[R] biclust package

[Martin Maechler]

>>>>> "UweL" == Uwe Ligges <ligges at statistik.tu-dortmund.de>
>>>>>     on Fri, 26 Feb 2010 17:24:43 +0100 writes:

    UweL> On 26.02.2010 17:04, linda garcia wrote:
    >> Dear all,
    >> I am using biclust package for biclustering. I wanted to
    >> know how can I extract my clusters from the object?
    >> 
    >> 
    >> library(biclust)
    >> test<- matrix(rnorm(5000), 100, 50)
    >> 
    >> test[11:20,11:20]<- rnorm(100, 3, 0.1)
    >> 
    >> loma<- binarize(test,2)
    >> 
    >> res<- biclust(x=loma, method=BCBimax(), minr=4, minc=4, number=10)
    >> 
    >> res
    >> 
    >> 
    >> Thanks for your help
    >> 
    >> 


    UweL> According to ?biclust which links to the Biclust class, there are slots 
    UweL> that indicate cluster assigmnets in:

    UweL> res at RowxNumber
    UweL> res at NumberxCol

Yes, indeed.  Reading the help page carefully *is* .... hmm, at
least recommended.

Note that
 
    str(res)

would also reveal to you about the components, you could use.
Here's a small script snippet,
which *would* reveal more if there wasn't a bug in biclust's
summary method :

str(res)## -> 'low-level' content.

## Better recommended:
class(res)# "Biclust"
showMethods(class = "Biclust")
## which reveals that there's a  summary() method.
##
## However,
sres <- summary(res)
## --> starts *printing* things [not according to "good R examples"]
## --> ends in an **ERROR**
##       .............
##       'x' must be an array of at least two dimensions
## (because it assumes things that are wrong)