X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2FMCview%2FPDBfile.java;h=58f8ed5b7a35f5b7242e24e8e1602bb4d4c3c860;hb=17e77c3f2949a0729322b4a8d907f3f34b6a9914;hp=3272d1540cf10186704f38b449028100a1ce996a;hpb=8d2724b83aca38ef75d68787cc5939d950467e63;p=jalview.git diff --git a/src/MCview/PDBfile.java b/src/MCview/PDBfile.java index 3272d15..58f8ed5 100755 --- a/src/MCview/PDBfile.java +++ b/src/MCview/PDBfile.java @@ -1,51 +1,97 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.0b1) - * 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. * * 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 . + * You should have received a copy of the GNU General Public License + * along with Jalview. If not, see . * The Jalview Authors are detailed in the 'AUTHORS' file. */ 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 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) + */ + private boolean predictSecondaryStructure = true; + + /* + * Set true (with predictSecondaryStructure=true) to predict secondary + * structure using an external service (currently Annotate3D for RNA only) */ - boolean VisibleChainAnnotation = false; + private boolean externalSecondaryStructure = false; - public PDBfile(String inFile, String inType) throws IOException + public PDBfile(boolean addAlignmentAnnotations, + boolean predictSecondaryStructure, boolean externalSecStr) { - super(inFile, inType); + super(); + this.visibleChainAnnotation = addAlignmentAnnotations; + this.predictSecondaryStructure = predictSecondaryStructure; + this.externalSecondaryStructure = externalSecStr; } - public PDBfile(FileParse source) throws IOException + public PDBfile(boolean addAlignmentAnnotations, + boolean predictSecondaryStructure, boolean externalSecStr, + String file, String protocol) throws IOException { - super(source); + super(false, file, protocol); + this.visibleChainAnnotation = addAlignmentAnnotations; + this.predictSecondaryStructure = predictSecondaryStructure; + this.externalSecondaryStructure = externalSecStr; + doParse(); + } + + public PDBfile(boolean addAlignmentAnnotations, + boolean predictSecondaryStructure, boolean externalSecStr, + FileParse source) throws IOException + { + super(false, source); + this.visibleChainAnnotation = addAlignmentAnnotations; + this.predictSecondaryStructure = predictSecondaryStructure; + this.externalSecondaryStructure = externalSecStr; + doParse(); } public String print() @@ -58,15 +104,16 @@ public class PDBfile extends jalview.io.AlignFile // TODO set the filename sensibly - try using data source name. id = safeName(getDataName()); - chains = new Vector(); - ArrayList rna=new ArrayList(), prot=new ArrayList(); + chains = new Vector(); + List rna = new ArrayList(); + List prot = new ArrayList(); PDBChain tmpchain; String line = null; boolean modelFlag = false; boolean terFlag = false; String lastID = ""; - int index = 0; + int indexx = 0; String atomnam = null; try { @@ -152,80 +199,28 @@ public class PDBfile extends jalview.io.AlignFile { 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) + 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()); - } - dataset.addPDBId(entry); - SequenceI chainseq = dataset.deriveSequence(); // PDBChain objects - // maintain reference to - // dataset - seqs.addElement(chainseq); - if(isRNA(chainseq)==true) - { - rna.add(chainseq); - } else { - 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]); - } + prot.add(chainseq); } } - 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(); - - }; - if (prot.size()>0) - try { - processPdbFileWithJmol(prot); - } catch (Exception x) + if (predictSecondaryStructure) { - System.err.println("Exceptions when dealing with RNA in pdb file"); - x.printStackTrace(); - - }; + predictSecondaryStructure(rna, prot); + } } catch (OutOfMemoryError er) { System.out.println("OUT OF MEMORY LOADING PDB FILE"); - throw new IOException("Out of memory loading PDB File"); + throw new IOException( + MessageManager + .getString("exception.outofmemory_loading_pdb_file")); } catch (NumberFormatException ex) { if (line != null) @@ -234,95 +229,253 @@ public class PDBfile extends jalview.io.AlignFile System.err.println(line); } } + markCalcIds(); } - private void processPdbFileWithJmol(ArrayList prot) throws Exception + + /** + * Predict secondary structure for RNA and/or protein sequences and add as + * annotations + * + * @param rnaSequences + * @param proteinSequences + */ + protected void predictSecondaryStructure(List rnaSequences, + List proteinSequences) { - try { - Class cl = Class.forName("jalview.ext.jmol.PDBFileWithJmol"); - if (cl!=null) + /* + * 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) { - 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); + System.err.println("Exceptions when dealing with RNA in pdb file"); + x.printStackTrace(); + } - } catch (ClassNotFoundException q) - {} + } + + /* + * 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(); + } + } } - private void processPdbFileWithAnnotate3d(ArrayList 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) + + /** + * 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) { - // 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)})); - replaceMatchingSeqsWith(rna, al, AlignSeq.DNA); + // entry.getProperty().put("CHAIN", chains.elementAt(i).id); + entry.setChainCode(String.valueOf(chain.id)); } - } catch (ClassNotFoundException x) + if (inFile != null) { - //ignore classnotfounds - occurs in applet - }; + 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 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 replaceMatchingSeqsWith(ArrayList ochains, AlignmentI al, String dnaOrProtein) + + private void markCalcIds() { - if (al!=null && al.getHeight()>0) + for (SequenceI sq : seqs) { - ArrayList matches=new ArrayList(); - ArrayList aligns=new ArrayList(); - - for (SequenceI sq:ochains) + if (sq.getAnnotation() != null) { - SequenceI bestm=null; - AlignSeq bestaseq=null; - int bestscore=0; - for (SequenceI msq:al.getSequences()) + for (AlignmentAnnotation aa : sq.getAnnotation()) { - AlignSeq aseq = AlignSeq.doGlobalNWAlignment(msq, sq, dnaOrProtein); - if (bestm==null || aseq.getMaxScore()>bestscore) + String oldId = aa.getCalcId(); + if (oldId == null) { - bestscore=aseq.getMaxScore(); - bestaseq= aseq; - bestm=msq; + oldId = ""; } + aa.setCalcId(CALC_ID_PREFIX); + aa.setProperty("PDBID", id); + aa.setProperty("oldCalcId", oldId); + } + } + } + } + + private void processPdbFileWithJmol(List 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[] { 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 replaceAndUpdateChains(List prot, AlignmentI al, + String pep, boolean b) + { + List> replaced = AlignSeq + .replaceMatchingSeqsWith(seqs, annotations, prot, al, pep, + false); + for (PDBChain ch : chains) + { + int p = 0; + for (SequenceI sq : (List) replaced.get(0)) + { + p++; + if (sq == ch.sequence || sq.getDatasetSequence() == ch.sequence) + { + p = -p; + break; } - 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 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) { - SequenceI sq,sp=seqs.get(p); - int q; - if ((q=ochains.indexOf(sp))>-1) + // 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()) { - 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 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