Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Gson GO mapper - to build a gson object with private GO annotation #493

Open
wants to merge 5 commits into
base: devel
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion DESCRIPTION
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
Package: clusterProfiler
Type: Package
Title: A universal enrichment tool for interpreting omics data
Version: 4.5.2.001
Version: 4.5.3
Authors@R: c(
person(given = "Guangchuang", family = "Yu", email = "[email protected]", role = c("aut", "cre", "cph"), comment = c(ORCID = "0000-0002-6485-8781")),
person(given = "Li-Gen", family = "Wang", email = "[email protected]", role = "ctb"),
Expand Down
1 change: 1 addition & 0 deletions NAMESPACE
Original file line number Diff line number Diff line change
Expand Up @@ -70,6 +70,7 @@ export(gseMKEGG)
export(gseWP)
export(gseaplot)
export(gsfilter)
export(gson_GO_mapper)
export(gson_GO)
export(gson_KEGG)
export(gson_KEGG_mapper)
Expand Down
83 changes: 83 additions & 0 deletions R/gson.R
Original file line number Diff line number Diff line change
Expand Up @@ -90,6 +90,89 @@ gson_WP <- function(organism) {
}


#' Build a gson object that annotate Gene Ontology
#'
#' @param data a two-column data.frame of original GO annotation. The columns are "gene_id" and "go_id".
#' @param ont type of GO annotation, which is "ALL", "BP", "MF", or "CC". default: "ALL".
#' @param species name of species. Default: NULL.
#' @param ... pass to `gson::gson()` constructor.
#'
#' @return a `gson` instance
#' @export
#'
#' @examples
#' data = data.frame(gene_id = "gene1",
#' go_id = c("GO:0035492", "GO:0009764", "GO:0031063", "GO:0033714", "GO:0036349"))
#' gson_go_mapper(data, species = "E. coli")
gson_GO_mapper = function(data,
ont = c("ALL", "BP", "CC", "MF"),
species = NULL,
...){
ont = match.arg(ont)

data = unique(data) # cleanup
if (nrow(data) == 0) {
simpleError("Data is empty in this call.")
}

# resources from `GO.db`
goterms = AnnotationDbi::Ontology(GO.db::GOTERM)
termname = AnnotationDbi::Term(GO.db::GOTERM)
go.db_info = GO.db::GO_dbInfo()
go.db_source_date = go.db_info[go.db_info$name == "GOSOURCEDATE", "value"]
ancestor_map = lapply(c(GO.db::GOBPANCESTOR,
GO.db::GOCCANCESTOR,
GO.db::GOMFANCESTOR),
as.list) %>%
unlist(recursive = FALSE)

# filter GO terms
data[["ontology"]] = goterms[data[["go_id"]]]
n_na_ont = sum(is.na(data[["ontology"]]))
if ( n_na_ont > 0){
warning(sprintf("%s GO term(s) are too new for current `GO.db` [source date: %s],\n and are to be dropped. Consider to update `GO.db` if possible.",
n_na_ont,
go.db_source_date))
}

# map to GO ancestor
ancestor_list = ancestor_map[data$go_id]
names(ancestor_list) = data$gene_id
ancestor_go = AnnotationDbi::unlist2(ancestor_list)

# gsid2gene
gsid2gene = data.frame(
gsid = c(ancestor_go, data$go_id),
gene = c(names(ancestor_go), data$gene_id),
ontology = goterms[c(ancestor_go, data$go_id)]
) %>%
dplyr::filter(.data$gsid != "all") %>%
unique()

if (ont != "ALL"){
gsid2gene = gsid2gene %>%
dplyr::filter(.data$ontology == ont)
}

# gsid2name
uniq_gsid = unique(gsid2gene$gsid) %>% as.character()
gsid2name = data.frame(
gsid = uniq_gsid,
name = termname[uniq_gsid] %>% as.character()
)

# construct `gson` object
gson::gson(
gsid2gene = gsid2gene,
gsid2name = gsid2name,
species = species,
gsname = paste0("Gene Ontology: ", ont),
version = sprintf("[GO.db source date: %s]", go.db_source_date),
accessed_date = as.character(Sys.Date()),
...
)
}


#' Build KEGG annotation for novel species using KEGG Mapper
#'
Expand Down