@prefix ex: <https://sparql.uniprot.org/.well-known/sparql-examples/> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
@prefix schema: <https://schema.org/> .
@prefix sh: <http://www.w3.org/ns/shacl#> .

ex:214_proteins_starting_with_methionine a sh:SPARQLExecutable,
        sh:SPARQLSelectExecutable ;
    rdfs:comment "Of reviewed human proteins, how many have a stored sequence starting with methionine (the universal translation start codon), and of those, how many have that initiator methionine later cleaved off post-translationally (up:Initiator_Methionine_Annotation with comment 'Removed') rather than retained in the mature protein"@en ;
    sh:prefixes _:sparql_examples_prefixes ;
    sh:select """PREFIX up: <http://purl.uniprot.org/core/>
PREFIX taxon: <http://purl.uniprot.org/taxonomy/>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>

SELECT
  (COUNT(DISTINCT ?protein) AS ?totalReviewedHumanProteins)
  (SUM(IF(?startsWithMet, 1, 0)) AS ?startWithMethionine)
  (SUM(IF(BOUND(?initiatorMetRemoved), 1, 0)) AS ?initiatorMethionineLaterRemoved)
WHERE {
  ?protein a up:Protein ;
    up:organism taxon:9606 ;
    up:reviewed true ;
    up:sequence ?sequence .
  ?sequence rdf:value ?seqValue .
  BIND(STRSTARTS(?seqValue, "M") AS ?startsWithMet)
  OPTIONAL {
    ?protein up:annotation ?initiatorMet .
    ?initiatorMet a up:Initiator_Methionine_Annotation ;
      rdfs:comment "Removed" .
    BIND(true AS ?initiatorMetRemoved)
  }
}""" ;
    schema:keywords "methionine" , "translation" , "sequence" ;
    schema:target <https://sparql.uniprot.org/sparql/> .