X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2FMCview%2FPDBfile.java;h=28ece4cca0433933294f348b9839d528b0b471e3;hb=c777b335d0332979123446f431b7f0c160eb4880;hp=132aea805e263be66b431a6284f04b7d2b88fa6e;hpb=060fb4cd10b89e532cfcc26039aafec6d83c052d;p=jalview.git diff --git a/src/MCview/PDBfile.java b/src/MCview/PDBfile.java index 132aea8..28ece4c 100755 --- a/src/MCview/PDBfile.java +++ b/src/MCview/PDBfile.java @@ -1,6 +1,6 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2) - * Copyright (C) 2014 The Jalview Authors + * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$) + * Copyright (C) $$Year-Rel$$ The Jalview Authors * * This file is part of Jalview. * @@ -20,6 +20,14 @@ */ package MCview; +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.analysis.AlignSeq; import jalview.datamodel.Alignment; import jalview.datamodel.AlignmentAnnotation; @@ -29,49 +37,59 @@ import jalview.datamodel.SequenceI; import jalview.io.FileParse; import jalview.util.MessageManager; -import java.awt.Color; -import java.io.IOException; -import java.util.ArrayList; -import java.util.Hashtable; -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 */ - 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; + + /* + * 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 visibleChainAnnotation, - boolean processSecondaryStructure) + 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(); } @@ -85,15 +103,16 @@ 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 { @@ -179,33 +198,10 @@ 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) - { - 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); } @@ -213,47 +209,10 @@ public class PDBfile extends jalview.io.AlignFile { 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 (rna.size() > 0) + if (predictSecondaryStructure) { - 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 from Jmol when processing data in pdb file"); - x.printStackTrace(); - - } - } + predictSecondaryStructure(rna, prot); } } catch (OutOfMemoryError er) { @@ -272,27 +231,117 @@ public class PDBfile extends jalview.io.AlignFile markCalcIds(); } - private static String calcIdPrefix = "JalviewPDB:"; + /** + * Predict secondary structure for RNA and/or protein sequences and add as + * annotations + * + * @param rnaSequences + * @param proteinSequences + */ + protected void predictSecondaryStructure(List rnaSequences, + List 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 - && (calcId.startsWith(calcIdPrefix) && calcId.indexOf( - calcIdPrefix, - calcIdPrefix.length() + 1) > -1); + return calcId != null && (CALC_ID_PREFIX.equals(calcId)); } - public static boolean isCalcIdForFile(String calcId, String pdbFile) + + public static boolean isCalcIdForFile(AlignmentAnnotation alan, + String pdbFile) { - return (calcId != null && calcId.startsWith(calcIdPrefix + pdbFile - + ":" + calcIdPrefix)); + 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 = calcIdPrefix.length(), end = calcId.indexOf(calcIdPrefix, s); + int s = CALC_ID_PREFIX.length(), end = calcId.indexOf(CALC_ID_PREFIX, s); String between = calcId.substring(s, end - 1); - return calcIdPrefix + alreadyLoadedPDB.get(between) + ":" + return CALC_ID_PREFIX + alreadyLoadedPDB.get(between) + ":" + calcId.substring(end); } @@ -300,18 +349,24 @@ public class PDBfile extends jalview.io.AlignFile { for (SequenceI sq : seqs) { - for (AlignmentAnnotation aa : sq.getAnnotation()) + if (sq.getAnnotation() != null) { - String oldId = aa.getCalcId(); - if (oldId == null) + for (AlignmentAnnotation aa : sq.getAnnotation()) { - oldId = ""; + String oldId = aa.getCalcId(); + if (oldId == null) + { + oldId = ""; + } + aa.setCalcId(CALC_ID_PREFIX); + aa.setProperty("PDBID", id); + aa.setProperty("oldCalcId", oldId); } - aa.setCalcId("JalviewPDB:" + id + ":JalviewPDB:" + oldId); } } } - private void processPdbFileWithJmol(ArrayList prot) + + private void processPdbFileWithJmol(List prot) throws Exception { try @@ -319,39 +374,64 @@ public class PDBfile extends jalview.io.AlignFile 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( + 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); + { AlignmentI.class }).invoke(jmf, al); for (SequenceI sq : al.getSequences()) { if (sq.getDatasetSequence() != null) { - if (sq.getDatasetSequence().getPDBId() != null) - { - sq.getDatasetSequence().getPDBId().clear(); - } + sq.getDatasetSequence().getPDBId().clear(); } else { - if (sq.getPDBId() != null) - { - sq.getPDBId().clear(); - } + sq.getPDBId().clear(); } } - AlignSeq.replaceMatchingSeqsWith(seqs, annotations, prot, al, AlignSeq.PEP, false); + replaceAndUpdateChains(prot, al, AlignSeq.PEP, false); } } catch (ClassNotFoundException q) { } } - private void processPdbFileWithAnnotate3d(ArrayList rna) + 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; + } + } + 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 rna) throws Exception { // System.out.println("this is a PDB format and RNA sequence"); @@ -385,11 +465,11 @@ public class PDBfile extends jalview.io.AlignFile { if (sq.getPDBId() != null) { - sq.getDatasetSequence().getPDBId().clear(); + sq.getPDBId().clear(); } } } - AlignSeq.replaceMatchingSeqsWith(seqs, annotations, rna, al, AlignSeq.DNA, false); + replaceAndUpdateChains(rna, al, AlignSeq.DNA, false); } } catch (ClassNotFoundException x) { @@ -418,7 +498,7 @@ public class PDBfile extends jalview.io.AlignFile { for (int i = 0; i < chains.size(); i++) { - ((PDBChain) chains.elementAt(i)).makeResidueList(); + chains.elementAt(i).makeResidueList(visibleChainAnnotation); } } @@ -426,7 +506,7 @@ public class PDBfile extends jalview.io.AlignFile { for (int i = 0; i < chains.size(); i++) { - ((PDBChain) chains.elementAt(i)).makeCaBondList(); + chains.elementAt(i).makeCaBondList(); } } @@ -434,9 +514,9 @@ public class PDBfile extends jalview.io.AlignFile { 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); } } @@ -447,7 +527,7 @@ public class PDBfile extends jalview.io.AlignFile { for (int i = 0; i < chains.size(); i++) { - ((PDBChain) chains.elementAt(i)).setChargeColours(); + chains.elementAt(i).setChargeColours(); } } @@ -455,7 +535,7 @@ public class PDBfile extends jalview.io.AlignFile { for (int i = 0; i < chains.size(); i++) { - ((PDBChain) chains.elementAt(i)).setChainColours(cs); + chains.elementAt(i).setChainColours(cs); } } @@ -463,17 +543,17 @@ public class PDBfile extends jalview.io.AlignFile { for (int i = 0; i < chains.size(); i++) { - ((PDBChain) chains.elementAt(i)).setChainColours(Color.getHSBColor( - 1.0f / 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; }