def add_literal_by_email(email, predicate, literal):
update = """
PREFIX email: <https://github.com/superphy#hasEmail>
PREFIX p: <%s>
INSERT{
?indv p: '%s'
}
WHERE {
?indv email: '%s'
}""" % (predicate, literal, email)
Endpoint.update(update)
return update
def add_literal_by_email(email, predicate, literal):
update = """
PREFIX email: <https://github.com/superphy#hasEmail>
PREFIX p: <%s>
INSERT{
?indv p: '%s'
}
WHERE {
?indv email: '%s'
}""" % (predicate, literal, email)
Endpoint.update(update)
return update
def get_all_genes(type_="all"):
gene_type = ""
if type_ == "vf":
gene_type = "?Gene rdf:type :virulence_factor ."
elif type_ == "amr":
gene_type = "?Gene rdf:type :antimicrobial_resistance ."
query = prefixes + """
SELECT ?Gene
(GROUP_CONCAT (DISTINCT ?_Gene_Name ; separator=',\\n') AS ?Gene_Name)
(GROUP_CONCAT (DISTINCT ?_Category ; separator=',\\n') AS ?Category)
(GROUP_CONCAT (DISTINCT ?_Sub_Category ; separator=',\\n') AS ?Sub_Category)
WHERE
{
{ ?Gene rdf:type gfvo:gene .
?Gene :has_name ?_Gene_Name .
%s}
OPTIONAL
{ ?Gene :has_category ?_Category}
OPTIONAL
{ ?Gene :has_sub_category ?_Sub_Category}
}
GROUP BY ?Gene
ORDER BY (?Gene)
""" % (gene_type)
return Endpoint.query(query)
def get_gene(name):
query = prefixes + """
SELECT ?Gene
(GROUP_CONCAT (DISTINCT ?_Gene_Name ; separator=',\\n') AS ?Gene_Name)
(GROUP_CONCAT (DISTINCT ?_Accession ; separator=',\\n') AS ?Accession)
(GROUP_CONCAT (DISTINCT ?_Sub_Category ; separator=',\\n') AS ?Sub_Category)
(GROUP_CONCAT (DISTINCT ?_Category_Id ; separator=',\\n') AS ?Category_Id)
(GROUP_CONCAT (DISTINCT ?_ARO_Accession ; separator=',\\n') AS ?ARO_Accession)
(GROUP_CONCAT (DISTINCT ?_ARO_Id ; separator=',\\n') AS ?ARO_Id)
(GROUP_CONCAT (DISTINCT ?_VFO_Id ; separator=',\\n') AS ?VFO_Id)
WHERE
{
{ ?Gene rdf:type gfvo:gene .
?Gene :has_name "%s"^^xsd:string .
?Gene :has_name ?_Gene_Name}
OPTIONAL
{ ?Gene :has_category ?_Category_Id}
OPTIONAL
{ ?Gene :has_has_sub_category ?_Sub_Category}
OPTIONAL
{ ?Gene :has_vfo_id ?_VFO_Id}
OPTIONAL
{ ?Gene :has_aro_accession ?_ARO_Accession}
OPTIONAL
{ ?Gene :has_aro_id ?_ARO_Id}
}
GROUP BY ?Gene
ORDER BY (?Gene)
""" % (name)
return Endpoint.query(query)
def get_regions(genome_list, gene_list):
genes = ""
genomes = ""
for gene in gene_list:
genes = genes + ' "%s" ' % gene
for genome in genome_list:
genomes = genomes + ' :%s ' % genome
query = prefixes + """
SELECT ?Region ?Gene_Name ?Genome
WHERE
{
VALUES ?Genome { %s }
VALUES ?Gene_Names { %s }
?Region a faldo:Region .
?Gene :has_copy ?Region ;
:has_name ?Gene_Name .
?Contig :has_gene ?Region ;
:is_contig_of ?Genome .
FILTER (?Gene_Name = ?Gene_Names)
}
""" % (genomes, genes)
print "query is:", query
return Endpoint.query(query)
def get_categories(type_):
query = prefixes
if type_ == "vf":
query += """
SELECT ?Category ?Subcategory
WHERE {
?cat rdfs:subClassOf vfo:category .
?subcat rdfs:subClassOf ?cat .
?cat rdfs:label ?Category .
?subcat rdfs:label ?Subcategory .
FILTER (?cat != ?subcat && ?cat != vfo:category) .
MINUS { ?cat owl:equivalentClass ?equivclass . }
}
"""
elif type == "amr":
## Temporarily loads vf data until amr categories are figured out
query += """
SELECT ?Category ?Subcategory
WHERE {
?cat rdfs:subClassOf vfo:category .
?subcat rdfs:subClassOf ?cat .
?cat rdfs:label ?Category .
?subcat rdfs:label ?Subcategory .
FILTER (?cat != ?subcat && ?cat != vfo:category) .
MINUS { ?cat owl:equivalentClass ?equivclass . }
}
"""
else:
raise ValueError("Non-valid gene type inserted.")
return Endpoint.query(query)
def last_user():
return Endpoint.query("""
PREFIX user: <https://github.com/superphy#User>
PREFIX RDF_type: <http://www.w3.org/1999/02/22-rdf-syntax-ns#type>
SELECT ?s
WHERE {
?s RDF_type: user:
}
ORDER BY DESC(?s)
LIMIT 1
""")
def last_user():
return Endpoint.query("""
PREFIX user: <https://github.com/superphy#User>
PREFIX RDF_type: <http://www.w3.org/1999/02/22-rdf-syntax-ns#type>
SELECT ?s
WHERE {
?s RDF_type: user:
}
ORDER BY DESC(?s)
LIMIT 1
""")
def insert_user(sparql_id, email):
return Endpoint.update("""
PREFIX user: <https://github.com/superphy#User>
PREFIX owl_NamedIndividual: <http://www.w3.org/2002/07/owl#>
PREFIX RDF_type: <http://www.w3.org/1999/02/22-rdf-syntax-ns#type>
PREFIX indv: <https://github.com/superphy#%s.User>
PREFIX email: <https://github.com/superphy#hasEmail>
INSERT DATA{
indv: RDF_type: owl_NamedIndividual:.
indv: RDF_type: user:.
indv: email: '%s'
}""" % (sparql_id, email.lower()))
def insert_user(sparql_id, email):
return Endpoint.update("""
PREFIX user: <https://github.com/superphy#User>
PREFIX owl_NamedIndividual: <http://www.w3.org/2002/07/owl#>
PREFIX RDF_type: <http://www.w3.org/1999/02/22-rdf-syntax-ns#type>
PREFIX indv: <https://github.com/superphy#%s.User>
PREFIX email: <https://github.com/superphy#hasEmail>
INSERT DATA{
indv: RDF_type: owl_NamedIndividual:.
indv: RDF_type: user:.
indv: email: '%s'
}""" % (sparql_id, email.lower()))
def get_genome_metadata(accession):
string = prefixes + """
PREFIX : <https://github.com/superphy#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX owl: <http://www.w3.org/2002/07/owl#>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX gfvo: <http://www.biointerchange.org/gfvo#>
SELECT ?Genome_Uri
(GROUP_CONCAT (DISTINCT ?_Syndrome ; separator=',\\n') AS ?Syndromes)(GROUP_CONCAT (DISTINCT ?_Accession ; separator=',\\n') AS ?Accession) (GROUP_CONCAT (DISTINCT ?_Biosample_Id ; separator=',\\n') AS ?Biosample_Id)(GROUP_CONCAT (DISTINCT ?_Bioproject_Id ; separator=',\\n') AS ?Bioproject_Id)(GROUP_CONCAT (DISTINCT ?_Strain ; separator=',\\n') AS ?Strain)(GROUP_CONCAT (DISTINCT ?_Serotype_O ; separator=',\\n') AS ?Serotype_O)(GROUP_CONCAT (DISTINCT ?_Serotype_H ; separator=',\\n') AS ?Serotype_H)(GROUP_CONCAT (DISTINCT ?_Scientific_Name ; separator=',\\n') AS ?Scientific_Name)(GROUP_CONCAT (DISTINCT ?_Common_Name ; separator=',\\n') AS ?Common_Name)(GROUP_CONCAT (DISTINCT ?_Isolation_Date ; separator=',\\n') AS ?Isolation_Date)(GROUP_CONCAT (DISTINCT ?_Geographic_Location ; separator=',\\n') AS ?Geographic_Location)
WHERE
{
{ ?Genome_Uri a gfvo:Genome .
?Genome_Uri :has_accession "%s"^^xsd:string}
OPTIONAL
{ ?Genome_Uri :has_bioproject ?_Bioproject_Id}
OPTIONAL
{ ?Genome_Uri :has_biosample ?_Biosample_Id}
OPTIONAL
{ ?Genome_Uri :has_Htype ?_Serotype_H_Uri .
?_Serotype_H_Uri rdfs:label ?_Serotype_H
}
OPTIONAL
{ ?Genome_Uri :has_Otype ?_Serotype_O_Uri .
?_Serotype_O_Uri rdfs:label ?_Serotype_O
}
OPTIONAL
{ ?Genome_Uri :has_geographic_location ?_Geographic_Location}
OPTIONAL
{ ?Genome_Uri :has_strain ?_Strain}
OPTIONAL
{ ?Genome_Uri :has_attribute ?_From_Host_Uri .
?_From_Host_Uri rdf:type :isolation_from_host .
?_From_Host_Uri :has_attribute ?_Host_Uri .
?_Host_Uri :scientific_name ?_Scientific_Name .
?_Host_Uri :common_name ?_Common_Name
}
OPTIONAL
{ ?Genome_Uri :has_isolation_date ?_Isolation_Date}
OPTIONAL
{ ?Genome_Uri :has_isolation_attribute ?_Syndrome_Uri .
?_Syndrome_Uri rdf:type :isolation_syndrome .
?_Syndrome_Uri rdfs:label ?_Syndrome
}
}
GROUP BY ?Genome_Uri
ORDER BY (?Genome_Uri)
""" % (accession)
return Endpoint.query(string)
def get_genome_metadata(accession):
string = prefixes + """
PREFIX : <https://github.com/superphy#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX owl: <http://www.w3.org/2002/07/owl#>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX gfvo: <http://www.biointerchange.org/gfvo#>
SELECT ?Genome_Uri
(GROUP_CONCAT (DISTINCT ?_Syndrome ; separator=',\\n') AS ?Syndromes)(GROUP_CONCAT (DISTINCT ?_Accession ; separator=',\\n') AS ?Accession) (GROUP_CONCAT (DISTINCT ?_Biosample_Id ; separator=',\\n') AS ?Biosample_Id)(GROUP_CONCAT (DISTINCT ?_Bioproject_Id ; separator=',\\n') AS ?Bioproject_Id)(GROUP_CONCAT (DISTINCT ?_Strain ; separator=',\\n') AS ?Strain)(GROUP_CONCAT (DISTINCT ?_Serotype_O ; separator=',\\n') AS ?Serotype_O)(GROUP_CONCAT (DISTINCT ?_Serotype_H ; separator=',\\n') AS ?Serotype_H)(GROUP_CONCAT (DISTINCT ?_Scientific_Name ; separator=',\\n') AS ?Scientific_Name)(GROUP_CONCAT (DISTINCT ?_Common_Name ; separator=',\\n') AS ?Common_Name)(GROUP_CONCAT (DISTINCT ?_Isolation_Date ; separator=',\\n') AS ?Isolation_Date)(GROUP_CONCAT (DISTINCT ?_Geographic_Location ; separator=',\\n') AS ?Geographic_Location)
WHERE
{
{ ?Genome_Uri a gfvo:Genome .
?Genome_Uri :has_accession "%s"^^xsd:string}
OPTIONAL
{ ?Genome_Uri :has_bioproject ?_Bioproject_Id}
OPTIONAL
{ ?Genome_Uri :has_biosample ?_Biosample_Id}
OPTIONAL
{ ?Genome_Uri :has_Htype ?_Serotype_H_Uri .
?_Serotype_H_Uri rdfs:label ?_Serotype_H
}
OPTIONAL
{ ?Genome_Uri :has_Otype ?_Serotype_O_Uri .
?_Serotype_O_Uri rdfs:label ?_Serotype_O
}
OPTIONAL
{ ?Genome_Uri :has_geographic_location ?_Geographic_Location}
OPTIONAL
{ ?Genome_Uri :has_strain ?_Strain}
OPTIONAL
{ ?Genome_Uri :has_attribute ?_From_Host_Uri .
?_From_Host_Uri rdf:type :isolation_from_host .
?_From_Host_Uri :has_attribute ?_Host_Uri .
?_Host_Uri :scientific_name ?_Scientific_Name .
?_Host_Uri :common_name ?_Common_Name
}
OPTIONAL
{ ?Genome_Uri :has_isolation_date ?_Isolation_Date}
OPTIONAL
{ ?Genome_Uri :has_isolation_attribute ?_Syndrome_Uri .
?_Syndrome_Uri rdf:type :isolation_syndrome .
?_Syndrome_Uri rdfs:label ?_Syndrome
}
}
GROUP BY ?Genome_Uri
ORDER BY (?Genome_Uri)
""" % (accession)
return Endpoint.query(string)
def find_regions(gene, genome):
query = prefixes + """
SELECT ?Region
WHERE
{
{ ?Region rdf:type faldo:Region .
?Gene :has_copy ?Region .
?Contig :has_gene ?Region .
?Contig :is_contig_of ?Genome .
?Gene :has_name "%s"^^xsd:string .
#?Genome :has_accession "%s"^^xsd:string .
}
}
""" % (gene, genome)
return Endpoint.query(query)
def get_all_literals():
return Endpoint.query("""
SELECT ?s ?p ?o
WHERE {
{?s ?p ?o
FILTER ISLITERAL(?o)
}
UNION
{?s ?p ?o
FILTER ISLITERAL(?p)
}
UNION
{?s ?p ?o
FILTER ISLITERAL(?s)
}
}""")
def get_all_literals():
return Endpoint.query("""
SELECT ?s ?p ?o
WHERE {
{?s ?p ?o
FILTER ISLITERAL(?o)
}
UNION
{?s ?p ?o
FILTER ISLITERAL(?p)
}
UNION
{?s ?p ?o
FILTER ISLITERAL(?s)
}
}""")
def get_all_syndromes():
"""
input - None
output - list of all the unique syndromes
"""
string = prefixes + """
SELECT ?syndromes
WHERE
{
?_Syndrome_Uri rdf:type :isolation_syndrome .
?_Syndrome_Uri rdfs:label ?syndromes
}
group by ?syndromes"""
syndrome_query = Endpoint.query(string)
syndromes = []
for item in syndrome_query['results']['bindings']:
syndromes.append(item[syndrome_query['head']['vars'][0]]['value'])
return syndromes
def get_all_uri_triples():
return Endpoint.query("""
SELECT ?s ?p ?o
WHERE {
{?s ?p ?o}
MINUS
{?s ?p ?o
FILTER ISLITERAL(?o)
}
MINUS
{
FILTER ISLITERAL(?p)
}
MINUS
{
FILTER ISLITERAL(?s)
}
}""")
def get_all_uri_triples():
return Endpoint.query("""
SELECT ?s ?p ?o
WHERE {
{?s ?p ?o}
MINUS
{?s ?p ?o
FILTER ISLITERAL(?o)
}
MINUS
{
FILTER ISLITERAL(?p)
}
MINUS
{
FILTER ISLITERAL(?s)
}
}""")
def get_all_syndromes():
"""
input - None
output - list of all the unique syndromes
"""
string = prefixes + """
SELECT ?syndromes
WHERE
{
?_Syndrome_Uri rdf:type :isolation_syndrome .
?_Syndrome_Uri rdfs:label ?syndromes
}
group by ?syndromes"""
syndrome_query = Endpoint.query(string)
syndromes = []
for item in syndrome_query['results']['bindings']:
syndromes.append(item[syndrome_query['head']['vars'][0]]['value'])
return syndromes
def get_all_genome_metadata():
string = prefixes + """
SELECT ?Genome_Uri
(GROUP_CONCAT (DISTINCT ?_Syndrome ; separator=',\\n') AS ?Syndromes)(GROUP_CONCAT (DISTINCT ?_Accession ; separator=',\\n') AS ?Accession) (GROUP_CONCAT (DISTINCT ?_Biosample_Id ; separator=',\\n') AS ?Biosample_Id)(GROUP_CONCAT (DISTINCT ?_Bioproject_Id ; separator=',\\n') AS ?Bioproject_Id)(GROUP_CONCAT (DISTINCT ?_Strain ; separator=',\\n') AS ?Strain)(GROUP_CONCAT (DISTINCT ?_Serotype_O ; separator=',\\n') AS ?Serotype_O)(GROUP_CONCAT (DISTINCT ?_Serotype_H ; separator=',\\n') AS ?Serotype_H)(GROUP_CONCAT (DISTINCT ?_Scientific_Name ; separator=',\\n') AS ?Scientific_Name)(GROUP_CONCAT (DISTINCT ?_Common_Name ; separator=',\\n') AS ?Common_Name)(GROUP_CONCAT (DISTINCT ?_Isolation_Date ; separator=',\\n') AS ?Isolation_Date)(GROUP_CONCAT (DISTINCT ?_Geographic_Location ; separator=',\\n') AS ?Geographic_Location)
WHERE
{ { ?Genome_Uri a gfvo:Genome }
OPTIONAL
{ ?Genome_Uri :has_bioproject ?_Bioproject_Id}
OPTIONAL
{ ?Genome_Uri :has_biosample ?_Biosample_Id}
OPTIONAL
{ ?Genome_Uri :has_Htype ?_Serotype_H_Uri .
?_Serotype_H_Uri rdfs:label ?_Serotype_H
}
OPTIONAL
{ ?Genome_Uri :has_Otype ?_Serotype_O_Uri .
?_Serotype_O_Uri rdfs:label ?_Serotype_O
}
OPTIONAL
{ ?Genome_Uri :has_geographic_location ?_Geographic_Location}
OPTIONAL
{ ?Genome_Uri :has_accession ?_Accession}
OPTIONAL
{ ?Genome_Uri :has_strain ?_Strain}
OPTIONAL
{ ?Genome_Uri :has_attribute ?_From_Host_Uri .
?_From_Host_Uri rdf:type :isolation_from_host .
?_From_Host_Uri :has_attribute ?_Host_Uri .
?_Host_Uri :scientific_name ?_Scientific_Name .
?_Host_Uri :common_name ?_Common_Name
}
OPTIONAL
{ ?Genome_Uri :has_isolation_date ?_Isolation_Date}
OPTIONAL
{ ?Genome_Uri :has_isolation_attribute ?_Syndrome_Uri .
?_Syndrome_Uri rdf:type :isolation_syndrome .
?_Syndrome_Uri rdfs:label ?_Syndrome
}
}
GROUP BY ?Genome_Uri
ORDER BY (?Genome_Uri)
"""
return Endpoint.query(string)
def get_all_genome_metadata():
string = prefixes + """
SELECT ?Genome_Uri
(GROUP_CONCAT (DISTINCT ?_Syndrome ; separator=',\\n') AS ?Syndromes)(GROUP_CONCAT (DISTINCT ?_Accession ; separator=',\\n') AS ?Accession) (GROUP_CONCAT (DISTINCT ?_Biosample_Id ; separator=',\\n') AS ?Biosample_Id)(GROUP_CONCAT (DISTINCT ?_Bioproject_Id ; separator=',\\n') AS ?Bioproject_Id)(GROUP_CONCAT (DISTINCT ?_Strain ; separator=',\\n') AS ?Strain)(GROUP_CONCAT (DISTINCT ?_Serotype_O ; separator=',\\n') AS ?Serotype_O)(GROUP_CONCAT (DISTINCT ?_Serotype_H ; separator=',\\n') AS ?Serotype_H)(GROUP_CONCAT (DISTINCT ?_Scientific_Name ; separator=',\\n') AS ?Scientific_Name)(GROUP_CONCAT (DISTINCT ?_Common_Name ; separator=',\\n') AS ?Common_Name)(GROUP_CONCAT (DISTINCT ?_Isolation_Date ; separator=',\\n') AS ?Isolation_Date)(GROUP_CONCAT (DISTINCT ?_Geographic_Location ; separator=',\\n') AS ?Geographic_Location)
WHERE
{ { ?Genome_Uri a gfvo:Genome }
OPTIONAL
{ ?Genome_Uri :has_bioproject ?_Bioproject_Id}
OPTIONAL
{ ?Genome_Uri :has_biosample ?_Biosample_Id}
OPTIONAL
{ ?Genome_Uri :has_Htype ?_Serotype_H_Uri .
?_Serotype_H_Uri rdfs:label ?_Serotype_H
}
OPTIONAL
{ ?Genome_Uri :has_Otype ?_Serotype_O_Uri .
?_Serotype_O_Uri rdfs:label ?_Serotype_O
}
OPTIONAL
{ ?Genome_Uri :has_geographic_location ?_Geographic_Location}
OPTIONAL
{ ?Genome_Uri :has_accession ?_Accession}
OPTIONAL
{ ?Genome_Uri :has_strain ?_Strain}
OPTIONAL
{ ?Genome_Uri :has_attribute ?_From_Host_Uri .
?_From_Host_Uri rdf:type :isolation_from_host .
?_From_Host_Uri :has_attribute ?_Host_Uri .
?_Host_Uri :scientific_name ?_Scientific_Name .
?_Host_Uri :common_name ?_Common_Name
}
OPTIONAL
{ ?Genome_Uri :has_isolation_date ?_Isolation_Date}
OPTIONAL
{ ?Genome_Uri :has_isolation_attribute ?_Syndrome_Uri .
?_Syndrome_Uri rdf:type :isolation_syndrome .
?_Syndrome_Uri rdfs:label ?_Syndrome
}
}
GROUP BY ?Genome_Uri
ORDER BY (?Genome_Uri)
"""
return Endpoint.query(string)
def email_exists(email):
return Endpoint.ask("""ASK {?x <https://github.com/superphy#hasEmail> '%s'}""" % (email))
def get_object_literals(): #Verified
return Endpoint.query("""SELECT ?s ?p ?o WHERE {?s ?p ?o FILTER ISLITERAL(?o)}""")
def get_all_triples(): #Verified
return Endpoint.query("""SELECT * {?s ?p ?o}""")
def get_x_triples(x):
return Endpoint.query("""SELECT * {?s ?p ?o} LIMIT %s""" % (x))
def get_x_triples(x):
return Endpoint.query("""SELECT * {?s ?p ?o} LIMIT %s""" % (x))
def get_object_literals(): #Verified
return Endpoint.query(
"""SELECT ?s ?p ?o WHERE {?s ?p ?o FILTER ISLITERAL(?o)}""")
def get_all_triples(): #Verified
return Endpoint.query("""SELECT * {?s ?p ?o}""")
def delete_all_triples():
Endpoint.update("""DELETE {?s?p?o} WHERE {?s?p?o}""")
def delete_all_triples():
Endpoint.update("""DELETE {?s?p?o} WHERE {?s?p?o}""")
def email_exists(email):
return Endpoint.ask(
"""ASK {?x <https://github.com/superphy#hasEmail> '%s'}""" % (email))
