optimalKMinimizeAmbiguity: Predict optimal K values by minimizing the difference between...
In bhklab/PDATK: Pancreatic Ductal Adenocarcinoma Tool-Kit

Predict optimal K values by minimizing the difference between the ECDF of clustering consensus at two points in a subinterval.

1	optimalKMinimizeAmbiguity(assayClusters, subinterval = c(0.1, 0.9))

assayClusters

A SimpleList of clustering results from a ConsensusMetaclusteringModel, as returned by models(object) where object is a trained ConsensusMetaclusteringModel object.

subinterval

A numeric vector of two float values, the first being the lower and second being the upper limit of the subinteral to compare cluster ambiguity over. Default is c(0.1, 0.9), i.e. comparing the 10th and 90th percentile of cluster consensus to calculate the ambiguity of a given clustering solution. This is the value used to selected the optimal K value from the potential solutions for each assay in the training data.

A numeric vector the same length as assayClusters, with an optimal K prediction for each assay in the rawdata slot of the trained ConsensusMetaclusteringModel object which assayClusters came from.

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