MolecularPermutationClassifierGenerics: Virtual functions for MolecularPermutationClassifier...

In pbcmc: Permutation-Based Confidence for Molecular Classification

Description

The following functions establish an organized framework for MolecularPermutationClassifier subclasses data processing. In this context, the later are supposed to be implemented with respective responsibilities. In particular, once the class is created the user has to:

filtrate:

Removes, from the exprs matrix, subjects not required by the classification algorithm.

classify:

Generates subject classification according to subclass implementations (PAM50, etc.).

permute:

Obtains subject classification based on the null correlation distribution by means permutation simulation.

subtype:

Obtaind the new classification using permutation results.

subjectReport:

A friendly report for physician treatment decision support.

databaseReport:

A pdf with all subjectReports, if a database is available.

Usage

filtrate(object, verbose = getOption("verbose", default = FALSE))  

classify(object, ..., verbose = getOption("verbose", default = FALSE)) 

permutate(object, nPerm = 10000L, pCutoff = 0.01, where = "fdr",   
    keep = FALSE, ..., seed = 1234567890, BPPARAM = bpparam(),   
    verbose = getOption("verbose", default = TRUE))   

subtypes(object, pCutoff = 0.01, ..., where = c("fdr", "pvalue")[1])

subjectReport(object, subject)   

databaseReport(object, fileName, ..., verbose = getOption("verbose", default = 
    TRUE))

Arguments

object	MolecularPermutationClassifier child class object
verbose	should the user feedback be displayed? By default value is "verbose" global option parameter, if present, or FALSE otherwise.
...	additional parameters for future implementations.
nPerm	integer with number of permutations. Default: 1e4L.
pCutoff	numeric with p-value or fdr cutoff used, i.e., variable<pCutoff. Default: 0.01.
where	character with significant value used. Default value is "fdr".
keep	should null distribution simulation values be kept?. Default: FALSE
seed	integer to use as random seed. Default: 1234567890.
BPPARAM	an optional BiocParallelParam instance determining the parallel back-end to be used during evaluation, or a list of BiocParallelParam instances, to be applied in sequence for nested calls to bplapply. Default=bpparam().
subject	integer to select the appropriate subject to report.
fileName	character with the name of the pdf report file to save.

Value

A MolecularPermutationClassifier child according to the actual object class.

Author(s)

Cristobal Fresno [e-mail], German A. Gonzalez [e-mail], Andrea S. Llera [e-mail] and Elmer Andres Fernandez [e-mail]

See Also

PAM50 for a complete example.

Other MolecularPermutationClassifier PAM50: PAM50-class, loadBCDataset

Examples

##Using pam50centroids package example data
data(pam50centroids)
pam50centroids
pam50centroids<-filtrate(pam50centroids, verbose=TRUE)   
pam50centroids<-classify(pam50centroids, std="none", verbose=TRUE)  
##Let's run a quick example with 100 permutations. It is recommended at 
##least 10.000   
pam50centroids<-permutate(pam50centroids, nPerm=100, pCutoff=0.01,  
corCutoff=0.1, verbose=TRUE)   
pam50centroids

pbcmc documentation built on Nov. 1, 2018, 2:09 a.m.