Retrieving Gene ontology (GO) annotations using Bioconductor annotation packages

GO.R

library(AnnotationDbi)
library(org.Hs.eg.db)
library(GO.db)

kTerm <- "GO:0007265"
# retrieve all genes annotated with the GO germ
df <- AnnotationDbi::select(org.Hs.eg.db, keys  = c(kTerm),
                            columns = c("ENTREZID", "ENSEMBL"), 
                            keytype = "GO")
nrow(df)  # 117 (some duplicate EntrezIds because we requested Ensembl ids, too)
length(unique(df$ENTREZID))  # 89

# retrieve all genes annotated with term GO:0008150 or any of its ancestor terms
df <- AnnotationDbi::select(org.Hs.eg.db, keys  = c(kTerm),
                            columns = c("ENTREZID", "ENSEMBL"), 
                            keytype = "GOALL")
length(unique(df$ENTREZID))  # 353

# retrieve GO annotations (terms and ancestor terms)
tbl <- AnnotationDbi::toTable(org.Hs.egGO2ALLEGS)
nrow(tbl)  # 3.4 million rows
table(tbl$Evidence)  # see http://geneontology.org/docs/guide-go-evidence-codes/

# retrieve the TERM and DEFINITON for a (or multiple) GO terms
AnnotationDbi::select(GO.db, keys=kTerm, keytype="GOID", columns=columns(GO.db))