uniform.beta.node.edge.score: Generate node scores,edge scores and network

In yuy113/wActNet: Detection of active subnetwork in metabolic weighted network

Generate node scores,edge scores and network

Description

Generate both node and edge scores for biological correlation network based on P values of clinical outcome and nodes and also P values by multiple permulation tests on all the possible edges in biological correlaton network This function calculates edge scores based on P values in multiple testing assuming P values follows a mixture of two beta distributions- beta(a,1),beta(1,1)-Uniform(0,1) with those in permutated samples through nonparametric permutation tests. Also this function calculates node scores based on P values in multiple testing assuming P values follows a mixture of two beta distributions- beta(a,1),beta(1,1)-Uniform(0,1)

Usage

uniform.beta.node.edge.score(pval.node, pval.edge, FDR.node, FDR.edge, dat)

Arguments

pval.node	P values from multiple hypothesis testing in vector format hypothesis testing on clinical outcome with each individual node (variable) The names of the edges (names of two connecting nodes(variables)) must be specified.
pval.edge	P values from multiple hypothesis testing in vector format The names of the edges (names of two connecting nodes(variables)) must be specified.
FDR.node	The overall level of False Discovery Rate level for multiple testing on all the nodes(variables) ,typically 0.05,0.01
FDR.edge	The level of False Discovery Rate level for multiple testing on all possible edges,typically 0.01,0.001
dat	Dataset containing the observations for p covariates (nodes) The column names of the dat must be specified.

Value

A list of five elements as decribed below:

This function returns an object with class NetworkScore. The items in the object are:

NodeScore	The vector of scores of the nodes in network
EdgeScore	The vector of scores of all possible edges in network
FDR.node	False Discovery Rate for multiple testing on the nodes in the network
FDR.edge	False Discovery Rate for multiple testing on all possible edges in the network
Network	An igraph object-Network with attributes in nodes-node score and name,and edges-edge scores and names

Examples

dat1<-matrix(rnorm(4000),ncol=40,nrow=100)
colnames(dat1)<-paste("Var", as.character(1:40),sep="")

# simulate the p values for all the possible edges in the network
ind.pos.pval.edge<-rbinom(40*39/2,1,0.5)
pval.edge<-(1-ind.pos.pval.edge)*runif(40*39/2)+ind.pos.pval.edge*rbeta(40*39/2,0.1,1)
names(pval.edge)<-unlist(sapply(1:39,function(i){sapply((i+1):40, function(j){paste(paste("Var",
as.character(i),sep=""),paste("Var",as.character(j),sep=""),sep="_")})}))

# simulate p values for all the nodes in the network
ind.pos.pval.node<-rbinom(40,1,0.2)
pval.node<-(1-ind.pos.pval.node)*runif(40)+ind.pos.pval.node*rbeta(40,0.1,1)
names(pval.node)<-paste("Var", as.character(1:40),sep="")

# generate the node score-NodeScore, edge scores-EdgeScore and igraph object-Network
network.test<-uniform.beta.node.edge.score(pval.node,pval.edge,0.05,0.05,dat1)

yuy113/wActNet documentation built on Sept. 30, 2024, 5:50 a.m.