Menu
▾
▴
[DL-Learner SVN] SF.net SVN: dl-learner:[3513] trunk/scripts/src/main/java/org/dllearner/ examples/pdb
|
From: <km...@us...> - 2011-12-21 14:38:51
|
Revision: 3513
http://dl-learner.svn.sourceforge.net/dl-learner/?rev=3513&view=rev
Author: kmpf
Date: 2011-12-21 14:38:40 +0000 (Wed, 21 Dec 2011)
Log Message:
-----------
Changed a SPARQL query
Modified Paths:
--------------
trunk/scripts/src/main/java/org/dllearner/examples/pdb/AminoAcids.java
trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java
trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBIdRdfModel.java
Modified: trunk/scripts/src/main/java/org/dllearner/examples/pdb/AminoAcids.java
===================================================================
--- trunk/scripts/src/main/java/org/dllearner/examples/pdb/AminoAcids.java 2011-12-21 10:15:12 UTC (rev 3512)
+++ trunk/scripts/src/main/java/org/dllearner/examples/pdb/AminoAcids.java 2011-12-21 14:38:40 UTC (rev 3513)
@@ -31,6 +31,7 @@
public static final Resource TYR = ResourceFactory.createResource("http://bio2rdf.org/pdb:Tyrosine");
public static final Resource SEL = ResourceFactory.createResource("http://bio2rdf.org/pdb:Selenomethionine");
public static final Resource HYT = ResourceFactory.createResource("http://bio2rdf.org/pdb:2-hydroxy-tryptophan");
+ public static final Resource SOC = ResourceFactory.createResource("http://bio2rdf.org/pdb:S-oxyCysteine");
public static HashMap<Resource, File> getAllConfFiles (String dir, String confFileName){
HashMap<Resource, File> aminoAcidsConfFiles = new HashMap<Resource, File>(30);
@@ -56,6 +57,8 @@
aminoAcidsConfFiles.put(TYR, new File(dir + confFileName.replace(".conf", "." + TYR.getLocalName() + ".conf")));
aminoAcidsConfFiles.put(SEL, new File(dir + confFileName.replace(".conf", "." + SEL.getLocalName() + ".conf")));
aminoAcidsConfFiles.put(HYT, new File(dir + confFileName.replace(".conf", "." + HYT.getLocalName() + ".conf")));
+ aminoAcidsConfFiles.put(SOC, new File(dir + confFileName.replace(".conf", "." + SOC.getLocalName() + ".conf")));
+
return aminoAcidsConfFiles;
}
@@ -85,6 +88,8 @@
resprint.put(TYR, new PrintStream(allConfFiles.get(TYR)));
resprint.put(SEL, new PrintStream(allConfFiles.get(SEL)));
resprint.put(HYT, new PrintStream(allConfFiles.get(HYT)));
+ resprint.put(SOC, new PrintStream(allConfFiles.get(SOC)));
+
} catch (FileNotFoundException e) {
e.printStackTrace();
}
@@ -116,6 +121,7 @@
resourceString.put(TYR, new StringBuffer(init));
resourceString.put(SEL, new StringBuffer(init));
resourceString.put(HYT, new StringBuffer(init));
+ resourceString.put(SOC, new StringBuffer(init));
return resourceString;
}
Modified: trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java
===================================================================
--- trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java 2011-12-21 10:15:12 UTC (rev 3512)
+++ trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java 2011-12-21 14:38:40 UTC (rev 3513)
@@ -103,15 +103,19 @@
Boolean dlLearn = false;
Boolean wekaLearn = false;
- int dataSet = 1;
+ int dataSet = 5;
/*
* data for test purpose
*/
- PDBProtein testProtein = new PDBProtein("1EDM","B");
-// PDBProtein testProtein = new PDBProtein("1LMB", "3");
-// PDBProtein testProtein = new PDBProtein("8ABP");
+ /* +++ Problem IDs +++
+ * Warum funktionieren die Abfragen mit den untenstehenden PDB IDs nicht???
+ */
+// PDBProtein testProtein = new PDBProtein("1HTR","P");
+// PDBProtein testProtein = new PDBProtein("2W9Y","A");
+ PDBProtein testProtein = new PDBProtein("3A4R","A");
+
/*
* create a training data set
@@ -411,6 +415,7 @@
for (int i = 0 ; i < negatives.size() ; i++ ) {
lp.append("\"" + negatives.get(i).getURI() + "\", ");
try{
+ _logger.info("Negative residue: " + negatives.get(i).getURI());
Statement spo = model.getModel().getProperty(negatives.get(i), type);
resourceStringBuffer.get(spo.getResource()).append("\"" + negatives.get(i).getURI() + "\", ");
} catch (NullPointerException e) {
Modified: trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBIdRdfModel.java
===================================================================
--- trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBIdRdfModel.java 2011-12-21 10:15:12 UTC (rev 3512)
+++ trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBIdRdfModel.java 2011-12-21 14:38:40 UTC (rev 3513)
@@ -7,11 +7,7 @@
import java.util.ArrayList;
import java.util.HashMap;
-import org.apache.log4j.ConsoleAppender;
-import org.apache.log4j.FileAppender;
-import org.apache.log4j.Level;
import org.apache.log4j.Logger;
-import org.apache.log4j.SimpleLayout;
import org.xml.sax.InputSource;
import com.dumontierlab.pdb2rdf.model.PdbRdfModel;
@@ -22,7 +18,6 @@
import com.hp.hpl.jena.query.QueryExecution;
import com.hp.hpl.jena.query.QueryExecutionFactory;
import com.hp.hpl.jena.query.QueryFactory;
-import com.hp.hpl.jena.rdf.model.Literal;
import com.hp.hpl.jena.rdf.model.NodeIterator;
import com.hp.hpl.jena.rdf.model.Property;
import com.hp.hpl.jena.rdf.model.RDFNode;
@@ -205,30 +200,36 @@
"PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> " +
"PREFIX fn: <http://www.w3.org/2005/xpath-functions#> " +
"PREFIX xsd: <http://www.w3.org/2001/XMLSchema#> " +
- "CONSTRUCT { ?x1 pdb:beginsAt ?x2 ." +
- " ?x1 pdb:endsAt ?x3 ." +
- " ?x5 dcterms:isPartOf ?x4 ." +
- " ?x5 rdf:type ?x6 ." +
- " ?x5 pdb:isImmediatelyBefore ?x7 ." +
- " ?x5 pdb:hasChainPosition ?x8 ." +
- " ?x8 rdfs:label ?residuePosition ." +
- " ?x8 pdb:hasValue ?x9 ." +
- " ?organism rdfs:label ?organismName ." +
- " ?seq rdf:type pdb:PolymerSequence ." +
- " ?seq pdb:hasValue ?sequence . } " +
+ "CONSTRUCT { " +
+ " ?x1 pdb:beginsAt ?x2 ." +
+ " ?x1 pdb:endsAt ?x3 ." +
+ " ?x5 dcterms:isPartOf ?x4 ." +
+ " ?x5 rdf:type ?x6 ." +
+ " ?x5 pdb:isImmediatelyBefore ?x7 ." +
+ " ?x5 pdb:hasChainPosition ?x8 ." +
+ " ?x8 pdb:hasValue ?x9 ." +
+ " ?organism rdfs:label ?organismName ." +
+ " ?seq rdf:type pdb:PolymerSequence ." +
+ " ?seq pdb:hasValue ?sequence . " +
+ "} " +
"WHERE { " +
- " OPTIONAL { ?x1 rdf:type pdb:Helix ." +
- " ?x1 pdb:beginsAt ?x2 ." +
- " ?x1 pdb:endsAt ?x3 . } . " +
- " ?x3 dcterms:isPartOf ?x4 ." +
- " ?x4 rdf:type <http://bio2rdf.org/pdb:Polypeptide(L)> ." +
- " ?x5 dcterms:isPartOf ?x4 ." +
- " ?x5 rdf:type ?x6 ." +
+ " OPTIONAL { ?x1 rdf:type pdb:Helix ." +
+ " ?x1 pdb:beginsAt ?x2 ." +
+ " ?x1 pdb:endsAt ?x3 . " +
+ "} . " +
+ " ?x3 dcterms:isPartOf ?x4 ." +
+ " ?x4 rdf:type <http://bio2rdf.org/pdb:Polypeptide(L)> ." +
+ //" <http://bio2rdf.org/pdb:3A4R/chemicalComponent_A0> dcterms:isPartOf ?x4 ." +
+ //" <http://bio2rdf.org/pdb:3A4R/chemicalComponent_A0> rdf:type ?x6 ." +
+ //" OPTIONAL { <http://bio2rdf.org/pdb:3A4R/chemicalComponent_A0> pdb:isImmediatelyBefore ?x7 . } ." +
+ //" <http://bio2rdf.org/pdb:3A4R/chemicalComponent_A0> pdb:hasChainPosition ?x8 ." +
+ " ?x5 dcterms:isPartOf ?x4 . " +
+ " ?x5 rdf:type ?x6 ." +
// with the optional clause i get the information by which amino acid
// a amino acid is followed
- " OPTIONAL { ?x5 pdb:isImmediatelyBefore ?x7 . } . " +
- " ?x5 pdb:hasChainPosition ?x8 ." +
- " ?x8 pdb:hasValue ?x9 Filter (xsd:int(?x9)) .";
+ " OPTIONAL { ?x5 pdb:isImmediatelyBefore ?x7 . } ." +
+ " ?x5 pdb:hasChainPosition ?x8 ." +
+ " ?x8 pdb:hasValue ?x9 Filter (datatype((?x9)) = xsd:integer) .";
if (chainID.length() == 1 && pdbID.length() == 4)
{
queryString +=
@@ -237,11 +238,13 @@
"/chain_" + chainID.toUpperCase() + "> .";
}
queryString +=
- " ?x4 pdb:hasPolymerSequence ?seq . " +
- " ?seq rdf:type pdb:PolymerSequence . " +
- " ?seq pdb:hasValue ?sequence . " +
- " OPTIONAL { ?organism rdfs:label ?organismName " +
- "FILTER (str(?organism) = fn:concat(str(?x4), '/extraction/source/gene/organism')) . } . }";
+ " ?x4 pdb:hasPolymerSequence ?seq . " +
+ " ?seq rdf:type pdb:PolymerSequence . " +
+ " ?seq pdb:hasValue ?sequence . " +
+ " OPTIONAL { ?organism rdfs:label ?organismName " +
+ "FILTER (str(?organism) = fn:concat(str(?x4), '/extraction/source/gene/organism')) . " +
+ "} . " +
+ "}";
_logger.debug(queryString);
Query query = QueryFactory.create(queryString);
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
