plotTerms: Plot relevance for all terms

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

Description

Plot relevance for all terms

Usage

plotTerms(object, terms = NULL, order_terms = TRUE, mad_filter = 0.2,
  annotated = TRUE, unannotated_dense = TRUE, unannotated_sparse = FALSE)

Arguments

object	an object of class Rcpp_SlalomModel
terms	integer or character vector, providing either indices for desired terms (if an integer) or the term names (if character); default is NULL, in which case all terms are plotted.
order_terms	logical(1), should factors be ordered by relevance ( TRUE, default), or in the order the come
mad_filter	numeric(1), filter factors by this mean absolute deviation to exclude outliers. For large datasets this can be set close to 0; default is 0.2.
annotated	logical(1), should annotated factors be plotted? Default is TRUE
unannotated_dense	logical(1), should dense unannotated factors be plotted? Default is TRUE
unannotated_sparse	logical(1), should sparse unannotated factors be plotted? Default is TRUE

Value

a ggplot plot object

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)
plotTerms(model)

slalom documentation built on Nov. 8, 2020, 5:24 p.m.