ISA.iterate: Perform the Iterative Signature Algorithm
In eisa: Expression data analysis via the Iterative Signature Algorithm

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

ISAIterate performs the ISA on an ExpressionSet object, from the given input seeds.

1 2	ISAIterate(data, feature.seeds, sample.seeds, thr.feat, thr.samp = thr.feat, ...)

`data`	An `ExpressionSet` or `ISAExpressionSet` object. If an `ExpressionSet` object is supplied, then it is normalised by calling `ISANormalize` on it.
`feature.seeds`	A matrix of feature seeds. The number of rows should match the number of features in the `ExpressionSet`, each column is a seed. Either this, or the `sample.seeds` argument must be given.
`sample.seeds`	A matrix of sample seeds. The number of rows should match the number of samples in the `ExpressionSet`, each column in a seed. Either this, or the `feature.seeds` argument must be given.
`thr.feat`	Numeric scalar or vector giving the threshold parameter for the features. Higher values indicate a more stringent threshold and the result biclusters will contain less features on average. The threshold is measured by the number of standard deviations from the mean, over the values of the feature vector. If it is a vector, then it must contain an entry for each seed.
`thr.samp`	Numeric scalar or vector giving the threshold parameter for the columns. The analogue of `thr.feat`.
`...`	Additional arguments, these are passed to the `isa.iterate` function in the `isa2` package. See also details below.

Performs the ISA from the given seeds. It is allowed to specify both type of seeds, then a half-iteration is performed on the sample.seeds and they are appended to the feature.seeds.

The isa.iterate function of the isa2 package is called to do all the work, this has the following extra parameters: direction, convergence, cor.limit, eps, corx, oscillation, maxiter. Please see the isa.iterate manual for details about them.

An ISAModules object.

Gabor Csardi csardi.gabor@gmail.com

Bergmann S, Ihmels J, Barkai N: Iterative signature algorithm for the analysis of large-scale gene expression data Phys Rev E Stat Nonlin Soft Matter Phys. 2003 Mar;67(3 Pt 1):031902. Epub 2003 Mar 11.

The ISA function for an easier interface with parameters.

library(ALL)
data(ALL)

# Only use a small sample, to make this example finish faster
ALL.normed <- ISANormalize(ALL)[sample(1:nrow(ALL), 1000),]

# Generate seeds and do ISA
seeds <- generate.seeds(nrow(ALL.normed), count=100)
modules <- ISAIterate(ALL.normed, seeds, thr.feat=3, thr.samp=2)
modules