@prefix ex: <https://sparql.uniprot.org/.well-known/sparql-examples/> .
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
@prefix schema: <https://schema.org/> .
@prefix sh: <http://www.w3.org/ns/shacl#> .
@prefix spex: <https://purl.expasy.org/sparql-examples/ontology#> .

ex:126_count_venom_related_proteins a sh:SPARQLExecutable, sh:SPARQLSelectExecutable;
  rdfs:comment "Count the number of entries that are annotated to be related to venomous activity in selected taxonomic groups"^^rdf:HTML;
  sh:prefixes _:sparql_examples_prefixes;
  sh:select """PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX taxon: <http://purl.uniprot.org/taxonomy/>
PREFIX up:  <http://purl.uniprot.org/core/>
PREFIX location: <http://purl.uniprot.org/locations/>
SELECT
  (COUNT(DISTINCT ?protein) AS ?proteins)
  ?grouping
  ?groupingScientificName
WHERE
{
  VALUES ?grouping {
    taxon:6103 #sea anemones
    taxon:8570 #snakes
    taxon:6855 #scorpions
    taxon:6893 #Araneae
    taxon:50557 #Insecta
    taxon:37797 #Conoidea
  }
  ?grouping up:scientificName ?groupingScientificName .
  ?taxon rdfs:subClassOf ?grouping.
  ?protein up:organism ?taxon .
  {
    ?protein up:annotation ?tsa .
    ?tsa a up:Tissue_Specificity_Annotation ;
           rdfs:comment ?tsac .
     FILTER(REGEX(?tsac, 'venom', 'i'))
  } UNION {
   ?protein up:annotation ?scla .
   # location:177 is nematocyst
   ?scla a up:Subcellular_Location_Annotation ;
          up:locatedIn/up:cellularComponent location:177 .
  }
}
GROUP BY ?grouping ?groupingScientificName
ORDER BY ?proteins""";
  schema:keywords "statistics", "tissue", "venom";
  schema:target <https://sparql.uniprot.org/sparql> .