table.evaluate: Evaluation of inferred gene networks

Description Usage Arguments References Examples

View source: R/table.evaluate.R

Description

The inferred network is evaluated by comparing to the reference network. The output is a tables of TP, FP, TN and FP with different edge weight cut-offs [1].

Usage

1
table.evaluate(inf.adj, ref.adj, directed = F)

Arguments

inf.adj

the inferred network matrix. Column names and row names match to the reference network.

ref.adj

the reference network matrix with 1 inidating connected edge and 0 unconnected edge.

directed

logical, to compare as directed or undirected networks. In a undirected network, only the upper triangular of the network matrix is used for evaluation.

References

[1] Meyer PE, Lafitte F, Bontempi G: minet: A R/Bioconductor package for inferring large transcriptional networks using mutual information. BMC Bioinformatics 2008, 9:461.

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
##load library
library(RLowPC)
##load data
data(gnwdata)
data.exp<-gnwdata$size100$ts1[,-c(1:3)]
genes<-colnames(data.exp)
ref.edge<-gnwdata$size100$net1
ref.edge[,3]<-1
ref.adj<-edgelist2adjmatrix(ref.edge,genes)
inf.cor<-abs(cor(data.exp))
diag(inf.cor)<-0
table.cor<-table.evaluate(inf.adj = inf.cor,ref.adj = ref.adj)
head(table.cor)

wyguo/RLowPCor documentation built on May 4, 2019, 12:04 p.m.