CogapsParams-class: CogapsParams

Description Slots

Description

Encapsulates all parameters for the CoGAPS algorithm

Slots

nPatterns

number of patterns CoGAPS will learn

nIterations

number of iterations for each phase of the algorithm

alphaA

sparsity parameter for feature matrix

alphaP

sparsity parameter for sample matrix

maxGibbsMassA

atomic mass restriction for feature matrix

maxGibbsMassP

atomic mass restriction for sample matrix

seed

random number generator seed

sparseOptimization

speeds up performance with sparse data (roughly >80 default uncertainty

distributed

either "genome-wide" or "single-cell" indicating which distributed algorithm should be used

nSets

[distributed parameter] number of sets to break data into

cut

[distributed parameter] number of branches at which to cut dendrogram used in pattern matching

minNS

[distributed parameter] minimum of individual set contributions a cluster must contain

maxNS

[distributed parameter] maximum of individual set contributions a cluster can contain

explicitSets

[distributed parameter] specify subsets by index or name

samplingAnnotation

[distributed parameter] specify categories along the rows (cols) to use for weighted sampling

samplingWeight

[distributed parameter] weights associated with samplingAnnotation

subsetIndices

set of indices to use from the data

subsetDim

which dimension (1=rows, 2=cols) to subset

geneNames

vector of names of genes in data

sampleNames

vector of names of samples in data

fixedPatterns

fix either 'A' or 'P' matrix to these values, in the context of distributed CoGAPS (GWCoGAPS/scCoGAPS), the first phase is skipped and fixedPatterns is used for all sets - allowing manual pattern matching, as well as fixed runs of standard CoGAPS

whichMatrixFixed

either 'A' or 'P', indicating which matrix is fixed

takePumpSamples

whether or not to take PUMP samples


CoGAPS documentation built on Nov. 8, 2020, 5:02 p.m.