mapIds gene annotation symbol ensembl

symbol2ensemblid

library(org.Hs.eg.db)

(fields = columns(org.Hs.eg.db))  # show annotations available 


symbols = c("MYC", "CCNE1", "TP53")

# get full gene annotation for MYC (takes 1 or 2 minutes to run)
geneinfo = lapply (fields, function (f) {
  message (f)
  # https://bioconductor.org/packages/devel/bioc/manuals/AnnotationDbi/man/AnnotationDbi.pdf
  mapIds(org.Hs.eg.db, symbols[1], keytype="SYMBOL", column=f, multiVals = "list")
})
names(geneinfo) = fields
geneinfo   # wow!

geneinfo$ENSEMBL[[1]]   # get the ENSEMBL ID for MYC
geneinfo$REFSEQ[[1]]  # get the Refseq accessions for MYC



# Specific function to convert from Symbol to Ensemblid
symbol2ensemblid = function(symbol = "TP53") {
  require(org.Hs.eg.db)
  if ( is.na(match(symbol, keys(org.Hs.eg.db, keytype = "SYMBOL"))) ) {
    toReturn = NA
  } else {
    toReturn = as.vector(mapIds(org.Hs.eg.db, symbol, keytype="SYMBOL", column="ENSEMBL", multiVals = "first"))
  }
  return(toReturn)
}

genes = c("GNAS", "ADCY1", "ADCY2", "PRKCA", "CREB1", "MITF")
genes

symbol2ensemblid("GNAS")

myensemblids = sapply(genes, symbol2ensemblid)
as.data.frame (myensemblids)