plot_contrast_heatmap: Plot heatmap of local contrast between two views

In saezlab/misty: Multiview Intercellular SpaTial modeling framework

Plot heatmap of local contrast between two views

Description

The heatmap shows the interactions that are present and have importance above a cutoff value in the to.view but but not in the from.view.

Usage

plot_contrast_heatmap(
  misty.results,
  from.view,
  to.view,
  cutoff = 1,
  trim = -Inf,
  trim.measure = c("gain.R2", "multi.R2", "intra.R2", "gain.RMSE", "multi.RMSE",
    "intra.RMSE")
)

Arguments

misty.results	a results list generated by collect_results().
from.view, to.view	abbreviated name of the view.
cutoff	importance threshold. Importances below this value will be colored white in the heatmap and considered as not relevant.
trim	display targets with performance value above (if R2 or gain) or below (otherwise) this value only.
trim.measure	the measure used for trimming.

Value

The misty.results list (invisibly).

See Also

collect_results() to generate a results list from raw results.

Other plotting functions: plot_contrast_results(), plot_improvement_stats(), plot_interaction_communities(), plot_interaction_heatmap(), plot_view_contributions()

Examples

all.samples <- list.dirs("results", recursive = FALSE)

misty.results <- collect_results(all.samples)

misty.results %>%
  plot_contrast_heatmap("intra", "para.10")

misty.results %>%
  plot_contrast_heatmap("intra", "para.10", cutoff = 0.5)

saezlab/misty documentation built on March 25, 2024, 4:11 p.m.