[VLPB] The number of protein-coding transcripts in tomato differ between SGN and EnsEMBL

[arnikz]

• SGN tomato (GFF->RDF)

PREFIX obo: <http://purl.obolibrary.org/obo/>
SELECT COUNT(DISTINCT ?s)
FROM <https://solgenomics.net/genome/Solanum_lycopersicum> {
   ?s a obo:SO_0000120 .
}

34725 transcripts

• EnsEMBL tomato (RDF)

PREFIX obo: <http://purl.obolibrary.org/obo/>
SELECT COUNT(DISTINCT *)
FROM <http://plants.ensembl.org/Solanum_lycopersicum> {
   ?s a <http://rdf.ebi.ac.uk/terms/ensembl/protein_coding> .
}

67570 transcripts

PREFIX obo: <http://purl.obolibrary.org/obo/>
SELECT COUNT(DISTINCT *)
FROM <http://plants.ensembl.org/Solanum_lycopersicum> {
   ?s a obo:SO_0000276 .
}

36938 transcripts

PREFIX obo: <http://purl.obolibrary.org/obo/>
SELECT COUNT(DISTINCT *)
FROM <http://plants.ensembl.org/Solanum_lycopersicum> {
   ?s a obo:SO_0000276 .
   FILTER regex(?s, 'Soly')
}

33785 transcripts

PREFIX obo: <http://purl.obolibrary.org/obo/>
SELECT COUNT(DISTINCT *)
FROM <http://plants.ensembl.org/Solanum_lycopersicum> {
   ?s a <http://rdf.ebi.ac.uk/terms/ensembl/protein_coding> , obo:SO_0000276 .
}

33785 transcripts