netbenchmark (version 1.4.2)

mrnet.wrap: mrnet wrapper function

Description

Default function for the MRNET network inference algorithm

Usage

mrnet.wrap(data)

Arguments

data

Numeric matrix with the microarray dataset to infer the network. Columns contain variables and rows contain samples.

Value

• mrnet.wrap returns a matrix which is the weighted adjacency matrix of the network inferred by MRNET algorithm. The wrapper uses the "spearman" correlation (can be used with continuous data) to estimate the entropy - see build.mim.

Details

The MRNET approach consists in repeating a MRMR feature selection procedure for each variable of the dataset. The MRMR method starts by selecting the variable $X_i$ having the highest mutual information with the target $Y$. In the following steps, given a set $\mathcal{S}$ of selected variables, the criterion updates $\mathcal{S}$ by choosing the variable $X_k$ that maximizes $I(X_k;Y) - \frac{1}{|\mathcal{S}|}\sum_{X_i \in \mathcal{S}} I(X_k;X_i)$ The weight of each pair $X_i,X_j$ will be the maximum score between the one computed when $X_i$ is the target and the one computed when $X_j$ is the target.

References

Patrick E. Meyer, Kevin Kontos, Frederic Lafitte and Gianluca Bontempi. Information-theoretic inference of large transcriptional regulatory networks. EURASIP Journal on Bioinformatics and Systems Biology, 2007.

Patrick E. Meyer, Frederic Lafitte and Gianluca Bontempi. minet: A R/Bioconductor Package for Inferring Large Transcriptional Networks Using Mutual Information. BMC Bioinformatics, Vol 9, 2008.

H. Peng, F.long and C.Ding. Feature selection based on mutual information: Criteria of max-dependency, max relevance and min redundancy. IEEE transaction on Pattern Analysis and Machine Intelligence, 2005.

See Also

netbenchmark, evaluate, mrnet

Examples

# Data
    data <- grndata::getData(datasource.name = "toy",FALSE)
    # Inference
    net <- mrnet.wrap(data)