docs

Makefile

@@ -58,14 +58,23 @@ pe-clean:
  docker rm $(IM) || echo not made 
 
 pe-build:
- test -f tests/out.tmp && rm tests/out.tmp || echo ok \
- @docker build -t $(IM):$(VERSION) . \
+ (test -f tests/out.tmp && rm tests/out.tmp || echo ok) && \
+ docker build -t $(IM):$(VERSION) . \
  && docker tag $(IM):$(VERSION) $(IM):latest
 
 
 pe-run:
  docker run -p 9083:9083 -e PORT=9083 --name sparqlprog $(IM)
 
+pe-run-bg:
+ docker run -p 9083:9083 -e PORT=9083 --name sparqlprog $(IM) &
+
+pe-test: pe-run-bg
+ sleep 3 ;\
+ python3 ../sparqlprog-python/sparqlprog.py -u http://localhost:9083 -e wd "continent(X)" ;\
+ docker kill sparqlprog ;\
+ docker rm sparqlprog
+
 pe-publish: pe-build
  @docker push $(IM):$(VERSION) \
  && docker push $(IM):latest

examples/ebi-examples.sh

@@ -11,3 +11,12 @@ pq-ebi -l sample
 # everything about https://www.ebi.ac.uk/biosamples/samples/SAMN02847463
 pq-ebi -l "rdf(biosd:'SAMN02847463',P,Y)"
 
+# sample property-values
+pq-ebi -l "sample_property_value(biosd:'SAMN02847463',P,V)"
+
+# distincty attributes
+# (may be too slow...)
+pq-ebi "aggregate(count(distinct(P)),rdf(A,ebi_atlas:propertyType,P),Num)" "x(Num)"
+
+# all distinct attributes (24732)
+pq-ebi --distinct "rdf(A,ebi_atlas:propertyType,P)" "x(P)

install.pl

@@ -9,6 +9,7 @@
 install_optional_packs :-
  writeln(loading),
  ensure_loaded(pack),
+ ensure_loaded(packplus),
  Opts=[interactive(false)],
  \+ \+ clause(optional_pack(_),_),
  forall(optional_pack(X),

pack.pl

@@ -1,6 +1,6 @@
 name('sparqlprog').
 title('Logic programming with SPARQL').
-version('0.2.7').
+version('0.2.8').
 author('Chris Mungall','[email protected]').
 author('Samer Abdallah','[email protected]').
 maintainer('Chris Mungall','[email protected]').
@@ -9,7 +9,6 @@
 requires(dcgutils).
 requires(regex).
 requires(typedef).
-optional_pack(obo_metadata).
 
 
 

packplus.pl

@@ -0,0 +1 @@
+optional_pack(obo_metadata).

prolog/sparqlprog/ontologies/ebi.pl

@@ -2,7 +2,15 @@
  [
 
  sample/1,
- sample_attribute_node/2,
+ sample_attribute/2,
+ attribute_property_value/3,
+ attribute_property_value/4,
+ attribute_property_value/5,
+ sample_biocharacteristic/2,
+ sample_property_value/3,
+ sample_property_value/4,
+ sample_depth/2,
+ sample_environment_feature/2,
 
  identifier/2,
  description/2,
@@ -52,11 +60,48 @@
 
 
 sample(A) :- rdf(A,rdf:type,biosd_terms:'Sample').
-sample_attribute_node(S,A) :-
- rdf(S,biosd_terms:'has-sample-attribute',A).
 
-%sample_
+%! sample_biocharacteristic(?S : ebi_biosample, ?A : ebi_attribute_node) is nondet.
+sample_biocharacteristic(S,A) :-
+ rdf(S,biosd_terms:'has-bio-characteristic',A).
+
+
+
+%! sample_attribute(?S : ebi_biosample, ?A : ebi_attribute_node) is nondet.
+sample_attribute(S,A) :-
+ rdf(S,biosd_terms:'has-sample-attribute',A).
 
+%! attribute_property_value(?A : ebi_attribute_node,
+% ?P : ebi_biosample_property,
+% ?V : ebi_biosample_value) is nondet.
+%
+attribute_property_value(A, P, V) :-
+ rdf(A,ebi_atlas:propertyType,P),
+ rdf(A,ebi_atlas:propertyValue,V).
+attribute_property_value(A, P, V, T) :-
+ rdf(A,rdf:type,T),
+ rdf(A,ebi_atlas:propertyType,P),
+ rdf(A,ebi_atlas:propertyValue,V).
+attribute_property_value(A, P, V, T, G) :-
+ rdf(A,rdf:type,T, G),
+ rdf(A,ebi_atlas:propertyType,P),
+ rdf(A,ebi_atlas:propertyValue,V).
+
+%! sample_property_value(?S : ebi_biosample,
+% ?P : ebi_biosample_property,
+% ?V : ebi_biosample_value) is nondet.
+%
+sample_property_value(S, P, V) :-
+ sample_attribute(S, A),
+ attribute_property_value(A,P,V).
+sample_property_value(S, P, V, T) :-
+ sample_attribute(S, A),
+ attribute_property_value(A,P,V, T).
+
+sample_depth(S,V) :-
+ sample_property_value(S, "depth"^^xsd:string, V).
+sample_environment_feature(S,V) :-
+ sample_property_value(S, "environment feature"^^xsd:string, V).
 
 % B seems to always be identifiers.org
 see_also(A,B) :- rdf(A,rdfs:seeAlso,B).

prolog/sparqlprog/ontologies/uniprot.pl

@@ -62,6 +62,7 @@
 :- type uniprot_annotation ---> atomic_iri.
 :- type uniprot_disease_annotation ---> uniprot_annotation.
 :- type uniprot_xref ---> atomic_iri.
+:- type uniprot_term ---> atomic_iri.
 :- type uniprot_sequence_string ---> string ^^ xsd_type.
 
 %! protein(?P : uniprot_protein) is nondet.
@@ -118,78 +119,45 @@
 
 
 %! is_dbsnp(?X : uniprot_xref) is nondet.
-%
-%
-%
 is_dbsnp(X) :- rdf(X,up:database,updb:dbSNP).
 
 
 
 %! transmembrane_annotation(?A : uniprot_annotation) is nondet.
-%
-%
-%
 transmembrane_annotation(A) :- rdf(A,rdf:type,up:'Transmembrane_Annotation').
 
 %! has_transmembrane_annotation(?P : uniprot_protein, ?A : uniprot_annotation) is nondet.
-%
-%
-%
 has_transmembrane_annotation(P,A) :- annotation(P,A),rdf(A,rdf:type,up:'Transmembrane_Annotation').
 
 
 
 %! mnemonic(?C, ?N) is nondet.
-%
-%
-%
 mnemonic(C,N) :- rdf(C,up:mnemonic,N).
 
 %! encoded_by(?P : uniprot_protein, ?G) is nondet.
-%
-%
-%
 encoded_by(P,G) :- rdf(P,up:encodedBy,G).
 
 
 %! recommended_name(?P : uniprot_protein, ?N) is nondet.
-%
-%
-%
 recommended_name(P,N) :- rdf(P,up:recommendedName,N).
 
 %! has_full_name(?P : uniprot_protein, ?X) is nondet.
-%
-%
-%
 has_full_name(P,X) :- rdf(P,up:recommendedName,N), rdf(N,up:fullName,X).
 
 % for genes only
 
 %! pref_label(?E, ?N) is nondet.
-%
-%
-%
 pref_label(E,N) :- rdf(E,skos:prefLabel,N).
 
 
 %! in_taxon(?P : uniprot_protein, ?T) is nondet.
-%
-%
-%
 in_taxon(P,T) :- rdf(P,up:organism,T).
 
 
 %! annotation(?P : uniprot_protein, ?A : uniprot_annotation) is nondet.
-%
-%
-%
 annotation(P,A) :- rdf(P,up:annotation,A).
 
 %! database(?X : uniprot_xref, ?D) is nondet.
-%
-%
-%
 database(X,D) :- rdf(X,up:database,D).
 
 
@@ -203,30 +171,30 @@
 
 
 %! annotation_range(?P : uniprot_annotation, ?B, ?E, ?R) is nondet.
-%
-%
-%
 annotation_range(P,B,E,R) :-
  rdf(P,up:range,I),
  begin_coord(I,B,R),
  end_coord(I,E,R).
 
 %! protein_begin(?P : uniprot_protein, ?B, ?R) is nondet.
-%
-%
-%
 protein_begin(P,B,R) :-
  rdf(P,up:range,I),
  begin_coord(I,B,R).
 
 
+
+%! classified_with(P : uniprot_protein, T : uniprot_term) is nondet.
+classified_with(P,T) :- rdf(P,up:classifiedWith,t).
+
+
 %! substitution(?A : uniprot_annotation, ?S : uniprot_sequence_string) is nondet.
 %
 % annotation A is associated with a substitution S
 %
 substitution(A,S) :- rdf(A,up:substitution,S).
 
 
+
 %! xref(?P : uniprot_protein, ?X : uniprot_xref) is nondet.
 %
 % P has xref X