wd_taxa_containing_all_compounds

• License: https://creativecommons.org/publicdomain/zero/1.0/

rq turtle/ttl

• natural products
• structural similarity
• taxa

Taxa containing at least n of the following compounds.

Use at

• https://query.wikidata.org/sparql

PREFIX hint: <http://www.bigdata.com/queryHints#>
PREFIX idsm: <https://idsm.elixir-czech.cz/sparql/endpoint/>
PREFIX sachem: <http://bioinfo.uochb.cas.cz/rdf/v1.0/sachem#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
#title: Taxa containing at least n of the following compounds.
SELECT DISTINCT ?taxon ?taxon_name WHERE {
  VALUES ?n {4}
  {
    SELECT ?taxon ?taxon_name (COUNT(DISTINCT ?compound) AS ?compoundCount) WHERE {
      {
        SELECT DISTINCT ?taxon ?taxon_name ?compound WHERE {
          {
            SELECT DISTINCT ?compound ?smiles WHERE {
              SERVICE idsm:wikidata {
                VALUES ?smiles {
                  "C=C[C@H]1[C@@H](OC=C2C1=CCOC2=O)O[C@H]3[C@@H]([C@H]([C@@H]([C@H](O3)CO)O)O)O"
                  "C=C[C@H]1[C@@H](OC=C2[C@]1(CCOC2=O)O)O[C@H]3[C@@H]([C@H]([C@@H]([C@H](O3)CO)O)O)O"
                  "C=C[C@@H]1[C@@H]2CCOC(=O)C2=CO[C@H]1O[C@H]3[C@@H]([C@H]([C@@H]([C@H](O3)CO)O)O)OC(=O)C4=C(C=C(C=C4O)O)O"
                  "COC1=CC(=C2C(=C1)OC3=C(C=CC(=C3C2=O)O[C@H]4[C@@H]([C@H]([C@@H]([C@H](O4)CO)O)O)O)O)O"
                }
                ?compound sachem:similarCompoundSearch [
                  sachem:query ?smiles;
                               sachem:cutoff "1.0"^^xsd:double
                ].
              }
            }
          } hint:Prior hint:runFirst "true".
          ?compound wdt:P703 ?child.
          ?child (wdt:P171*) ?taxon.
          ?taxon wdt:P225 ?taxon_name.
        }
      }
    }
    GROUP BY ?taxon ?taxon_name
  }
  FILTER((xsd:integer(?compoundCount)) >= ?n)
}
LIMIT 10000

graph TD
classDef projected fill:lightgreen;
classDef literal fill:orange;
classDef iri fill:yellow;
  v5("?child")
  v4("?compound")
  v8("?compoundCount")
  v3("?n")
  v3("?smiles")
  v6("?taxon"):::projected 
  v7("?taxon_name"):::projected 
  a1((" "))
  c6([http://www.bigdata.com/queryHints#Prior]):::iri 
  c4(["1.0^^xsd:double"]):::literal 
  c8(["true"]):::literal 
  f0[["http://www.w3.org/2001/XMLSchema#integer(?compoundCount) >= ?n"]]
  f0 --> v8
  f0 --> v3
  bind1[/VALUES ?n/]
  bind1-->v3
  bind10(["4^^xsd:integer"])
  bind10 --> bind1
  subgraph s1["https://idsm.elixir-czech.cz/sparql/endpoint/wikidata"]
    style s1 stroke-width:4px;
    bind2[/VALUES ?smiles/]
    bind2-->v3
    bind20(["C=C#91;C@H#93;1#91;C@@H#93;(OC=C2C1=CCOC2=O)O#91;C@H#93;3#91;C@@H#93;(#91;C@H#93;(#91;C@@H#93;(#91;C@H#93;(O3)CO)O)O)O"])
    bind20 --> bind2
    bind21(["C=C#91;C@H#93;1#91;C@@H#93;(OC=C2#91;C@#93;1(CCOC2=O)O)O#91;C@H#93;3#91;C@@H#93;(#91;C@H#93;(#91;C@@H#93;(#91;C@H#93;(O3)CO)O)O)O"])
    bind21 --> bind2
    bind22(["C=C#91;C@@H#93;1#91;C@@H#93;2CCOC(=O)C2=CO#91;C@H#93;1O#91;C@H#93;3#91;C@@H#93;(#91;C@H#93;(#91;C@@H#93;(#91;C@H#93;(O3)CO)O)O)OC(=O)C4=C(C=C(C=C4O)O)O"])
    bind22 --> bind2
    bind23(["COC1=CC(=C2C(=C1)OC3=C(C=CC(=C3C2=O)O#91;C@H#93;4#91;C@@H#93;(#91;C@H#93;(#91;C@@H#93;(#91;C@H#93;(O4)CO)O)O)O)O)O"])
    bind23 --> bind2
    a1 --"sachem:query"-->  v3
    a1 --"sachem:cutoff"-->  c4
    v4 --"sachem:similarCompoundSearch"-->  a1
  end
  c6 --http://www.bigdata.com/queryHints#runFirst-->  c8
  v4 --"wdt:P703"-->  v5
  v5 --"wdt:P171"-->  v6
  v6 --"wdt:P225"-->  v7
  bind4[/"count(?compound)"/]
  v4 --o bind4
  bind4 --as--o v8