2 * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3 * Copyright (C) $$Year-Rel$$ The Jalview Authors
5 * This file is part of Jalview.
7 * Jalview is free software: you can redistribute it and/or
8 * modify it under the terms of the GNU General Public License
9 * as published by the Free Software Foundation, either version 3
10 * of the License, or (at your option) any later version.
12 * Jalview is distributed in the hope that it will be useful, but
13 * WITHOUT ANY WARRANTY; without even the implied warranty
14 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
15 * PURPOSE. See the GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
19 * The Jalview Authors are detailed in the 'AUTHORS' file.
23 import jalview.analysis.AlignSeq;
24 import jalview.datamodel.AlignmentAnnotation;
25 import jalview.datamodel.Annotation;
26 import jalview.datamodel.Mapping;
27 import jalview.datamodel.Sequence;
28 import jalview.datamodel.SequenceFeature;
29 import jalview.datamodel.SequenceI;
30 import jalview.schemes.ColourSchemeI;
31 import jalview.schemes.ResidueProperties;
32 import jalview.structure.StructureImportSettings;
33 import jalview.structure.StructureMapping;
34 import jalview.util.Comparison;
36 import java.awt.Color;
37 import java.util.List;
38 import java.util.Vector;
42 public static final String RESNUM_FEATURE = "RESNUM";
44 private static final String IEASTATUS = "IEA:jalview";
48 public Vector<Bond> bonds = new Vector<Bond>();
50 public Vector<Atom> atoms = new Vector<Atom>();
52 public Vector<Residue> residues = new Vector<Residue>();
57 * sequence is the sequence extracted by the chain parsing code
59 public SequenceI sequence;
62 * shadow is the sequence created by any other parsing processes (e.g. Jmol,
65 public SequenceI shadow = null;
67 public boolean isNa = false;
69 public boolean isVisible = true;
71 public int pdbstart = 0;
73 public int pdbend = 0;
75 public int seqstart = 0;
77 public int seqend = 0;
79 public String pdbid = "";
81 public PDBChain(String thePdbid, String theId)
83 this.pdbid = thePdbid == null ? thePdbid : thePdbid.toLowerCase();
88 * character used to write newlines
90 protected String newline = System.getProperty("line.separator");
92 public Mapping shadowMap;
94 public void setNewlineString(String nl)
99 public String getNewlineString()
104 public String print()
106 StringBuilder tmp = new StringBuilder(256);
110 tmp.append(b.at1.resName).append(" ").append(b.at1.resNumber)
111 .append(" ").append(offset).append(newline);
114 return tmp.toString();
118 * Annotate the residues with their corresponding positions in s1 using the
119 * alignment in as NOTE: This clears all atom.alignmentMapping values on the
125 public void makeExactMapping(AlignSeq as, SequenceI s1)
127 int pdbpos = as.getSeq2Start() - 2;
128 int alignpos = s1.getStart() + as.getSeq1Start() - 3;
129 // first clear out any old alignmentMapping values:
130 for (Atom atom : atoms)
132 atom.alignmentMapping = -1;
134 // and now trace the alignment onto the atom set.
135 for (int i = 0; i < as.astr1.length(); i++)
137 if (as.astr1.charAt(i) != '-')
142 if (as.astr2.charAt(i) != '-')
147 boolean sameResidue = Comparison.isSameResidue(as.astr1.charAt(i),
148 as.astr2.charAt(i), false);
151 if (pdbpos >= residues.size())
155 Residue res = residues.elementAt(pdbpos);
156 for (Atom atom : res.atoms)
158 atom.alignmentMapping = alignpos;
165 * Copies over the RESNUM seqfeatures from the internal chain sequence to the
170 * The Status of the transferred annotation
172 public void transferRESNUMFeatures(SequenceI seq,
176 while (sq != null && sq.getDatasetSequence() != null)
178 sq = sq.getDatasetSequence();
186 * Remove any existing features for this chain if they exist ?
187 * SequenceFeature[] seqsfeatures=seq.getSequenceFeatures(); int
188 * totfeat=seqsfeatures.length; // Remove any features for this exact chain
189 * ? for (int i=0; i<seqsfeatures.length; i++) { }
193 status = PDBChain.IEASTATUS;
196 List<SequenceFeature> features = sequence.getSequenceFeatures();
197 for (SequenceFeature feature : features)
199 if (feature.getFeatureGroup() != null
200 && feature.getFeatureGroup().equals(pdbid))
202 int newBegin = 1 + residues.elementAt(feature.getBegin() - offset).atoms
203 .elementAt(0).alignmentMapping;
204 int newEnd = 1 + residues.elementAt(feature.getEnd() - offset).atoms
205 .elementAt(0).alignmentMapping;
206 SequenceFeature tx = new SequenceFeature(feature, newBegin, newEnd,
207 feature.getFeatureGroup(), feature.getScore());
209 + ((tx.getStatus() == null || tx.getStatus().length() == 0)
211 : ":" + tx.getStatus()));
212 if (tx.begin != 0 && tx.end != 0)
214 sq.addSequenceFeature(tx);
221 * Traverses the list of residues and constructs bonds where CA-to-CA atoms or
222 * P-to-P atoms are found. Also sets the 'isNa' flag if more than 99% of
223 * residues contain a P not a CA.
225 public void makeCaBondList()
229 for (int i = 0; i < (residues.size() - 1); i++)
231 Residue tmpres = residues.elementAt(i);
232 Residue tmpres2 = residues.elementAt(i + 1);
233 Atom at1 = tmpres.findAtom("CA");
234 Atom at2 = tmpres2.findAtom("CA");
236 if ((at1 == null) && (at2 == null))
239 at1 = tmpres.findAtom("P");
240 at2 = tmpres2.findAtom("P");
242 if ((at1 != null) && (at2 != null))
244 if (at1.chain.equals(at2.chain))
255 System.out.println("not found " + i);
260 * If > 99% 'P', flag as nucleotide; note the count doesn't include the last
263 if (residues.size() > 1 && (numNa / (residues.size() - 1) > 0.99))
270 * Construct a bond from atom1 to atom2 and add it to the list of bonds for
276 public void makeBond(Atom at1, Atom at2)
278 bonds.addElement(new Bond(at1, at2));
282 * Traverses the list of atoms and
284 * <li>constructs a list of Residues, each containing all the atoms that share
285 * the same residue number</li>
286 * <li>adds a RESNUM sequence feature for each position</li>
287 * <li>creates the sequence string</li>
288 * <li>determines if nucleotide</li>
289 * <li>saves the residue number of the first atom as 'offset'</li>
290 * <li>adds temp factor annotation if the flag is set to do so</li>
293 * @param visibleChainAnnotation
295 public void makeResidueList(boolean visibleChainAnnotation)
299 boolean deoxyn = false;
300 boolean nucleotide = false;
301 StringBuilder seq = new StringBuilder(256);
302 Vector<SequenceFeature> resFeatures = new Vector<SequenceFeature>();
303 Vector<Annotation> resAnnotation = new Vector<Annotation>();
304 int i, iSize = atoms.size() - 1;
307 for (i = 0; i <= iSize; i++)
309 Atom tmp = atoms.elementAt(i);
310 resNumber = tmp.resNumber;
311 insCode = tmp.insCode;
321 Vector<Atom> resAtoms = new Vector<Atom>();
322 // Add atoms to a vector while the residue number
323 // remains the same as the first atom's resNumber (res)
324 while ((resNumber == res) && (ins == insCode) && (i < atoms.size()))
326 resAtoms.add(atoms.elementAt(i));
329 if (i < atoms.size())
331 resNumber = atoms.elementAt(i).resNumber;
332 insCode = atoms.elementAt(i).insCode;
340 // We need this to keep in step with the outer for i = loop
343 // Add inserted residues as features to the base residue
344 Atom currAtom = resAtoms.get(0);
345 if (currAtom.insCode != ' ' && !residues.isEmpty()
346 && residues.lastElement().atoms
347 .get(0).resNumber == currAtom.resNumber)
349 String desc = currAtom.resName + ":" + currAtom.resNumIns + " "
351 SequenceFeature sf = new SequenceFeature("INSERTION", desc, offset
352 + count - 1, offset + count - 1, "PDB_INS");
353 resFeatures.addElement(sf);
354 residues.lastElement().atoms.addAll(resAtoms);
358 // Make a new Residue object with the new atoms vector
359 residues.addElement(new Residue(resAtoms, resNumber - 1, count));
361 Residue tmpres = residues.lastElement();
362 Atom tmpat = tmpres.atoms.get(0);
363 // Make A new SequenceFeature for the current residue numbering
364 String desc = tmpat.resName
365 + ":" + tmpat.resNumIns + " " + pdbid + id;
366 SequenceFeature sf = new SequenceFeature(RESNUM_FEATURE, desc,
367 offset + count, offset + count, pdbid);
368 resFeatures.addElement(sf);
369 resAnnotation.addElement(new Annotation(tmpat.tfactor));
370 // Keep totting up the sequence
372 if ((symbol = ResidueProperties.getAA3Hash()
373 .get(tmpat.resName)) == null)
375 String nucname = tmpat.resName.trim();
376 // use the aaIndex rather than call 'toLower' - which would take a bit
378 deoxyn = nucname.length() == 2
379 && ResidueProperties.aaIndex[nucname
380 .charAt(0)] == ResidueProperties.aaIndex['D'];
381 if (tmpat.name.equalsIgnoreCase("CA")
382 || ResidueProperties.nucleotideIndex[nucname
383 .charAt((deoxyn ? 1 : 0))] == -1)
385 char r = ResidueProperties.getSingleCharacterCode(
386 ResidueProperties.getCanonicalAminoAcid(tmpat.resName));
387 seq.append(r == '0' ? 'X' : r);
388 // System.err.println("PDBReader:Null aa3Hash for " +
395 seq.append(nucname.charAt((deoxyn ? 1 : 0)));
403 "Warning: mixed nucleotide and amino acid chain.. its gonna do bad things to you!");
405 seq.append(ResidueProperties.aa[((Integer) symbol).intValue()]);
416 sequence = new Sequence(id, seq.toString(), offset, resNumber - 1); // Note:
420 // Add normalised feature scores to RESNUM indicating start/end of sequence
421 // sf.setScore(offset+count);
423 // System.out.println("PDB Sequence is :\nSequence = " + seq);
424 // System.out.println("No of residues = " + residues.size());
426 if (StructureImportSettings.isShowSeqFeatures())
428 for (i = 0, iSize = resFeatures.size(); i < iSize; i++)
430 sequence.addSequenceFeature(resFeatures.elementAt(i));
431 resFeatures.setElementAt(null, i);
434 if (visibleChainAnnotation)
436 Annotation[] annots = new Annotation[resAnnotation.size()];
438 for (i = 0, iSize = annots.length; i < iSize; i++)
440 annots[i] = resAnnotation.elementAt(i);
441 if (annots[i].value > max)
443 max = annots[i].value;
445 resAnnotation.setElementAt(null, i);
448 AlignmentAnnotation tfactorann = new AlignmentAnnotation(
449 "Temperature Factor", "Temperature Factor for " + pdbid + id,
450 annots, 0, max, AlignmentAnnotation.LINE_GRAPH);
451 tfactorann.setSequenceRef(sequence);
452 sequence.addAlignmentAnnotation(tfactorann);
457 * Colour start/end of bonds by charge
459 * <li>ASP and GLU red</li>
460 * <li>LYS and ARG blue</li>
461 * <li>CYS yellow</li>
462 * <li>others light gray</li>
465 public void setChargeColours()
469 if (b.at1 != null && b.at2 != null)
471 b.startCol = getChargeColour(b.at1.resName);
472 b.endCol = getChargeColour(b.at2.resName);
476 b.startCol = Color.gray;
477 b.endCol = Color.gray;
482 public static Color getChargeColour(String resName)
484 Color result = Color.lightGray;
485 if ("ASP".equals(resName) || "GLU".equals(resName))
489 else if ("LYS".equals(resName) || "ARG".equals(resName))
493 else if ("CYS".equals(resName))
495 result = Color.yellow;
501 * Sets the start/end colours of bonds to those of the start/end atoms
502 * according to the specified colour scheme. Note: currently only works for
507 public void setChainColours(ColourSchemeI cs)
514 index = ResidueProperties.aa3Hash.get(b.at1.resName).intValue();
515 b.startCol = cs.findColour(ResidueProperties.aa[index].charAt(0), 0,
518 index = ResidueProperties.aa3Hash.get(b.at2.resName).intValue();
519 b.endCol = cs.findColour(ResidueProperties.aa[index].charAt(0), 0,
522 } catch (Exception e)
524 b.startCol = Color.gray;
525 b.endCol = Color.gray;
530 public void setChainColours(Color col)
540 * copy any sequence annotation onto the sequence mapped using the provided
544 * - positional mapping between destination sequence and pdb resnum
546 * - mapping between destination sequence and local chain
548 public void transferResidueAnnotation(StructureMapping mapping,
549 jalview.datamodel.Mapping sqmpping)
551 SequenceI sq = mapping.getSequence();
555 while (dsq.getDatasetSequence() != null)
557 dsq = dsq.getDatasetSequence();
559 // any annotation will be transferred onto the dataset sequence
561 if (shadow != null && shadow.getAnnotation() != null)
564 for (AlignmentAnnotation ana : shadow.getAnnotation())
566 List<AlignmentAnnotation> transfer = sq
567 .getAlignmentAnnotations(ana.getCalcId(), ana.label);
568 if (transfer == null || transfer.size() == 0)
570 ana = new AlignmentAnnotation(ana);
571 ana.liftOver(sequence, shadowMap);
572 ana.liftOver(dsq, sqmpping);
573 dsq.addAlignmentAnnotation(ana);
583 if (sequence != null && sequence.getAnnotation() != null)
585 for (AlignmentAnnotation ana : sequence.getAnnotation())
587 List<AlignmentAnnotation> transfer = dsq
588 .getAlignmentAnnotations(ana.getCalcId(), ana.label);
589 if (transfer == null || transfer.size() == 0)
591 ana = new AlignmentAnnotation(ana);
592 ana.liftOver(dsq, sqmpping);
593 dsq.addAlignmentAnnotation(ana);
594 // mapping.transfer(ana);
605 // Useful for debugging mappings - adds annotation for mapped position
606 float min = -1, max = 0;
607 Annotation[] an = new Annotation[sq.getEnd() - sq.getStart() + 1];
608 for (int i = sq.getStart(), j = sq
609 .getEnd(), k = 0; i <= j; i++, k++)
611 int prn = mapping.getPDBResNum(k + 1);
613 an[k] = new Annotation(prn);
631 sq.addAlignmentAnnotation(new AlignmentAnnotation("PDB.RESNUM",
632 "PDB Residue Numbering for " + this.pdbid + ":" + this.id,
633 an, min, max, AlignmentAnnotation.LINE_GRAPH));