X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2FMCview%2FPDBfile.java;h=ebc52aaf0aa0643410590de2c330fd5611782160;hb=39b4859e1a1b011af5d06058461db4d075acb578;hp=26d44b1a976a34866baa6ab4b9286a073b3cbb71;hpb=f8ccad28f3a8fc90f4f0a13ec0c8d230dec6b230;p=jalview.git diff --git a/src/MCview/PDBfile.java b/src/MCview/PDBfile.java index 26d44b1..ebc52aa 100755 --- a/src/MCview/PDBfile.java +++ b/src/MCview/PDBfile.java @@ -1,170 +1,257 @@ /* -* Jalview - A Sequence Alignment Editor and Viewer -* Copyright (C) 2006 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle -* -* This program 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 2 -* of the License, or (at your option) any later version. -* -* This program 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 this program; if not, write to the Free Software -* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA -*/ + * 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. + * + * 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 jalview.datamodel.*; +import jalview.datamodel.AlignmentAnnotation; +import jalview.datamodel.DBRefSource; +import jalview.datamodel.SequenceI; +import jalview.io.DataSourceType; +import jalview.io.FileParse; +import jalview.io.StructureFile; +import jalview.util.MessageManager; -import java.io.*; +import java.io.IOException; +import java.util.ArrayList; +import java.util.Hashtable; +import java.util.List; +import java.util.Vector; -import java.util.*; -import java.awt.Color; +public class PDBfile extends StructureFile +{ + private static String CALC_ID_PREFIX = "JalviewPDB"; + public PDBfile(boolean addAlignmentAnnotations, + boolean predictSecondaryStructure, boolean externalSecStr) + { + super(); + addSettings(addAlignmentAnnotations, predictSecondaryStructure, + externalSecStr); + } -public class PDBfile extends jalview.io.AlignFile { - public Vector chains; - public String id; + public PDBfile(boolean addAlignmentAnnotations, boolean predictSecStr, + boolean externalSecStr, String dataObject, + DataSourceType sourceType) throws IOException + { + super(false, dataObject, sourceType); + addSettings(addAlignmentAnnotations, predictSecStr, externalSecStr); + doParse(); + } - public PDBfile(String inFile, String inType) throws IOException - { - super(inFile, inType); - } + public PDBfile(boolean addAlignmentAnnotations, boolean predictSecStr, + boolean externalSecStr, FileParse source) throws IOException + { + super(false, source); + addSettings(addAlignmentAnnotations, predictSecStr, externalSecStr); + doParse(); + } - public String print() - { - return null; - } + @Override + public String print(SequenceI[] seqs, boolean jvSuffix) + { + return null; + } - public void parse() throws IOException - { - try{ - chains = new Vector(); + @Override + public void parse() throws IOException + { + setDbRefType(DBRefSource.PDB); + // TODO set the filename sensibly - try using data source name. + setId(safeName(getDataName())); - PDBChain tmpchain; - String line; - boolean modelFlag = false; - boolean terFlag = false; + setChains(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; - while ( (line = nextLine()) != null) + int indexx = 0; + String atomnam = null; + try + { + while ((line = nextLine()) != null) + { + if (line.indexOf("HEADER") == 0) { - if (line.indexOf("HEADER") == 0) + if (line.length() > 62) { - id = line.substring(62, 67).trim(); - 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???? - if (!line.substring(12, 15).trim().equals("CA")) + String tid; + if (line.length() > 67) { - continue; + tid = line.substring(62, 67).trim(); } - - Atom tmpatom = new Atom(line); - tmpchain = findChain(tmpatom.chain); - if (tmpchain != null) + else { - tmpchain.atoms.addElement(tmpatom); + tid = line.substring(62).trim(); } - else + if (tid.length() > 0) { - tmpchain = new PDBChain(id,tmpatom.chain); - chains.addElement(tmpchain); - tmpchain.atoms.addElement(tmpatom); + setId(tid); } + continue; } - index++; } - - makeResidueList(); - makeCaBondList(); - - if (id == null) + // Were we to do anything with SEQRES - we start it here + if (line.indexOf("SEQRES") == 0) { - id = inFile.getName(); } - for (int i = 0; i < chains.size(); i++) + + if (line.indexOf("MODEL") == 0) { - SequenceI dataset = ( (PDBChain) chains.elementAt(i)). - sequence; - dataset.setName(id + "|" + dataset.getName()); - PDBEntry entry = new PDBEntry(); - entry.setId(id); - if (inFile != null) - entry.setFile(inFile.getAbsolutePath()); - dataset.addPDBId(entry); - getSeqs().addElement(dataset.deriveSequence()); // PDBChain objects maintain reference to dataset + modelFlag = true; } - }catch(OutOfMemoryError er) - { - System.out.println("OUT OF MEMORY LOADING PDB FILE"); - throw new IOException("Out of memory loading PDB File"); - } - } - public void makeResidueList() { - for (int i = 0; i < chains.size(); i++) { - ((PDBChain) chains.elementAt(i)).makeResidueList(); + if (line.indexOf("TER") == 0) + { + terFlag = true; } - } - public void makeCaBondList() { - for (int i = 0; i < chains.size(); i++) { - ((PDBChain) chains.elementAt(i)).makeCaBondList(); + 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; + } - 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); + Atom tmpatom = new Atom(line); + try + { + tmpchain = findChain(tmpatom.chain); + if (tmpatom.resNumIns.trim().equals(lastID)) + { + // phosphorylated protein - seen both CA and P.. + continue; } + tmpchain.atoms.addElement(tmpatom); + } catch (Exception e) + { + tmpchain = new PDBChain(getId(), tmpatom.chain); + getChains().add(tmpchain); + tmpchain.atoms.addElement(tmpatom); + } + lastID = tmpatom.resNumIns.trim(); } + index++; + } - return null; - } + makeResidueList(); + makeCaBondList(); - public void setChargeColours() { - for (int i = 0; i < chains.size(); i++) { - ((PDBChain) chains.elementAt(i)).setChargeColours(); + if (getId() == null) + { + setId(inFile.getName()); + } + for (PDBChain chain : getChains()) + { + SequenceI chainseq = postProcessChain(chain); + if (isRNA(chainseq)) + { + rna.add(chainseq); } - } - - public void setColours(jalview.schemes.ColourSchemeI cs) { - for (int i = 0; i < chains.size(); i++) { - ((PDBChain) chains.elementAt(i)).setChainColours(cs); + else + { + prot.add(chainseq); } + } + if (predictSecondaryStructure) + { + addSecondaryStructure(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(); + } + + /** + * Process a parsed chain to construct and return a Sequence, and add it to + * the list of sequences parsed. + * + * @param chain + * @return + */ + + public static boolean isCalcIdHandled(String calcId) + { + return calcId != null && (CALC_ID_PREFIX.equals(calcId)); + } - public void setChainColours() + 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 markCalcIds() + { + for (SequenceI sq : seqs) { - for (int i = 0; i < chains.size(); i++) - { - ((PDBChain) chains.elementAt(i)).setChainColours( - Color.getHSBColor(1.0f / (float)i, .4f, 1.0f) - ); + 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", getId()); + aa.setProperty("oldCalcId", oldId); } + } } + } + }