LMGene calls function genediff to calculate the unadjusted gene-specific and posterior p-values of all genes
and then calculates the FDR-adjusted p-values of all genes.
Significant genes for each factor in model (based on either the gene-specific or posterior FDR-adjusted p-values) are output.
An ExpressionSet object. Any transformation and normalization of exprs(eS) should be conducted prior
to use in LMGene.
model
Specifies model to be used. Default is to use all variables from eS without interactions. See details.
level
Significance level
posterior
If TRUE, the posterior FDR-adjusted p-values are used in listing significant genes for each factor. Default
is to use gene-specific FDR-adjusted p-values.
method
Method by which the posterior p-values are calculated. Default is "MLE".
Details
If you have data in a matrix and information about experimental design factors, then you
can use neweS to convert the data into an ExpressionSet object. Please see
neweS for more detail.
The level argument indicates the False Discovery Rate, e.g. level=0.05 means a 5 percent FDR.
The model argument is an optional character string, constructed like the right-hand
side of a formula for lm. It specifies which of the variables in the ExpressionSet will
be used in the model and whether interaction terms will be included. If model=NULL,
it uses all variables from the ExpressionSet without interactions. Be careful of using
interaction terms with factors; this often leads to overfitting, which will yield an error.
See genediff for details of method.
Value
lmres
A list with one component for each factor in model. Each component consists of a character vector with one element
per significant gene. If no genes are significant for a given factor, the component for that factor is set to "No significant genes".
Author(s)
David Rocke and Geun-Cheol Lee
References
Benjamini, Y. and Hochberg, Y. (1995) Controlling the false discovery rate: a practical and powerful
approach to multiple testing, Journal of the Royal Statistical Society, Series B, 57,
289–300.
David M. Rocke (2004) Design and analysis of experiments with high throughput biological assay data,
Seminars in Cell & Developmental Biology, 15, 703–713.