predictClasses-ConsensusMetaclusteringModel-ANY-method: Compute the Optimal Clustering Solution for a Trained...

In bhklab/PDATK: Pancreatic Ductal Adenocarcinoma Tool-Kit

Description

Compute the optimal clustering solution out of possibilities generated with trainModel. Assigns the cluster labels to the MultiAssayExperiment object.

Usage

## S4 method for signature 'ConsensusMetaclusteringModel,ANY'
predictClasses(object, ..., optimal_k_function = optimalKMinimizeAmbiguity)

Arguments

object	A MutliAssayExperiment object
...	Fall through arguments to optimal_k_function. For the default optimal_k_function, you can specify subinterval argument which defines the interval of the ECDF to minimize ambiguity over. Defaults to c(0.1, 0.9) if not specified. See ?optimalKMinimizeAmbiguity for more details on the subinterval parameter.
optimal_k_function	A function which accepts as its input models(object) of a trained ConsensusMetaclusteringModel object, and returns a vector of optimal K values, one for each assay in rawdata(object). The default method is optimalKMinimizeAmbiguity, see ?optimalKMinimizeAmbiguity for more details. Please note this argument must be named or it will not work.

Value

A object ConsensusMetaclusteringModel, with class predictions assigned to the colData of trianData

bhklab/PDATK documentation built on Dec. 27, 2021, 7:46 a.m.