Menu
▾
▴
[DL-Learner SVN] SF.net SVN: dl-learner:[3444] trunk/scripts/src/main/java/org/dllearner/ examples/pdb
|
From: <km...@us...> - 2011-11-28 12:11:57
|
Revision: 3444
http://dl-learner.svn.sourceforge.net/dl-learner/?rev=3444&view=rev
Author: kmpf
Date: 2011-11-28 12:11:47 +0000 (Mon, 28 Nov 2011)
Log Message:
-----------
Logger configuration changed.
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
trunk/scripts/src/main/java/org/dllearner/examples/pdb/ProteinDataSet.java
Modified: trunk/scripts/src/main/java/org/dllearner/examples/pdb/AminoAcids.java
===================================================================
--- trunk/scripts/src/main/java/org/dllearner/examples/pdb/AminoAcids.java 2011-11-28 11:22:01 UTC (rev 3443)
+++ trunk/scripts/src/main/java/org/dllearner/examples/pdb/AminoAcids.java 2011-11-28 12:11:47 UTC (rev 3444)
@@ -84,6 +84,7 @@
resprint.put(TRP, new PrintStream(allConfFiles.get(TRP)));
resprint.put(TYR, new PrintStream(allConfFiles.get(TYR)));
resprint.put(SEL, new PrintStream(allConfFiles.get(SEL)));
+ resprint.put(HYT, new PrintStream(allConfFiles.get(HYT)));
} catch (FileNotFoundException e) {
e.printStackTrace();
}
@@ -114,6 +115,7 @@
resourceString.put(TRP, new StringBuffer(init));
resourceString.put(TYR, new StringBuffer(init));
resourceString.put(SEL, new StringBuffer(init));
+ resourceString.put(HYT, new StringBuffer(init));
return resourceString;
}
@@ -172,6 +174,14 @@
return resnum;
}
+ /*
+ * +++ Amino acid properties +++
+ *
+ * the following amino acid properties were gathered from
+ * http://www.russelllab.org/aas/
+ *
+ */
+
public static HashMap<String, String> getAminoAcidNumericArffAttributeMap(){
// Hydrophobicity hydrophilic = 0; Hydrophobic = 1; aromatic = 2; aliphatic = 3
// Polarity unpolar = 0; polar = 1; positive = 2; negative = 3;
@@ -232,7 +242,6 @@
resdata.put(new String("X"), new String("?,?,?")); // unknown residue (e.g. modified amino acids)
resdata.put(new String("Y"), new String("Aromatic,Polar,Large"));
resdata.put(new String("U"), new String("?,?,?"));
-
return resdata;
}
}
Modified: trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java
===================================================================
--- trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java 2011-11-28 11:22:01 UTC (rev 3443)
+++ trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java 2011-11-28 12:11:47 UTC (rev 3444)
@@ -53,7 +53,7 @@
// console, you have to set the threshold and log level to trace
// (but we recommend just setting the log level to trace and observe
// the log file)
- consoleAppender.setThreshold(Level.DEBUG);
+ consoleAppender.setThreshold(Level.INFO);
// logger 2 is writes to a file; it records all debug messages
// (you can choose HTML or TXT)
@@ -66,11 +66,12 @@
fileName = _dataDir + "log/log.html";
} else {
// simple variant: layout2 = new SimpleLayout();
- layout2 = new PatternLayout("%r [%t] %-5p %c :\n%m%n\n");
+ layout2 = new PatternLayout("%d [%t] %-5p %c : %m%n");
fileName = _dataDir + "log/log.txt";
}
try {
fileAppenderNormal = new FileAppender(layout2, fileName, false);
+ fileAppenderNormal.setThreshold(Level.INFO);
} catch (IOException e) {
e.printStackTrace();
}
@@ -79,7 +80,7 @@
_rootLogger.removeAllAppenders();
_rootLogger.addAppender(consoleAppender);
_rootLogger.addAppender(fileAppenderNormal);
- _rootLogger.setLevel(Level.DEBUG);
+ _rootLogger.setLevel(Level.INFO);
Boolean fasta = true;
@@ -102,12 +103,12 @@
Boolean dlLearn = false;
Boolean wekaLearn = false;
- int dataSet = 5;
+ int dataSet = 1;
/*
* data for test purpose
*/
- PDBProtein testProtein = new PDBProtein("1XFF","A");
+ PDBProtein testProtein = new PDBProtein("1EDM","B");
// PDBProtein testProtein = new PDBProtein("1LMB", "3");
// PDBProtein testProtein = new PDBProtein("8ABP");
@@ -146,6 +147,7 @@
if (rdfConf || arff) {
PDBProtein protein = proteinSet.getProteinset().get(i);
+ _logger.info("Start with extracting data from: " + protein.getPdbID());
String pdbDir = _dataDir + protein.getPdbID() + "/";
File directory = new File(pdbDir);
if(! directory.exists()) directory.mkdir();
@@ -153,7 +155,7 @@
//String arffFilePath = pdbDir + protein.getArffFileName();
_logger.info("PDB ID: " + protein.getPdbID());
- _logger.info("chain ID: " + protein.getChainID());
+ _logger.info("Chain ID: " + protein.getChainID());
trainmodel = new PDBIdRdfModel(protein);
@@ -189,6 +191,8 @@
trainmodel.removeStatementsWithObject(residue);
Property isPartOf = ResourceFactory.createProperty("http://purl.org/dc/terms/", "isPartOf");
trainmodel.removeStatementsWithPoperty(isPartOf);
+ Property hasValue = ResourceFactory.createProperty("http://bio2rdf.org/pdb:", "hasValue");
+ trainmodel.removeStatementsWithPoperty(hasValue);
/*
* we add the information which amino acid is the fourth predecessor of which other amino acid
*/
@@ -533,7 +537,7 @@
dataLine.append( "?" );
}
- _logger.info(dataLine);
+ _logger.debug(dataLine);
out.println(dataLine);
}
@@ -623,7 +627,7 @@
dataLine.append( "?" );
}
- _logger.info(dataLine);
+ _logger.debug(dataLine);
out.println(dataLine);
}
Modified: trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBIdRdfModel.java
===================================================================
--- trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBIdRdfModel.java 2011-11-28 11:22:01 UTC (rev 3443)
+++ trunk/scripts/src/main/java/org/dllearner/examples/pdb/PDBIdRdfModel.java 2011-11-28 12:11:47 UTC (rev 3444)
@@ -34,7 +34,7 @@
public class PDBIdRdfModel {
- private static Logger _logger = Logger.getRootLogger();
+ private static Logger _logger = Logger.getLogger(HelixRDFCreator.class);
private PdbRdfModel _pdbIdModel = new PdbRdfModel();
private PdbRdfModel _removedFromModel = new PdbRdfModel();
@@ -48,9 +48,9 @@
this._protein = protein;
this._pdbIdModel = this.getPdbRdfModel();
this.getProtein().setSequence(extractSequence(_pdbIdModel));
- System.out.println("Sequence: " + this.getProtein().getSequence());
+ _logger.info("Sequence: " + this.getProtein().getSequence());
this.getProtein().setSpecies(extractSpecies(_pdbIdModel));
- System.out.println("Species: " + this.getProtein().getSpecies());
+ _logger.info("Species: " + this.getProtein().getSpecies());
createPositivesAndNegatives();
this._positionResource = createPositionResidueMap();
}
@@ -122,7 +122,7 @@
" ?x1 pdb:isImmediatelyBefore ?x4 ." +
" OPTIONAL { ?x5 rdfs:label ?species FILTER (str(?x5) = fn:concat(str(?x2), '/extraction/source/gene/organism')) . } . }";
- // System.out.println(queryString);
+ _logger.debug(queryString);
PdbRdfModel construct = new PdbRdfModel();
Query query = QueryFactory.create(queryString);
@@ -138,10 +138,7 @@
{
RDFNode nextRes = niter.next();
species = nextRes.toString();
-/* QuerySolution soln = results.nextSolution() ;
- Literal l = soln.getLiteral("species") ; // Get a result variable - must be a literal
- species = l.getString();*/
- System.out.println(species);
+ _logger.debug(species);
}
}
finally
@@ -166,7 +163,7 @@
NodeIterator niter = model.listObjectsOfProperty(nextRes, hasValue);
sequence = niter.next().toString();
- System.out.println("Sequence: " + sequence);
+ _logger.debug("Sequence: " + sequence);
}
} ;
return sequence;
@@ -219,9 +216,10 @@
" ?organism rdfs:label ?organismName ." +
" ?seq rdf:type pdb:PolymerSequence ." +
" ?seq pdb:hasValue ?sequence . } " +
- "WHERE { ?x1 rdf:type pdb:Helix ." +
+ "WHERE { " +
+ " OPTIONAL { ?x1 rdf:type pdb:Helix ." +
" ?x1 pdb:beginsAt ?x2 ." +
- " ?x1 pdb:endsAt ?x3 ." +
+ " ?x1 pdb:endsAt ?x3 . } . " +
" ?x3 dcterms:isPartOf ?x4 ." +
" ?x4 rdf:type <http://bio2rdf.org/pdb:Polypeptide(L)> ." +
" ?x5 dcterms:isPartOf ?x4 ." +
@@ -245,7 +243,7 @@
" OPTIONAL { ?organism rdfs:label ?organismName " +
"FILTER (str(?organism) = fn:concat(str(?x4), '/extraction/source/gene/organism')) . } . }";
- System.out.println(queryString);
+ _logger.debug(queryString);
Query query = QueryFactory.create(queryString);
QueryExecution qe = QueryExecutionFactory.create(query, model);
construct.add(qe.execConstruct());
@@ -318,7 +316,6 @@
position = positionLabels.get(0);
} else {
position = new Integer(0);
- _logger.error("");
}
return position.intValue();
}
@@ -347,7 +344,7 @@
"PREFIX x:<" + prop.getNameSpace() + "> " +
"CONSTRUCT { ?x1 x:" + prop.getLocalName()+ " ?x2 . } " +
"WHERE { ?x1 x:" + prop.getLocalName() + " ?x2 . }";
- //System.out.println(queryString);
+ _logger.debug(queryString);
Query query = QueryFactory.create(queryString);
QueryExecution qe = QueryExecutionFactory.create(query, _pdbIdModel);
StmtIterator stmtiter = qe.execConstruct().listStatements();
@@ -365,7 +362,7 @@
"PREFIX x:<" + res.getNameSpace() + "> " +
"CONSTRUCT { ?x1 ?x2 x:" + res.getLocalName() + " . } " +
"WHERE { ?x1 ?x2 x:" + res.getLocalName() + " . }";
- // System.out.println(queryString);
+ _logger.debug(queryString);
Query query = QueryFactory.create(queryString);
QueryExecution qe = QueryExecutionFactory.create(query, _pdbIdModel);
StmtIterator stmtiter = qe.execConstruct().listStatements();
@@ -392,7 +389,7 @@
while (riter.hasNext()) {
// Initialization of variables needed
Resource firstAA = riter.nextResource();
- System.out.println("First AA: " + firstAA.getLocalName());
+ _logger.debug("First AA: " + firstAA.getLocalName());
Resource currentAA = firstAA;
Resource nextAA = firstAA;
boolean inHelix = false;
@@ -427,15 +424,15 @@
} while (currentAA.hasProperty(iib)) ;
}
_positives = pos;
- System.out.println("+++ Positive set +++");
+ _logger.debug("+++ Positive set +++");
for (int i = 0; i < pos.size(); i++){
- System.out.println("Das " + i + "te Element: " + pos.get(i).getLocalName());
+ _logger.debug("Das " + i + "te Element: " + pos.get(i).getLocalName());
}
_negatives = neg;
- System.out.println("+++ Negatvie set +++");
+ _logger.debug("+++ Negatvie set +++");
for (int i = 0; i < neg.size(); i++){
- System.out.println("Das " + i + "te Element: " + neg.get(i).getLocalName());
+ _logger.debug("Das " + i + "te Element: " + neg.get(i).getLocalName());
}
}
@@ -473,84 +470,4 @@
this.getProtein().setFastaFileName(fastaFileName);
this.createFastaFile(dir);
}
-
-
- /*
- * OLD STUFF
- *
- // every element in riter stands for a AA-chain start
- // every first amino acid indicates a new AA-chain
- while (riter.hasNext())
- {
- // Initialization of variables needed
- int i = 0;
- Resource aaOne = riter.nextResource();
- Resource currentaa = aaOne;
- Resource nextaa = aaOne;
- boolean inHelix = false;
- _logger.debug(currentaa.getURI());
- // look if there is a next AA
- do {
- ++i;
- _logger.debug(i);
- //looks weird, but is needed to enter loop even for the last AA which does not have a iib-Property
- currentaa = nextaa;
- NodeIterator resType = model.listObjectsOfProperty(currentaa,type);
-
- // die Guten ins Töpfchen ...
- // if we get an non-empty iterator for pdb:beginsAt the next AAs are within a AA-helix
- if(model.listResourcesWithProperty(ba, currentaa).hasNext() && !inHelix )
- {
- inHelix = true;
- }
- // die Schlechten ins Kröpfchen
- // if we get an non-empty iterator for pdb:endsAt and are already within a AA-helix
- // the AAs AFTER the current ones aren't within a helix
- if (model.listResourcesWithProperty(ea, currentaa).hasNext() && inHelix)
- {
- inHelix = false;
- }
- // get next AA if there is one
- if (model.listObjectsOfProperty(currentaa, iib).hasNext())
- {
- nextaa = model.getProperty(currentaa, iib).getResource();
- }
-
- // add current amino acid to positives or negatives set
- while(resType.hasNext())
- {
- Resource aaType = resType.next().asResource();
- _logger.info(aaType.getURI());
- if (resdata.get(aaType) != null)
- {
- if (inHelix)
- {
- data += i + "," + 1 + "," + resdata.get(aaType);
- }
- else
- {
- data += i + "," + 0 + "," + resdata.get(aaType);
- }
- }
- }
-
- } while (currentaa.hasProperty(iib)) ;
- }
-
- try
- {
- PrintStream out = new PrintStream (new File(arffFilePath));
- out.println(relation);
- out.print(attribute);
- out.print(data);
- out.close();
- }
- catch (FileNotFoundException e )
- {
- System.err.println("Datei " + arffFilePath + " konnte nicht angelegt werden!");
- e.printStackTrace();
- }
-
-
- */
}
Modified: trunk/scripts/src/main/java/org/dllearner/examples/pdb/ProteinDataSet.java
===================================================================
--- trunk/scripts/src/main/java/org/dllearner/examples/pdb/ProteinDataSet.java 2011-11-28 11:22:01 UTC (rev 3443)
+++ trunk/scripts/src/main/java/org/dllearner/examples/pdb/ProteinDataSet.java 2011-11-28 12:11:47 UTC (rev 3444)
@@ -11,8 +11,12 @@
import java.util.HashMap;
import java.util.Random;
+import org.apache.log4j.Logger;
+
public class ProteinDataSet {
+ private static Logger _logger = Logger.getLogger(HelixRDFCreator.class);
+
private static String _dataDir = "../test/pdb/";
@@ -71,11 +75,11 @@
pdbproteins.close();
// get number of lines
int linenr = lines.size();
- System.out.println("File "+ pdbIDlist.getCanonicalPath() + " has " + linenr + " lines.");
+ _logger.info("File "+ pdbIDlist.getCanonicalPath() + " has " + linenr + " lines.");
this._proteinSet = new ArrayList<PDBProtein>(linenr);
for (int i = 0; i < linenr; i++)
{
- System.out.println("LINES element " + i + " contains " + lines.get(i));
+ _logger.info("LINES element " + i + " contains " + lines.get(i));
this._proteinSet.add(
new PDBProtein(
this.getPdbID(i, lines),
@@ -85,7 +89,7 @@
}
catch (IOException e)
{
- System.err.println("File " + pdbIDlist.getAbsolutePath() + " could not be read in!");
+ _logger.error("File " + pdbIDlist.getAbsolutePath() + " could not be read in!");
// TODO Auto-generated catch block
e.printStackTrace();
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
