pairwise.posterior {nem}R Documentation

Infers a phenotypic hierarchy edge by edge

Description

Function pairwise.posterior estimates the hierarchy edge by edge. In each step only a pair of nodes is involved and no exhaustive enumeration of model space is needed as in function score.

Usage

pairwise.posterior(D, type="mLL", para=NULL, hyperpara=NULL,Pe=NULL, Pm=NULL, verbose=TRUE)

#S3 methods for class 'pairwise'
plot.pairwise(x, what="graph", remove.singletons=FALSE, PDF=FALSE, filename="nemplot.pdf", ...)
print.pairwise(x,...) 

Arguments

D data matrix. Columns correspond to the nodes in the silencing scheme. Rows are phenotypes.
type (1.) marginal likelihood "mLL" depending on paramters a and b, or (2.) full marginal likelihood "FULLmLL" integrated over a and b and depending on hyperparameters a0, a1, b0, b1
para vector with parameters a and b
hyperpara vector with hyperparameters a0, b0, a1, b1
Pe prior position of effect reporters. Default: uniform over nodes in hierarchy
Pm local model prior for the four models tested at each node: a vector of length 4 with positive entries summing to one
verbose do you want to see progress statements printed or not? Default: TRUE
x an object of class 'pairwise'
what type of plot: 'graph' or 'pos'. Default: 'graph'
remove.singletons remove single nodes which are not connected to any other node when plotting? Default: FALSE
PDF output as pdf file? Default: FALSE
filename name of the pdf if any. Default: "nemplot.pdf"
... additional arguments for plotting

Details

pairwise.posterior is a fast(er) heuristic alternative to exhaustive search by the function score. For each pair (A,B) of perturbed genes it chooses between four possible models: A..B (unconnected), A->B (superset), A<-B (subset), or A<->B (undistinguishable). The result is the graph built from the maximum aposteriori models for each edge.

plot.pairwise plots the inferred phenotypic hierarchy as a directed graph, and print.pairwise gives an overview over the 'pairwise' object.

Value

graph the inferred directed graph (graphNEL object)
pos posterior over effect positions
mappos MAP estimate of effect positions
scores a matrix with the posterior probabilities for each local model as rows
type as used in function call
para as used in function call
hyperpara as used in function call

Author(s)

Florian Markowetz <URL: http://genomics.princeton.edu/~florian>

See Also

score, nem

Examples

   data("BoutrosRNAi2002") 
   res <- pairwise.posterior(BoutrosRNAiDiscrete[,9:16],para=c(.13,.05))
   
   # plot graph
   plot(res,what="graph")
   
   # plot posterior over effect positions
   plot(res,what="pos")
   
   # estimate of effect positions
   res$mappos
   

[Package nem version 1.2.0 Index]