Menu
▾
▴
[DL-Learner SVN] SF.net SVN: dl-learner:[3391] trunk/scripts
|
From: <km...@us...> - 2011-11-10 08:15:47
|
Revision: 3391
http://dl-learner.svn.sourceforge.net/dl-learner/?rev=3391&view=rev
Author: kmpf
Date: 2011-11-10 08:15:41 +0000 (Thu, 10 Nov 2011)
Log Message:
-----------
Bug fixed SPARQL query that retrieves the data used in the intern PDBRdfModel.
Modified Paths:
--------------
trunk/scripts/pom.xml
trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java
trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBIdRdfModel.java
trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBWekaLearner.java
Modified: trunk/scripts/pom.xml
===================================================================
--- trunk/scripts/pom.xml 2011-11-09 10:02:03 UTC (rev 3390)
+++ trunk/scripts/pom.xml 2011-11-10 08:15:41 UTC (rev 3391)
@@ -64,5 +64,11 @@
<artifactId>commons-compress</artifactId>
<version>1.2</version>
</dependency>
+ <dependency>
+ <groupId>weka</groupId>
+ <artifactId>weka</artifactId>
+ <version>3.6.5</version>
+ </dependency>
+
</dependencies>
</project>
Modified: trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java
===================================================================
--- trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java 2011-11-09 10:02:03 UTC (rev 3390)
+++ trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java 2011-11-10 08:15:41 UTC (rev 3391)
@@ -109,8 +109,10 @@
/*
* data for test purpose
*/
- PDBProtein testProtein = new PDBProtein("1XFF");
+ PDBProtein testProtein = new PDBProtein("1XFF","A");
// PDBProtein testProtein = new PDBProtein("1LMB", "3");
+// PDBProtein testProtein = new PDBProtein("8ABP");
+
/*
* create a training data set
@@ -185,7 +187,8 @@
trainmodel.removeStatementsWithPoperty(endsAt);
Resource residue = ResourceFactory.createResource("http://bio2rdf.org/pdb:Residue");
trainmodel.removeStatementsWithObject(residue);
-
+ Property isPartOf = ResourceFactory.createProperty("http://purl.org/dc/terms/", "isPartOf");
+ trainmodel.removeStatementsWithPoperty(isPartOf);
/*
* we add the information which amino acid is the fourth predecessor of which other amino acid
*/
@@ -228,20 +231,23 @@
* proteins that originate from that particular species. If it already exists
* we will append to it.
*/
- File speciesProteins = new File(_dataDir + protein.getSpecies() + ".pos");
- try {
- String line = protein.getPdbID() + "." + protein.getChainID() + "." + protein.getSpecies() + "\n";
- FileWriter out = new FileWriter(speciesProteins, true);
- _logger.debug("Write " + line + "to file " + speciesProteins.getPath());
- out.write(line);
- out.close();
- } catch (FileNotFoundException e) {
- _logger.error("Could not find file " + speciesProteins.getPath() );
- e.printStackTrace();
- } catch (IOException e) {
- _logger.error("Something went wrong while trying to write to " + speciesProteins.getPath() );
- e.printStackTrace();
+ if (protein.getSpecies() != ""){
+ File speciesProteins = new File(_dataDir + protein.getSpecies() + ".pos");
+
+ try {
+ String line = protein.getPdbID() + "." + protein.getChainID() + "." + protein.getSpecies() + "\n";
+ FileWriter out = new FileWriter(speciesProteins, true);
+ _logger.debug("Write " + line + " to file " + speciesProteins.getPath());
+ out.write(line);
+ out.close();
+ } catch (FileNotFoundException e) {
+ _logger.error("Could not find file " + speciesProteins.getPath() + speciesProteins.getName());
+ e.printStackTrace();
+ } catch (IOException e) {
+ _logger.error("Something went wrong while trying to write to " + speciesProteins.getPath() + speciesProteins.getName());
+ e.printStackTrace();
+ }
}
}
}
Modified: trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBIdRdfModel.java
===================================================================
--- trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBIdRdfModel.java 2011-11-09 10:02:03 UTC (rev 3390)
+++ trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBIdRdfModel.java 2011-11-10 08:15:41 UTC (rev 3391)
@@ -100,12 +100,11 @@
"PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> " +
"PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> " +
"PREFIX fn: <http://www.w3.org/2005/xpath-functions#> " +
- "CONSTRUCT { pdb:" + this.getProtein().getPdbID() + "/extraction/source/gene/organism rdfs:label ?species. }" +
+ "CONSTRUCT { <http://bio2rdf.org/pdb:" + this.getProtein().getPdbID() + "/extraction/source/gene/organism> rdfs:label ?species. }" +
"WHERE { ?x1 dcterms:isPartOf ?x2 ." +
- " ?x1 rdf:type> ?x3 ." +
+ " ?x1 rdf:type ?x3 ." +
" ?x1 pdb:isImmediatelyBefore ?x4 ." +
- " ?x5 rdfs:label ?species " +
- " FILTER (str(?x5) = fn:concat(str(?x2), '/extraction/source/gene/organism')) . }";
+ " OPTIONAL { ?x5 rdfs:label ?species FILTER (str(?x5) = fn:concat(str(?x2), '/extraction/source/gene/organism')) . } . }";
// System.out.println(queryString);
@@ -151,7 +150,7 @@
NodeIterator niter = model.listObjectsOfProperty(nextRes, hasValue);
sequence = niter.next().toString();
- System.out.println(sequence);
+ System.out.println("Sequence: " + sequence);
}
}
return sequence;
@@ -206,23 +205,25 @@
" ?x3 dcterms:isPartOf ?x4 ." +
" ?x4 rdf:type <http://bio2rdf.org/pdb:Polypeptide(L)> ." +
" ?x5 dcterms:isPartOf ?x4 ." +
- " ?x5 rdf:type ?x6 .";
+ " ?x5 rdf:type ?x6 ." +
+ " ?x5 pdb:hasChainPosition ?x8 . " +
+ " OPTIONAL { ?x5 pdb:isImmediatelyBefore ?x7 . } . ";
+
if (chainID.length() == 1 && pdbID.length() == 4)
{
queryString +=
- " ?x5 pdb:hasChainPosition ?x8 ." +
- " ?x8 dcterms:isPartOf pdb:" +
+ " ?x8 dcterms:isPartOf <http://bio2rdf.org/pdb:" +
pdbID.toUpperCase() +
"/chain_" + chainID.toUpperCase() + "> .";
}
queryString +=
- " ?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 ." +
+ " ?seq pdb:hasValue ?sequence . " +
// with the Optional clause i get the information by which amino acid
// a amino acid is followed
- " OPTIONAL { ?x5 pdb:isImmediatelyBefore ?x7 . } .}";
+ " OPTIONAL { ?organism rdfs:label ?organismName " +
+ "FILTER (str(?organism) = fn:concat(str(?x4), '/extraction/source/gene/organism')) . } . }";
System.out.println(queryString);
Query query = QueryFactory.create(queryString);
@@ -324,6 +325,7 @@
while (riter.hasNext()) {
// Initialization of variables needed
Resource firstAA = riter.nextResource();
+ System.out.println("First AA: " + firstAA.getLocalName());
Resource currentAA = firstAA;
Resource nextAA = firstAA;
boolean inHelix = false;
@@ -358,7 +360,16 @@
} while (currentAA.hasProperty(iib)) ;
}
_positives = pos;
+ System.out.println("+++ Positive set +++");
+ for (int i = 0; i < pos.size(); i++){
+ System.out.println("Das " + i + "te Element: " + pos.get(i).getLocalName());
+ }
+
_negatives = neg;
+ System.out.println("+++ Negatvie set +++");
+ for (int i = 0; i < neg.size(); i++){
+ System.out.println("Das " + i + "te Element: " + neg.get(i).getLocalName());
+ }
}
public void createFastaFile(String dir){
@@ -366,23 +377,24 @@
String fastaFilePath = dir + this.getProtein().getFastaFileName();
PrintStream out = new PrintStream (new File(fastaFilePath));
out.println(">" + this.getProtein().getPdbID() + "." + this.getProtein().getChainID() + "." + this.getProtein().getSpecies());
- int seqLength = this.getProtein().getSequence().length();
+ String sequence = this.getProtein().getSequence();
+ int seqLength = sequence.length();
if (seqLength > 80) {
// write sequence in 80 character blocks into file
int beginIndex = 0;
int endIndex = 80;
- for (int i = 1; endIndex <= seqLength; i++ ){
- out.println(this.getProtein().getSequence().substring(beginIndex, endIndex));
- if (seqLength - endIndex <= 80){
- out.println(this.getProtein().getSequence().substring(endIndex, seqLength));
+ while ( endIndex <= seqLength ){
+ out.println(sequence.substring(beginIndex, endIndex));
+ if (seqLength - endIndex < 80){
+ out.println(sequence.substring(endIndex, seqLength));
}
beginIndex = endIndex;
- endIndex += (i * 80);
+ endIndex += 80;
}
} else {
- out.println(this.getProtein().getSequence());
+ out.println(sequence);
}
out.close();
} catch (IOException e) {
Modified: trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBWekaLearner.java
===================================================================
--- trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBWekaLearner.java 2011-11-09 10:02:03 UTC (rev 3390)
+++ trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBWekaLearner.java 2011-11-10 08:15:41 UTC (rev 3391)
@@ -1,11 +1,6 @@
package org.dllearner.examples.pdb;
import java.io.File;
-import java.io.IOException;
-
-import org.apache.log4j.Logger;
-/*
-import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.util.Random;
@@ -20,14 +15,14 @@
import weka.classifiers.bayes.NaiveBayes;
import weka.core.Instances;
import weka.core.converters.ConverterUtils.DataSource;
-*/
+
public class PDBWekaLearner {
private static Logger logger = Logger.getRootLogger();
public PDBWekaLearner (File arffFile) throws IOException{
- /*
+
// create logger (configure this to your needs)
SimpleLayout layout = new SimpleLayout();
FileAppender fileAppender = new FileAppender(layout, "log/sample_log.txt", false);
@@ -75,6 +70,6 @@
} catch (Exception e){
e.printStackTrace();
}
- */
+
}
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
