:
> 1: In if (d0 == Inf) d0 <- 999 * d[1] :
>  the condition has length > 1 and only the first element will be used
> 2: In if (d0 == Inf) d0 <- 999 * d[1] :
>  the condition has length > 1 and only the first element will be used
> 3: In if (d0 == Inf) d0 <- 999 * d[1] :
>  the condition has length > 1 and only the first element will be used
> 4:etc, etc
>
>> sessionInfo()
> R version 3.0.2 Patched (2013-11-10 r64185)
> Platform: x86_64-w64-mingw32/x64 (64-bit)
>
> locale:
> [1] LC_COLLATE=English_United States.1252
> [2] LC_CTYPE=English_United States.1252
> [3] LC_MONETARY=English_United States.1252
> [4] LC_NUMERIC=C
> [5] LC_TIME=English_United States.1252
>
> attached base packages:
> [1] splines   stats     graphics  grDevices utils     datasets  methods
> [8] base
>
> other attached packages:
> [1] ellipse_0.3-8  statmod_1.4.18 limma_3.18.3
>>
>
> ---------------------------------------------------------
> Guido Hooiveld, PhD
> Nutrition, Metabolism & Genomics Group
> Division of Human Nutrition
> Wageningen University
> Biotechnion, Bomenweg 2
> NL-6703 HD Wageningen
> the Netherlands
> tel: (+)31 317 485788
> fax: (+)31 317 483342
> email:      guido.hooiveld at wur.nl
> internet:   http://nutrigene.4t.com
> http://scholar.google.com/citations?user=qFHaMnoAAAAJ
> http://www.researcherid.com/rid/F-4912-2010

______________________________________________________________________
The information in this email is confidential and intend...{{dropped:4}}



More information about the Bioconductor mailing list