198_sequence_integrity_metadata

sequence
checksum
mass
UniParc

For reviewed human proteins, get the mass and MD5 checksum recorded on the canonical sequence together with the sequence length recorded on the corresponding UniParc entry — the kind of 'does this sequence match what I have locally' check downstream tooling actually runs

Use at

https://sparql.uniprot.org/sparql/

PREFIX up: <http://purl.uniprot.org/core/>
PREFIX taxon: <http://purl.uniprot.org/taxonomy/>

SELECT
  ?protein
  ?mass
  ?md5Checksum
  ?length
WHERE {
  ?protein a up:Protein ;
    up:organism taxon:9606 ;
    up:reviewed true ;
    up:sequence ?sequence .
  ?sequence up:mass ?mass ;
    up:md5Checksum ?md5Checksum .
  ?uniparc up:sequenceFor ?protein ;
    up:length ?length .
}

graph TD
classDef projected fill:lightgreen;
classDef literal fill:orange;
classDef iri fill:yellow;
  v6("?length"):::projected 
  v3("?mass"):::projected 
  v4("?md5Checksum"):::projected 
  v1("?protein"):::projected 
  v2("?sequence")
  v5("?uniparc")
  c6(["true^^xsd:boolean"]):::literal 
  c2(["up:Protein"]):::iri 
  c4(["taxon:9606"]):::iri 
  v1 --"a"-->  c2
  v1 --"up:organism"-->  c4
  v1 --"up:reviewed"-->  c6
  v1 --"up:sequence"-->  v2
  v2 --"up:mass"-->  v3
  v2 --"up:md5Checksum"-->  v4
  v5 --"up:sequenceFor"-->  v1
  v5 --"up:length"-->  v6