/* * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2) * Copyright (C) 2014 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. * * 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 . * 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.io.FileParse; import jalview.util.MessageManager; public class PDBfile extends jalview.io.AlignFile { public Vector chains; public String id; /** * set to true to add chain alignment annotation as visible annotation. */ boolean VisibleChainAnnotation = false; public PDBfile(String inFile, String inType) throws IOException { super(inFile, inType); } public PDBfile(FileParse source) throws IOException { super(source); } public String print() { return null; } public void parse() throws IOException { // TODO set the filename sensibly - try using data source name. id = safeName(getDataName()); chains = new Vector(); ArrayList rna = new ArrayList(), prot = new ArrayList(); PDBChain tmpchain; String line = null; boolean modelFlag = false; boolean terFlag = false; String lastID = ""; int index = 0; String atomnam = null; try { while ((line = nextLine()) != null) { if (line.indexOf("HEADER") == 0) { if (line.length() > 62) { String tid; if (line.length() > 67) { tid = line.substring(62, 67).trim(); } else { tid = line.substring(62).trim(); } if (tid.length() > 0) { id = tid; } continue; } } // Were we to do anything with SEQRES - we start it here if (line.indexOf("SEQRES") == 0) { } if (line.indexOf("MODEL") == 0) { modelFlag = true; } if (line.indexOf("TER") == 0) { terFlag = true; } if (modelFlag && line.indexOf("ENDMDL") == 0) { break; } if (line.indexOf("ATOM") == 0 || (line.indexOf("HETATM") == 0 && !terFlag)) { terFlag = false; // Jalview is only interested in CA bonds???? atomnam = line.substring(12, 15).trim(); if (!atomnam.equals("CA") && !atomnam.equals("P")) { continue; } Atom tmpatom = new Atom(line); tmpchain = findChain(tmpatom.chain); if (tmpchain != null) { if (tmpatom.resNumIns.trim().equals(lastID)) { // phosphorylated protein - seen both CA and P.. continue; } tmpchain.atoms.addElement(tmpatom); } else { tmpchain = new PDBChain(id, tmpatom.chain); chains.addElement(tmpchain); tmpchain.atoms.addElement(tmpatom); } lastID = tmpatom.resNumIns.trim(); } index++; } makeResidueList(); makeCaBondList(); if (id == null) { id = inFile.getName(); } for (int i = 0; i < chains.size(); i++) { 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) { 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]); } } } 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) { System.err .println("Exceptions when dealing with RNA in pdb file"); x.printStackTrace(); } ; } 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); } } } private void processPdbFileWithJmol(ArrayList 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); } } catch (ClassNotFoundException q) { } } 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) { // 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); } } 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 ochains, AlignmentI al, String dnaOrProtein) { if (al != null && al.getHeight() > 0) { ArrayList matches = new ArrayList(); ArrayList aligns = new ArrayList(); for (SequenceI sq : ochains) { SequenceI bestm = null; AlignSeq bestaseq = null; int bestscore = 0; for (SequenceI msq : al.getSequences()) { AlignSeq aseq = AlignSeq.doGlobalNWAlignment(msq, sq, dnaOrProtein); if (bestm == null || aseq.getMaxScore() > bestscore) { 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 { ap++; } } if (sq.getAnnotation() != null) { annotations.addAll(inspos, Arrays.asList(sq.getAnnotation())); } } } } } /** * make a friendly ID string. * * @param dataName * @return truncated dataName to after last '/' */ private String safeName(String dataName) { int p = 0; while ((p = dataName.indexOf("/")) > -1 && p < dataName.length()) { dataName = dataName.substring(p + 1); } return dataName; } public void makeResidueList() { for (int i = 0; i < chains.size(); i++) { ((PDBChain) chains.elementAt(i)).makeResidueList(); } } public void makeCaBondList() { for (int i = 0; i < chains.size(); i++) { ((PDBChain) chains.elementAt(i)).makeCaBondList(); } } public PDBChain findChain(String id) { for (int i = 0; i < chains.size(); i++) { if (((PDBChain) chains.elementAt(i)).id.equals(id)) { return (PDBChain) chains.elementAt(i); } } return null; } public void setChargeColours() { for (int i = 0; i < chains.size(); i++) { ((PDBChain) chains.elementAt(i)).setChargeColours(); } } public void setColours(jalview.schemes.ColourSchemeI cs) { for (int i = 0; i < chains.size(); i++) { ((PDBChain) chains.elementAt(i)).setChainColours(cs); } } public void setChainColours() { for (int i = 0; i < chains.size(); i++) { ((PDBChain) chains.elementAt(i)).setChainColours(Color.getHSBColor( 1.0f / (float) i, .4f, 1.0f)); } } public boolean isRNA(SequenceI seqs) { 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; } }