Plot a summary heatmap of the combined differential expression and classification models results

plot_biomarkers_summary_heatmap plots a summary heatmap of the combined differential expression and classification models results. The heatmap shows the log2 fold change and adjusted p-value of the differential expression results, and the scaled importance and sign of the classification models results. The heatmap is ordered and the selected assays are based on the specified control group.

Usage

plot_biomarkers_summary_heatmap(
  de_results,
  ml_results,
  order_by = NULL,
  pval_lim = 0.05,
  logfc_lim = 0
)

Arguments

de_results

A list of differential expression results.

ml_results

A list of classification models results.

order_by

The control group to order the heatmap.

pval_lim

The p-value limit to filter the differential expression results of the order_by group.

logfc_lim

The log2 fold change limit to filter the differential expression results of the order_by group.

Value

The summary heatmap of the combined differential expression and classification models results.

Details

It is very important the de_results and ml_results are in the same order and in the right format (see examples).

Examples

# Prepare differential expression results
de_results_amlbrc <- do_limma(example_data,
                              example_metadata,
                              case = "AML",
                              control = c("BRC"),
                              wide = FALSE,
                              only_female = "BRC")
#> Comparing AML with BRC.
#> Warning: 486 rows were removed because they contain NAs in Disease or Sex, Age!

de_results_amlcll <- do_limma(example_data,
                              example_metadata,
                              case = "AML",
                              control = c("CLL"),
                              wide = FALSE,
                              only_female = "BRC")
#> Comparing AML with CLL.
#> Warning: 488 rows were removed because they contain NAs in Disease or Sex, Age!

de_results_amllungc <- do_limma(example_data,
                                example_metadata,
                                case = "AML",
                                control = c("LUNGC"),
                                wide = FALSE,
                                only_female = "BRC")
#> Comparing AML with LUNGC.
#> Warning: 486 rows were removed because they contain NAs in Disease or Sex, Age!

# Combine the results
res_de <- list("BRC" = de_results_amlbrc,
               "CLL" = de_results_amlcll,
               "LUNGC" = de_results_amllungc)

res_amlbrc <- do_rreg(example_data,
                      example_metadata,
                      case = "AML",
                      type = 'elnet',
                      control = c("BRC"),
                      wide = FALSE,
                      only_female = "BRC",
                      cv_sets = 2,
                      grid_size = 1,
                      ncores = 1)
#> Joining with `by = join_by(DAid)`
#> Sets and groups are ready. Model fitting is starting...
#> Classification model for AML as case is starting...
#> Warning: Due to the small size of the grid, a Latin hypercube design will be used.

res_amlcll <- do_rreg(example_data,
                      example_metadata,
                      case = "AML",
                      type = 'elnet',
                      control = c("CLL"),
                      wide = FALSE,
                      only_female = "BRC",
                      cv_sets = 2,
                      grid_size = 1,
                      ncores = 1)
#> Joining with `by = join_by(DAid)`
#> Sets and groups are ready. Model fitting is starting...
#> Classification model for AML as case is starting...
#> Warning: Due to the small size of the grid, a Latin hypercube design will be used.

res_amllungc <- do_rreg(example_data,
                        example_metadata,
                        case = "AML",
                        control = c("LUNGC"),
                        type = 'elnet',
                        wide = FALSE,
                        only_female = "BRC",
                        cv_sets = 2,
                        grid_size = 1,
                        ncores = 1)
#> Joining with `by = join_by(DAid)`
#> Sets and groups are ready. Model fitting is starting...
#> Classification model for AML as case is starting...
#> Warning: Due to the small size of the grid, a Latin hypercube design will be used.

# Combine the results
res_ml <- list("BRC" = res_amlbrc,
               "CLL" = res_amlcll,
               "LUNGC" = res_amllungc)

# Create the summary heatmap
plot_biomarkers_summary_heatmap(res_de, res_ml, order_by = "BRC")
#> Warning: Removed 22 rows containing missing values or values outside the scale range
#> (`geom_point()`).
#> Warning: Removed 22 rows containing missing values or values outside the scale range
#> (`geom_point()`).