/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7)
- * Copyright (C) 2011 J Procter, AM Waterhouse, J Engelhardt, LM Lui, G Barton, M Clamp, S Searle
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
*
* This file is part of Jalview.
*
* Jalview is free software: you can redistribute it and/or
* modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
- *
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *
* Jalview is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR
* PURPOSE. See the GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
*/
package MCview;
-import java.io.*;
-import java.util.*;
-
-import java.awt.*;
-
-import javax.xml.parsers.ParserConfigurationException;
-
-import org.xml.sax.SAXException;
-
-import fr.orsay.lri.varna.exceptions.ExceptionFileFormatOrSyntax;
-import fr.orsay.lri.varna.exceptions.ExceptionLoadingFailed;
-import fr.orsay.lri.varna.exceptions.ExceptionPermissionDenied;
+import java.awt.Color;
+import java.io.IOException;
+import java.lang.reflect.Constructor;
+import java.util.ArrayList;
+import java.util.Hashtable;
+import java.util.List;
+import java.util.Vector;
-import jalview.datamodel.*;
+import jalview.analysis.AlignSeq;
+import jalview.datamodel.Alignment;
+import jalview.datamodel.AlignmentAnnotation;
+import jalview.datamodel.AlignmentI;
+import jalview.datamodel.PDBEntry;
+import jalview.datamodel.SequenceI;
import jalview.io.FileParse;
-import jalview.io.RnamlFile;
-import jalview.ws.jws1.Annotate3D;
+import jalview.util.MessageManager;
public class PDBfile extends jalview.io.AlignFile
{
- public Vector chains;
+ private static String CALC_ID_PREFIX = "JalviewPDB";
+
+ public Vector<PDBChain> chains;
public String id;
/**
- * set to true to add chain alignment annotation as visible annotation.
+ * set to true to add derived sequence annotations (temp factor read from
+ * file, or computed secondary structure) to the alignment
+ */
+ private boolean visibleChainAnnotation = false;
+
+ /*
+ * Set true to predict secondary structure (using JMol for protein, Annotate3D
+ * for RNA)
*/
- boolean VisibleChainAnnotation = false;
+ private boolean predictSecondaryStructure = true;
- public PDBfile(String inFile, String inType) throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed, InterruptedException
+ /*
+ * Set true (with predictSecondaryStructure=true) to predict secondary
+ * structure using an external service (currently Annotate3D for RNA only)
+ */
+ private boolean externalSecondaryStructure = false;
+
+ public PDBfile(boolean addAlignmentAnnotations, boolean predictSecondaryStructure,
+ boolean externalSecStr)
+ {
+ super();
+ this.visibleChainAnnotation = addAlignmentAnnotations;
+ this.predictSecondaryStructure = predictSecondaryStructure;
+ this.externalSecondaryStructure = externalSecStr;
+ }
+
+ public PDBfile(boolean addAlignmentAnnotations, boolean predictSecondaryStructure,
+ boolean externalSecStr, String file, String protocol)
+ throws IOException
{
- super(inFile, inType);
+ super(false, file, protocol);
+ this.visibleChainAnnotation = addAlignmentAnnotations;
+ this.predictSecondaryStructure = predictSecondaryStructure;
+ this.externalSecondaryStructure = externalSecStr;
+ doParse();
}
- public PDBfile(FileParse source) throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed, InterruptedException
+ public PDBfile(boolean addAlignmentAnnotations, boolean predictSecondaryStructure,
+ boolean externalSecStr, FileParse source) throws IOException
{
- super(source);
+ super(false, source);
+ this.visibleChainAnnotation = addAlignmentAnnotations;
+ this.predictSecondaryStructure = predictSecondaryStructure;
+ this.externalSecondaryStructure = externalSecStr;
+ doParse();
}
public String print()
return null;
}
- public void parse() throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed, InterruptedException
+ public void parse() throws IOException
{
// TODO set the filename sensibly - try using data source name.
id = safeName(getDataName());
-
- chains = new Vector();
- PDBChain tmpchain;
- String line=null;
- boolean modelFlag = false;
- boolean terFlag = false;
- String lastID = "";
+ chains = new Vector<PDBChain>();
+ List<SequenceI> rna = new ArrayList<SequenceI>();
+ List<SequenceI> prot = new ArrayList<SequenceI>();
+ PDBChain tmpchain;
+ String line = null;
+ boolean modelFlag = false;
+ boolean terFlag = false;
+ String lastID = "";
- int index = 0;
- String atomnam = null;
- try
- {
+ int indexx = 0;
+ String atomnam = null;
+ try
+ {
while ((line = nextLine()) != null)
{
if (line.indexOf("HEADER") == 0)
{
id = inFile.getName();
}
- for (int i = 0; i < chains.size(); i++)
+ for (PDBChain chain : chains)
{
- SequenceI dataset = ((PDBChain) chains.elementAt(i)).sequence;
- dataset.setName(id + "|" + dataset.getName());
- PDBEntry entry = new PDBEntry();
- entry.setId(id);
- if (inFile != null)
+ SequenceI chainseq = postProcessChain(chain);
+ if (isRNA(chainseq))
{
- entry.setFile(inFile.getAbsolutePath());
+ rna.add(chainseq);
}
else
{
- // TODO: decide if we should dump the datasource to disk
- entry.setFile(getDataName());
+ prot.add(chainseq);
}
- dataset.addPDBId(entry);
- SequenceI chainseq = dataset.deriveSequence(); // PDBChain objects
- // maintain reference to
- // dataset
- seqs.addElement(chainseq);
- if(isRNA(chainseq)==true)
- {
- System.out.println("this is a PDB format and RNA sequence");
- Annotate3D an3d = new Annotate3D(id);
- System.out.println(id);
- //BufferedWriter r = an3d.getReader();
-
- BufferedReader in = new BufferedReader(new FileReader("temp.rnaml"));
-
- String str;
- while ((str = in.readLine()) != null) {
- System.out.println(str);
- System.out.println("toto");
-
- }
- String type = "File";
- RnamlFile rnaml =new RnamlFile("temp.rnaml",type);
- System.out.println("Create rnamfile object");
- //rnaml.parse("temp");
- this.annotations =rnaml.getAnnot();
-
- }
-
- AlignmentAnnotation[] chainannot = chainseq.getAnnotation();
-
- if (chainannot != null)
+ }
+ if (predictSecondaryStructure)
+ {
+ predictSecondaryStructure(rna, prot);
+ }
+ } catch (OutOfMemoryError er)
+ {
+ System.out.println("OUT OF MEMORY LOADING PDB FILE");
+ throw new IOException(
+ MessageManager
+ .getString("exception.outofmemory_loading_pdb_file"));
+ } catch (NumberFormatException ex)
+ {
+ if (line != null)
+ {
+ System.err.println("Couldn't read number from line:");
+ System.err.println(line);
+ }
+ }
+ markCalcIds();
+ }
+
+ /**
+ * Predict secondary structure for RNA and/or protein sequences and add as
+ * annotations
+ *
+ * @param rnaSequences
+ * @param proteinSequences
+ */
+ protected void predictSecondaryStructure(List<SequenceI> rnaSequences,
+ List<SequenceI> proteinSequences)
+ {
+ /*
+ * Currently using Annotate3D for RNA, but only if the 'use external
+ * prediction' flag is set
+ */
+ if (externalSecondaryStructure && rnaSequences.size() > 0)
+ {
+ try
+ {
+ processPdbFileWithAnnotate3d(rnaSequences);
+ } catch (Exception x)
+ {
+ System.err
+ .println("Exceptions when dealing with RNA in pdb file");
+ x.printStackTrace();
+
+ }
+ }
+
+ /*
+ * Currently using JMol PDB parser for peptide
+ */
+ if (proteinSequences.size() > 0)
+ {
+ try
+ {
+ processPdbFileWithJmol(proteinSequences);
+ } catch (Exception x)
+ {
+ System.err
+ .println("Exceptions from Jmol when processing data in pdb file");
+ x.printStackTrace();
+ }
+ }
+ }
+
+ /**
+ * Process a parsed chain to construct and return a Sequence, and add it to
+ * the list of sequences parsed.
+ *
+ * @param chain
+ * @return
+ */
+ protected SequenceI postProcessChain(PDBChain chain)
+ {
+ SequenceI dataset = chain.sequence;
+ dataset.setName(id + "|" + dataset.getName());
+ PDBEntry entry = new PDBEntry();
+ entry.setId(id);
+ entry.setType(PDBEntry.Type.PDB);
+ entry.setProperty(new Hashtable());
+ if (chain.id != null)
+ {
+ // entry.getProperty().put("CHAIN", chains.elementAt(i).id);
+ entry.setChainCode(String.valueOf(chain.id));
+ }
+ if (inFile != null)
+ {
+ entry.setFile(inFile.getAbsolutePath());
+ }
+ else
+ {
+ // TODO: decide if we should dump the datasource to disk
+ entry.setFile(getDataName());
+ }
+ dataset.addPDBId(entry);
+ // PDBChain objects maintain reference to dataset
+ SequenceI chainseq = dataset.deriveSequence();
+ seqs.addElement(chainseq);
+
+ AlignmentAnnotation[] chainannot = chainseq.getAnnotation();
+
+ if (chainannot != null && visibleChainAnnotation)
+ {
+ for (int ai = 0; ai < chainannot.length; ai++)
+ {
+ chainannot[ai].visible = visibleChainAnnotation;
+ annotations.addElement(chainannot[ai]);
+ }
+ }
+ return chainseq;
+ }
+
+ public static boolean isCalcIdHandled(String calcId)
+ {
+ return calcId != null && (CALC_ID_PREFIX.equals(calcId));
+ }
+
+ public static boolean isCalcIdForFile(AlignmentAnnotation alan,
+ String pdbFile)
+ {
+ return alan.getCalcId() != null
+ && CALC_ID_PREFIX.equals(alan.getCalcId())
+ && pdbFile.equals(alan.getProperty("PDBID"));
+ }
+
+ public static String relocateCalcId(String calcId,
+ Hashtable<String, String> alreadyLoadedPDB) throws Exception
+ {
+ int s = CALC_ID_PREFIX.length(), end = calcId.indexOf(CALC_ID_PREFIX, s);
+ String between = calcId.substring(s, end - 1);
+ return CALC_ID_PREFIX + alreadyLoadedPDB.get(between) + ":"
+ + calcId.substring(end);
+ }
+
+ private void markCalcIds()
+ {
+ for (SequenceI sq : seqs)
+ {
+ if (sq.getAnnotation() != null)
+ {
+ for (AlignmentAnnotation aa : sq.getAnnotation())
{
- for (int ai = 0; ai < chainannot.length; ai++)
+ String oldId = aa.getCalcId();
+ if (oldId == null)
{
-
- chainannot[ai].visible = VisibleChainAnnotation;
- annotations.addElement(chainannot[ai]);
+ oldId = "";
}
+ aa.setCalcId(CALC_ID_PREFIX);
+ aa.setProperty("PDBID", id);
+ aa.setProperty("oldCalcId", oldId);
}
}
- } catch (OutOfMemoryError er)
+ }
+ }
+
+ private void processPdbFileWithJmol(List<SequenceI> prot)
+ throws Exception
+ {
+ try
+ {
+ Class cl = Class.forName("jalview.ext.jmol.PDBFileWithJmol");
+ if (cl != null)
+ {
+ final Constructor constructor = cl.getConstructor(new Class[]
+ { FileParse.class });
+ final Object[] args = new Object[]
+ { new FileParse(getDataName(), type) };
+ Object jmf = constructor.newInstance(args);
+ AlignmentI al = new Alignment((SequenceI[]) cl.getMethod(
+ "getSeqsAsArray", new Class[]
+ {}).invoke(jmf));
+ cl.getMethod("addAnnotations", new Class[]
+ { Alignment.class }).invoke(jmf, al);
+ for (SequenceI sq : al.getSequences())
+ {
+ if (sq.getDatasetSequence() != null)
+ {
+ sq.getDatasetSequence().getPDBId().clear();
+ }
+ else
+ {
+ sq.getPDBId().clear();
+ }
+ }
+ replaceAndUpdateChains(prot, al, AlignSeq.PEP, false);
+ }
+ } catch (ClassNotFoundException q)
{
- System.out.println("OUT OF MEMORY LOADING PDB FILE");
- throw new IOException("Out of memory loading PDB File");
}
- catch (NumberFormatException ex)
+ }
+
+ private void replaceAndUpdateChains(List<SequenceI> prot,
+ AlignmentI al, String pep, boolean b)
+ {
+ List<List<? extends Object>> replaced = AlignSeq
+ .replaceMatchingSeqsWith(seqs, annotations, prot, al, pep,
+ false);
+ for (PDBChain ch : chains)
{
- if (line!=null) {
- System.err.println("Couldn't read number from line:");
- System.err.println(line);
+ int p = 0;
+ for (SequenceI sq : (List<SequenceI>) replaced.get(0))
+ {
+ p++;
+ if (sq == ch.sequence || sq.getDatasetSequence() == ch.sequence)
+ {
+ p = -p;
+ break;
+ }
+ }
+ if (p < 0)
+ {
+ p = -p - 1;
+ // set shadow entry for chains
+ ch.shadow = (SequenceI) replaced.get(1).get(p);
+ ch.shadowMap = ((AlignSeq) replaced.get(2).get(p))
+ .getMappingFromS1(false);
}
}
}
+ private void processPdbFileWithAnnotate3d(List<SequenceI> rna)
+ throws Exception
+ {
+ // System.out.println("this is a PDB format and RNA sequence");
+ // note: we use reflection here so that the applet can compile and run
+ // without the HTTPClient bits and pieces needed for accessing Annotate3D
+ // web service
+ try
+ {
+ Class cl = Class.forName("jalview.ws.jws1.Annotate3D");
+ if (cl != null)
+ {
+ // TODO: use the PDB ID of the structure if one is available, to save
+ // bandwidth and avoid uploading the whole structure to the service
+ Object annotate3d = cl.getConstructor(new Class[]
+ {}).newInstance(new Object[]
+ {});
+ AlignmentI al = ((AlignmentI) cl.getMethod("getRNAMLFor",
+ new Class[]
+ { FileParse.class }).invoke(annotate3d, new Object[]
+ { new FileParse(getDataName(), type) }));
+ for (SequenceI sq : al.getSequences())
+ {
+ if (sq.getDatasetSequence() != null)
+ {
+ if (sq.getDatasetSequence().getPDBId() != null)
+ {
+ sq.getDatasetSequence().getPDBId().clear();
+ }
+ }
+ else
+ {
+ if (sq.getPDBId() != null)
+ {
+ sq.getPDBId().clear();
+ }
+ }
+ }
+ replaceAndUpdateChains(rna, al, AlignSeq.DNA, false);
+ }
+ } catch (ClassNotFoundException x)
+ {
+ // ignore classnotfounds - occurs in applet
+ }
+ ;
+ }
+
/**
* make a friendly ID string.
*
{
for (int i = 0; i < chains.size(); i++)
{
- ((PDBChain) chains.elementAt(i)).makeResidueList();
+ chains.elementAt(i).makeResidueList(visibleChainAnnotation);
}
}
{
for (int i = 0; i < chains.size(); i++)
{
- ((PDBChain) chains.elementAt(i)).makeCaBondList();
+ chains.elementAt(i).makeCaBondList();
}
}
{
for (int i = 0; i < chains.size(); i++)
{
- if (((PDBChain) chains.elementAt(i)).id.equals(id))
+ if (chains.elementAt(i).id.equals(id))
{
- return (PDBChain) chains.elementAt(i);
+ return chains.elementAt(i);
}
}
{
for (int i = 0; i < chains.size(); i++)
{
- ((PDBChain) chains.elementAt(i)).setChargeColours();
+ chains.elementAt(i).setChargeColours();
}
}
{
for (int i = 0; i < chains.size(); i++)
{
- ((PDBChain) chains.elementAt(i)).setChainColours(cs);
+ chains.elementAt(i).setChainColours(cs);
}
}
{
for (int i = 0; i < chains.size(); i++)
{
- ((PDBChain) chains.elementAt(i)).setChainColours(Color.getHSBColor(
- 1.0f / (float) i, .4f, 1.0f));
+ // divide by zero --> infinity --> 255 ;-)
+ chains.elementAt(i).setChainColours(
+ Color.getHSBColor(1.0f / i, .4f, 1.0f));
}
}
- public boolean isRNA(SequenceI seqs)
+
+ public static boolean isRNA(SequenceI seq)
{
- for (int i=0;i<seqs.getLength();i++){
- if((seqs.getCharAt(i)!='A') &&(seqs.getCharAt(i)!='C')&&(seqs.getCharAt(i)!='G')&&(seqs.getCharAt(i)!='U'))
- {
- return false;
- }
- }
-
- return true;
-
-
+ for (char c : seq.getSequence())
+ {
+ if ((c != 'A') && (c != 'C') && (c != 'G') && (c != 'U'))
+ {
+ return false;
+ }
+ }
+
+ return true;
+
}
}