human protein (E38)

language code	label	description	aliases	edit
en	human protein	schema of a human protein according to Gene Wiki		edit
eo	homa proteino			edit
fr	protéine humaine			edit
it	proteina umana	schema per descrivere una proteina umana		edit
ja	ヒトのタンパク質	Gene Wikiにおいてヒトのタンパク質を記述するためのスキーマ		edit
pl	ludzkie białko			edit
pt	proteína humana			edit
vec	proteina omana		proteina umana	edit
check entities against this Schemaedit
# BASE <https://raw.githubusercontent.com/SuLab/Genewiki-ShEx/master/proteins/Wikidata-human-proteins.shex>
# Shape Expression for Human proteins in Wikidata

PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX p: <http://www.wikidata.org/prop/>
PREFIX prov: <http://www.w3.org/ns/prov#>
PREFIX pq: <http://www.wikidata.org/prop/qualifier/>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX prv: <http://www.wikidata.org/prop/reference/value/>
PREFIX pr:  <http://www.wikidata.org/prop/reference/>
PREFIX ps: <http://www.wikidata.org/prop/statement/>
PREFIX interpro: <http://micel.io/genewiki/interpro/>

start = @<#wikidata-human-protein>

# wikidata-human protein is the main shape for a human protein data model in Wikidata. Each line between the brackets
# represents the structure that can be enforced to validate human protein annotations in Wikidata
#
# We distinguish between value statements, identifier statements, and erronuous statements.
# Value statements contain either actual values, or pointers to other Wikidata items. Identifier statements capture
# external identifiers, erronuous statements are those that are errors.
#

<#wikidata-human-protein> {
	# STATEMENTS
	p:P31 @<#P31_instance_of> ;
	p:P361 @<#P361_part_of>* ;
	p:P527 @<#P527_has_part>* ;
	p:P680 @<#P680_molecular_function>* ;
	p:P681 @<#P681_cell_component>* ;
	p:P682 @<#P682_biological_process>* ;
	p:P702 @<#P702_encoded_by> ;
	p:P703 @<#P703_found_in_taxon_human> ;
	p:P1910 @<#P1910_decreased_expression_in>* ;

	# IDENTIFIERS
	p:P352 @<#P352_uniprot_id>+ ;
	p:P705 @<#P705_ensembl_protein_id>* ;
	p:P637 @<#P637_RefSeq_Protein_ID>* ; 
    p:P639 @<#P639_RefSeq_RNA_ID>* ; # Currently, we decided to model this, but change in the future if we find a more acurate representation

}

# Shape expressions for Wikidata statements

<#P31_instance_of> {
	ps:P31 [wd:Q8054] ;
	prov:wasDerivedFrom @<#protein_reference>;
}
 
<#P352_uniprot_id> {
	ps:P352 LITERAL ;
	prov:wasDerivedFrom IRI;
}

<#P361_part_of> {
	ps:P361 IRI ;
	prov:wasDerivedFrom @<#interpro_reference>;
}

<#P527_has_part> {
	ps:P527 IRI ;
	prov:wasDerivedFrom IRI;
}

<#P637_RefSeq_Protein_ID> {
	ps:P637 LITERAL ;
	prov:wasDerivedFrom IRI;
}

<#P680_molecular_function> {
	ps:P680 @<#molecular_function> ;
	pq:P459 @<#determination_method>+ ;
	prov:wasDerivedFrom IRI+;
}
<#P681_cell_component> {
	ps:P681 @<#cell_component> ;
	pq:P459 @<#determination_method>+ ;
	prov:wasDerivedFrom IRI+;
}
<#P682_biological_process> {
	ps:P682 @<#biological_process> ;
	pq:P459 @<#determination_method>+ ;
	prov:wasDerivedFrom IRI+;
}

<#P639_RefSeq_RNA_ID> {
	ps:P637 LITERAL ;
	prov:wasDerivedFrom IRI;
}

<#molecular_function> {
    p:P31{
    	ps:P31   [wd:Q14860489]
    }
}

<#cell_component> {
    p:P31{
    	ps:P31   [wd:Q5058355]
    }
}
<#biological_process> {
    p:P31{
    	ps:P31   [wd:Q2996394]
    }
}

<#determination_method> [
  wd:Q23174122	
wd:Q23174671	
wd:Q23174952	
wd:Q23175558	
wd:Q23190827	
wd:Q23190853	
wd:Q23190881	
wd:Q23173789	
wd:Q23174389	
wd:Q23190854	
wd:Q23190856	
wd:Q23190842	
wd:Q23175251	
wd:Q23190637	
wd:Q23190825	
wd:Q23190738	
wd:Q23190852	
wd:Q23190857	
wd:Q23190850	
wd:Q23190826
]

<#P702_encoded_by> {	
     ps:P702 @<#human_gene> ;
	 prov:wasDerivedFrom IRI+ 
} 

<#P703_found_in_taxon_human> {	
     ps:P703 [wd:Q15978631] ;
	 prov:wasDerivedFrom IRI+ 
}

<#P1910_decreased_expression_in> {
	ps:P1910 @<#disease> ;
	pq:P459 @<#determination_method> ;
	prov:wasDerivedFrom IRI+
} 

<#disease> {
	wdt:P699 LITERAL ;
}

# Identifiers
<#P705_ensembl_protein_id> {
	ps:P705 LITERAL ;
	prov:wasDerivedFrom IRI ;
}


# REFERENCES
<#protein_reference> {}

#<#protein_reference> @<#uniprot_reference> OR  
#	@<#literature_reference> 

<#uniprot_reference> {
	pr:P248	[
	    wd:Q905695
	    wd:Q58943792 
	    wd:Q28018111
	] ;
	pr:P352	LITERAL ;
	pr:P813	xsd:dateTime ;
	pr:P854 IRI? ;
	pr:P1640 wd:Q905695? ;
}

<#interpro_reference> {
	pr:P248	@<#interpro_release> ;
	pr:P854 IRI ;
}

<#literature_reference> {
	pr:P248 @<#wikicite> ;
	pr:P813 xsd:dateTime ;
	pr:P854 IRI ;
}

<#wikicite> {
	wdt:P31 [wd:Q13442814] ;
}

<#interpro_release> {
	p:P629 {
		ps:P629	[
		  wd:Q3047275
		  wd:Q58943792
		  wd:Q3331189
		] ;
	}
}

# Subgraphs
<#human_gene> {
	p:P31 {
		ps:P31 [wd:Q7187]
	}
}