@Test
public void testSparql() {
String queryStr = "select distinct ?Concept where {[] a ?Concept} LIMIT 10";
Query query = QueryFactory.create(queryStr);
// Remote execution.
try (QueryExecution qexec =
QueryExecutionFactory.sparqlService("http://dbpedia.org/sparql", query)) {
// Set the DBpedia specific timeout.
((QueryEngineHTTP) qexec).addParam("timeout", "10000");
// Execute.
ResultSet rs = qexec.execSelect();
ResultSetFormatter.out(System.out, rs, query);
} catch (Exception e) {
e.printStackTrace();
}
}
@Test
public void testDOQuery2() {
String queryString =
"prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>\n"
+ "prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>\n"
+ "prefix owl: <http://www.w3.org/2002/07/owl#>\n"
+ "\n"
+ "select *\n"
+ "from <http://purl.obolibrary.org/obo/merged/DOID>\n"
+ "\n"
+ "WHERE {\n"
+ " <http://purl.obolibrary.org/obo/DOID_1485> <http://www.w3.org/2000/01/rdf-schema#subClassOf> ?o\n"
+ "}";
Query query = QueryFactory.create(queryString);
System.out.println("String: " + queryString);
QueryExecution qExe =
QueryExecutionFactory.sparqlService("http://sparql.hegroup.org/sparql/", query);
ResultSet results = qExe.execSelect();
ResultSetFormatter.out(System.out, results, query);
}
@Override
public EntityDefinition open(Assembler a, Resource root, Mode mode) {
String prologue = "PREFIX : <" + NS + "> PREFIX list: <http://jena.apache.org/ARQ/list#> ";
Model model = root.getModel();
String qs1 =
StrUtils.strjoinNL(
prologue,
"SELECT * {",
" ?eMap :entityField ?entityField ;",
" :map ?map ;",
" :defaultField ?dftField .",
" OPTIONAL {",
" ?eMap :graphField ?graphField",
" }",
" OPTIONAL {",
" ?eMap :langField ?langField",
" }",
" OPTIONAL {",
" ?eMap :uidField ?uidField",
" }",
"}");
ParameterizedSparqlString pss = new ParameterizedSparqlString(qs1);
pss.setIri("eMap", root.getURI());
Query query1 = QueryFactory.create(pss.toString());
QueryExecution qexec1 = QueryExecutionFactory.create(query1, model);
ResultSet rs1 = qexec1.execSelect();
List<QuerySolution> results = ResultSetFormatter.toList(rs1);
if (results.size() == 0) {
Log.warn(this, "Failed to find a valid EntityMap for : " + root);
throw new TextIndexException("Failed to find a valid EntityMap for : " + root);
}
if (results.size() != 1) {
Log.warn(this, "Multiple matches for EntityMap for : " + root);
throw new TextIndexException("Multiple matches for EntityMap for : " + root);
}
QuerySolution qsol1 = results.get(0);
String entityField = qsol1.getLiteral("entityField").getLexicalForm();
String graphField =
qsol1.contains("graphField") ? qsol1.getLiteral("graphField").getLexicalForm() : null;
String langField =
qsol1.contains("langField") ? qsol1.getLiteral("langField").getLexicalForm() : null;
String defaultField =
qsol1.contains("dftField") ? qsol1.getLiteral("dftField").getLexicalForm() : null;
String uniqueIdField =
qsol1.contains("uidField") ? qsol1.getLiteral("uidField").getLexicalForm() : null;
Multimap<String, Node> mapDefs = HashMultimap.create();
Map<String, Analyzer> analyzerDefs = new HashMap<>();
Statement listStmt = root.getProperty(TextVocab.pMap);
while (listStmt != null) {
RDFNode n = listStmt.getObject();
if (!n.isResource()) {
throw new TextIndexException("Text list node is not a resource : " + n);
}
Resource listResource = n.asResource();
if (listResource.equals(RDF.nil)) {
break; // end of the list
}
Statement listEntryStmt = listResource.getProperty(RDF.first);
if (listEntryStmt == null) {
throw new TextIndexException("Text map list is not well formed. No rdf:first property");
}
n = listEntryStmt.getObject();
if (!n.isResource()) {
throw new TextIndexException("Text map list entry is not a resource : " + n);
}
Resource listEntry = n.asResource();
Statement fieldStatement = listEntry.getProperty(TextVocab.pField);
if (fieldStatement == null) {
throw new TextIndexException("Text map entry has no field property");
}
n = fieldStatement.getObject();
if (!n.isLiteral()) {
throw new TextIndexException("Text map entry field property has no literal value : " + n);
}
String field = n.asLiteral().getLexicalForm();
Statement predicateStatement = listEntry.getProperty(TextVocab.pPredicate);
if (predicateStatement == null) {
throw new TextIndexException("Text map entry has no predicate property");
}
n = predicateStatement.getObject();
if (!n.isURIResource()) {
throw new TextIndexException(
"Text map entry predicate property has non resource value : " + n);
}
mapDefs.put(field, n.asNode());
Statement analyzerStatement = listEntry.getProperty(TextVocab.pAnalyzer);
if (analyzerStatement != null) {
n = analyzerStatement.getObject();
if (!n.isResource()) {
throw new TextIndexException("Text map entry analyzer property is not a resource : " + n);
}
Resource analyzerResource = n.asResource();
Analyzer analyzer = (Analyzer) a.open(analyzerResource);
analyzerDefs.put(field, analyzer);
}
// move on to the next element in the list
listStmt = listResource.getProperty(RDF.rest);
}
// Primary field/predicate
if (defaultField != null) {
Collection<Node> c = mapDefs.get(defaultField);
if (c.isEmpty())
throw new TextIndexException("No definition of primary field '" + defaultField + "'");
}
EntityDefinition docDef = new EntityDefinition(entityField, defaultField);
docDef.setGraphField(graphField);
docDef.setLangField(langField);
docDef.setUidField(uniqueIdField);
for (String f : mapDefs.keys()) {
for (Node p : mapDefs.get(f)) docDef.set(f, p);
}
for (String f : analyzerDefs.keySet()) {
docDef.setAnalyzer(f, analyzerDefs.get(f));
}
return docDef;
}
@Test
public void testDO() {
String doid = "1485";
String queryString =
"prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>\n"
+ "prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>\n"
+ "prefix owl: <http://www.w3.org/2002/07/owl#>\n"
+ "\n"
+ "select ?s ?p ?o \n"
+ "from <http://purl.obolibrary.org/obo/merged/DOID>\n"
+ "\n"
+ "WHERE {\n"
+ " <http://purl.obolibrary.org/obo/DOID_"
+ doid
+ "> ?p ?o\n"
+ "}";
Query query = QueryFactory.create(queryString);
QueryExecution qExe =
QueryExecutionFactory.sparqlService("http://sparql.hegroup.org/sparql/", query);
ResultSet results = qExe.execSelect();
ResultSetFormatter.out(System.out, results, query);
assertNotNull(results);
/*Model model = ModelFactory.createDefaultModel();
Selector selector = new SimpleSelector(null, model.getProperty("<http://www.geneontology.org/formats/oboInOwl#hasDbXref>"), (RDFNode) null); // you need to cast the last null as otherwise the method is ambigious
*/
List<String> dbXref = new ArrayList<>();
List<String> iao = new ArrayList<>();
List<String> exactSynonym = new ArrayList<>();
List<String> alternativeId = new ArrayList<>();
String diseaseLabel;
while (results.hasNext()) {
QuerySolution querySolution = results.nextSolution();
if (querySolution.get("p").toString().matches("rdfs:label ")) {
diseaseLabel = querySolution.get("o").toString();
}
if (querySolution
.get("p")
.toString()
.matches("http://www.geneontology.org/formats/oboInOwl#hasDbXref")) {
System.out.println(
querySolution.get("p").toString() + " " + querySolution.get("o").toString());
dbXref.add(querySolution.get("o").toString());
}
if (querySolution.get("p").toString().matches("http://purl.obolibrary.org/obo/IAO_0000115")) {
System.out.println(
querySolution.get("p").toString() + " " + querySolution.get("o").toString());
iao.add(querySolution.get("o").toString());
}
if (querySolution
.get("p")
.toString()
.matches("http://www.geneontology.org/formats/oboInOwl#hasExactSynonym")) {
System.out.println(
querySolution.get("p").toString() + " " + querySolution.get("o").toString());
exactSynonym.add(querySolution.get("o").toString());
}
if (querySolution
.get("p")
.toString()
.matches("http://www.geneontology.org/formats/oboInOwl#hasAlternativeId")) {
System.out.println(
querySolution.get("p").toString() + " " + querySolution.get("o").toString());
alternativeId.add(querySolution.get("o").toString());
}
}
assertNotNull(dbXref);
assertNotNull(iao);
}
@Test
public void testWURCS() {
String ct =
"RES\n"
+ "1b:b-dglc-HEX-1:5\n"
+ "2s:n-acetyl\n"
+ "3b:b-dglc-HEX-1:5\n"
+ "4s:n-acetyl\n"
+ "5b:b-dman-HEX-1:5\n"
+ "6b:a-dman-HEX-1:5\n"
+ "7b:a-dman-HEX-1:5\n"
+ "8b:a-dman-HEX-1:5\n"
+ "9b:a-dman-HEX-1:5\n"
+ "10b:a-dman-HEX-1:5\n"
+ "LIN\n"
+ "1:1d(2+1)2n\n"
+ "2:1o(4+1)3d\n"
+ "3:3d(2+1)4n\n"
+ "4:3o(4+1)5d\n"
+ "5:5o(3+1)6d\n"
+ "6:6o(2+1)7d\n"
+ "7:5o(6+1)8d\n"
+ "8:8o(3+1)9d\n"
+ "9:8o(6+1)10d\n"
+ "UND\n"
+ "UND1:100.0:100.0\n"
+ "ParentIDs:7|9|10\n"
+ "SubtreeLinkageID1:o(2+1)d\n"
+ "RES\n"
+ "11b:a-dman-HEX-1:5";
ct = ct.replaceAll("\n", "\\\\n");
String queryString =
"PREFIX glycan: <http://purl.jp/bio/12/glyco/glycan#>\n"
+ "PREFIX glytoucan: <http://www.glytoucan.org/glyco/owl/glytoucan#>\n"
+ "PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>\n"
+ "\n"
+ "SELECT DISTINCT ?Sequence\n"
+ "FROM <http://rdf.glytoucan.org>\n"
+ "FROM <http://rdf.glytoucan.org/sequence/wurcs>\n"
+ "\n"
+ "WHERE {\n"
+ "?SaccharideURI a glycan:saccharide .\n"
+ "?SaccharideURI glycan:has_glycosequence ?GlycanSequenceURI .\n"
+ "?GlycanSequenceURI glycan:has_sequence ?Sequence .\n"
+ "?GlycanSequenceURI glycan:in_carbohydrate_format glycan:carbohydrate_format_wurcs .\n"
+ "?SaccharideURI glycan:has_glycosequence ?FormatGlycoSequenceURI .\n"
+ "?FormatGlycoSequenceURI glycan:in_carbohydrate_format glycan:carbohydrate_format_glycoct .\n"
+ "?FormatGlycoSequenceURI glycan:has_sequence"
+ " \""
+ ct
+ "\""
+ "^^xsd:string ."
+ "}";
System.out.println("String: " + queryString);
Query query = QueryFactory.create(queryString);
QueryExecution qExe =
QueryExecutionFactory.sparqlService("http://test.ts.glytoucan.org/sparql", query);
ResultSet results = qExe.execSelect();
ResultSetFormatter.out(System.out, results, query);
}
@Test
public void testGlycotoucanCTSearch() {
List<Structure> structures = Ebean.find(Structure.class).findList();
String ct = "";
for (Structure structure : structures) {
if (structure.id >= 7400) {
if (structure.glycanst.startsWith("v--")) {
structure.glycanst = structure.glycanst.replace("v--", "FreeEnd--");
}
if (structure.glycanst.startsWith("FreenEnd")) {
structure.glycanst = structure.glycanst.replace("FreenEnd", "FreeEnd");
}
if (structure.glycanst.startsWith("FreeEnd?")) {
structure.glycanst = structure.glycanst.replace("FreeEnd?", "FreeEnd--?");
}
if (structure.glycanst.startsWith("<Gly") || structure.glycanst.contains("0.0000u")) {
continue;
}
System.out.println(structure.getGlycanst());
BuilderWorkspace workspace = new BuilderWorkspace(new GlycanRendererAWT());
workspace.setNotation("cfg"); // cfgbw | uoxf | uoxfcol | text
GlycanRenderer renderer = workspace.getGlycanRenderer();
org.eurocarbdb.application.glycanbuilder.Glycan glycan =
org.eurocarbdb.application.glycanbuilder.Glycan.fromString(structure.glycanst);
ct = glycan.toGlycoCTCondensed();
// System.out.println(ct);
// }
// }
/*String ct = "RES\\n" +
"1b:a-dgal-HEX-1:5\\n" +
"2s:n-acetyl\\n" +
"3b:b-dgal-HEX-1:5\\n" +
"4b:a-lgal-HEX-1:5|6:d\\n" +
"5b:a-dgal-HEX-1:5\\n" +
"6s:n-acetyl\\n" +
"7b:b-dglc-HEX-1:5\\n" +
"8s:n-acetyl\\n" +
"LIN\\n" +
"1:1d(2+1)2n\\n" +
"2:1o(3+1)3d\\n" +
"3:3o(2+1)4d\\n" +
"4:3o(3+1)5d\\n" +
"5:5d(2+1)6n\\n" +
"6:1o(6+1)7d\\n" +
"7:7d(2+1)8n";
ct = "RES\n" +
"1b:b-dglc-HEX-1:5\n" +
"2s:n-acetyl\n" +
"3b:b-dglc-HEX-1:5\n" +
"4s:n-acetyl\n" +
"5b:b-dman-HEX-1:5\n" +
"6b:a-dman-HEX-1:5\n" +
"7b:a-dman-HEX-1:5\n" +
"8b:a-lgal-HEX-1:5|6:d\n" +
"LIN\n" +
"1:1d(2+1)2n\n" +
"2:1o(4+1)3d\n" +
"3:3d(2+1)4n\n" +
"4:3o(4+1)5d\n" +
"5:5o(3+1)6d\n" +
"6:5o(6+1)7d\n" +
"7:1o(6+1)8d\n" +
"UND\n" +
"UND1:100.0:100.0\n" +
"ParentIDs:1|3|5|6|7|8\n" +
"SubtreeLinkageID1:x(-1+1)x\n" +
"RES\n" +
"9b:b-dglc-HEX-1:5\n" +
"10s:n-acetyl\n" +
"11b:a-lgal-HEX-1:5|6:d\n" +
"12b:b-dgal-HEX-1:5\n" +
"13b:a-dgro-dgal-NON-2:6|1:a|2:keto|3:d\n" +
"14s:n-acetyl\n" +
"LIN\n" +
"8:9d(2+1)10n\n" +
"9:9o(3+1)11d\n" +
"10:9o(4+1)12d\n" +
"11:12o(-1+2)13d\n" +
"12:13d(5+1)14n\n" +
"UND2:100.0:100.0\n" +
"ParentIDs:1|3|5|6|7|8\n" +
"SubtreeLinkageID1:x(-1+1)x\n" +
"RES\n" +
"15b:b-dglc-HEX-1:5\n" +
"16s:n-acetyl\n" +
"17b:a-lgal-HEX-1:5|6:d\n" +
"18b:b-dgal-HEX-1:5\n" +
"LIN\n" +
"13:15d(2+1)16n\n" +
"14:15o(3+1)17d\n" +
"15:15o(4+1)18d\n" +
"UND3:100.0:100.0\n" +
"ParentIDs:1|3|5|6|7|8\n" +
"SubtreeLinkageID1:x(-1+1)x\n" +
"RES\n" +
"19b:b-dglc-HEX-1:5\n" +
"20s:n-acetyl\n" +
"21b:b-dgal-HEX-1:5\n" +
"LIN\n" +
"16:19d(2+1)20n\n" +
"17:19o(4+1)21d";
*/
ct = ct.replaceAll("\n", "\\\\n").replaceAll("x\\(", "u\\(").replaceAll("\\)x", "\\)u");
System.out.println("new ct: " + ct);
String queryString =
"PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>\n"
+ "PREFIX glycan: <http://purl.jp/bio/12/glyco/glycan#>\n"
+ "PREFIX wurcs: <http://www.glycoinfo.org/glyco/owl/wurcs#>\n"
+ "SELECT DISTINCT ?glycan ?c\n"
+ "# FROM <http://rdf.glycoinfo.org/wurcs/0.5.0>\n"
+ "# FROM <http://rdf.glycoinfo.org/wurcs/0.5.0/ms>\n"
+ "WHERE {\n"
+ " ?glycan a \tglycan:glycosequence ;\n"
+ "\tglycan:in_carbohydrate_format glycan:carbohydrate_format_glycoct ;\n"
+ "\tglycan:has_sequence\n"
+ "\t\t?c filter(contains(?c, \"RES\\n1b:b-dglc-HEX-1\")) .\n"
+
// "\t\t?c filter(contains(?c, \"" + ct + "\" )) .\n" +
"\n"
+ " }\n"
+ " ORDER BY ?glycan\n"
+ "limit 10";
System.out.println("String: " + queryString + "\t\tID: " + structure.id);
Query query = QueryFactory.create(queryString);
QueryExecution qExe =
QueryExecutionFactory.sparqlService("http://test.ts.glytoucan.org/sparql", query);
ResultSet results = qExe.execSelect();
ResultSetFormatter.out(System.out, results, query);
}
}
}