compareGraphs: compareGraphs

In ddepn: Dynamic Deterministic Effects Propagation Networks: Infer signalling networks for timecourse RPPA data.

Description

Given an original and inferred network, count number of true/false positives and negatives. Calculate sensitivity and specificity measures.

Usage

compareGraphs(phiorig,phi,ignore.type=FALSE)

Arguments

phiorig	Original graph. Stored as adjacency matrix.
phi	Inferred graph. Stored as adjaceny matrix.
ignore.type	Boolean. If TRUE, only compare edge abundance, if FALSE, also take into account the type of the edge for counting numbers of true and false edges.

Details

Counts the number of tp as: activations in phi and phiorig + inhibitions in phi and phiorig.
Counts the number of fp as: activations or inhibitions in phi and no edge in phiorig.
Counts the number of tn as: no edge in phi and no edge in phiorig.
Counts the number of fn as: no edge in phi and activation or inhibition in phiorig.

Value

Vector of comparison measures:

tp	True positives
fp	False positives
tn	True negatives
fn	False negatives
sn	Sensitivity: sn = tp/(tp+fn)
sp	Specificity: sp = tn/(tn+fp)
prec	Precision: prec = tp / (tp + fp)
f1	F1: 2*prec*sn / (prec + sn)

Author(s)

Christian Bender

Examples

## Not run: 
  library(ddepn)
  phi <- matrix(sample(c(0,1,2),9,replace=TRUE),nrow=3,ncol=3)
  phiorig <- matrix(sample(c(0,1,2),9,replace=TRUE),nrow=3,ncol=3)
  compareGraphs(phi,phiorig)

## End(Not run)

ddepn documentation built on May 2, 2019, 4:42 p.m.