Nothing
#' interal method for enrichment analysis
#'
#' using the hypergeometric model
#' @title ora-gson
#' @param gene a vector of entrez gene id.
#' @param qvalueCutoff cutoff of qvalue
#' @param universe background genes, default is the intersection of the 'universe' with genes that have annotations.
#' Users can set `options(enrichment_force_universe = TRUE)` to force the 'universe' untouched.
#' @param weight A named numeric vector of weights for background genes. If provided, Weighted ORA will be performed.
#' @inheritParams enrichit_params
#' @return A `enrichResult` instance. The `result` slot carries the three
#' significance columns `pvalue`, `p.adjust`, and `qvalue`:
#' raw nominal p-values, BH-style multiple-testing adjusted p-values
#' (via `stats::p.adjust()`; default `pAdjustMethod = "BH"`), and
#' Storey q-values (via `qvalue::qvalue()`). If q-value estimation
#' fails, `qvalue` remains `NA`. See `?as_enrichResult` for the full
#' column semantics.
#' @importClassesFrom methods data.frame
#' @importFrom methods new
#' @importFrom stats p.adjust
#' @keywords manip
#' @author Guangchuang Yu <https://yulab-smu.top>
#' @export
ora_gson <- function(gene,
pvalueCutoff,
pAdjustMethod="BH",
universe = NULL,
weight = NULL,
minGSSize=10,
maxGSSize=500,
qvalueCutoff=0.2,
gson){
if (!inherits(gson, "GSON")) {
stop("gson should be a GSON object")
}
## query external ID to Term ID
gene <- as.character(unique(gene))
# Extract gene sets from GSON
gsid2gene <- gson@gsid2gene
# ID Match Check
if (!check_gene_id(gene, gsid2gene)) {
return(NULL)
}
# Handle universe
annotatedGenes <- unique(gsid2gene$gene)
extID <- annotatedGenes
if (missing(universe))
universe <- NULL
if(!is.null(universe)) {
## A numeric/integer/factor universe (e.g. plain Entrez IDs supplied as
## numbers) is a perfectly meaningful background and should not be
## silently discarded -- coerce it to character the same way `gene`
## is coerced a few lines above. Only genuinely non-vector input
## (list, data.frame, S4 object, ...) is still rejected.
## see https://github.com/YuLab-SMU/clusterProfiler/issues/217
## https://github.com/YuLab-SMU/clusterProfiler/issues/737
if (!is.character(universe)) {
if (is.atomic(universe) && !is.null(universe)) {
message(
"`universe` is not in character, converting via as.character()..."
)
universe <- as.character(universe)
} else {
message("`universe` is not in character and will be ignored...")
universe <- NULL
}
}
if (!is.null(universe)) {
force_universe <- getOption("enrichment_force_universe", FALSE)
if (force_universe) {
extID <- universe
} else {
extID <- intersect(extID, universe)
}
}
}
# Prepare Gene Sets
geneSets <- split(gsid2gene$gene, gsid2gene$gsid)
## Intersect the gene sets with the background only when the background was
## actually RESTRICTED. An intersection with the full annotated gene list is
## the identity -- the sets come from that same table -- but it is not free:
## base `intersect()` hashes `extID` once per set, measured at 20 s for the
## 14,209 human GO BP sets (PBMC 10k, 2026-10-18), and ORA runs once per
## cluster in compareCluster(). Note that clusterProfiler passes the full
## annotated list EXPLICITLY when the caller supplies no universe, so
## `universe != NULL` alone is not the right test; `extID` is shorter than
## the annotated set only when a universe actually removed genes.
if (!is.null(universe) && length(extID) < length(annotatedGenes)) {
geneSets <- filter_gene_sets(geneSets, extID)
}
# Filter by size
idx <- get_geneSet_index(geneSets, minGSSize, maxGSSize)
if (sum(idx) == 0) {
msg <- paste("No gene sets have size between", minGSSize, "and", maxGSSize, "...")
message(msg)
message("--> return NULL...")
return (NULL)
}
geneSets <- geneSets[idx]
ora_res <- ora(gene, geneSets, universe = extID, weight = weight)
if (is.null(ora_res) || nrow(ora_res) == 0) {
return(NULL)
}
# Rename columns to match expectation
if ("PValue" %in% names(ora_res)) {
names(ora_res)[names(ora_res) == "PValue"] <- "pvalue"
}
if ("GeneSet" %in% names(ora_res)) {
names(ora_res)[names(ora_res) == "GeneSet"] <- "ID"
}
if ("DEInSet" %in% names(ora_res)) {
names(ora_res)[names(ora_res) == "DEInSet"] <- "Count"
}
# Only gene sets with at least one matched input gene should contribute to
# multiple testing correction. Keeping zero-overlap rows here inflates the
# number of hypotheses and shifts adjusted statistics relative to the
# historical DOSE/clusterProfiler behavior.
if ("Count" %in% names(ora_res)) {
ora_res <- ora_res[ora_res$Count > 0, , drop = FALSE]
}
if (nrow(ora_res) == 0) {
return(NULL)
}
# Calculate ratios
if (all(c("Count", "DESize") %in% names(ora_res))) {
ora_res$GeneRatio <- paste0(ora_res$Count, "/", ora_res$DESize)
}
if (all(c("SetSize", "UniverseSize") %in% names(ora_res))) {
ora_res$BgRatio <- paste0(ora_res$SetSize, "/", ora_res$UniverseSize)
}
# Calculate RichFactor and FoldEnrichment
if (all(c("Count", "SetSize", "DESize", "UniverseSize") %in% names(ora_res))) {
ora_res$RichFactor <- ora_res$Count / ora_res$SetSize
ora_res$FoldEnrichment <- (ora_res$Count / ora_res$DESize) / (ora_res$SetSize / ora_res$UniverseSize)
}
p <- suppressWarnings(as.numeric(ora_res$pvalue))
invalid <- is.na(p) | !is.finite(p) | p < 0 | p > 1
if (any(invalid)) {
ids <- as.character(ora_res$ID)
bad_i <- which(invalid)
head_i <- bad_i[seq_len(min(length(bad_i), 10))]
bad_preview <- paste0(ids[head_i], "=", format(p[head_i], digits = 4, scientific = TRUE), collapse = ", ")
warning(
"Invalid p-values detected in ORA result (",
length(bad_i),
"/",
length(p),
"). Examples: ",
bad_preview
)
too_small <- !is.na(p) & is.finite(p) & p < 0
too_large <- !is.na(p) & is.finite(p) & p > 1
p[too_small] <- 0
p[too_large] <- 1
ora_res$pvalue <- p
} else if (!isTRUE(all.equal(p, ora_res$pvalue))) {
ora_res$pvalue <- p
}
# Calculate p.adjust
ora_res$p.adjust <- p.adjust(ora_res$pvalue, method=pAdjustMethod)
# Calculate qvalue
ora_res$qvalue <- calculate_qvalue(ora_res$pvalue)
# Calculate zScore
# Need k, M, n, N
N <- length(extID)
n <- length(intersect(gene, extID))
k <- ora_res$Count
# M = size of gene set (in universe)
# Map ID to M
# ora_res$ID should match names(geneSets)
M <- sapply(geneSets[ora_res$ID], length)
mu <- M * n / N
sigma <- mu * (N - n) * (N - M) / N / (N - 1)
zScore <- (k - mu) / sqrt(sigma)
ora_res$zScore <- zScore
## Fisher's exact odds ratio: what fisher.test()$estimate reports for the 2x2
## table below. FoldEnrichment is a ratio of proportions, whereas the odds
## ratio is the effect size the test itself is built on, so it is worth
## exposing next to it.
##
## in gene set not in gene set
## in list k n - k
## not in list M - k N - M - n + k
##
## A zero cell gives 0 or Inf, exactly as fisher.test() does.
ora_res$oddsRatio <- (k * (N - M - n + k)) / ((n - k) * (M - k))
# Add Description
gsid2name <- gson@gsid2name
if (!is.null(gsid2name) && "ID" %in% names(ora_res)) {
description <- gsid2name$name[match(ora_res$ID, gsid2name$gsid)]
na_idx <- is.na(description)
description[na_idx] <- ora_res$ID[na_idx]
ora_res$Description <- description
}
if (!"Description" %in% names(ora_res)) {
ora_res$Description <- ora_res$ID
}
# Reorder columns
expected_cols <- c("ID", "Description", "GeneRatio", "BgRatio", "RichFactor", "FoldEnrichment", "oddsRatio", "zScore", "pvalue", "p.adjust", "qvalue", "geneID", "Count")
# Ensure all expected columns exist
missing_cols <- setdiff(expected_cols, names(ora_res))
if (length(missing_cols) > 0) {
warning("Missing columns in ORA result: ", paste(missing_cols, collapse=", "),
". Filling with NA. (Note: 'qvalue' may be missing if p-value distribution does not allow q-value calculation)")
for (col in missing_cols) {
ora_res[[col]] <- NA
}
}
## Keep the denominators the engine already computed. `DESize` is the
## GeneRatio denominator (query genes inside the universe) and
## `UniverseSize` the BgRatio denominator (universe ∩ annotated genes);
## both were calculated here and then dropped, which is why four users in a
## row (clusterProfiler#703, #523, #618, #723) had to ask what the
## denominators of the "20/207" strings actually are. `SetSize` stays too:
## RichFactor divides by it, so all three ratios are now checkable from the
## table itself. GSEA's gsea_gson() has always kept its extra columns.
extra_cols <- intersect(c("SetSize", "DESize", "UniverseSize"), names(ora_res))
ora_res <- ora_res[, c(expected_cols, extra_cols)]
# Sort by pvalue
ora_res <- ora_res[order(ora_res$pvalue), ]
# Set row names
# Ensure IDs are robust (handle NA and duplicates)
ids <- as.character(ora_res$ID)
# Handle NA IDs (convert to string "NA")
if (any(is.na(ids))) {
warning("NA values detected in gene set IDs. Replacing with string 'NA'.")
ids[is.na(ids)] <- "NA"
}
# Handle Duplicate IDs
if (any(duplicated(ids))) {
dup_ids <- unique(ids[duplicated(ids)])
warning("Duplicate gene set IDs detected: ", paste(head(dup_ids), collapse=", "),
"... (Total ", length(dup_ids), "). Unique suffixes added.")
ids <- make.unique(ids)
}
rownames(ora_res) <- ids
x <- new("enrichResult",
result = ora_res,
pvalueCutoff = pvalueCutoff,
pAdjustMethod = pAdjustMethod,
qvalueCutoff = qvalueCutoff,
gene = as.character(gene),
universe = extID,
geneSets = geneSets,
organism = if (!is.null(gson@species)) gson@species else "UNKNOWN",
keytype = if (!is.null(gson@keytype)) gson@keytype else "UNKNOWN",
ontology = if (!is.null(gson@gsname)) gsub(".*;", "", gson@gsname) else "UNKNOWN",
readable = FALSE
)
return(x)
}
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.