Reasoning with the Variation Ontology using Apache Jena #OWL #RDF
The Variation Ontology (VariO), "is an ontology for standardized, systematic description of effects, consequences and mechanisms of variations".
In this post I will use the Apache Jena library for RDF to load this ontology. It will then be used to extract a set of variations that are a sub-class of a given class of Variation.
Loading the ontology
The OWL ontology is available for download here: http://www.variationontology.org/download/VariO_0.979.owl. A new RDF model for an OWL ontology is created and the owl file is loaded.OntModel ontModel = ModelFactory.createOntologyModel(); InputStream in = FileManager.get().open(VO_OWL_URL); ontModel.read(in, ""); in.close();
Creating a Reasoner
A OWL Reasoner is then created and associated to the previous model:Reasoner reasoner = ReasonerRegistry.getOWLReasoner(); reasoner=this.reasoner.bindSchema(ontModel);
Creating a random set of variations
A new RDF model is created to hold a few instances of random Variations. For each instance, we add a random property 'my:chromosome', a random property 'my:position' and we associated one of the following type:- vo:VariO_0000029 "modified amino acid", a sub-Class of vo:VariO_0000028 ("post translationally modified protein")
- vo:VariO_0000030 "spliced protein", a sub-Class of vo:VariO_0000028 ("post translationally modified protein")
- vo:VariO_0000033 "effect on protein subcellular localization". It is NOT a sub-class of vo:VariO_0000028
Random rand=new Random();
com.hp.hpl.jena.rdf.model.Model instances = ModelFactory.createDefaultModel();
instances.setNsPrefix("vo",VO_PREFIX);
instances.setNsPrefix("my",MY_URI);
for(int i=0;i< 10;++i)
{
Resource subject= null;
Resource rdftype=null;
switch(i%3)
{
case 0:
{
//modified amino acid
subject=instances.createResource(AnonId.create("modaa_"+i));
rdftype=instances.createResource(VO_PREFIX+"VariO_0000029");
break;
}
case 1:
{
//spliced protein
subject=instances.createResource(AnonId.create("spliced_"+i));
rdftype=instances.createResource(VO_PREFIX+"VariO_0000030");
break;
}
default:
{
//effect on protein subcellular localization
subject=instances.createResource(AnonId.create("subcell_"+i));
rdftype=instances.createResource(VO_PREFIX+"VariO_0000033");
break;
}
}
instances.add(subject, RDF.type, rdftype);
instances.add(subject, hasChromosome, instances.createLiteral("chr"+(1+rand.nextInt(22))));
instances.add(subject, hasPosition, instances.createTypedLiteral(rand.nextInt(1000000)));
}
Reasoning
A new inference model is created using the reasoner and the instances of variation. An iterator is used to only list the variations being a subclasses of vo:VariO_0000028 and having a property "my:chromosome" and a property "my:position".InfModel model = ModelFactory.createInfModel (reasoner, instances);
ExtendedIterator<Statement> sti = model.listStatements(
null, null, model.createResource(VO_PREFIX+"VariO_0000028"));
sti=sti.filterKeep(new Filter<Statement>()
{
@Override
public boolean accept(Statement stmt)
{
return stmt.getSubject().getProperty(hasChromosome)!=null &&
stmt.getSubject().getProperty(hasPosition)!=null
;
}
});Loop over the iterator and print the result:
while(sti.hasNext() )
{
Statement stmt = sti.next();
System.out.println("\t+ " + PrintUtil.print(stmt));
Statement val=stmt.getSubject().getProperty(hasChromosome);
System.out.println("\t\tChromosome:\t"+val.getObject());
val=stmt.getSubject().getProperty(hasPosition);
System.out.println("\t\tPosition:\t"+val.getObject());
}Result
+ (spliced_7 rdf:type http://purl.obolibrary.org/obo/VariO_0000028)
Chromosome: chr7
Position: 134172^^http://www.w3.org/2001/XMLSchema#int
+ (spliced_4 rdf:type http://purl.obolibrary.org/obo/VariO_0000028)
Chromosome: chr13
Position: 674316^^http://www.w3.org/2001/XMLSchema#int
+ (spliced_1 rdf:type http://purl.obolibrary.org/obo/VariO_0000028)
Chromosome: chr22
Position: 457596^^http://www.w3.org/2001/XMLSchema#int
+ (modaa_9 rdf:type http://purl.obolibrary.org/obo/VariO_0000028)
Chromosome: chr12
Position: 803303^^http://www.w3.org/2001/XMLSchema#int
+ (modaa_6 rdf:type http://purl.obolibrary.org/obo/VariO_0000028)
Chromosome: chr15
Position: 794137^^http://www.w3.org/2001/XMLSchema#int
+ (modaa_3 rdf:type http://purl.obolibrary.org/obo/VariO_0000028)
Chromosome: chr14
Position: 34487^^http://www.w3.org/2001/XMLSchema#int
+ (modaa_0 rdf:type http://purl.obolibrary.org/obo/VariO_0000028)
Chromosome: chr15
Position: 536371^^http://www.w3.org/2001/XMLSchema#intFull source code
import java.io.IOException;
import java.io.InputStream;
import java.util.Random;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.hp.hpl.jena.ontology.OntModel;
import com.hp.hpl.jena.ontology.OntModelSpec;
import com.hp.hpl.jena.rdf.model.AnonId;
import com.hp.hpl.jena.rdf.model.InfModel;
import com.hp.hpl.jena.rdf.model.ModelFactory;
import com.hp.hpl.jena.rdf.model.Property;
import com.hp.hpl.jena.rdf.model.Resource;
import com.hp.hpl.jena.rdf.model.Statement;
import com.hp.hpl.jena.reasoner.Reasoner;
import com.hp.hpl.jena.reasoner.ReasonerRegistry;
import com.hp.hpl.jena.util.FileManager;
import com.hp.hpl.jena.util.PrintUtil;
import com.hp.hpl.jena.util.iterator.ExtendedIterator;
import com.hp.hpl.jena.util.iterator.Filter;
import com.hp.hpl.jena.vocabulary.RDF;
public class VariationOntologyReasoner
{
private static final String VO_PREFIX="http://purl.obolibrary.org/obo/";
private static final String MY_URI="urn:my:ontology";
private static final String VO_OWL_URL="http://www.variationontology.org/download/VariO_0.979.owl";
private Reasoner reasoner;
static final private Property hasChromosome=ModelFactory.createDefaultModel().createProperty(MY_URI,"chromosome");
static final private Property hasPosition=ModelFactory.createDefaultModel().createProperty(MY_URI,"position");
private VariationOntologyReasoner() throws IOException
{
OntModel ontModel = ModelFactory.createOntologyModel();
InputStream in = FileManager.get().open(VO_OWL_URL);
ontModel.read(in, "");
in.close();
this.reasoner = ReasonerRegistry.getOWLReasoner();
this.reasoner=this.reasoner.bindSchema(ontModel);
}
private void run()
{
Random rand=new Random();
com.hp.hpl.jena.rdf.model.Model instances = ModelFactory.createDefaultModel();
instances.setNsPrefix("vo",VO_PREFIX);
instances.setNsPrefix("my",MY_URI);
for(int i=0;i< 10;++i)
{
Resource subject= null;
Resource rdftype=null;
switch(i%3)
{
case 0:
{
//modified amino acid
subject=instances.createResource(AnonId.create("modaa_"+i));
rdftype=instances.createResource(VO_PREFIX+"VariO_0000029");
break;
}
case 1:
{
subject=instances.createResource(AnonId.create("spliced_"+i));
rdftype=instances.createResource(VO_PREFIX+"VariO_0000030");
break;
}
default:
{
//effect on protein subcellular localization
subject=instances.createResource(AnonId.create("subcell_"+i));
rdftype=instances.createResource(VO_PREFIX+"VariO_0000033");
break;
}
}
instances.add(subject, RDF.type, rdftype);
instances.add(subject, hasChromosome, instances.createLiteral("chr"+(1+rand.nextInt(22))));
instances.add(subject, hasPosition, instances.createTypedLiteral(rand.nextInt(1000000)));
}
InfModel model = ModelFactory.createInfModel (reasoner, instances);
ExtendedIterator<Statement> sti = model.listStatements(null, null, model.createResource(VO_PREFIX+"VariO_0000028"));
sti=sti.filterKeep(new Filter<Statement>()
{
@Override
public boolean accept(Statement stmt)
{
return stmt.getSubject().getProperty(hasChromosome)!=null &&
stmt.getSubject().getProperty(hasPosition)!=null
;
}
});
while(sti.hasNext() )
{
Statement stmt = sti.next();
System.out.println("\t+ " + PrintUtil.print(stmt));
Statement val=stmt.getSubject().getProperty(hasChromosome);
System.out.println("\t\tChromosome:\t"+val.getObject());
val=stmt.getSubject().getProperty(hasPosition);
System.out.println("\t\tPosition:\t"+val.getObject());
}
}
public static void main(String[] args) throws Exception
{
VariationOntologyReasoner app=new VariationOntologyReasoner();
app.run();
}
}That's it,
Pierre
