In sigven/oncoEnrichR: Cancer-dedicated gene set interpretation

Subcellular compartment localization

The query set is annotated with data from COMPARTMENTS, a weekly updated database of subcellular localization data for human proteins, and results are here presented in two different views:
A subcellular anatogram - acting as a "heatmap" of subcellular structures associated with proteins in the query set
- Compartments are here limited to the key compartments (n = 24) defined within the gganatogram package
- An accompanying legend is also provided - depicting the locations of the various subcellular structures
A subcellular data browser
- Subcellular compartment annotations pr. protein in the query set ("By Gene")
  - Here, a maximum of n = 2,500 annotations are shown (the complete set are listed in the Excel output of oncoEnrichR)
- All unique subcellular compartment annotations and their target members ("By Compartment")
- Subcellular compartment annotations per gene are provided with a confidence score between 3 and 5 - indicating the quality/reliability of a given compartment annotation
  - Minimum confidence score (pr. COMPARTMENTS channel) - user-provided: r onc_enrich_report$config$subcellcomp$minimum_confidence
  - Minimum number of supporting COMPARTMENTS channels pr. annotation - user-provided: r onc_enrich_report$config$subcellcomp$minimum_channels
  - Ignore cytosol as a subcellular location: r !onc_enrich_report$config$subcellcomp$show_cytosol

Subcellular anatogram {.tabset}

Heatmap - query set

In the heatmap below, value refers to the fraction of target genes that are annotated with a particular compartment/subcellular structure

suppressPackageStartupMessages(library(gganatogram))

subcellcomp_geneset_density <- 
  onc_enrich_report[['data']][['subcellcomp']][['anatogram']]

if(onc_enrich_report[['config']][['subcellcomp']][['show_cytosol']] == F){
  subcellcomp_geneset_density <- 
    subcellcomp_geneset_density |>
    dplyr::filter(organ != "cytosol")
}

gganatogram::gganatogram(data = subcellcomp_geneset_density,
                         outline = T,
                         fillOutline = 'lightgray',
                         organism = 'cell',
                         fill = 'value') +
  ggplot2::theme_void() +
  ggplot2::coord_fixed() +
  ggplot2::scale_fill_gradient(low ="#FFEDA0", high = "#800026")

plot_data <- onc_enrich_report[['data']][['subcellcomp']][['anatogram']] |>
  dplyr::arrange(value)
plot_data$organ <- factor(plot_data$organ, levels = plot_data$organ)
plot_data$toDownlight <- "NO"

if(onc_enrich_report[['config']][['subcellcomp']][['show_cytosol']] == F){
  plot_data <- plot_data |>
    dplyr::mutate(toDownlight = dplyr::if_else(
      organ == "cytosol",
      as.character("YES"),
      as.character(toDownlight)
    ))
}

p <- ggplot2::ggplot(
  plot_data, 
  ggplot2::aes( x = organ, y = value, fill = toDownlight) ) +
  ggplot2::geom_bar( stat = "identity" ) +
  ggplot2::ylab("Percent of query gene set") +
  ggplot2::scale_fill_manual(
    values = c("YES"="gray", "NO"="BLACK" ), guide = FALSE ) +
  ggplot2::xlab("") +
  ggplot2::ylim(0,100) +
  ggplot2::theme_classic() +
  ggplot2::coord_flip() +
  ggplot2::theme(
    legend.position = "none",
    axis.text.x = ggplot2::element_text(size = 11, vjust = 0.5),
    legend.text = ggplot2::element_text(face="bold", family = "Helvetica", size = 11),
    axis.text.y = ggplot2::element_text(family = "Helvetica", size = 11),
    axis.title.x = ggplot2::element_text(family = "Helvetica", size = 11),
    axis.title.y = ggplot2::element_text(family = "Helvetica", size = 11)
  )

plotly::ggplotly(p, width = 600, height = 600)

Legend - subcellular structures

suppressPackageStartupMessages(library(gganatogram))
ggpubr::ggarrange(
  plotlist = 
    onc_enrich_report[['config']][['subcellcomp']][['gganatogram_legend']][1:24], 
  ncol = 4, nrow = 6)

Subcellular data browser{.tabset}

By gene

subcell_comp_all <- 
  crosstalk::SharedData$new(onc_enrich_report[['data']][['subcellcomp']][['all']])

crosstalk::bscols(
  list(
    crosstalk::filter_select("target_gene", "Target gene", 
                             subcell_comp_all,~symbol),
    crosstalk::filter_select("supporting_channels", "Supporting channels", 
                             subcell_comp_all, ~supporting_channels)
  ),
  list(
    crosstalk::filter_select("supporting_sources", "Supporting sources", 
                             subcell_comp_all, ~supporting_sources),
    crosstalk::filter_slider("minimum_confidence", 
                             "Minimum confidence level (across channels)", 
                             subcell_comp_all, ~minimum_confidence, step = 1, 
                             min = 3, max = 5)
  )
)

htmltools::br()
DT::datatable(subcell_comp_all, escape = F, 
              extensions=c("Buttons","Responsive"), width = "100%",
              options=list(buttons = c('csv','excel'),dom = 'Bfrtip')
)

By compartment

Genes listed per compartment are calculated using only compartment annotations with a minimum confidence level (pr. channel) of: r onc_enrich_report$config$subcellcomp$minimum_confidence

htmltools::br()
DT::datatable(onc_enrich_report[['data']][['subcellcomp']][['grouped']], 
              escape = F, extensions=c("Buttons","Responsive"), 
              width = "100%",
  options=list(buttons = c('csv','excel'),dom = 'Bfrtip'))

{.unlisted .unnumbered .toc-ignore}

Citation Note : If you use the output of the Subcellular localization module of oncoEnrichR in your research, please cite the following resources and tools: