Nothing
library(testthat)
library(enrichit)
# Define a helper function to compute expected p-values using phyper
expected_pvalue <- function(set_size, overlap, de_total, universe_size) {
# hypergeometric: probability of >= overlap successes
# q = overlap - 1, lower.tail = FALSE
phyper(overlap - 1, set_size, universe_size - set_size, de_total, lower.tail = FALSE)
}
test_that("ORA function returns correct p-values and format", {
# Example data from documentation
de_genes <- c("Gene1", "Gene2", "Gene3", "Gene4", "Gene5")
all_genes <- paste0("Gene", 1:1000)
gs1 <- paste0("Gene", 1:50)
gs2 <- paste0("Gene", 51:150)
gs3 <- paste0("Gene", 151:300)
gene_sets <- list(Pathway1 = gs1, Pathway2 = gs2, Pathway3 = gs3)
result <- ora(gene = de_genes, gene_sets = gene_sets, universe = all_genes)
# Verify columns exist
expected_cols <- c("ID", "GeneRatio", "BgRatio", "RichFactor", "FoldEnrichment", "pvalue", "geneID", "Count")
expect_true(all(expected_cols %in% colnames(result)))
# Manual calculations
manual_p1 <- expected_pvalue(set_size = 50, overlap = 5, de_total = 5, universe_size = 1000)
manual_p2 <- expected_pvalue(set_size = 100, overlap = 0, de_total = 5, universe_size = 1000)
manual_p3 <- expected_pvalue(set_size = 150, overlap = 0, de_total = 5, universe_size = 1000)
# Compare with ORA output (allow tiny numerical tolerance)
expect_equal(result$pvalue[result$ID == "Pathway1"], manual_p1, tolerance = 1e-10)
expect_equal(result$pvalue[result$ID == "Pathway2"], manual_p2, tolerance = 1e-10)
expect_equal(result$pvalue[result$ID == "Pathway3"], manual_p3, tolerance = 1e-10)
# Check content of new columns for Pathway1
p1_res <- result[result$ID == "Pathway1", ]
expect_equal(p1_res$Count, 5)
expect_equal(p1_res$GeneRatio, "5/5")
expect_equal(p1_res$BgRatio, "50/1000")
expect_equal(p1_res$RichFactor, 5/50)
expect_equal(p1_res$FoldEnrichment, (5/5) / (50/1000))
# Check that all expected genes are present in geneID
genes_in_id <- strsplit(p1_res$geneID, "/")[[1]]
expect_true(all(c("Gene1", "Gene2", "Gene3", "Gene4", "Gene5") %in% genes_in_id))
expect_equal(length(genes_in_id), 5)
})
test_that("ora_gson excludes zero-overlap sets from multiple testing correction", {
skip_if_not_installed("gson")
gsid2gene <- data.frame(
gsid = c("set1", "set1", "set2", "set2", "set3", "set3"),
gene = c("Gene1", "Gene2", "Gene2", "Gene3", "Gene4", "Gene5"),
stringsAsFactors = FALSE
)
gsid2name <- data.frame(
gsid = c("set1", "set2", "set3"),
name = c("Set 1", "Set 2", "Set 3"),
stringsAsFactors = FALSE
)
gson_obj <- gson::gson(
gsid2gene = gsid2gene,
gsid2name = gsid2name,
species = "test",
gsname = "test",
version = "test",
accessed_date = as.character(Sys.Date()),
keytype = "UNKNOWN"
)
res <- ora_gson(
gene = c("Gene1", "Gene2"),
pvalueCutoff = 1,
pAdjustMethod = "BH",
universe = c("Gene1", "Gene2", "Gene3", "Gene4", "Gene5"),
minGSSize = 1,
maxGSSize = 10,
qvalueCutoff = 1,
gson = gson_obj
)
expect_s4_class(res, "enrichResult")
expect_equal(res@result$ID, c("set1", "set2"))
expect_true(all(res@result$Count > 0))
raw_p <- c(
expected_pvalue(set_size = 2, overlap = 2, de_total = 2, universe_size = 5),
expected_pvalue(set_size = 2, overlap = 1, de_total = 2, universe_size = 5)
)
expect_equal(res@result$pvalue, raw_p, tolerance = 1e-10)
expect_equal(res@result$p.adjust, p.adjust(raw_p, method = "BH"), tolerance = 1e-10)
})
test_that("weighted ORA runs on a small universe", {
skip_if_not_installed("BiasedUrn")
de_genes <- c("Gene1", "Gene2", "Gene3")
all_genes <- paste0("Gene", 1:30)
gene_sets <- list(
Pathway1 = paste0("Gene", 1:6),
Pathway2 = paste0("Gene", 10:18)
)
weight <- setNames(rep(1, 30), all_genes)
weight[c("Gene1", "Gene2", "Gene3", "Gene4", "Gene5", "Gene6")] <- 3
unweighted <- ora(gene = de_genes, gene_sets = gene_sets, universe = all_genes)
weighted <- ora(gene = de_genes, gene_sets = gene_sets, universe = all_genes, weight = weight)
expect_true(is.data.frame(weighted))
expect_true(all(c("ID", "pvalue", "Count") %in% colnames(weighted)))
expect_false(isTRUE(all.equal(weighted$pvalue, unweighted$pvalue)))
})
test_that("ORA results carry a Fisher odds ratio (#501)", {
de_genes <- c("Gene1", "Gene2", "Gene3", "Gene4", "Gene5")
all_genes <- paste0("Gene", 1:1000)
gene_sets <- list(
P1 = paste0("Gene", 1:50), # overlaps the DE list
P2 = paste0("Gene", 51:150), # does not
P3 = paste0("Gene", 201:260)
)
res <- ora(gene = de_genes, gene_sets = gene_sets, universe = all_genes)
expect_true("oddsRatio" %in% colnames(res))
# sits with the other effect sizes
expect_equal(match("oddsRatio", colnames(res)),
match("FoldEnrichment", colnames(res)) + 1)
for (i in seq_len(nrow(res))) {
k <- res$Count[i]
n <- as.numeric(strsplit(as.character(res$GeneRatio[i]), "/")[[1]])[2]
br <- as.numeric(strsplit(as.character(res$BgRatio[i]), "/")[[1]])
M <- br[1]; N <- br[2]
# the column is the 2x2 cross-product odds ratio
cross <- (k * (N - M - n + k)) / ((n - k) * (M - k))
expect_equal(res$oddsRatio[i], cross, tolerance = 1e-10)
# and the reported p-value is Fisher's exact test on that same table,
# which is what makes the odds ratio the matching effect size
tab <- matrix(c(k, n - k, M - k, N - M - n + k), nrow = 2, byrow = TRUE)
if (all(tab > 0)) {
expect_equal(
res$pvalue[i],
unname(fisher.test(tab, alternative = "greater")$p.value),
tolerance = 1e-8
)
} else {
# a degenerate table gives 0 (no overlap) or Inf (complete overlap)
# rather than a finite ratio - just confirm it is a number, since the
# formula check above already pinned the value down
expect_true(is.numeric(res$oddsRatio[i]))
}
}
})
## -- skipping the identity intersect must not change any result -------------
## Without a universe, `extID` is `unique(gsid2gene$gene)` and every gene set
## already comes from that table, so the old unconditional
## `lapply(geneSets, intersect, extID)` was an identity operation -- but it
## hashed extID once per set (20 s for the 14,209 human GO BP sets, measured
## 2026-10-18) and ORA runs once per cluster. The intersect is now conditional
## on a universe being supplied. This test pins the equivalence: passing the
## full annotated gene list as `universe` (which still takes the intersection
## branch) must give exactly the same result as passing none.
test_that("ora_gson without universe equals ora_gson with the full gene universe", {
skip_if_not_installed("gson")
gsid2gene <- data.frame(
gsid = c("set1", "set1", "set2", "set2", "set3", "set3", "set4", "set4"),
gene = c("Gene1", "Gene2", "Gene2", "Gene3", "Gene4", "Gene5", "Gene1", "Gene4"),
stringsAsFactors = FALSE
)
gsid2name <- data.frame(
gsid = c("set1", "set2", "set3", "set4"),
name = c("Set 1", "Set 2", "Set 3", "Set 4"),
stringsAsFactors = FALSE
)
gson_obj <- gson::gson(
gsid2gene = gsid2gene,
gsid2name = gsid2name,
species = "test",
gsname = "test",
version = "test",
accessed_date = as.character(Sys.Date()),
keytype = "UNKNOWN"
)
args <- list(
gene = c("Gene1", "Gene2"),
pvalueCutoff = 1,
pAdjustMethod = "BH",
minGSSize = 1,
maxGSSize = 10,
qvalueCutoff = 1,
gson = gson_obj
)
no_universe <- do.call(ora_gson, args)
explicit <- do.call(ora_gson, c(args, list(universe = unique(gsid2gene$gene))))
expect_equal(no_universe@result$ID, explicit@result$ID)
expect_equal(no_universe@result$pvalue, explicit@result$pvalue, tolerance = 1e-12)
expect_equal(no_universe@result$p.adjust, explicit@result$p.adjust, tolerance = 1e-12)
expect_equal(no_universe@result$Count, explicit@result$Count)
})
## -- the identity skip must still intersect a RESTRICTED universe ----------
## clusterProfiler passes the full annotated gene list explicitly when the
## caller supplies no universe, so "a universe was given" is not the same as
## "the background was restricted". This pins the latter: a universe that
## removes a gene must still shrink the gene sets.
test_that("ora_gson still intersects when the universe removes annotated genes", {
skip_if_not_installed("gson")
gsid2gene <- data.frame(
gsid = c("set1", "set1", "set2", "set2", "set3"),
gene = c("Gene1", "Gene2", "Gene2", "Gene3", "Gene4"),
stringsAsFactors = FALSE
)
gsid2name <- data.frame(
gsid = c("set1", "set2", "set3"),
name = c("Set 1", "Set 2", "Set 3"),
stringsAsFactors = FALSE
)
gson_obj <- gson::gson(
gsid2gene = gsid2gene,
gsid2name = gsid2name,
species = "test",
gsname = "test",
version = "test",
accessed_date = as.character(Sys.Date()),
keytype = "UNKNOWN"
)
## Gene4 is annotated but excluded from the background, so set3 must shrink
## from 1 gene to 0 and disappear from the result.
res <- ora_gson(
gene = c("Gene1", "Gene2"),
pvalueCutoff = 1,
pAdjustMethod = "BH",
universe = c("Gene1", "Gene2", "Gene3"),
minGSSize = 1,
maxGSSize = 10,
qvalueCutoff = 1,
gson = gson_obj
)
expect_s4_class(res, "enrichResult")
expect_false("set3" %in% res@result$ID)
expect_true(all(c("set1", "set2") %in% res@result$ID))
## Background size in BgRatio must be the restricted one (3), not 4.
expect_true(all(grepl("/3$", res@result$BgRatio)))
## And the full annotated list (the clusterProfiler default spelling) must be
## treated as unrestricted, matching the no-universe result exactly.
full <- ora_gson(
gene = c("Gene1", "Gene2"), pvalueCutoff = 1, pAdjustMethod = "BH",
universe = unique(gsid2gene$gene), minGSSize = 1, maxGSSize = 10,
qvalueCutoff = 1, gson = gson_obj
)
bare <- ora_gson(
gene = c("Gene1", "Gene2"), pvalueCutoff = 1, pAdjustMethod = "BH",
minGSSize = 1, maxGSSize = 10, qvalueCutoff = 1, gson = gson_obj
)
expect_equal(full@result$ID, bare@result$ID)
expect_equal(full@result$pvalue, bare@result$pvalue, tolerance = 1e-12)
})
## -- geneID order must be reproducible --------------------------------------
## `ora_cpp()` used to build the geneID column by iterating a
## std::unordered_set, so the same input returned the same genes in a different
## order in different processes (measured 2026-10-18). It now walks the input
## gene order, which is deterministic and easier to read.
test_that("ora_cpp keeps the input gene order in geneID", {
genes <- c("g3", "g1", "g4")
sets <- list(s1 = c("g1", "g2", "g3", "g4"), s2 = c("g1", "g4"))
out <- enrichit:::ora_cpp(genes, c("g1", "g2", "g3", "g4"), sets, c("s1", "s2"))
expect_equal(out$geneID, c("g3/g1/g4", "g1/g4"))
## And it is stable across repeated calls in one process.
again <- enrichit:::ora_cpp(genes, c("g1", "g2", "g3", "g4"), sets, c("s1", "s2"))
expect_identical(out$geneID, again$geneID)
})
test_that("ORA results carry the denominators all three ratios are computed from", {
skip_if_not_installed("gson")
## Fully specified input, so every expected number below can be worked out by
## hand rather than read back off the result:
## universe g1..g100 (100 genes)
## query g1..g10 (10 genes)
## set A g1..g5 (5 genes, all in the query)
## set B g6..g25 (20 genes, 5 of them in the query)
## The annotated domain is A union B = g1..g25, so the background the ratios
## use is 25 genes even though the universe offered was 100 -- that
## intersection is exactly what four users had to ask about
## (clusterProfiler#703, #523, #618, #723), and it is why UniverseSize is
## reported instead of leaving the 25 implicit.
u <- paste0("g", 1:100)
query <- paste0("g", 1:10)
sets <- list(A = paste0("g", 1:5), B = paste0("g", 6:25))
g <- gson::gson(
gsid2gene = data.frame(gsid = rep(names(sets), lengths(sets)),
gene = unlist(sets, use.names = FALSE)),
gsid2name = data.frame(gsid = names(sets), name = names(sets))
)
res <- ora_gson(query, pvalueCutoff = 1, universe = u, gson = g,
qvalueCutoff = 1, minGSSize = 1)
df <- res@result
expect_identical(df$ID, c("A", "B"))
## the denominators, stated as values
expect_identical(df$SetSize, c(5L, 20L))
expect_identical(df$DESize, c(10L, 10L))
expect_identical(df$UniverseSize, c(25L, 25L))
## and the three ratios are reproducible from them
expect_identical(df$GeneRatio, c("5/10", "5/10"))
expect_identical(df$BgRatio, c("5/25", "20/25"))
expect_identical(df$RichFactor, c(1, 0.25))
## the identities hold for every row, which is the property the columns exist
## to make checkable
expect_identical(df$Count, as.integer(sub("/.*", "", df$GeneRatio)))
expect_identical(df$GeneRatio, paste0(df$Count, "/", df$DESize))
expect_identical(df$BgRatio, paste0(df$SetSize, "/", df$UniverseSize))
expect_identical(df$RichFactor, df$Count / df$SetSize)
## the original column set is untouched: the denominators were appended
expect_identical(
colnames(df)[1:13],
c("ID", "Description", "GeneRatio", "BgRatio", "RichFactor",
"FoldEnrichment", "oddsRatio", "zScore", "pvalue", "p.adjust",
"qvalue", "geneID", "Count")
)
})
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.