Probe annotation file for microarray platform MoGene-1_0-st-v1 – Open Source Biology & Genetics Interest Group

Hi, I would use the pre-built Bioconductor annotation databases / packages for this array (I have used this array a few times over the years):

mogene10sttranscriptcluster.db
mogene10stprobeset.db

Most likely mogene10sttranscriptcluster.db is what you want:

require(mogene10sttranscriptcluster.db)

columns(mogene10sttranscriptcluster.db)
 [6] "ENTREZID"     "ENZYME"       "EVIDENCE"     "EVIDENCEALL"  "GENENAME"    
[11] "GO"           "GOALL"        "IPI"          "MGI"          "ONTOLOGY"    
[16] "ONTOLOGYALL"  "PATH"         "PFAM"         "PMID"         "PROBEID"     
[21] "PROSITE"      "REFSEQ"       "SYMBOL"       "UNIGENE"      "UNIPROT"     

head(keys(mogene10sttranscriptcluster.db))
[1] "10338001" "10338002" "10338003" "10338004" "10338005" "10338006"

annotTable <- select(
  mogene10sttranscriptcluster.db,
  keys = keys(mogene10sttranscriptcluster.db),
  column = c('PROBEID', 'SYMBOL', 'ENTREZID', 'ENSEMBL'),
  keytype="PROBEID")

head(annotTable)
   PROBEID SYMBOL ENTREZID ENSEMBL
1 10338001   <NA>     <NA>    <NA>
2 10338002   <NA>     <NA>    <NA>
3 10338003   <NA>     <NA>    <NA>
4 10338004   <NA>     <NA>    <NA>
5 10338005   <NA>     <NA>    <NA>
6 10338006   <NA>     <NA>    <NA>

dim(annotTable)
[1] 53244     4

There is data there – don’t worry / no te preocupes / لا تقلق:

head(annotTable[!is.na(annotTable$SYMBOL),])
      PROBEID  SYMBOL ENTREZID            ENSEMBL
6618 10344624  Lypla1    18777 ENSMUSG00000025903
6619 10344633   Tcea1    21399 ENSMUSG00000033813
6620 10344637 Atp6v1h   108664 ENSMUSG00000033793
6621 10344653   Oprk1    18387 ENSMUSG00000025905
6622 10344658  Rb1cc1    12421 ENSMUSG00000025907
6623 10344674  Alkal1   620393 ENSMUSG00000087247

dim(annotTable[!is.na(annotTable$SYMBOL),])
[1] 42056     4

annotTable.filt <- annotTable[!is.na(annotTable$SYMBOL),]

# select 10 random probes
probes <- annotTable.filt$PROBEID[sample(1:nrow(annotTable.filt), 10)]

mapIds(
  mogene10sttranscriptcluster.db,
  keys = probes,
  column = 'SYMBOL',
  keytype="PROBEID")

  10367033   10519951   10396485   10431424   10398173   10550770   10403558 
  "Zbtb39"     "Gsap"    "Syne2"   "Plxnb2"     "Vrk1" "Vmn1r114"   "Ero1lb" 
  10363512   10596053   10608237 
   "Sar1a"     "Pccb"  "Gm20736"

Kevin

Categories

Tags