plot.bayesian {sma} | R Documentation |
This function takes the normalized expression estimates from a multi-slide microarray experiment (M-values output by stat.ma) and plots an odds ratio for each gene: log( Pr(the gene is differentially expressed) / Pr(the gene is not differentially expressed) ) vs the gene-specific average M-value. Alternatively, the output of stat.bayesian() can be given as input. The resulting plot is the same, but tedious calculations don't have to be done all over again.
plot.bayesian(X=NULL, nb=NULL, nw=1, lods=NULL, Xprep=NULL, para=list(p = 0.01, v = NULL, a = NULL, c = NULL, k = NULL))
X |
List containing matrix of (normalized) log expression ratios M = log_2 (R/G) (E.g. output from stat.ma()) |
nb |
Number of slides containing spots for a gene (common for all genes). Unnecessary argument if nw=1. |
nw |
Number of spots for a gene within each slide (common to all genes).Default is 1. |
lods |
The log odds ratio for each gene. Not necessary input. See details! |
Xprep |
Some data structures useful in this graphical presentation. Not necessary input. See details! |
para |
Estimates of the parameters used in the Bayesian calculations. Not necessary input. See details! |
Ingrid Lönnstedt ingrid@math.uu.se
Yee Hwa Yang, yeehwa@stat.berkeley.edu
data(MouseArray) ## mouse.setup <- init.grid() ## mouse.data <- init.data() ## see \emph{init.data} ## mouse.lratio <- stat.ma(mouse.data, mouse.setup) #Alternative 1 ## mouse.bayesian<-stat.bayesian(X=mouse.lratio) ## plot.bayesian(Xprep=mouse.bayesian$Xprep, lods=mouse.bayesian$lods) #Alternative 2 ## plot.bayesian(X=mouse.lratio) #My changes ## my.para<-mouse.bayesian$para ## my.para$p<-0.005 ## plot.bayesian(Xprep=mouse.bayesian$Xprep, para=my.para)