[BioC] [Limma] lmFit handle missing value in phenotype

[Moshe Olshansky]

You are right.  My mistake. Sorry...

> Hi, Moshe,
>
> I still did not get it. How to use your method?
>
> lmFit<-(x,design) which x allow missing values, but design didn't.
>
> usually, I want to adjust batch effects, I will include it in design
> matrix, i.e.
>                case  control  batch
>                  1        0           1
>                   0       1           1
>                   1       0           2
> which x is expression matrix, and then I will get the differential
> expressed gene between case and control with adjusting batch.
>
> In this case, I just want to simply use "weight" instead of  "batch" in
> design matrix. But unfortunately, you can't have missing values in design
> matrix which I think it's very often if we have many samples.
>
> 2012/4/4 Moshe Olshansky <olshansky at wehi.edu.au>
>
>> Why do you want to include weight in the design matrix?
>> It may be more reasonable to include weight in the linear model, i.e.
>> expression ~ condition + weight and then your design matrix will have
>> two
>> columns (if there are two conditions): the first column will contain 0's
>> and 1's depending on the condition (group) of the patient while the
>> second
>> one will be identically 1. And then the weights of the patients will be
>> in
>> the values (i.e. the second argument to lmFit) which I believe allows
>> missing values.
>> But this implicitly assumes that the weight (or some function of it -
>> you
>> can use any transformation you like) contributes additively (and
>> linearly)
>> to the expression (or it's logarithm).
>>
>> Moshe.
>>
>> > Hi,
>> >
>> > I am using Limma to get differential expressed genes between case and
>> > control samples. In addition, I want to adjust the "weight" of
>> patients
>> by
>> > including it in the "design" matrix. However, one weight value of a
>> > patient
>> > is missing, so I have a "NA" in design matrix. When I run lmFit, I got
>> the
>> > error message :Error in qr.default(x) : NA/NaN/Inf in foreign function
>> > call
>> > (arg 1).
>> >
>> > Can limma handle the missing value in design matrix or I have to
>> remove
>> > this sample ?
>> >
>> > Thanks,
>> >
>> > Chen
>> >
>> >       [[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
>> >
>>
>>
>>
>> ______________________________________________________________________
>> The information in this email is confidential and intended solely for
>> the
>> addressee.
>> You must not disclose, forward, print or use it without the permission
>> of
>> the sender.
>> ______________________________________________________________________
>>
>



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