[R] Overlapping Matrices By column correlation

Karim Mezhoud kmezhoud at gmail.com
Fri Jan 9 16:57:02 CET 2015


Thanks David.
It seems not easy to compare multiple Matrices.
karim

  Ô__
 c/ /'_;~~~~kmezhoud
(*) \(*)   ⴽⴰⵔⵉⵎ  ⵎⴻⵣⵀⵓⴷ
http://bioinformatics.tn/



On Thu, Jan 8, 2015 at 6:40 PM, David Winsemius <dwinsemius at comcast.net>
wrote:

>
> On Jan 8, 2015, at 2:26 AM, Karim Mezhoud wrote:
>
> > Mantel test is interesting but it can't displays wish columns are
> similar.
> >
> > Here an example:  M
> >                        gene1   gene2  gene3  gene4   gene5
> > Sample1           2            4            1           7            2
> > Sample2          0               NA        2.3      1            9
> > Sample3
> > ......
> >
> > M1, M2, M3 are three matrices of genes expression from three diseases.
> > genes in columns and samples in rows.
> > I would like to know which diseases has nearest gene expression profile
> to
> > others? and which genes are in common?
>
> Two things we need:
>
> 1) Reproducible example: Perhaps dput(list( M1[1:10,1:10) , M2[ 1:10.1:10]
> ))
>
> 2) A suggested metric for distance between such data objects that would be
> acceptable to practitioners in whatever dark arts this activity is being
> conducted
>
> > Any suggestion?
> > Thanks
> > Karim
> >
> >       [[alternative HTML version deleted]]
>
> This is a plain text mailing list.
>
> > PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> > and provide commented, minimal, self-contained, reproducible code.
>
> --
>
> David Winsemius
> Alameda, CA, USA
>
>

	[[alternative HTML version deleted]]



More information about the R-help mailing list