GLMnetwork: Infer a network from RNA-seq expression.

In RNAseqNet: Log-Linear Poisson Graphical Model with Hot-Deck Multiple Imputation

Description

GLMnetwork infers a network from RNA-seq expression with the log-linear Poisson graphical model of (Allen and Liu, 2012).

Usage

GLMnetwork(counts, lambdas = NULL, normalize = TRUE)

Arguments

counts	a n x p matrix of RNA-seq expression (numeric matrix or data frame)
lambdas	a sequence of decreasing positive numbers to control the regularization (numeric vector). Default to NULL
normalize	logical value to normalize predictors in the log-linear Poisson graphical model. If TRUE, log normalization and scaling are performed prior the model is fit. Default to TRUE

Details

When input lambdas are null the default sequence of glmnet for the first model (the one with the first column of count as the target) is used.

Value

S3 object of class GLMnetwork: a list consisting of

• lambda regularization parameters used for LLGM path(vector)

• path a list having the same length than lambda. It contains the estimated coefficients (in a matrix) along the path

Author(s)

Alyssa Imbert, [e-mail]

Nathalie Vialaneix, [e-mail]

References

Allen, G. and Liu, Z. (2012) A log-linear model for inferring genetic networks from high-throughput sequencing data. In Proceedings of IEEE International Conference on Bioinformatics and Biomedecine (BIBM).

See Also

stabilitySelection

Examples

data(lung)
lambdas <- 4 * 10^(seq(0, -2, length = 10))
ref_lung <- GLMnetwork(lung, lambdas = lambdas)

RNAseqNet documentation built on July 2, 2020, 4:15 a.m.