A mini introduction to Biopax Explorer

###################################################
from biopax_explorer.pattern.pattern import PatternExecutor, Pattern
from biopax_explorer.query import  EntityNode
from biopax_explorer.biopax import *
import json 
    
##################################################

p=Pattern()
   
prot = EntityNode("PR", Protein())
prot.whereAttribute("name", "glucokinase","CONTAINS")
entityReference=EntityNode("EN", EntityReference())
prot.connectedWith(entityReference, "entityReference")
p.define(prot,entityReference)
 

pe=PatternExecutor()
pe.datasetFile("data/input/export_all_g6p.xml") 

 
result = pe.fetchEntities(p)
print("#automatic result mapping")
for entity_row in result[:1]:#only first result row
  for entity in entity_row:
      if isinstance(entity,Protein):
          print("first match of ",entity.meta_label," : ",entity.get_displayName(),",",entity.get_name())
          print( entity.to_json() )

#automatic result mapping
first match of  PR  :  ADPGK , ADP-dependent glucokinase
{
  "uri": "http://www.reactome.org/biopax/56/71387#Protein186",
  "dataSource": {
    "__uri__": "http://www.reactome.org/biopax/56/71387#Provenance1",
    "comment": null,
    "xref": null,
    "displayName": null,
    "name": null,
    "standardName": null
  },
  "evidence": null,
  "xref": {
    "__class__": "Xref",
    "uri": "http://www.reactome.org/biopax/56/71387#UnificationXref_reactome_R-HSA-5696062"
  },
  "availability": null,
  "comment": "http://www.reactome.org/biopax/56/71387#Protein186http://www.reactome.org/biopax/56/71387#Complex122@Layout@http://www.reactome.org/biopax/56/71387#Pathway6@20@1399",
  "displayName": "ADPGK",
  "name": "ADP-dependent glucokinase",
  "standardName": null,
  "cellularLocation": {
    "__class__": "CellularLocationVocabulary",
    "uri": "http://localhost:3030/g6p/CellularLocationVocabulary_b761180db8a874567188c589b45cab17"
  },
  "feature": {
    "__class__": "EntityFeature",
    "uri": "http://www.reactome.org/biopax/56/71387#FragmentFeature174"
  },
  "memberPhysicalEntity": null,
  "notFeature": null,
  "entityReference": {
    "__class__": "EntityReference",
    "uri": "http://identifiers.org/uniprot/Q9BRR6"
  },
  "__class__": "Protein"
}

querylist=PatternExecutor().queries(p)
print("#sparql code generation")
for q in querylist:
    print("#---generated sparql query---\n\n")
    print(q)

#sparql code generation
#---generated sparql query---


prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
prefix bi: <http://www.biopax.org/release/biopax-level3.owl#>
select ?s2 ?o2 ?entityReferencen0EN ?s2__rdft ?o2__rdft
where {
?s2 ?entityReferencen0EN ?o2 .
?s2 rdf:type ?s2__rdft .
?o2 rdf:type ?o2__rdft .
{ ?o2 a bi:EntityReference }  UNION  { ?o2 a bi:RnaReference }  UNION  { ?o2 a bi:RnaRegionReference }  UNION  { ?o2 a bi:DnaReference }  UNION  { ?o2 a bi:ProteinReference }  UNION  { ?o2 a bi:SmallMoleculeReference }  UNION  { ?o2 a bi:DnaRegionReference }  .
{ ?s2 bi:name ?name }.
{ ?s2 a bi:Protein }
FILTER (  ?entityReferencen0EN =  bi:entityReference  ) .
FILTER ( CONTAINS(?name,'glucokinase')  ) .
}