Menu
▾
▴
[DL-Learner SVN] SF.net SVN: dl-learner:[2791] trunk/scripts/src/main/java/org/dllearner/ examples/pdb
|
From: <km...@us...> - 2011-05-12 06:51:52
|
Revision: 2791
http://dl-learner.svn.sourceforge.net/dl-learner/?rev=2791&view=rev
Author: kmpf
Date: 2011-05-12 06:51:43 +0000 (Thu, 12 May 2011)
Log Message:
-----------
Modified Paths:
--------------
trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java
trunk/scripts/src/main/java/org/dllearner/examples/pdb/TrainAndTestSet.java
Added Paths:
-----------
trunk/scripts/src/main/java/org/dllearner/examples/pdb/PdbProtein.java
Modified: trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java
===================================================================
--- trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java 2011-05-11 12:44:11 UTC (rev 2790)
+++ trunk/scripts/src/main/java/org/dllearner/examples/pdb/HelixRDFCreator.java 2011-05-12 06:51:43 UTC (rev 2791)
@@ -71,9 +71,23 @@
private static ArrayList<Resource> positives;
private static ArrayList<Resource> negatives;
-
+ public void setPositives(ArrayList<Resource> pos){
+ positives = pos;
+ }
- private static String saveDir = "../test/pdb/";
+ public void setNegatives(ArrayList<Resource> neg){
+ negatives = neg;
+ }
+
+ public ArrayList<Resource> getPositives(){
+ return positives;
+ }
+
+ public ArrayList<Resource> getNegatives(){
+ return negatives;
+ }
+
+ private static String dataDir = "../test/pdb/";
private static HashMap<Resource, File> confFilePerResidue;
private static File confFileForAll;
@@ -82,79 +96,133 @@
* TODO: remove beginsAt, endsAt from model
*/
public static void main(String[] args) {
+ Boolean test = true;
+ int dataSet = 1;
+ /*
+ * get dataset files
+ */
+ String bt426 = dataDir + "bt426.list";
+ File bt426List = new File(bt426);
+ String plp273 = dataDir + "plp273.list";
+ File plp273List = new File(plp273);
+ String plp364 = dataDir + "plp364.list";
+ File plp364List = new File(plp364);
+ String plp399 = dataDir + "plp399.list";
+ File plp399List = new File(plp399);
+
+ /*
+ * data for test purpose
+ */
+ String pdbID = "3LQH";
+ String chainID = "";
- TrainAndTestSet sets;
+ /*
+ * generate trainset and fill trainmodel
+ */
PdbRdfModel trainmodel = new PdbRdfModel();
- //do{
- String pdbID = "3LQH";
- sets = new TrainAndTestSet(pdbID);
- trainmodel.add(getRdfModelForIds(sets.getTrainset()));
- /*
- * String[] id = {"200L"};
- * trainmodel.add(getRdfModelForIds(id));
- */
+ TrainAndTestSet trainSet = new TrainAndTestSet();
+
+ if (test)
+ {
+ trainSet = new TrainAndTestSet(pdbID, chainID);
+ }
+ else
+ {
+ switch (dataSet) {
+ case 1: trainSet = new TrainAndTestSet(bt426List); break;
+ case 2: trainSet = new TrainAndTestSet(plp273List); break;
+ case 3: trainSet = new TrainAndTestSet(plp364List); break;
+ case 4: trainSet = new TrainAndTestSet(plp399List); break;
+ }
+ }
- // PdbRdfModel testmodel = getRdfModelForIds(sets.getTestset());
+
+ /*
+ * generate a PdbRdfModel for every pdbID
+ */
+
+ for (int i = 0; i < trainSet.getTrainset().length; i++)
+ {
+ String[] pdbIDs = {trainSet.getTrainset()[i].getPdbID()};
+ trainmodel.removeAll();
+ trainmodel.add(getRdfModelForIds(trainSet.getTrainset()[i].getPdbID(), trainSet.getTrainset()[i].getChainID()));
+
/*
- * as we have to handle several amino acid chains we need the first
+ * as we have sometimes to handle several amino acid chains we need the first
* amino acid of every chain, they are returned within a ResIterator
*/
ResIterator niter = getFirstAA(trainmodel);
- ResIterator riter = getFirstAA(trainmodel);
+ ResIterator riter = niter;
/*
* we add some distance Information to our model
*/
trainmodel = addDistanceInfo(trainmodel);
-
+
/*
* take all amino acids which are in helices and put them into the
* global positives ArrayList, and all others in the global negatives ArrayList
*/
createPositivesAndNegatives(niter, trainmodel);
- //} while(positives.size() > 100 && negatives.size() > 100);
-
- SimpleDateFormat df = new SimpleDateFormat("_yyyy_MM_dd_HH_mm");
- String date = df.format(new Date());
- String rdffile = "Helixtrainer" + date + ".rdf";
- String arfffile = "Helixtrainer" + date + ".arff";
- String filename = saveDir + rdffile;
-
- createArffFile(date, arfffile, trainmodel, sets, riter);
- /*
- * remove all triples that contain information about begin and end of helices
- */
- Property ba = ResourceFactory.createProperty("http://bio2rdf.org/pdb:", "beginsAt");
- trainmodel = removeStatementsWithPoperty(trainmodel, ba);
- Property ea = ResourceFactory.createProperty("http://bio2rdf.org/pdb:", "endsAt");
- trainmodel = removeStatementsWithPoperty(trainmodel, ea);
- Resource residue = ResourceFactory.createResource("http://bio2rdf.org/pdb:Residue");
- trainmodel = removeStatementsWithObject(trainmodel, residue);
-
-
- try
- {
+ SimpleDateFormat df = new SimpleDateFormat("_yyyy_MM_dd_HH_mm");
+ String date = df.format(new Date());
+ String rdfFile;
+ String arffFile;
+ if (trainSet.getTrainset()[i].getChainID().length() == 0)
+ {
+ rdfFile = trainSet.getTrainset()[i].getPdbID().toUpperCase() + date + ".rdf";
+ arffFile = trainSet.getTrainset()[i].getPdbID().toUpperCase() + date + ".arff";
+ }
+ else
+ {
+ rdfFile = trainSet.getTrainset()[i].getPdbID().toUpperCase() + "."
+ + trainSet.getTrainset()[i].getChainID().toUpperCase() + date + ".rdf";
+ arffFile = trainSet.getTrainset()[i].getPdbID().toUpperCase() + "."
+ + trainSet.getTrainset()[i].getChainID().toUpperCase() + date + ".arff";
+ }
+ String dir = dataDir + trainSet.getTrainset()[i].getPdbID() + "/";
+ File directory = new File(dir);
+ directory.mkdir();
+ String rdfFilePath = dir + rdfFile;
+ String arffFilePath = dir + arffFile;
+
+ createArffFile(arffFilePath, trainmodel, trainSet, riter);
/*
- * creatConfFile()
- * writes the conf-Files and saves there File-objects in:
- * confFileForAll and confFilePerResidue
+ * remove all triples that contain information about begin and end of helices
*/
- createConfFile(date, rdffile, trainmodel);
- PrintStream out = new PrintStream (new File(filename));
+ Property ba = ResourceFactory.createProperty("http://bio2rdf.org/pdb:", "beginsAt");
+ trainmodel = removeStatementsWithPoperty(trainmodel, ba);
+ Property ea = ResourceFactory.createProperty("http://bio2rdf.org/pdb:", "endsAt");
+ trainmodel = removeStatementsWithPoperty(trainmodel, ea);
+ Resource residue = ResourceFactory.createResource("http://bio2rdf.org/pdb:Residue");
+ trainmodel = removeStatementsWithObject(trainmodel, residue);
- // Output results
- trainmodel.write(out, "RDF/XML");
- // Important - free up resources used running the query
- out.close();
- }
- catch (IOException e)
- {
- System.err.println("OutputStream konnte nicht geschlossen werden!");
- }
-
+ try
+ {
+ /*
+ * creatConfFile()
+ * writes the conf-Files and saves there File-objects in:
+ * confFileForAll and confFilePerResidue
+ */
+ createConfFile(dir, date, rdfFile, trainmodel);
+ PrintStream out = new PrintStream (new File(rdfFilePath));
+
+ // Output results
+ trainmodel.write(out, "RDF/XML");
+
+ // Important - free up resources used running the query
+ out.close();
+ }
+ catch (IOException e)
+ {
+ System.err.println("OutputStream konnte nicht geschlossen werden!");
+ }
+
+ }
+
/*
* load RDF file and perform learn algorithm for every .conf-file
*/
@@ -191,34 +259,41 @@
*/
}
- private static PdbRdfModel getRdfModelForIds(String[] pdbIDs) {
+ private static PdbRdfModel getRdfModelForIds(String pdbID ,String chainID) {
- // i is an Iterator over an XML InputSource
+ /*
+ * i is an Iterator over an XML InputSource
+ */
+ String[] pdbIDs = {pdbID};
Pdb2RdfInputIterator i = new PdbsIterator(pdbIDs);
PdbXmlParser parser = new PdbXmlParser();
PdbRdfModel allmodels = new PdbRdfModel();
-
try {
-
- while (i.hasNext()) {
+ while (i.hasNext())
+ {
final InputSource input = i.next();
PdbRdfModel model = parser.parse(input, new PdbRdfModel());
- // jedes Model muss gleich nach den relevanten Daten durchsucht werden,
- // da ansonsten Probleme mit der Speichergröße auftreten können.
- allmodels.add(getData(model));
-
- }
- } catch (IOException e) {
+ /*
+ * jedes Model muss gleich nach den relevanten Daten durchsucht werden,
+ * da ansonsten Probleme mit der Speichergröße auftreten können.
+ */
+ allmodels.add(getData(model, pdbID, chainID));
+ }
+ }
+ catch (IOException e)
+ {
// TODO Auto-generated catch block
e.printStackTrace();
- } catch (SAXException e) {
+ }
+ catch (SAXException e)
+ {
// TODO Auto-generated catch block
e.printStackTrace();
}
return allmodels;
}
- private static PdbRdfModel getData(PdbRdfModel model) {
+ private static PdbRdfModel getData(PdbRdfModel model, String pdbID, String chainID) {
// Beispiel einer SELECT Abfrage
/* String selectQuery =
@@ -234,30 +309,70 @@
// CONSTRUCT Abfrage
PdbRdfModel construct = new PdbRdfModel();
- /* i do it kind of difficult, but i want to be certain that i only get the sequences of
+ /*
+ * i do it kind of difficult, but i want to be certain that i only get the sequences of
* Polypeptides(L) which contain at least one Helix. Furthermore i collect the information
* about at which position helices begin and end.
- * NOTE: this information has to be removed before oututing the model. But i will use this
+ * NOTE: this information has to be removed before outputing the model. But i will use this
* to check for positive and negative train amino acids
*/
- String queryString =
- "PREFIX pdb: <http://bio2rdf.org/pdb:> " +
- "CONSTRUCT { ?x1 <http://bio2rdf.org/pdb:beginsAt> ?x2 ." +
- " ?x1 <http://bio2rdf.org/pdb:endsAt> ?x3 . " +
- " ?x5 <http://purl.org/dc/terms/isPartOf> ?x4 . " +
- " ?x5 <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> ?x6 ." +
- " ?x5 <http://bio2rdf.org/pdb:isImmediatelyBefore> ?x7 . } " +
- "WHERE { ?x1 <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://bio2rdf.org/pdb:Helix> ." +
- " ?x1 <http://bio2rdf.org/pdb:beginsAt> ?x2 ." +
- " ?x1 <http://bio2rdf.org/pdb:endsAt> ?x3 ." +
- " ?x3 <http://purl.org/dc/terms/isPartOf> ?x4 ." +
- " ?x4 <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://bio2rdf.org/pdb:Polypeptide(L)> ." +
- " ?x5 <http://purl.org/dc/terms/isPartOf> ?x4 ." +
- " ?x5 <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> ?x6 ." +
- // with the Optional clause i get the information by which amino acid
- // a amino acid is followed
- " OPTIONAL { ?x5 <http://bio2rdf.org/pdb:isImmediatelyBefore> ?x7 . } .}";
+ /*
+ * ich brauche noch die selektion der chain und die info über den genursprungsorganismus
+ * rdf:resource="http://bio2rdf.org/pdb:3LQH/chain_A"
+ * http://bio2rdf.org/pdb:3LQH/chain_A/position_1596
+ */
+
+ String queryString = "";
+
+ if (chainID.length() != 1 || pdbID.length() != 4)
+ {
+ queryString =
+ "PREFIX pdb: <http://bio2rdf.org/pdb:> " +
+ "PREFIX dcterms: <http://purl.org/dc/terms/> " +
+ "PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> " +
+ "CONSTRUCT { ?x1 <http://bio2rdf.org/pdb:beginsAt> ?x2 ." +
+ " ?x1 <http://bio2rdf.org/pdb:endsAt> ?x3 . " +
+ " ?x5 <http://purl.org/dc/terms/isPartOf> ?x4 . " +
+ " ?x5 <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> ?x6 ." +
+ " ?x5 <http://bio2rdf.org/pdb:isImmediatelyBefore> ?x7 . } " +
+ "WHERE { ?x1 <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://bio2rdf.org/pdb:Helix> ." +
+ " ?x1 <http://bio2rdf.org/pdb:beginsAt> ?x2 ." +
+ " ?x1 <http://bio2rdf.org/pdb:endsAt> ?x3 ." +
+ " ?x3 <http://purl.org/dc/terms/isPartOf> ?x4 ." +
+ " ?x4 <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://bio2rdf.org/pdb:Polypeptide(L)> ." +
+ " ?x5 <http://purl.org/dc/terms/isPartOf> ?x4 ." +
+ " ?x5 <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> ?x6 ." +
+ // with the Optional clause i get the information by which amino acid
+ // a amino acid is followed
+ " OPTIONAL { ?x5 <http://bio2rdf.org/pdb:isImmediatelyBefore> ?x7 . } .}";
+ }
+ else
+ {
+ queryString =
+ "PREFIX pdb: <http://bio2rdf.org/pdb:> " +
+ "PREFIX dcterms: <http://purl.org/dc/terms/> " +
+ "PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> " +
+ "CONSTRUCT { ?x1 <http://bio2rdf.org/pdb:beginsAt> ?x2 ." +
+ " ?x1 <http://bio2rdf.org/pdb:endsAt> ?x3 . " +
+ " ?x5 <http://purl.org/dc/terms/isPartOf> ?x4 . " +
+ " ?x5 <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> ?x6 ." +
+ " ?x5 <http://bio2rdf.org/pdb:isImmediatelyBefore> ?x7 . } " +
+ "WHERE { ?x1 <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://bio2rdf.org/pdb:Helix> ." +
+ " ?x1 <http://bio2rdf.org/pdb:beginsAt> ?x2 ." +
+ " ?x1 <http://bio2rdf.org/pdb:endsAt> ?x3 ." +
+ " ?x3 <http://purl.org/dc/terms/isPartOf> ?x4 ." +
+ " ?x4 <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://bio2rdf.org/pdb:Polypeptide(L)> ." +
+ " ?x5 <http://purl.org/dc/terms/isPartOf> ?x4 ." +
+ " ?x5 <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> ?x6 ." +
+ " ?x5 <http://bio2rdf.org/pdb:hasChainPosition> ?x8 ." +
+ " ?x8 <http://purl.org/dc/terms/isPartOf> <http://bio2rdf.org/pdb:" + pdbID.toUpperCase() +
+ "/chain_" + chainID.toUpperCase() + "> ." +
+ // with the Optional clause i get the information by which amino acid
+ // a amino acid is followed
+ " OPTIONAL { ?x5 <http://bio2rdf.org/pdb:isImmediatelyBefore> ?x7 . } .}";
+ }
+ System.out.println(queryString);
Query query = QueryFactory.create(queryString);
QueryExecution qe = QueryExecutionFactory.create(query, model);
construct.add(qe.execConstruct());
@@ -394,11 +509,11 @@
}
- private static void createConfFile(String date, String rdffile, PdbRdfModel model){
+ private static void createConfFile(String dir, String date, String rdffile, PdbRdfModel model){
try
{
// the file with all amino acids
- String pdbname = saveDir + "pdb" + date + ".conf";
+ String pdbname = dir + "pdb" + date + ".conf";
confFileForAll = new File(pdbname);
PrintStream out = new PrintStream (confFileForAll);
// add import statements
@@ -407,27 +522,27 @@
out.println();
HashMap<Resource, File> resConfFiles = new HashMap<Resource, File>(30);
- resConfFiles.put(ala, new File(saveDir + ala.getLocalName() + date + ".conf"));
- resConfFiles.put(cys, new File(saveDir + cys.getLocalName() + date + ".conf"));
- resConfFiles.put(asp, new File(saveDir + asp.getLocalName() + date + ".conf"));
- resConfFiles.put(glu, new File(saveDir + glu.getLocalName() + date + ".conf"));
- resConfFiles.put(phe, new File(saveDir + phe.getLocalName() + date + ".conf"));
- resConfFiles.put(gly, new File(saveDir + gly.getLocalName() + date + ".conf"));
- resConfFiles.put(his, new File(saveDir + his.getLocalName() + date + ".conf"));
- resConfFiles.put(ile, new File(saveDir + ile.getLocalName() + date + ".conf"));
- resConfFiles.put(lys, new File(saveDir + lys.getLocalName() + date + ".conf"));
- resConfFiles.put(leu, new File(saveDir + leu.getLocalName() + date + ".conf"));
- resConfFiles.put(met, new File(saveDir + met.getLocalName() + date + ".conf"));
- resConfFiles.put(asn, new File(saveDir + asn.getLocalName() + date + ".conf"));
- resConfFiles.put(pro, new File(saveDir + pro.getLocalName() + date + ".conf"));
- resConfFiles.put(gln, new File(saveDir + gln.getLocalName() + date + ".conf"));
- resConfFiles.put(arg, new File(saveDir + arg.getLocalName() + date + ".conf"));
- resConfFiles.put(ser, new File(saveDir + ser.getLocalName() + date + ".conf"));
- resConfFiles.put(thr, new File(saveDir + thr.getLocalName() + date + ".conf"));
- resConfFiles.put(val, new File(saveDir + val.getLocalName() + date + ".conf"));
- resConfFiles.put(trp, new File(saveDir + trp.getLocalName() + date + ".conf"));
- resConfFiles.put(tyr, new File(saveDir + tyr.getLocalName() + date + ".conf"));
- resConfFiles.put(sel, new File(saveDir + sel.getLocalName() + date + ".conf"));
+ resConfFiles.put(ala, new File(dir + ala.getLocalName() + date + ".conf"));
+ resConfFiles.put(cys, new File(dir + cys.getLocalName() + date + ".conf"));
+ resConfFiles.put(asp, new File(dir + asp.getLocalName() + date + ".conf"));
+ resConfFiles.put(glu, new File(dir + glu.getLocalName() + date + ".conf"));
+ resConfFiles.put(phe, new File(dir + phe.getLocalName() + date + ".conf"));
+ resConfFiles.put(gly, new File(dir + gly.getLocalName() + date + ".conf"));
+ resConfFiles.put(his, new File(dir + his.getLocalName() + date + ".conf"));
+ resConfFiles.put(ile, new File(dir + ile.getLocalName() + date + ".conf"));
+ resConfFiles.put(lys, new File(dir + lys.getLocalName() + date + ".conf"));
+ resConfFiles.put(leu, new File(dir + leu.getLocalName() + date + ".conf"));
+ resConfFiles.put(met, new File(dir + met.getLocalName() + date + ".conf"));
+ resConfFiles.put(asn, new File(dir + asn.getLocalName() + date + ".conf"));
+ resConfFiles.put(pro, new File(dir + pro.getLocalName() + date + ".conf"));
+ resConfFiles.put(gln, new File(dir + gln.getLocalName() + date + ".conf"));
+ resConfFiles.put(arg, new File(dir + arg.getLocalName() + date + ".conf"));
+ resConfFiles.put(ser, new File(dir + ser.getLocalName() + date + ".conf"));
+ resConfFiles.put(thr, new File(dir + thr.getLocalName() + date + ".conf"));
+ resConfFiles.put(val, new File(dir + val.getLocalName() + date + ".conf"));
+ resConfFiles.put(trp, new File(dir + trp.getLocalName() + date + ".conf"));
+ resConfFiles.put(tyr, new File(dir + tyr.getLocalName() + date + ".conf"));
+ resConfFiles.put(sel, new File(dir + sel.getLocalName() + date + ".conf"));
confFilePerResidue = resConfFiles;
@@ -518,19 +633,16 @@
}
}
- private static void createArffFile(String date, String arfffile, PdbRdfModel model, TrainAndTestSet sets, ResIterator riter){
- String arffname = saveDir + "pdb" + date + ".arff";
+ private static void createArffFile(String arffFilePath, PdbRdfModel model, TrainAndTestSet sets, ResIterator riter){
-
-
String relation = "@RELATION ";
for (int i = 0; i < sets.getTrainset().length ; i++){
- System.out.println("Element " + i + "= " + sets.getTrainset()[i]);
+ System.out.println("Element " + i + " = " + sets.getTrainset()[i].getPdbID());
relation += sets.getTrainset()[i];
}
/*
- * ATTRIBUTEs
+ * ATTRIBUTES
*/
// Integer declaring Position in chain
@@ -586,7 +698,8 @@
// every element in riter stands for a AA-chain start
// every first amino acid indicates a new AA-chain
- while (riter.hasNext()) {
+ while (riter.hasNext())
+ {
// Initialization of variables needed
int i = 0;
Resource aaOne = riter.nextResource();
@@ -604,28 +717,36 @@
// 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 ){
+ 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){
+ if (model.listResourcesWithProperty(ea, currentaa).hasNext() && inHelix)
+ {
inHelix = false;
}
// get next AA if there is one
- if (model.listObjectsOfProperty(currentaa, iib).hasNext()){
+ if (model.listObjectsOfProperty(currentaa, iib).hasNext())
+ {
nextaa = model.getProperty(currentaa, iib).getResource();
}
// add current amino acid to positives or negatives set
- while(resType.hasNext()){
+ while(resType.hasNext())
+ {
Resource aaType = resType.next().asResource();
System.out.println(aaType.getURI());
- if (resdata.get(aaType) != null){
- if (inHelix){
+ if (resdata.get(aaType) != null)
+ {
+ if (inHelix)
+ {
data += i + "," + 1 + "," + resdata.get(aaType);
- } else {
+ }
+ else
+ {
data += i + "," + 0 + "," + resdata.get(aaType);
}
}
@@ -634,19 +755,18 @@
} while (currentaa.hasProperty(iib)) ;
}
- try{
- PrintStream out = new PrintStream (new File(arffname));
+ 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 " + arffname + "konnte nicht angelegt werden!");
+ }
+ catch (FileNotFoundException e )
+ {
+ System.err.println("Datei " + arffFilePath + " konnte nicht angelegt werden!");
e.printStackTrace();
}
-
-
-
}
-}
\ No newline at end of file
+}
Added: trunk/scripts/src/main/java/org/dllearner/examples/pdb/PdbProtein.java
===================================================================
--- trunk/scripts/src/main/java/org/dllearner/examples/pdb/PdbProtein.java (rev 0)
+++ trunk/scripts/src/main/java/org/dllearner/examples/pdb/PdbProtein.java 2011-05-12 06:51:43 UTC (rev 2791)
@@ -0,0 +1,43 @@
+package org.dllearner.examples.pdb;
+
+public class PdbProtein {
+
+ private String pdbID;
+ private String chainID;
+ private String species;
+
+ public PdbProtein(String pdbID) {
+ this.pdbID = pdbID;
+ }
+
+ public PdbProtein(String pdbID, String chainID) {
+ this.pdbID = pdbID;
+ this.chainID = chainID;
+ }
+ public PdbProtein() {
+ this.pdbID = "";
+ this.chainID = "";
+ }
+
+ public String getPdbID() {
+ return pdbID;
+ }
+ public void setPdbID(String pdbID) {
+ this.pdbID = pdbID;
+ }
+ public String getChainID() {
+ return chainID;
+ }
+ public void setChainID(String chain) {
+ this.chainID = chain;
+ }
+ public String getSpecies() {
+ return species;
+ }
+ public void setSpecies(String species) {
+ this.species = species;
+ }
+
+
+
+}
Modified: trunk/scripts/src/main/java/org/dllearner/examples/pdb/TrainAndTestSet.java
===================================================================
--- trunk/scripts/src/main/java/org/dllearner/examples/pdb/TrainAndTestSet.java 2011-05-11 12:44:11 UTC (rev 2790)
+++ trunk/scripts/src/main/java/org/dllearner/examples/pdb/TrainAndTestSet.java 2011-05-12 06:51:43 UTC (rev 2791)
@@ -1,5 +1,7 @@
package org.dllearner.examples.pdb;
+import java.io.File;
+import java.io.FileReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.LineNumberReader;
@@ -11,29 +13,40 @@
public class TrainAndTestSet {
- private String[] trainset;
- private String[] testset;
- private HashMap<Integer,String> setentries;
- private ArrayList<String> pdbprotlines;
+ private PdbProtein[] trainset;
- public String[] getTrainset() {
+ public PdbProtein[] getTrainset() {
return trainset;
}
-
- public String[] getTestset() {
- return testset;
+
+
+ public TrainAndTestSet () {
+ String pdbID = "";
+ PdbProtein[] pdbProteins = {new PdbProtein(pdbID)};
+ this.trainset = pdbProteins;
}
public TrainAndTestSet (String pdbID) {
- String[] pdbIDs = {pdbID};
- this.trainset = pdbIDs;
+ PdbProtein[] pdbProteins = {new PdbProtein(pdbID)};
+ this.trainset = pdbProteins;
}
+ public TrainAndTestSet (String pdbID, String chainID) {
+ PdbProtein[] pdbProteins = {new PdbProtein(pdbID, chainID)};
+ this.trainset = pdbProteins;
+ }
+
public TrainAndTestSet (String[] pdbIDs) {
- this.trainset = pdbIDs;
+ PdbProtein pdbProt;
+ PdbProtein[] pdbProteins = new PdbProtein[pdbIDs.length];
+ for (int i = 0; i < pdbIDs.length; i++ )
+ {
+ pdbProt = new PdbProtein(pdbIDs[i]);
+ pdbProteins[i] = pdbProt;
+ }
+ this.trainset = pdbProteins;
}
-
public TrainAndTestSet (int setsize) {
// we read in the online file with all PDB-entries
@@ -41,14 +54,12 @@
try {
pdbEntryType = new URL("ftp://ftp.wwpdb.org/pub/pdb/derived_data/pdb_entry_type.txt");
LineNumberReader pdbproteins = new LineNumberReader(new InputStreamReader(pdbEntryType.openStream()));
-
- // we calculate the number of lines in that file and
- // read all lines into the global variable pdbprotlines
- int linenr = this.getNumberOfLines(pdbproteins);
+ // read all lines in lines
+ ArrayList<String> lines = this.readInFile(pdbproteins);
pdbproteins.close();
-
-
- // System.out.println("PDB Prot File has "+linenr+" lines." );
+ // get number of lines
+ int linenr = lines.size();
+ System.out.println("PDB Prot File has "+linenr+" lines." );
// handling of incorrect setsize values
if ((2*setsize) >= linenr) {
@@ -59,9 +70,7 @@
}
// lets create Train- and Testset
- this.trainset = this.createSet(setsize, linenr);
- this.testset = this.createSet(setsize, linenr);
-
+ this.trainset = this.createSet(setsize, linenr, lines);
} catch (MalformedURLException e) {
// TODO Auto-generated catch block
e.printStackTrace();
@@ -71,77 +80,84 @@
}
}
- // this method counts the number of lines in the read in file and
- // fills pdbprotlines with content
- private int getNumberOfLines (LineNumberReader lnr) {
- try {
- int count = 0;
- ArrayList<String> arraylist = new ArrayList<String>();
- String line;
-
-
- while ((line = lnr.readLine()) != null) {
- arraylist.add(count, line);
- count++;
+
+ public TrainAndTestSet (File pdbIDlist) {
+ try
+ {
+ LineNumberReader pdbproteins = new LineNumberReader(new FileReader(pdbIDlist));
+ ArrayList<String> lines = this.readInFile(pdbproteins);
+ pdbproteins.close();
+ // get number of lines
+ int linenr = lines.size();
+ PdbProtein[] proteins = new PdbProtein[linenr];
+ for (int i = 0; i < linenr; i++)
+ {
+ proteins[i].setPdbID(getpdbid(i, lines));
+ proteins[i].setChainID(getChainID(i, lines));
}
- this.pdbprotlines = arraylist;
-
- return count;
+ this.trainset = proteins;
}
- catch (IOException e) {
+ catch (IOException e)
+ {
// TODO Auto-generated catch block
e.printStackTrace();
- return 0;
}
+
}
-/* private void createArrayList(int linenumber){
+ private ArrayList<String> readInFile (LineNumberReader lnr) {
+ ArrayList<String> arraylist = new ArrayList<String>();
try {
- ArrayList<String> arraylist = new ArrayList<String>();
- LineNumberReader lnr = new LineNumberReader(new FileReader(this.pdbproteins));
- for (int i = 0; i < linenumber; i++) {
- String line = lnr.readLine();
- arraylist.add(i, line);
- // System.out.println("Line "+ i +": "+ line);
+ String line;
+ while ((line = lnr.readLine()) != null)
+ {
+ arraylist.add(line);
}
- this.pdbprotlines = arraylist;
- } catch (FileNotFoundException e) {
+ }
+ catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
- } catch (IOException e) {
- // TODO Auto-generated catch block
- e.printStackTrace();
}
-
+ return arraylist;
}
- */
//creates Sets of PDB IDs equal to setsize
- private String [] createSet(int setsize, int linenr){
- String [] set = new String [setsize];
- if (this.setentries == null) {
- this.setentries = new HashMap<Integer,String>(2*setsize);
- }
- HashMap<Integer,String> setmap = this.setentries;
+ private PdbProtein[] createSet(int setsize, int linenr, ArrayList<String> lines){
+
+ PdbProtein[] set = new PdbProtein[setsize];
+ HashMap<Integer,String> setmap = new HashMap<Integer,String>(2*setsize);
+
Random gen = new Random();
for (int i = 0; i < setsize; i++) {
int lnr = gen.nextInt(linenr);
while (setmap.containsKey(Integer.valueOf(lnr))) {
lnr = gen.nextInt(linenr);
}
- set[i] = this.getpdbid(lnr);
- setmap.put(Integer.valueOf(lnr), set[i]);
+ set[i].setPdbID(this.getpdbid(lnr, lines));
+ setmap.put(Integer.valueOf(lnr), set[i].getPdbID());
}
- this.setentries = setmap;
return set;
}
- private String getpdbid (int lineNumber) {
+ private String getpdbid (int lineNumber, ArrayList<String> lines ) {
// Initialize a LineNumberReader
- ArrayList<String> arraylist = pdbprotlines;
- String line =(String) arraylist.get(lineNumber);
+ String line =(String) lines.get(lineNumber);
String pdb_id = line.substring(0, 4);
return pdb_id;
}
+
+ private String getChainID (int lineNumber, ArrayList<String> lines) {
+ String line =(String) lines.get(lineNumber);
+ String chainID;
+ if (line.length() > 4)
+ {
+ chainID = line.substring(5, 7);
+ }
+ else
+ {
+ chainID = "";
+ }
+ return chainID;
+ }
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
