GSEA Plot

This function generates various types of plots for Gene Set Enrichment Analysis (GSEA) results.

Usage

GSEAPlot(
  srt,
  db = "GO_BP",
  group.by = NULL,
  test.use = "wilcox",
  res = NULL,
  plot_type = c("line", "bar", "network", "enrichmap", "wordcloud", "comparison"),
  group_use = NULL,
  id_use = NULL,
  pvalueCutoff = NULL,
  padjustCutoff = 0.05,
  topTerm = ifelse(plot_type == "enrichmap", 100, 6),
  direction = c("pos", "neg", "both"),
  compare_only_sig = FALSE,
  topWord = 100,
  word_type = c("term", "feature"),
  word_size = c(2, 8),
  words_excluded = NULL,
  line_width = 1.5,
  line_alpha = 1,
  line_color = "#6BB82D",
  n_coregene = 10,
  sample_coregene = FALSE,
  features_label = NULL,
  label.fg = "black",
  label.bg = "white",
  label.bg.r = 0.1,
  label.size = 4,
  network_layout = "fr",
  network_labelsize = 5,
  network_blendmode = "blend",
  network_layoutadjust = TRUE,
  network_adjscale = 60,
  network_adjiter = 100,
  enrichmap_layout = "fr",
  enrichmap_cluster = "fast_greedy",
  enrichmap_label = c("term", "feature"),
  enrichmap_labelsize = 5,
  enrlichmap_nlabel = 4,
  enrichmap_show_keyword = FALSE,
  enrichmap_mark = c("ellipse", "hull"),
  enrichmap_expand = c(0.5, 0.5),
  character_width = 50,
  lineheight = 0.7,
  palette = "Spectral",
  palcolor = NULL,
  aspect.ratio = NULL,
  legend.position = "right",
  legend.direction = "vertical",
  theme_use = "theme_scop",
  theme_args = list(),
  combine = TRUE,
  nrow = NULL,
  ncol = NULL,
  byrow = TRUE,
  seed = 11
)

Arguments

srt

A Seurat object containing the results of RunDEtest and RunGSEA. If specified, GSEA results will be extracted from the Seurat object automatically. If not specified, the res arguments must be provided.

db

The database to use for enrichment plot. Default is "GO_BP".

group.by

A character vector specifying the grouping variable in the Seurat object. This argument is only used if srt is specified.

test.use

A character vector specifying the test to be used in differential expression analysis. This argument is only used if srt is specified.

res

Enrichment results generated by RunGSEA function. If provided, 'srt', 'test.use' and 'group.by' are ignored.

plot_type

The type of plot to generate. Options are: "line", "comparison", "bar", "network", "enrichmap", "wordcloud". Default is "line".

group_use

The group(s) to be used for enrichment plot. Default is NULL.

id_use

List of IDs to be used to display specific terms in the enrichment plot. Default value is NULL.

pvalueCutoff

The p-value cutoff. Only work when padjustCutoff is NULL. Default is NULL.

padjustCutoff

The p-adjusted cutoff. Default is 0.05.

topTerm

The number of top terms to display. Default is 6, or 100 if plot_type is "enrichmap".

direction

The direction of enrichment to include in the plot. Must be one of "pos", "neg", or "both". Default is "both".

compare_only_sig

Whether to compare only significant terms. Default is FALSE.

topWord

The number of top words to display for wordcloud. Default is 100.

word_type

The type of words to display in wordcloud. Options are "term" and "feature". Default is "term".

word_size

The size range for words in wordcloud. Default is c(2, 8).

words_excluded

Words to be excluded from the wordcloud. Default is NULL, which means that the built-in words (words_excluded) will be used.

line_width

The linewidth for the line plot.

line_alpha

The alpha value for the line plot.

line_color

The color for the line plot.

n_coregene

The number of core genes to label in the line plot.

sample_coregene

Whether to randomly sample core genes for labeling in the line plot.

features_label

A character vector of feature names to include as labels in the line plot.

label.fg

The color of the labels.

label.bg

The background color of the labels.

label.bg.r

The radius of the rounding of the label's background.

label.size

The size of the labels.

network_layout

The layout algorithm to use for network plot. Options are "fr", "kk", "random", "circle", "tree", "grid", or other algorithm from igraph package. Default is "fr".

network_labelsize

The label size for network plot. Default is 5.

network_blendmode

The blend mode for network plot. Default is "blend".

network_layoutadjust

Whether to adjust the layout of the network plot to avoid overlapping words. Default is TRUE.

network_adjscale

The scale for adjusting network plot layout. Default is 60.

network_adjiter

The number of iterations for adjusting network plot layout. Default is 100.

enrichmap_layout

The layout algorithm to use for enrichmap plot. Options are "fr", "kk", "random", "circle", "tree", "grid", or other algorithm from igraph package. Default is "fr".

enrichmap_cluster

The clustering algorithm to use for enrichmap plot. Options are "walktrap", "fast_greedy", or other algorithm from igraph package. Default is "fast_greedy".

enrichmap_label

The label type for enrichmap plot. Options are "term" and "feature". Default is "term".

enrichmap_labelsize

The label size for enrichmap plot. Default is 5.

enrlichmap_nlabel

The number of labels to display for each cluster in enrichmap plot. Default is 4.

enrichmap_show_keyword

Whether to show the keyword of terms or features in enrichmap plot. Default is FALSE.

enrichmap_mark

The mark shape for enrichmap plot. Options are "ellipse" and "hull". Default is "ellipse".

enrichmap_expand

The expansion factor for enrichmap plot. Default is c(0.5, 0.5).

character_width

The maximum width of character of descriptions. Default is 50.

lineheight

The line height for y-axis labels. Default is 0.7.

palette

Color palette name. Available palettes can be found in thisplot::show_palettes. Default is "Spectral".

palcolor

Custom colors used to create a color palette. Default is NULL.

aspect.ratio

Aspect ratio of the panel. Default is 1.

legend.position

The position of legends, one of "none", "left", "right", "bottom", "top". Default is "right".

legend.direction

The direction of the legend in the plot. Can be one of "vertical" or "horizontal".

theme_use

Theme used. Can be a character string or a theme function. Default is "theme_scop".

theme_args

Other arguments passed to the theme_use. Default is list().

combine

Combine plots into a single patchwork object. If FALSE, return a list of ggplot objects.

nrow

Number of rows in the combined plot. Default is NULL, which means determined automatically based on the number of plots.

ncol

Number of columns in the combined plot. Default is NULL, which means determined automatically based on the number of plots.

byrow

Whether to arrange the plots by row in the combined plot. Default is TRUE.

seed

Random seed for reproducibility. Default is 11.

See also

RunGSEA

Examples

data(pancreas_sub)
pancreas_sub <- standard_scop(pancreas_sub)
#> ℹ [2026-05-14 06:12:39] Start standard processing workflow...
#> ℹ [2026-05-14 06:12:40] Checking a list of <Seurat>...
#> ! [2026-05-14 06:12:40] Data 1/1 of the `srt_list` is "unknown"
#> ℹ [2026-05-14 06:12:40] Perform `NormalizeData()` with `normalization.method = 'LogNormalize'` on 1/1 of `srt_list`...
#> ℹ [2026-05-14 06:12:42] Perform `Seurat::FindVariableFeatures()` on 1/1 of `srt_list`...
#> ℹ [2026-05-14 06:12:42] Use the separate HVF from `srt_list`
#> ℹ [2026-05-14 06:12:42] Number of available HVF: 2000
#> ℹ [2026-05-14 06:12:43] Finished check
#> ℹ [2026-05-14 06:12:43] Perform `Seurat::ScaleData()`
#> ℹ [2026-05-14 06:12:43] Perform pca linear dimension reduction
#> ℹ [2026-05-14 06:12:43] Use stored estimated dimensions 1:20 for Standardpca
#> ℹ [2026-05-14 06:12:44] Perform `Seurat::FindClusters()` with `cluster_algorithm = 'louvain'` and `cluster_resolution = 0.6`
#> ℹ [2026-05-14 06:12:44] Reorder clusters...
#> ℹ [2026-05-14 06:12:44] Skip `log1p()` because `layer = data` is not "counts"
#> ℹ [2026-05-14 06:12:44] Perform umap nonlinear dimension reduction
#> ℹ [2026-05-14 06:12:44] Perform umap nonlinear dimension reduction using Standardpca (1:20)
#> ℹ [2026-05-14 06:12:49] Perform umap nonlinear dimension reduction using Standardpca (1:20)
#> ✔ [2026-05-14 06:12:54] Standard processing workflow completed
pancreas_sub <- RunDEtest(
  pancreas_sub,
  group.by = "CellType"
)
#> ℹ [2026-05-14 06:12:54] Data type is log-normalized
#> ℹ [2026-05-14 06:12:54] Start differential expression test
#> ℹ [2026-05-14 06:12:54] Find all markers(wilcox) among [1] 5 groups...
#> ℹ [2026-05-14 06:12:54] Using 1 core
#> ⠙ [2026-05-14 06:12:54] Running for Ductal [1/5] ■■          20% | ETA:  1s
#> ✔ [2026-05-14 06:12:54] Completed 5 tasks in 951ms
#> 
#> ℹ [2026-05-14 06:12:54] Building results
#> ✔ [2026-05-14 06:12:55] Differential expression test completed
pancreas_sub <- RunGSEA(
  pancreas_sub,
  group.by = "CellType",
  db = "GO_BP",
  species = "Mus_musculus"
)
#> ℹ [2026-05-14 06:12:55] Start GSEA analysis
#> ! [2026-05-14 06:12:55] All values in the `geneScore` are greater than zero. Set scoreType = 'pos'
#> ℹ [2026-05-14 06:12:55] Species: "Mus_musculus"
#> ℹ [2026-05-14 06:12:55] Loading cached: GO_BP version: 3.23.0 nterm:14957 created: 2026-05-14 06:04:39
#> ℹ [2026-05-14 06:12:56] Using 1 core
#> Registered S3 methods overwritten by 'callr':
#>   method                    from
#>   format.callr_status_error     
#>   print.callr_status_error      
#> Registered S3 method overwritten by 'ggtree':
#>   method         from     
#>   fortify.igraph ggnetwork
#> ⠙ [2026-05-14 06:12:56] Running for 1 [1/5] ■■          20% | ETA: 33s
#> ⠹ [2026-05-14 06:12:56] Running for 2 [2/5] ■■■■        40% | ETA: 17s
#> ⠸ [2026-05-14 06:12:56] Running for 3 [3/5] ■■■■■■      60% | ETA: 11s
#> ⠼ [2026-05-14 06:12:56] Running for 4 [4/5] ■■■■■■■■    80% | ETA:  5s
#> ✔ [2026-05-14 06:12:56] Completed 5 tasks in 22.5s
#> 
#> ℹ [2026-05-14 06:12:56] Building results
#> ✔ [2026-05-14 06:13:19] GSEA analysis done
GSEAPlot(
  pancreas_sub,
  db = "GO_BP",
  group.by = "CellType",
  group_use = "Ductal"
)


p1 <- GSEAPlot(
  pancreas_sub,
  db = "GO_BP",
  group.by = "CellType",
  group_use = "Ductal",
  id_use = "GO:0006412"
)
#> Error in `.rowNamesDF<-`(x, value = value): missing values in 'row.names' are not allowed
p1
#> Error: object 'p1' not found

thisplot::panel_fix_overall(p1, height = 6)
#> Error: object 'p1' not found

GSEAPlot(
  pancreas_sub,
  db = "GO_BP",
  group.by = "CellType",
  topTerm = 3,
  plot_type = "comparison"
)
#> Warning: No shared levels found between `names(values)` of the manual scale and the
#> data's alpha values.
#> Warning: Removed 9786 rows containing missing values or values outside the scale range
#> (`geom_point()`).

GSEAPlot(
  pancreas_sub,
  db = "GO_BP",
  group.by = "CellType",
  topTerm = 3,
  plot_type = "comparison",
  direction = "pos"
)
#> Warning: No shared levels found between `names(values)` of the manual scale and the
#> data's alpha values.
#> Warning: Removed 9786 rows containing missing values or values outside the scale range
#> (`geom_point()`).

GSEAPlot(
  pancreas_sub,
  db = "GO_BP",
  group.by = "CellType",
  topTerm = 3,
  plot_type = "comparison",
  compare_only_sig = TRUE
)
#> Warning: No shared levels found between `names(values)` of the manual scale and the
#> data's alpha values.
#> Warning: Removed 9786 rows containing missing values or values outside the scale range
#> (`geom_point()`).

GSEAPlot(
  pancreas_sub,
  db = "GO_BP",
  group.by = "CellType",
  plot_type = "bar"
)
#> Error in `.rowNamesDF<-`(x, value = value): missing values in 'row.names' are not allowed
GSEAPlot(
  pancreas_sub,
  db = "GO_BP",
  group.by = "CellType",
  plot_type = "bar",
  direction = "both"
)
#> Error in `.rowNamesDF<-`(x, value = value): missing values in 'row.names' are not allowed
GSEAPlot(
  pancreas_sub,
  db = "GO_BP",
  group.by = "CellType",
  group_use = "Ductal",
  plot_type = "bar",
  topTerm = 20,
  direction = "both",
  palcolor = c("red3", "steelblue")
)


GSEAPlot(
  pancreas_sub,
  db = "GO_BP",
  group.by = "CellType",
  group_use = "Ductal",
  plot_type = "network"
)
#> ✔ [2026-05-14 06:13:22] shadowtext installed successfully

GSEAPlot(
  pancreas_sub,
  db = "GO_BP",
  group.by = "CellType",
  group_use = "Ductal",
  plot_type = "enrichmap"
)

GSEAPlot(
  pancreas_sub,
  db = "GO_BP",
  group.by = "CellType",
  group_use = "Ductal",
  plot_type = "wordcloud"
)

GSEAPlot(
  pancreas_sub,
  db = "GO_BP",
  group.by = "CellType",
  group_use = "Ductal",
  plot_type = "wordcloud",
  word_type = "feature"
)