plot_batch_using_freq_msi: Plot the distribution of the features across batches in two...

In prybakowska/CytoQP: Cytometry data quality control and cleaninig

Plot the distribution of the features across batches in two dimensional space

Description

Uses ggplot draw the distribution of the samples across batches

Usage

plot_batch_using_freq_msi(
  df_plot,
  fill = NULL,
  shape = NULL,
  color = NULL,
  split_by_normalization = TRUE,
  fill_legend_name = NULL,
  color_legend_name = NULL,
  shape_legend_name = NULL,
  title = NULL,
  manual_colors = NULL
)

Arguments

df_plot	Data frame that contains dim1 and dim2 obtained upon dimensional reduction. This data frame is generated by prepare_data_for_plotting.
fill	As in ggplot2, defines by which variable the points are colored.
shape	As in ggplot2, defines by which variable the shapes are plotted.
color	As in ggplot2, defines by which variable the borderd of the points are colored.
fill_legend_name	Character, specifies the name of the legend for fill.
color_legend_name	Character, specifies the name of the legend for fill.
shape_legend_name	Character, specifies the name of the legend for fill.
title	Character, the title of the plot.
manual_colors	Character, vector of the colors to be used, the number of colors needs to be equal to the length of batch_pattern.
split_by_batch	Logical, if TRUE (defult) the plots are split (facet_wrap) by normalization.

Value

ggplot

Examples

# Define files before normalization
gate_dir <- file.path(dir, "Gated")
files_before_norm <- list.files(gate_dir,
                                pattern = ".fcs",
                                full.names = T)

# Define files after normalization
norm_dir <- file.path(dir, "CytoNormed")
files_after_norm <- list.files(norm_dir,
                               pattern = ".fcs",
                               full.names = T)

# files needs to be in the same order, check and order if needed
test_match_order(x = basename(gsub("Norm_","",files_after_norm)),
                 basename(files_before_norm))

batch_labels <- stringr::str_match(basename(files_before_norm), "day[0-9]*")[,1]

mx <- extract_pctgs_msi_per_flowsom(files_after_norm = files_after_norm,
                                    files_before_norm = files_before_norm,
                                    nCells = 50000,
                                    phenotyping_markers = c("CD", "HLA", "IgD"),
                                    functional_markers = c("MIP", "MCP", "IL",
                                                           "IFNa", "TNF", "TGF",
                                                           "Gr"),
                                    xdim = 10,
                                    ydim = 10,
                                    n_metaclusters = 35,
                                    out_dir = norm_dir,
                                    arcsine_transform = TRUE,
                                    save_matrix = TRUE,
                                    seed = 343)
# create the list to store the plots
 plots <- list()
 for (name in names(mx[[1]])){
 df_plot <- prepare_data_for_plotting(frequency_msi_list = mx,
                                       matrix_type = name,
                                      n_neighbours = 11, seed = 1)


 batch <- stringr::str_match(rownames(df_plot), "day[0-9]*")[,1]
 samples_id <- ifelse(grepl("p1", rownames(df_plot)),"p1",
                      ifelse(grepl("p2", rownames(df_plot)), "p2", "ref"))
 stimulation <- stringr::str_match(rownames(df_plot), "UNS|RSQ|IMQ|LPS|CPG")[,1]

 plots[[name]] <- plot_batch_using_freq_msi(df_plot = df_plot, fill = batch,
                                            shape = samples_id, color = batch,
                                            split_by_normalization = TRUE, title = name)

}

gg_a <- grid_arrange_common_legend(plot_lists = plots, nrow = 2, ncol = 2,
                                  position = "right")

ggplot2::ggsave(filename ="batch_effect_frequency_MSI.png",
               device = "png",
              path = norm_dir,
               plot = gg_a,
               units = "cm",
               width = 22,
               height = 14, dpi = 300)

prybakowska/CytoQP documentation built on June 28, 2022, 12:36 a.m.