Generate box plots or violin plots to show how the errors are distributed

Source: R/evalMetrics.R

Generate violin plots or box plots to show how the errors are distributed by proportion bins of 0.1. Errors can be displayed all mixed or split by cell type (CellType) or number of cell types present in the samples (nCellTypes). See the facet.by argument and examples for more details.

distErrorPlot(
  object,
  error,
  colors,
  x.by = "pBin",
  facet.by = NULL,
  color.by = "nCellTypes",
  filter.sc = TRUE,
  error.label = FALSE,
  pos.x.label = 4.6,
  pos.y.label = NULL,
  size.point = 0.1,
  alpha.point = 1,
  type = "violinplot",
  ylimit = NULL,
  nrow = NULL,
  ncol = NULL,
  title = NULL,
  theme = NULL,
  ...
)

Arguments

object

DigitalDLSorter object with trained.model slot containing metrics in the test.deconv.metrics slot of a DigitalDLSorterDNN object.

error

The error to be represented. Available errors are absolute error ('AbsErr'), proportional absolute error ('ppAbsErr'), squared error ('SqrErr') and proportional squared error ('ppSqrErr').

colors

Vector of colors to be used. Only vectors with a number of colors equal to or greater than the levels of color.by will be accepted. By default, a custom color list is used.

x.by

Variable used for the X-axis. When facet.by is not NULL, the best choice is pBin (probability bins). The options are nCellTypes (number of different cell types), CellType (cell type) and pBin.

facet.by

Variable used to display data in different panels. If NULL, the plot is not split into different panels. Options are nCellTypes (number of different cell types) and CellType (cell type).

color.by

Variable used to color the data. Options are nCellTypes and CellType.

filter.sc

Boolean indicating whether single-cell profiles are filtered out and only errors associated with pseudo-bulk samples are displayed (TRUE by default).

error.label

Boolean indicating whether to display the average error as a plot annotation (FALSE by default).

pos.x.label

X-axis position of error annotations.

pos.y.label

Y-axis position of error annotations.

size.point

Size of points (0.1 by default).

alpha.point

Alpha of points (0.1 by default).

type

Type of plot: 'boxplot' or 'violinplot'. The latter by default.

ylimit

Upper limit in Y-axis if it is required (NULL by default).

nrow

Number of rows if facet.by is not NULL.

ncol

Number of columns if facet.by is not NULL.

title

Title of the plot.

theme

ggplot2 theme.

...

Additional arguments for the facet_wrap function from ggplot2 if facet.by is not NULL.

Value

A ggplot object with the representation of the desired errors.

Examples

if (FALSE) {
set.seed(123)
sce <- SingleCellExperiment::SingleCellExperiment(
  assays = list(
    counts = matrix(
      rpois(30, lambda = 5), nrow = 15, ncol = 20,
      dimnames = list(paste0("Gene", seq(15)), paste0("RHC", seq(20)))
    )
  ),
  colData = data.frame(
    Cell_ID = paste0("RHC", seq(20)),
    Cell_Type = sample(x = paste0("CellType", seq(6)), size = 20,
                       replace = TRUE)
  ),
  rowData = data.frame(
    Gene_ID = paste0("Gene", seq(15))
  )
)
DDLS <- createDDLSobject(
  sc.data = sce,
  sc.cell.ID.column = "Cell_ID",
  sc.gene.ID.column = "Gene_ID",
  sc.filt.genes.cluster = FALSE, 
  sc.log.FC = FALSE
)
probMatrixValid <- data.frame(
  Cell_Type = paste0("CellType", seq(6)),
  from = c(1, 1, 1, 15, 15, 30),
  to = c(15, 15, 30, 50, 50, 70)
)
DDLS <- generateBulkCellMatrix(
  object = DDLS,
  cell.ID.column = "Cell_ID",
  cell.type.column = "Cell_Type",
  prob.design = probMatrixValid,
  num.bulk.samples = 50,
  verbose = TRUE
)
# training of DDLS model
tensorflow::tf$compat$v1$disable_eager_execution()
DDLS <- trainDDLSModel(
  object = DDLS,
  on.the.fly = TRUE,
  batch.size = 15,
  num.epochs = 5
)
# evaluation using test data
DDLS <- calculateEvalMetrics(
  object = DDLS
)
# representation, for more examples, see the vignettes
distErrorPlot(
  object = DDLS,
  error = "AbsErr",
  facet.by = "CellType",
  color.by = "nCellTypes",
  error.label = TRUE
)
distErrorPlot(
  object = DDLS,
  error = "AbsErr",
  x.by = "CellType",
  facet.by = NULL,
  filter.sc = FALSE,
  color.by = "CellType",
  error.label = TRUE
)
}