plotRelevance: Plot results of a Slalom model

In PMBio/slalom: Factorial Latent Variable Modeling of Single-Cell RNA-Seq Data

Description

Plot results of a Slalom model

Usage

plotRelevance(object, n_active = 20, mad_filter = 0.4, annotated = TRUE,
  unannotated_dense = FALSE, unannotated_sparse = FALSE)

Arguments

object	an object of class Rcpp_SlalomModel
n_active	number of terms (factors) to be plotted (default is 20)
mad_filter	numeric(1), filter factors by this mean absolute deviation to exclude outliers. For large datasets this can be set to 0
annotated	logical(1), should annotated factors be plotted? Default is TRUE
unannotated_dense	logical(1), should dense unannotated factors be plotted? Default is FALSE
unannotated_sparse	logical(1), should sparse unannotated factors be plotted? Default is FALSE

Value

invisibly returns a list containing the two ggplot objects that make up the plot

Examples

gmtfile <- system.file("extdata", "reactome_subset.gmt", package = "slalom")
genesets <- GSEABase::getGmt(gmtfile)
data("mesc")
model <- newSlalomModel(mesc, genesets, n_hidden = 5, min_genes = 10)
model <- initSlalom(model)
model <- trainSlalom(model, nIterations = 10)
plotRelevance(model)

PMBio/slalom documentation built on May 20, 2019, 1:26 p.m.