nbiNet: Network Based Inference

In abhik1368/netpredictor: Algorithms to search for missing link in a graph.

Description

Given a bipartite graph , a two phase resource transfer Information from X(x,y,z) set of nodes gets distributed to Y set of nodes and then again goes back to resource X. This process allows us to define a technique for the calculation of the weight matrix W. if the similarity matrices are not provided it uses bipartite graph to compute netowrk based inference .

Usage

nbiNet(A, alpha = 0.5, lamda = 0.5, s1 = NA, s2 = NA,
  format = c("igraph", "matrix", "pairs"))

Arguments

A	Adjacency Matrix
alpha	Tuning parameter (value between 0 and 1) to adjust the performance of the algorithm.
lamda	Tuning parameter (value between 0 and 1) which determines how the distribution of resources takes place in thesecond phase
s1	Target Similarity matrix
s2	Chemical Similarity Matrix
format	type of file as Adjacnency file

Details

Network based inference on Bipartite networks

References

• Cheng F, et al. Prediction of drug target interactions and drug repositioning via network-based inference. PLoS Comput. Biol. 2012;8:e1002503.

• Zhou T, et al. Solving the apparent diversity-accuracy dilemma of recommender systems. Proc. Natl Acad. Sci. USA 2010;107:4511-4515.

• Zhou T, et al. Bipartite network projection and personal recommendation. Phys. Rev. E Stat. Nonlin. Soft Matter Phys. 2007;76:046115.

• Blog post from Abhik Seal http://data2quest.blogspot.com/2015/02/link-prediction-using-network-based.html

Examples

data(Enzyme)
A <- t(enzyme_ADJ)
S1 = as.matrix(enzyme_Csim)
S2 = as.matrix(enzyme_Gsim)
g1 = upgrade_graph(graph.incidence(A))
## other format available \code{format = c("igraph","matrix","pairs")}
M2 <- nbiNet(A,alpha=0.5, lamda=0.5,  s1=S1, s2=S2,format = "matrix")
M3 <- nbiNet(A,alpha=0.5,lamda=0.5,format="matrix")

abhik1368/netpredictor documentation built on May 10, 2019, 4:09 a.m.