Last active
December 19, 2015 02:18
-
-
Save nakao/5881623 to your computer and use it in GitHub Desktop.
List human proteins which have natural variants described also in OMIM. The query returns protein id, gene label, mutation(cf. A301R), omim id and citation id at UniProt SPARQL endpoint http://beta.sparql.uniprot.org/sparql .
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
PREFIX rdf:<http://www.w3.org/1999/02/22-rdf-syntax-ns#> | |
PREFIX skos:<http://www.w3.org/2004/02/skos/core#> | |
PREFIX owl:<http://www.w3.org/2002/07/owl#> | |
PREFIX bibo:<http://purl.org/ontology/bibo/> | |
PREFIX dc:<http://purl.org/dc/terms/> | |
PREFIX xsd:<http://www.w3.org/2001/XMLSchema#> | |
PREFIX up:<http://purl.uniprot.org/core/> | |
PREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#> | |
SELECT ?protein ?geneLabel ?hgsv ?omim ?citation | |
WHERE | |
{ | |
?protein a up:Protein ; | |
up:organism <http://purl.uniprot.org/taxonomy/9606> ; # Human | |
up:annotation ?annotation ; | |
up:annotation ?diseaseA ; | |
up:encodedBy ?gene . | |
?gene skos:prefLabel ?geneLabel . | |
?diseaseA a up:Disease_Annotation ; # Disease annotated protein | |
up:disease ?disease . | |
?disease up:mnemonic ?dMnemonic ; # Disease initials, like "ALS" | |
rdfs:seeAlso ?omim . | |
?omim up:database <http://purl.uniprot.org/database/MIM> . | |
?annotation a up:Natural_Variant_Annotation ; # | |
rdfs:comment ?text ; | |
up:substitution ?sub ; | |
up:range ?range . | |
?range up:begin ?begin ; | |
up:end ?end . | |
?reif a rdf:Statement ; | |
rdf:subject ?protein ; | |
rdf:predicate up:annotation ; | |
rdf:object ?annotation ; | |
up:attribution ?attribution . | |
?attribution up:source ?citation . # citation of Natural Variant Annotation | |
BIND(strlen(?sub) as ?len) # length of substitution of a natural variation | |
FILTER (?len > 1 || ?len = 0) | |
BIND(IF(?len >0, "ins", "del") AS ?insdel) # positive length sub -> ins | |
FILTER (contains(?text, ?dMnemonic)) # Desisese mnemonic contains Natural Variant Annotation text | |
?protein up:sequence ?sequence . | |
?sequence rdf:value ?value ; | |
up:precursor true . | |
BIND(substr(?value,?begin,(?end-?begin)+1) AS ?rep) # At a Natural Variant Annotation position, pick the original amino acid in protein sequence. | |
BIND(concat(?rep,str(?begin),?sub) AS ?hgsv) # make "A301R" mutation code | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment