clr: Create an adjacency matrix based on context likelihood or...

View source: R/statistical.R

clrR Documentation

Create an adjacency matrix based on context likelihood or relatedness network


'clr' infers an adjacency matrix using context likelihood/relatedness network using the 'clr' function from the 'parmigene' package. 'clr' will return the adjacency matrix containing the Context Likelihood of Relatedness Network-adjusted scores of Mutual Information values.


clr(mi, ...)



matrix, where columns are samples and the rows are features (metabolites), cell entries are mutual information values between the features. As input, the mutual information (e.g. raw MI estimates) from the 'knnmi.all' function of the 'parmigene' package can be used.


not used here


For more details on the 'clr' function, refer to '?parmigene::clr'. CLR computes the score sqrt(z_i ^2 + z_j ^2) for each pair of variables i, j, where z_i = max(0, ( I(X_i, X_j) - mean(X_i) ) / sd(X_i) ). mean(X_i) and sd(X_i) are the mean and standard deviation of the mutual information values I(X_i, X_k) for all k = 1, ..., n. For more information on the CLR algorithm see Faith et al. (2007).


matrix, matrix with edges inferred from Context Likelihood of Relatedness Network algorithm 'clr'


Thomas Naake,


Faith et al. (2007): Large-Scale Mapping and Validation of Escherichia coli Transcriptional Regulation from a Compendium of Expression Profiles. PLoS Biology, e8, doi: [10.1371/journal.pbio.0050008](


data("x_test", package = "MetNet")
x <- x_test[1:10, 3:ncol(x_test)]
x <- as.matrix(x)
x_z <- apply(x, 1, function(y) (y - mean(y)) / sd(y))
mi_x_z <- parmigene::knnmi.all(x_z)

tnaake/MetNet documentation built on June 30, 2022, 10:50 a.m.