[BioC] PLIER affinities

[Jeremy Gollub]

Hi, All -

I'm confused by the affinities returned by justPlier (from the plier
package).  My understanding is that the PLIER algorithm is supposed to
produce a single affinity per PM/MM probe pair, across the entire set of
arrays analyzed.  However, justPlier() returns the values in a matrix of
dimensions <# of probe pairs> X <# of chips> - e.g, 175,477 X 18, for
18 RAE230A arrays.  The column names of this matrix are the names of the
samples/arrays; the row names are the probe set names, repeated
(apparently) once for each probe pair in the set (i.e., there are 11 rows
with the name 1367452_at).

Upon closer inspection, the matrix contains only 175,407 non-zero values,
which would be consistent with a single value per probe pair.  All columns
contain some non-zero values, approximately 15,923 (one per probe set) in
the first 11 columns, and 36 in the other 7 (perhaps due to control probe
sets with more probes).  All rows below 15,924 contain only zeros.

Do I misunderstand?  Or should the affinities in fact be a one-dimensional
vector with one value per probe pair, making this an error in the way
justPlier(), or the C++ code, return the values?

SessionInfo() output below.

Thanks,

- Jeremy

> sessionInfo()
R version 2.1.1, 2005-06-20, i386-pc-mingw32 

attached base packages:
[1]
"tools"     "methods"   "stats"     "graphics"  "grDevices" "utils"     "datasets" 
[8] "base"     

other attached packages:
rae230acdf      plier       affy reposTools    Biobase 
   "1.5.1"    "1.0.0"    "1.6.7"   "1.5.19"   "1.5.12" 

--
Jeremy Gollub, Ph.D.
jgollub at genome.stanford.edu