Visualize Subtype Prediction Scores in A Violin-style plot

Visualize subtype prediction score for a set subtype in a violin plot.

Usage

plot_subscore_violin(
  these_predictions,
  this_subtype,
  out_path = NULL,
  out_format = "png",
  plot_width = 4,
  plot_height = 4,
  plot_adjust = 2,
  plot_scale = "width",
  plot_trim = FALSE,
  return_data = FALSE
)

Arguments

these_predictions: Required parameter, should be the output from classify_samples().
this_subtype: Required parameter. Should be one of the set subtype classes from the LundTax nomenclature.
out_path: Optional, set path to export plot.
out_format: Required parameter if out_path is specified. Can be "png" (default) or "pdf". The user can further specify the dimensions of the returned plot with plot_width and plot_height.
plot_width: This parameter controls the width in inches. Default is 4 (1200 pixels at 300 PPI).
plot_height: This parameter controls the height in inches. Default is 4 (1200 pixels at 300 PPI).
plot_adjust: A multiplicate bandwidth adjustment. This makes it possible to adjust the bandwidth while still using the a bandwidth estimator. For example, adjust = 1/2 means use half of the default bandwidth.
plot_scale: if "area" (default), all violins have the same area (before trimming the tails). If "count", areas are scaled proportionally to the number of observations. If "width", all violins have the same maximum width.
plot_trim: If TRUE (default), trim the tails of the violins to the range of the data. If FALSE, don't trim the tails.
return_data: Set to TRUE to return tidy data used by the plotting function. Default is FALSE.

Value

Nothing.

Details

Take the output from classify_samples and return a violin plot where each violin represent the distribution of the, for that class, subtype prediction score. Set the subtype of desire with this_subtype. The subtype can be one of the subtypes included in the LundTax subtype classification nomenclature. Parameters starting with the plot prefix are available for the user to gain more control of the returned plot. The user can also return the wrangled data used in the plot by setting return_data = TRUE.

Examples

#run predictor
sjodahl_classes = classify_samples(this_data = sjodahl_2017, 
                                   log_transform = FALSE, 
                                   adjust = TRUE, 
                                   impute = TRUE, 
                                   include_data = TRUE, 
                                   verbose = FALSE)
                                  
#plot GU
plot_subscore_violin(these_predictions = sjodahl_classes, 
                     this_subtype = "GU", 
                     plot_adjust = 2,
                     plot_trim = FALSE)
#> Warning: Arguments in `...` must be used.
#> ✖ Problematic argument:
#> • show.legend = FALSE
#> ℹ Did you misspell an argument name?
#> Warning: Removed 344 rows containing missing values or values outside the scale range
#> (`geom_violin()`).



#plot UroA
plot_subscore_violin(these_predictions = sjodahl_classes, 
                     this_subtype = "UroA", 
                     plot_adjust = 3,
                     plot_scale = "width",
                     plot_trim = TRUE, return_data = FALSE)
#> Warning: Arguments in `...` must be used.
#> ✖ Problematic argument:
#> • show.legend = FALSE
#> ℹ Did you misspell an argument name?


#return data
plot_data = plot_subscore_violin(these_predictions = sjodahl_classes, 
                                 this_subtype = "UroA", 
                                 return_data = TRUE)
#> No plot generated, returning tidy data instead...

#view data                                  
head(plot_data)
#>   sample_id subtype  value
#> 1     1.CEL    UroA 0.9350
#> 2     4.CEL    UroA 0.9334
#> 3    15.CEL    UroA 0.9868
#> 4    28.CEL    UroA 0.9838
#> 5    37.CEL    UroA 0.9530
#> 6    45.CEL    UroA 0.9996