/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2)
- * Copyright (C) 2014 The Jalview Authors
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.9)
+ * Copyright (C) 2015 The Jalview Authors
*
* This file is part of Jalview.
*
*/
package MCview;
-import java.io.*;
-import java.util.*;
-
-import java.awt.*;
-
import jalview.analysis.AlignSeq;
-import jalview.datamodel.*;
+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.util.MessageManager;
+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;
+
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
*/
- boolean VisibleChainAnnotation = false;
+ private boolean visibleChainAnnotation = false;
- boolean processSecondaryStructure=true;
-
+ /*
+ * Set true to predict secondary structure (using JMol for protein, Annotate3D
+ * for RNA)
+ */
+ private boolean predictSecondaryStructure = true;
- public PDBfile(boolean visibleChainAnnotation,
- boolean processSecondaryStructure)
+ /*
+ * 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();
- VisibleChainAnnotation = visibleChainAnnotation;
- this.processSecondaryStructure = processSecondaryStructure;
+ this.visibleChainAnnotation = addAlignmentAnnotations;
+ this.predictSecondaryStructure = predictSecondaryStructure;
+ this.externalSecondaryStructure = externalSecStr;
}
- public PDBfile(boolean visibleChainAnnotation,
- boolean processSecondaryStructure, String file, String protocol) throws IOException
+ public PDBfile(boolean addAlignmentAnnotations,
+ boolean predictSecondaryStructure, boolean externalSecStr,
+ String file, String protocol) throws IOException
{
super(false, file, protocol);
- VisibleChainAnnotation = visibleChainAnnotation;
- this.processSecondaryStructure = processSecondaryStructure;
+ this.visibleChainAnnotation = addAlignmentAnnotations;
+ this.predictSecondaryStructure = predictSecondaryStructure;
+ this.externalSecondaryStructure = externalSecStr;
doParse();
}
- public PDBfile(boolean visibleChainAnnotation,
- boolean processSecondaryStructure, FileParse source) throws IOException
+ public PDBfile(boolean addAlignmentAnnotations,
+ boolean predictSecondaryStructure, boolean externalSecStr,
+ FileParse source) throws IOException
{
super(false, source);
- VisibleChainAnnotation = visibleChainAnnotation;
- this.processSecondaryStructure = processSecondaryStructure;
+ this.visibleChainAnnotation = addAlignmentAnnotations;
+ this.predictSecondaryStructure = predictSecondaryStructure;
+ this.externalSecondaryStructure = externalSecStr;
doParse();
}
// TODO set the filename sensibly - try using data source name.
id = safeName(getDataName());
- chains = new Vector();
- ArrayList<SequenceI> rna = new ArrayList<SequenceI>(), prot = new ArrayList<SequenceI>();
+ 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;
+ int indexx = 0;
String atomnam = null;
try
{
{
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);
- entry.setProperty(new Hashtable());
- if (((PDBChain) chains.elementAt(i)).id != null)
- {
- entry.getProperty().put("CHAIN",
- ((PDBChain) chains.elementAt(i)).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);
- SequenceI chainseq = dataset.deriveSequence(); // PDBChain objects
- // maintain reference to
- // dataset
- seqs.addElement(chainseq);
- if (isRNA(chainseq) == true)
+ SequenceI chainseq = postProcessChain(chain);
+ if (isRNA(chainseq))
{
rna.add(chainseq);
}
{
prot.add(chainseq);
}
-
- AlignmentAnnotation[] chainannot = chainseq.getAnnotation();
-
- if (chainannot != null)
- {
- for (int ai = 0; ai < chainannot.length; ai++)
- {
-
- chainannot[ai].visible = VisibleChainAnnotation;
- annotations.addElement(chainannot[ai]);
- }
- }
}
- if (processSecondaryStructure)
+ if (predictSecondaryStructure)
{
- if (rna.size() > 0)
- try
- {
- processPdbFileWithAnnotate3d(rna);
- } catch (Exception x)
- {
- System.err
- .println("Exceptions when dealing with RNA in pdb file");
- x.printStackTrace();
-
- }
- ;
- if (prot.size() > 0)
- try
- {
- processPdbFileWithJmol(prot);
- } catch (Exception x)
- {
- System.err
- .println("Exceptions when dealing with RNA in pdb file");
- x.printStackTrace();
-
- }
+ predictSecondaryStructure(rna, prot);
}
} catch (OutOfMemoryError er)
{
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));
}
- private void processPdbFileWithJmol(ArrayList<SequenceI> prot)
+ 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())
+ {
+ String oldId = aa.getCalcId();
+ if (oldId == null)
+ {
+ oldId = "";
+ }
+ aa.setCalcId(CALC_ID_PREFIX);
+ aa.setProperty("PDBID", id);
+ aa.setProperty("oldCalcId", oldId);
+ }
+ }
+ }
+ }
+
+ private void processPdbFileWithJmol(List<SequenceI> prot)
throws Exception
{
try
Class cl = Class.forName("jalview.ext.jmol.PDBFileWithJmol");
if (cl != null)
{
- Object jmf = cl.getConstructor(new Class[]
- { FileParse.class }).newInstance(new Object[]
- { new FileParse(getDataName(), type) });
- Alignment al = new Alignment((SequenceI[]) cl.getMethod(
- "getSeqsAsArray", new Class[]
- {}).invoke(jmf));
- cl.getMethod("addAnnotations", new Class[]
- { Alignment.class }).invoke(jmf, al);
- replaceMatchingSeqsWith(prot, al, AlignSeq.PEP);
+ 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[] { AlignmentI.class })
+ .invoke(jmf, al);
+ for (SequenceI sq : al.getSequences())
+ {
+ if (sq.getDatasetSequence() != null)
+ {
+ sq.getDatasetSequence().getAllPDBEntries().clear();
+ }
+ else
+ {
+ sq.getAllPDBEntries().clear();
+ }
+ }
+ replaceAndUpdateChains(prot, al, AlignSeq.PEP, false);
}
} catch (ClassNotFoundException q)
{
}
}
- private void processPdbFileWithAnnotate3d(ArrayList<SequenceI> rna)
+ 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)
+ {
+ 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");
{
// 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[]
- {});
+ 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) }));
- replaceMatchingSeqsWith(rna, al, AlignSeq.DNA);
- }
- } catch (ClassNotFoundException x)
- {
- // ignore classnotfounds - occurs in applet
- }
- ;
- }
-
- /**
- * matches ochains against al and populates seqs with the best match between
- * each ochain and the set in al
- *
- * @param ochains
- * @param al
- * @param dnaOrProtein
- */
- private void replaceMatchingSeqsWith(ArrayList<SequenceI> ochains,
- AlignmentI al, String dnaOrProtein)
- {
- if (al != null && al.getHeight() > 0)
- {
- ArrayList<SequenceI> matches = new ArrayList<SequenceI>();
- ArrayList<AlignSeq> aligns = new ArrayList<AlignSeq>();
-
- for (SequenceI sq : ochains)
- {
- SequenceI bestm = null;
- AlignSeq bestaseq = null;
- int bestscore = 0;
- for (SequenceI msq : al.getSequences())
+ new Class[] { FileParse.class }).invoke(annotate3d,
+ new Object[] { new FileParse(getDataName(), type) }));
+ for (SequenceI sq : al.getSequences())
{
- AlignSeq aseq = AlignSeq.doGlobalNWAlignment(msq, sq,
- dnaOrProtein);
- if (bestm == null || aseq.getMaxScore() > bestscore)
+ if (sq.getDatasetSequence() != null)
{
- bestscore = aseq.getMaxScore();
- bestaseq = aseq;
- bestm = msq;
- }
- }
- System.out.println("Best Score for " + (matches.size() + 1) + " :"
- + bestscore);
- matches.add(bestm);
- aligns.add(bestaseq);
- al.deleteSequence(bestm);
- }
- for (int p = 0, pSize = seqs.size(); p < pSize; p++)
- {
- SequenceI sq, sp = seqs.get(p);
- int q;
- if ((q = ochains.indexOf(sp)) > -1)
- {
- seqs.set(p, sq = matches.get(q));
- sq.setName(sp.getName());
- sq.setDescription(sp.getDescription());
- sq.transferAnnotation(sp, aligns.get(q).getMappingFromS1(false));
- int inspos = -1;
- for (int ap = 0; ap < annotations.size();)
- {
- if (((AlignmentAnnotation) annotations.get(ap)).sequenceRef == sp)
- {
- if (inspos == -1)
- {
- inspos = ap;
- }
- annotations.remove(ap);
- }
- else
+ if (sq.getDatasetSequence().getAllPDBEntries() != null)
{
- ap++;
+ sq.getDatasetSequence().getAllPDBEntries().clear();
}
}
- if (sq.getAnnotation() != null)
+ else
{
- annotations.addAll(inspos, Arrays.asList(sq.getAnnotation()));
+ if (sq.getAllPDBEntries() != null)
+ {
+ sq.getAllPDBEntries().clear();
+ }
}
}
+ replaceAndUpdateChains(rna, al, AlignSeq.DNA, false);
}
+ } catch (ClassNotFoundException x)
+ {
+ // ignore classnotfounds - occurs in applet
}
+ ;
}
/**
{
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++)
+ for (char c : seq.getSequence())
{
- if ((seqs.getCharAt(i) != 'A') && (seqs.getCharAt(i) != 'C')
- && (seqs.getCharAt(i) != 'G') && (seqs.getCharAt(i) != 'U'))
+ if ((c != 'A') && (c != 'C') && (c != 'G') && (c != 'U'))
{
return false;
}
git://source.jalview.org / jalview.git / blobdiff