getMI: Functions to calculate mutual information
In weiyi-bitw/cafr: Attractor Metagenes Finding Algorithm

Description Usage Arguments Details Value Note Author(s) References See Also Examples

Functions to calculate mutual information using B-spline method.

1 2	getMI(x, y, bin=6, so=3, rankBased=FALSE, normalize=TRUE, negateMI=FALSE) getAllMIWz(data, x, bin=6, so=3, rankBased=FALSE, normalize=TRUE, sorting=FALSE, negateMI=FALSE)

`x, y`	A vector of expression values
`data`	An expression matrix with genes in the rows, samples in the columns.
`bin`	Number of bins used when estimate mutual information (default=6).
`so`	Spline order used when estimate mutual information (default=3).
`rankBased`	When `TRUE`, convert the expression values into ranks.
`normalize`	When `TRUE`, normalize the mutual information by dividing the value by the maximum of the self-mutual information of the two variables `max(getMI(x, x), getMI(y, y))`.
`sorting`	Whether sort the output vector of MI's.
`negateMI`	When `TRUE`, negate the mutual information if the two vectors have negative momentum.

getMI evaluate the mutual information between two vectors using B-spline functions. The function calls a C function implemented by Daub. The default setting uses six bins and third-order B-splines. getAllMIWz evaluates the mutual information between every row in data and the given vector x. The output vector of mutual information will be sorted if sorting is TRUE.

The normalize option normalizes the mutual information by dividing the value by the maximum of the self-mutual information of the two variables. It makes all the MI's between 0 and 1 and thus beneficial to calculation of Attractor Metagenes.

getMI returns the mutual information between two vectors. getAllMIWz returns a vector of mutual information between each row of data and the vector x.

Missing values are not allowed as the input to the function in the current version.

Wei-Yi Cheng

Carsten O Daub, Ralf Steuer, Joachim Selbig and Sebastian Kloska, Estimating mutual information using B-spline functions - an improved similarity measure for analysing gene expression data. BMC Bioinformatics 2004, 5:118.

Wei-Yi Cheng, Tai-Hsien Ou Yang and Dimitris Anastassiou, Biomolecular events in cancer revealed by attractor metagenes, PLoS Computational Biology, Vol. 9, Issue 2, February 2013.

findAttractor for finding attractor using mutual information. getCorr, getAllCorWz

# Load the toy dataset extracted from TCGA OV data
data(ov)
#==============
# First example: find the mutual information between CENPA and MELK
#==============
x <- ov["CENPA",]
y <- ov["MELK",]
mi <- getMI(x, y)

#==============
# Second example: evaluate the mutual information between every gene in the dataset and CENPA
#==============
mis <- getAllMIWz(ov, x, sorting=TRUE)