X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2FMCview%2FPDBChain.java;h=f2dd3d09b9424d0d8f1a59909b7c977285fb0ba0;hb=3d0101179759ef157b088ea135423cd909512d9f;hp=30712f2228f98d9dcf1e610d5dfa232b03e5f44b;hpb=bdcab58436069b690cc613f19961d6cda35d6b97;p=jalview.git diff --git a/src/MCview/PDBChain.java b/src/MCview/PDBChain.java index 30712f2..f2dd3d0 100755 --- a/src/MCview/PDBChain.java +++ b/src/MCview/PDBChain.java @@ -1,76 +1,142 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer - * Copyright (C) 2007 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 + * 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. - * - * 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. - * + * + * 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 this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA + * along with Jalview. If not, see . + * The Jalview Authors are detailed in the 'AUTHORS' file. */ package MCview; -import java.util.*; - -import java.awt.*; - -import jalview.analysis.*; -import jalview.datamodel.*; -import jalview.schemes.*; +import jalview.analysis.AlignSeq; +import jalview.datamodel.AlignmentAnnotation; +import jalview.datamodel.Annotation; +import jalview.datamodel.Mapping; +import jalview.datamodel.Sequence; +import jalview.datamodel.SequenceFeature; +import jalview.datamodel.SequenceI; +import jalview.schemes.ColourSchemeI; +import jalview.schemes.ResidueProperties; +import jalview.structure.StructureImportSettings; import jalview.structure.StructureMapping; +import jalview.util.Comparison; + +import java.awt.Color; +import java.util.List; +import java.util.Vector; public class PDBChain { + public static final String RESNUM_FEATURE = "RESNUM"; + /** * SequenceFeature group for PDB File features added to sequences */ private static final String PDBFILEFEATURE = "PDBFile"; + private static final String IEASTATUS = "IEA:jalview"; + public String id; - public Vector bonds = new Vector(); - public Vector atoms = new Vector(); - public Vector residues = new Vector(); + + public Vector bonds = new Vector(); + + public Vector atoms = new Vector(); + + public Vector residues = new Vector(); + public int offset; - public Sequence sequence; + + /** + * sequence is the sequence extracted by the chain parsing code + */ + public SequenceI sequence; + + /** + * shadow is the sequence created by any other parsing processes (e.g. Jmol, + * RNAview) + */ + public SequenceI shadow = null; + + public boolean isNa = false; + public boolean isVisible = true; + public int pdbstart = 0; + public int pdbend = 0; + public int seqstart = 0; + public int seqend = 0; + public String pdbid = ""; + public PDBChain(String pdbid, String id) { - this.pdbid = pdbid.toLowerCase(); + this.pdbid = pdbid == null ? pdbid : pdbid.toLowerCase(); this.id = id; } + /** + * character used to write newlines + */ + protected String newline = System.getProperty("line.separator"); + + public Mapping shadowMap; + + public void setNewlineString(String nl) + { + newline = nl; + } + + public String getNewlineString() + { + return newline; + } + public String print() { - String tmp = ""; + StringBuilder tmp = new StringBuilder(256); - for (int i = 0; i < bonds.size(); i++) + for (Bond b : bonds) { - tmp = tmp + ( (Bond) bonds.elementAt(i)).at1.resName + " " + - ( (Bond) bonds.elementAt(i)).at1.resNumber + " " + offset + - "\n"; + tmp.append(b.at1.resName).append(" ").append(b.at1.resNumber) + .append(" ").append(offset).append(newline); } - return tmp; + return tmp.toString(); } + /** + * Annotate the residues with their corresponding positions in s1 using the + * alignment in as NOTE: This clears all atom.alignmentMapping values on the + * structure. + * + * @param as + * @param s1 + */ public void makeExactMapping(AlignSeq as, SequenceI s1) { int pdbpos = as.getSeq2Start() - 2; int alignpos = s1.getStart() + as.getSeq1Start() - 3; - + // first clear out any old alignmentMapping values: + for (Atom atom : atoms) + { + atom.alignmentMapping = -1; + } + // and now trace the alignment onto the atom set. for (int i = 0; i < as.astr1.length(); i++) { if (as.astr1.charAt(i) != '-') @@ -83,28 +149,37 @@ public class PDBChain pdbpos++; } - if (as.astr1.charAt(i) == as.astr2.charAt(i)) + boolean sameResidue = Comparison.isSameResidue(as.astr1.charAt(i), + as.astr2.charAt(i), false); + if (sameResidue) { - Residue res = (Residue) residues.elementAt(pdbpos); - Enumeration en = res.atoms.elements(); - while (en.hasMoreElements()) + if (pdbpos >= residues.size()) + { + continue; + } + Residue res = residues.elementAt(pdbpos); + for (Atom atom : res.atoms) { - Atom atom = (Atom) en.nextElement(); atom.alignmentMapping = alignpos; } } } } + /** - * copy over the RESNUM seqfeatures from the internal chain sequence to the mapped sequence + * copy over the RESNUM seqfeatures from the internal chain sequence to the + * mapped sequence + * * @param seq - * @param status The Status of the transferred annotation + * @param status + * The Status of the transferred annotation * @return the features added to sq (or its dataset) */ - public SequenceFeature[] transferRESNUMFeatures(SequenceI seq, String status) + public SequenceFeature[] transferRESNUMFeatures(SequenceI seq, + String status) { SequenceI sq = seq; - while (sq!=null && sq.getDatasetSequence()!=null) + while (sq != null && sq.getDatasetSequence() != null) { sq = sq.getDatasetSequence(); if (sq == sequence) @@ -114,50 +189,72 @@ public class PDBChain } /** * Remove any existing features for this chain if they exist ? - * SequenceFeature[] seqsfeatures=seq.getSequenceFeatures(); - int totfeat=seqsfeatures.length; - // Remove any features for this exact chain ? - for (int i=0; i 99% 'P', flag as nucleotide; note the count doesn't include the last + * residue + */ + if (residues.size() > 1 && (numNa / (residues.size() - 1) > 0.99)) + { + isNa = true; + } } + /** + * Construct a bond from atom1 to atom2 and add it to the list of bonds for + * this chain + * + * @param at1 + * @param at2 + */ public void makeBond(Atom at1, Atom at2) { - float[] start = new float[3]; - float[] end = new float[3]; - - start[0] = at1.x; - start[1] = at1.y; - start[2] = at1.z; - - end[0] = at2.x; - end[1] = at2.y; - end[2] = at2.z; - - bonds.addElement(new Bond(start, end, at1, at2)); + bonds.addElement(new Bond(at1, at2)); } - public void makeResidueList() + /** + * Traverses the list of atoms and + *
    + *
  • constructs a list of Residues, each containing all the atoms that share + * the same residue number
  • + *
  • adds a RESNUM sequence feature for each position
  • + *
  • creates the sequence string
  • + *
  • determines if nucleotide
  • + *
  • saves the residue number of the first atom as 'offset'
  • + *
  • adds temp factor annotation if the flag is set to do so
  • + *
+ * + * @param visibleChainAnnotation + */ + public void makeResidueList(boolean visibleChainAnnotation) { int count = 0; - StringBuffer seq = new StringBuffer(); - Vector resFeatures = new Vector(); - Vector resAnnotation = new Vector(); + Object symbol; + boolean deoxyn = false; + boolean nucleotide = false; + StringBuilder seq = new StringBuilder(256); + Vector resFeatures = new Vector(); + Vector resAnnotation = new Vector(); int i, iSize = atoms.size() - 1; int resNumber = -1; + char insCode = ' '; for (i = 0; i <= iSize; i++) { - Atom tmp = (Atom) atoms.elementAt(i); + Atom tmp = atoms.elementAt(i); resNumber = tmp.resNumber; + insCode = tmp.insCode; + int res = resNumber; + char ins = insCode; if (i == 0) { offset = resNumber; } - Vector resAtoms = new Vector(); - //Add atoms to a vector while the residue number - //remains the same as the first atom's resNumber (res) - while ( (resNumber == res) && (i < atoms.size())) + Vector resAtoms = new Vector(); + // Add atoms to a vector while the residue number + // remains the same as the first atom's resNumber (res) + while ((resNumber == res) && (ins == insCode) && (i < atoms.size())) { - resAtoms.addElement( (Atom) atoms.elementAt(i)); + resAtoms.add(atoms.elementAt(i)); i++; if (i < atoms.size()) { - resNumber = ( (Atom) atoms.elementAt(i)).resNumber; + resNumber = atoms.elementAt(i).resNumber; + insCode = atoms.elementAt(i).insCode; } else { @@ -221,147 +345,190 @@ public class PDBChain } } - //We need this to keep in step with the outer for i = loop + // We need this to keep in step with the outer for i = loop i--; - //Make a new Residue object with the new atoms vector - residues.addElement(new Residue(resAtoms, resNumber - 1, count)); - - Residue tmpres = (Residue) residues.lastElement(); - Atom tmpat = (Atom) tmpres.atoms.elementAt(0); - // Make A new SequenceFeature for the current residue numbering - SequenceFeature sf = - new SequenceFeature("RESNUM", - tmpat.resName + ":" + tmpat.resNumIns + " " + - pdbid + id, - "", offset + count, offset + count, - pdbid); - - //MCview.PDBChain.PDBFILEFEATURE); - resFeatures.addElement(sf); - resAnnotation.addElement(new Annotation(tmpat.tfactor)); - // Keep totting up the sequence - if (ResidueProperties.getAA3Hash().get(tmpat.resName) == null) + // Add inserted residues as features to the base residue + Atom currAtom = resAtoms.get(0); + if (currAtom.insCode != ' ' && !residues.isEmpty() + && residues.lastElement().atoms + .get(0).resNumber == currAtom.resNumber) { - seq.append("X"); - // System.err.println("PDBReader:Null aa3Hash for " + - // tmpat.resName); + SequenceFeature sf = new SequenceFeature("INSERTION", + currAtom.resName + ":" + currAtom.resNumIns + " " + pdbid + + id, + "", offset + count - 1, offset + count - 1, "PDB_INS"); + resFeatures.addElement(sf); + residues.lastElement().atoms.addAll(resAtoms); } else { - seq.append(ResidueProperties.aa[ ( (Integer) ResidueProperties. - getAA3Hash() - .get(tmpat.resName)).intValue()]); + // Make a new Residue object with the new atoms vector + residues.addElement(new Residue(resAtoms, resNumber - 1, count)); + + Residue tmpres = residues.lastElement(); + Atom tmpat = tmpres.atoms.get(0); + // Make A new SequenceFeature for the current residue numbering + SequenceFeature sf = new SequenceFeature(RESNUM_FEATURE, + tmpat.resName + ":" + tmpat.resNumIns + " " + pdbid + id, + "", offset + count, offset + count, pdbid); + resFeatures.addElement(sf); + resAnnotation.addElement(new Annotation(tmpat.tfactor)); + // Keep totting up the sequence + + if ((symbol = ResidueProperties.getAA3Hash() + .get(tmpat.resName)) == null) + { + String nucname = tmpat.resName.trim(); + // use the aaIndex rather than call 'toLower' - which would take a bit + // more time. + deoxyn = nucname.length() == 2 + && ResidueProperties.aaIndex[nucname + .charAt(0)] == ResidueProperties.aaIndex['D']; + if (tmpat.name.equalsIgnoreCase("CA") + || ResidueProperties.nucleotideIndex[nucname + .charAt((deoxyn ? 1 : 0))] == -1) + { + char r = ResidueProperties.getSingleCharacterCode( + ResidueProperties.getCanonicalAminoAcid(tmpat.resName)); + seq.append(r == '0' ? 'X' : r); + // System.err.println("PDBReader:Null aa3Hash for " + + // tmpat.resName); + } + else + { + // nucleotide flag + nucleotide = true; + seq.append(nucname.charAt((deoxyn ? 1 : 0))); + } + } + else + { + if (nucleotide) + { + System.err.println( + "Warning: mixed nucleotide and amino acid chain.. its gonna do bad things to you!"); + } + seq.append(ResidueProperties.aa[((Integer) symbol).intValue()]); + } + count++; } - count++; } if (id.length() < 1) { id = " "; } - - sequence = new Sequence(id, seq.toString(), offset, resNumber - 1); // Note: resNumber-offset ~= seq.size() - // System.out.println("PDB Sequence is :\nSequence = " + seq); - // System.out.println("No of residues = " + residues.size()); - for (i = 0, iSize = resFeatures.size(); i < iSize; i++) + isNa = nucleotide; + sequence = new Sequence(id, seq.toString(), offset, resNumber - 1); // Note: + // resNumber-offset + // ~= + // seq.size() + // Add normalised feature scores to RESNUM indicating start/end of sequence + // sf.setScore(offset+count); + + // System.out.println("PDB Sequence is :\nSequence = " + seq); + // System.out.println("No of residues = " + residues.size()); + + if (StructureImportSettings.isShowSeqFeatures()) { - sequence.addSequenceFeature( (SequenceFeature) resFeatures.elementAt(i)); - resFeatures.setElementAt(null, i); + for (i = 0, iSize = resFeatures.size(); i < iSize; i++) + { + sequence.addSequenceFeature(resFeatures.elementAt(i)); + resFeatures.setElementAt(null, i); + } } - Annotation[] annots = new Annotation[resAnnotation.size()]; - float max=0; - for (i=0,iSize=annots.length; imax) - max = annots[i].value; - resAnnotation.setElementAt(null, i); + Annotation[] annots = new Annotation[resAnnotation.size()]; + float max = 0; + for (i = 0, iSize = annots.length; i < iSize; i++) + { + annots[i] = resAnnotation.elementAt(i); + if (annots[i].value > max) + { + max = annots[i].value; + } + resAnnotation.setElementAt(null, i); + } + + AlignmentAnnotation tfactorann = new AlignmentAnnotation( + "Temperature Factor", "Temperature Factor for " + pdbid + id, + annots, 0, max, AlignmentAnnotation.LINE_GRAPH); + tfactorann.setSequenceRef(sequence); + sequence.addAlignmentAnnotation(tfactorann); } - AlignmentAnnotation tfactorann = new AlignmentAnnotation("PDB.CATempFactor","CA Temperature Factor for "+sequence.getName(), - annots, 0, max, AlignmentAnnotation.LINE_GRAPH); - tfactorann.setSequenceRef(sequence); - sequence.addAlignmentAnnotation(tfactorann); } + /** + * Colour start/end of bonds by charge + *
    + *
  • ASP and GLU red
  • + *
  • LYS and ARG blue
  • + *
  • CYS yellow
  • + *
  • others light gray
  • + *
+ */ public void setChargeColours() { - for (int i = 0; i < bonds.size(); i++) + for (Bond b : bonds) { - try + if (b.at1 != null && b.at2 != null) { - Bond b = (Bond) bonds.elementAt(i); - - if (b.at1.resName.equalsIgnoreCase("ASP") || - b.at1.resName.equalsIgnoreCase("GLU")) - { - b.startCol = Color.red; - } - else if (b.at1.resName.equalsIgnoreCase("LYS") || - b.at1.resName.equalsIgnoreCase("ARG")) - { - b.startCol = Color.blue; - } - else if (b.at1.resName.equalsIgnoreCase("CYS")) - { - b.startCol = Color.yellow; - } - else - { - b.startCol = Color.lightGray; - } - - if (b.at2.resName.equalsIgnoreCase("ASP") || - b.at2.resName.equalsIgnoreCase("GLU")) - { - b.endCol = Color.red; - } - else if (b.at2.resName.equalsIgnoreCase("LYS") || - b.at2.resName.equalsIgnoreCase("ARG")) - { - b.endCol = Color.blue; - } - else if (b.at2.resName.equalsIgnoreCase("CYS")) - { - b.endCol = Color.yellow; - } - else - { - b.endCol = Color.lightGray; - } + b.startCol = getChargeColour(b.at1.resName); + b.endCol = getChargeColour(b.at2.resName); } - catch (Exception e) + else { - Bond b = (Bond) bonds.elementAt(i); b.startCol = Color.gray; b.endCol = Color.gray; } } } - public void setChainColours(jalview.schemes.ColourSchemeI cs) + public static Color getChargeColour(String resName) + { + Color result = Color.lightGray; + if ("ASP".equals(resName) || "GLU".equals(resName)) + { + result = Color.red; + } + else if ("LYS".equals(resName) || "ARG".equals(resName)) + { + result = Color.blue; + } + else if ("CYS".equals(resName)) + { + result = Color.yellow; + } + return result; + } + + /** + * Sets the start/end colours of bonds to those of the start/end atoms + * according to the specified colour scheme. Note: currently only works for + * peptide residues. + * + * @param cs + */ + public void setChainColours(ColourSchemeI cs) { - Bond b; int index; - for (int i = 0; i < bonds.size(); i++) + for (Bond b : bonds) { try { - b = (Bond) bonds.elementAt(i); - - index = ( (Integer) ResidueProperties.aa3Hash.get(b.at1. - resName)).intValue(); - b.startCol = cs.findColour(ResidueProperties.aa[index].charAt(0)); + index = ResidueProperties.aa3Hash.get(b.at1.resName).intValue(); + b.startCol = cs.findColour(ResidueProperties.aa[index].charAt(0), 0, + null, null, 0f); - index = ( (Integer) ResidueProperties.aa3Hash.get(b.at2.resName)). - intValue(); - b.endCol = cs.findColour(ResidueProperties.aa[index].charAt(0)); + index = ResidueProperties.aa3Hash.get(b.at2.resName).intValue(); + b.endCol = cs.findColour(ResidueProperties.aa[index].charAt(0), 0, + null, null, 0f); - } - catch (Exception e) + } catch (Exception e) { - b = (Bond) bonds.elementAt(i); b.startCol = Color.gray; b.endCol = Color.gray; } @@ -370,58 +537,109 @@ public class PDBChain public void setChainColours(Color col) { - for (int i = 0; i < bonds.size(); i++) + for (Bond b : bonds) { - Bond tmp = (Bond) bonds.elementAt(i); - tmp.startCol = col; - tmp.endCol = col; + b.startCol = col; + b.endCol = col; } } - public AlignmentAnnotation[] transferResidueAnnotation(SequenceI seq, String status) - { - AlignmentAnnotation[] transferred = null; - - return transferred; - - } - /** - * copy any sequence annotation onto the sequence mapped using the provided StructureMapping + * copy any sequence annotation onto the sequence mapped using the provided + * StructureMapping + * * @param mapping + * - positional mapping between destination sequence and pdb resnum + * @param sqmpping + * - mapping between destination sequence and local chain */ - public void transferResidueAnnotation(StructureMapping mapping) + public void transferResidueAnnotation(StructureMapping mapping, + jalview.datamodel.Mapping sqmpping) { SequenceI sq = mapping.getSequence(); - if (sq!=null) + SequenceI dsq = sq; + if (sq != null) { - if (sequence!=null && sequence.getAnnotation()!=null) + while (dsq.getDatasetSequence() != null) { - + dsq = dsq.getDatasetSequence(); } - float min=-1,max=0; - Annotation[] an=new Annotation[sq.getEnd()-sq.getStart()+1]; - for (int i=sq.getStart(),j=sq.getEnd(),k=0; i<=j; i++,k++) + // any annotation will be transferred onto the dataset sequence + + if (shadow != null && shadow.getAnnotation() != null) { - int prn = mapping.getPDBResNum(k+1); - an[k] = new Annotation((float)prn); - if (min==-1) + for (AlignmentAnnotation ana : shadow.getAnnotation()) { - min=k; - max=k; - } else { - if (min>k) + List transfer = sq + .getAlignmentAnnotations(ana.getCalcId(), ana.label); + if (transfer == null || transfer.size() == 0) + { + ana = new AlignmentAnnotation(ana); + ana.liftOver(sequence, shadowMap); + ana.liftOver(dsq, sqmpping); + dsq.addAlignmentAnnotation(ana); + } + else { - min=k; - } else - if (max transfer = dsq + .getAlignmentAnnotations(ana.getCalcId(), ana.label); + if (transfer == null || transfer.size() == 0) + { + ana = new AlignmentAnnotation(ana); + ana.liftOver(dsq, sqmpping); + dsq.addAlignmentAnnotation(ana); + // mapping.transfer(ana); + } + else + { + continue; + } + } + } + } + if (false) + { + // Useful for debugging mappings - adds annotation for mapped position + float min = -1, max = 0; + Annotation[] an = new Annotation[sq.getEnd() - sq.getStart() + 1]; + for (int i = sq.getStart(), j = sq + .getEnd(), k = 0; i <= j; i++, k++) + { + int prn = mapping.getPDBResNum(k + 1); + + an[k] = new Annotation(prn); + if (min == -1) + { + min = k; + max = k; + } + else + { + if (min > k) + { + min = k; + } + else if (max < k) { - max=k; + max = k; } + } } + sq.addAlignmentAnnotation(new AlignmentAnnotation("PDB.RESNUM", + "PDB Residue Numbering for " + this.pdbid + ":" + this.id, + an, min, max, AlignmentAnnotation.LINE_GRAPH)); } - sq.addAlignmentAnnotation(new AlignmentAnnotation("PDB.RESNUM", "PDB Residue Numbering for "+this.pdbid+":"+this.id, an, (float)min,(float)max, AlignmentAnnotation.LINE_GRAPH)); } } }