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";
45 * SequenceFeature group for PDB File features added to sequences
47 private static final String PDBFILEFEATURE = "PDBFile";
49 private static final String IEASTATUS = "IEA:jalview";
53 public Vector<Bond> bonds = new Vector<Bond>();
55 public Vector<Atom> atoms = new Vector<Atom>();
57 public Vector<Residue> residues = new Vector<Residue>();
62 * sequence is the sequence extracted by the chain parsing code
64 public SequenceI sequence;
67 * shadow is the sequence created by any other parsing processes (e.g. Jmol,
70 public SequenceI shadow = null;
72 public boolean isNa = false;
74 public boolean isVisible = true;
76 public int pdbstart = 0;
78 public int pdbend = 0;
80 public int seqstart = 0;
82 public int seqend = 0;
84 public String pdbid = "";
86 public PDBChain(String pdbid, String id)
88 this.pdbid = pdbid == null ? pdbid : pdbid.toLowerCase();
93 * character used to write newlines
95 protected String newline = System.getProperty("line.separator");
97 public Mapping shadowMap;
99 public void setNewlineString(String nl)
104 public String getNewlineString()
109 public String print()
111 StringBuilder tmp = new StringBuilder(256);
115 tmp.append(b.at1.resName).append(" ").append(b.at1.resNumber)
116 .append(" ").append(offset).append(newline);
119 return tmp.toString();
123 * Annotate the residues with their corresponding positions in s1 using the
124 * alignment in as NOTE: This clears all atom.alignmentMapping values on the
130 public void makeExactMapping(AlignSeq as, SequenceI s1)
132 int pdbpos = as.getSeq2Start() - 2;
133 int alignpos = s1.getStart() + as.getSeq1Start() - 3;
134 // first clear out any old alignmentMapping values:
135 for (Atom atom : atoms)
137 atom.alignmentMapping = -1;
139 // and now trace the alignment onto the atom set.
140 for (int i = 0; i < as.astr1.length(); i++)
142 if (as.astr1.charAt(i) != '-')
147 if (as.astr2.charAt(i) != '-')
152 boolean sameResidue = Comparison.isSameResidue(as.astr1.charAt(i),
153 as.astr2.charAt(i), false);
156 if (pdbpos >= residues.size())
160 Residue res = residues.elementAt(pdbpos);
161 for (Atom atom : res.atoms)
163 atom.alignmentMapping = alignpos;
170 * copy over the RESNUM seqfeatures from the internal chain sequence to the
175 * The Status of the transferred annotation
176 * @return the features added to sq (or its dataset)
178 public SequenceFeature[] transferRESNUMFeatures(SequenceI seq,
182 while (sq != null && sq.getDatasetSequence() != null)
184 sq = sq.getDatasetSequence();
191 * Remove any existing features for this chain if they exist ?
192 * SequenceFeature[] seqsfeatures=seq.getSequenceFeatures(); int
193 * totfeat=seqsfeatures.length; // Remove any features for this exact chain
194 * ? for (int i=0; i<seqsfeatures.length; i++) { }
198 status = PDBChain.IEASTATUS;
200 SequenceFeature[] features = sequence.getSequenceFeatures();
201 if (features == null)
205 for (int i = 0; i < features.length; i++)
207 if (features[i].getFeatureGroup() != null
208 && features[i].getFeatureGroup().equals(pdbid))
210 int newBegin = 1 + residues.elementAt(features[i].getBegin()
212 .elementAt(0).alignmentMapping;
213 int newEnd = 1 + residues.elementAt(features[i].getEnd() - offset).atoms
214 .elementAt(0).alignmentMapping;
215 SequenceFeature tx = new SequenceFeature(features[i], newBegin,
216 newEnd, features[i].getFeatureGroup());
218 + ((tx.getStatus() == null || tx.getStatus().length() == 0) ? ""
219 : ":" + tx.getStatus()));
220 if (tx.begin != 0 && tx.end != 0)
222 sq.addSequenceFeature(tx);
230 * Traverses the list of residues and constructs bonds where CA-to-CA atoms or
231 * P-to-P atoms are found. Also sets the 'isNa' flag if more than 99% of
232 * residues contain a P not a CA.
234 public void makeCaBondList()
238 for (int i = 0; i < (residues.size() - 1); i++)
240 Residue tmpres = residues.elementAt(i);
241 Residue tmpres2 = residues.elementAt(i + 1);
242 Atom at1 = tmpres.findAtom("CA");
243 Atom at2 = tmpres2.findAtom("CA");
245 if ((at1 == null) && (at2 == null))
248 at1 = tmpres.findAtom("P");
249 at2 = tmpres2.findAtom("P");
251 if ((at1 != null) && (at2 != null))
253 if (at1.chain.equals(at2.chain))
264 System.out.println("not found " + i);
269 * If > 99% 'P', flag as nucleotide; note the count doesn't include the last
272 if (residues.size() > 1 && (numNa / (residues.size() - 1) > 0.99))
279 * Construct a bond from atom1 to atom2 and add it to the list of bonds for
285 public void makeBond(Atom at1, Atom at2)
287 bonds.addElement(new Bond(at1, at2));
291 * Traverses the list of atoms and
293 * <li>constructs a list of Residues, each containing all the atoms that share
294 * the same residue number</li>
295 * <li>adds a RESNUM sequence feature for each position</li>
296 * <li>creates the sequence string</li>
297 * <li>determines if nucleotide</li>
298 * <li>saves the residue number of the first atom as 'offset'</li>
299 * <li>adds temp factor annotation if the flag is set to do so</li>
302 * @param visibleChainAnnotation
304 public void makeResidueList(boolean visibleChainAnnotation)
308 boolean deoxyn = false;
309 boolean nucleotide = false;
310 StringBuilder seq = new StringBuilder(256);
311 Vector<SequenceFeature> resFeatures = new Vector<SequenceFeature>();
312 Vector<Annotation> resAnnotation = new Vector<Annotation>();
313 int i, iSize = atoms.size() - 1;
316 for (i = 0; i <= iSize; i++)
318 Atom tmp = atoms.elementAt(i);
319 resNumber = tmp.resNumber;
320 insCode = tmp.insCode;
330 Vector<Atom> resAtoms = new Vector<Atom>();
331 // Add atoms to a vector while the residue number
332 // remains the same as the first atom's resNumber (res)
333 while ((resNumber == res) && (ins == insCode) && (i < atoms.size()))
335 resAtoms.add(atoms.elementAt(i));
338 if (i < atoms.size())
340 resNumber = atoms.elementAt(i).resNumber;
341 insCode = atoms.elementAt(i).insCode;
349 // We need this to keep in step with the outer for i = loop
352 // Add inserted residues as features to the base residue
353 Atom currAtom = resAtoms.get(0);
354 if (currAtom.insCode != ' '
355 && !residues.isEmpty()
356 && residues.lastElement().atoms.get(0).resNumber == currAtom.resNumber)
358 SequenceFeature sf = new SequenceFeature("INSERTION",
359 currAtom.resName + ":" + currAtom.resNumIns + " " + pdbid
360 + id, "", offset + count - 1, offset + count - 1,
362 resFeatures.addElement(sf);
363 residues.lastElement().atoms.addAll(resAtoms);
368 // Make a new Residue object with the new atoms vector
369 residues.addElement(new Residue(resAtoms, resNumber - 1, count));
371 Residue tmpres = residues.lastElement();
372 Atom tmpat = tmpres.atoms.get(0);
373 // Make A new SequenceFeature for the current residue numbering
374 SequenceFeature sf = new SequenceFeature(RESNUM_FEATURE, tmpat.resName
375 + ":" + tmpat.resNumIns + " " + pdbid + id, "", offset
376 + count, offset + count, pdbid);
377 resFeatures.addElement(sf);
378 resAnnotation.addElement(new Annotation(tmpat.tfactor));
379 // Keep totting up the sequence
381 if ((symbol = ResidueProperties.getAA3Hash().get(tmpat.resName)) == null)
383 String nucname = tmpat.resName.trim();
384 // use the aaIndex rather than call 'toLower' - which would take a bit
386 deoxyn = nucname.length() == 2
387 && ResidueProperties.aaIndex[nucname.charAt(0)] == ResidueProperties.aaIndex['D'];
388 if (tmpat.name.equalsIgnoreCase("CA")
389 || ResidueProperties.nucleotideIndex[nucname
390 .charAt((deoxyn ? 1 : 0))] == -1)
392 char r = ResidueProperties
393 .getSingleCharacterCode(ResidueProperties
394 .getCanonicalAminoAcid(tmpat.resName));
395 seq.append(r == '0' ? 'X' : r);
396 // System.err.println("PDBReader:Null aa3Hash for " +
403 seq.append(nucname.charAt((deoxyn ? 1 : 0)));
411 .println("Warning: mixed nucleotide and amino acid chain.. its gonna do bad things to you!");
413 seq.append(ResidueProperties.aa[((Integer) symbol).intValue()]);
424 sequence = new Sequence(id, seq.toString(), offset, resNumber - 1); // Note:
428 // Add normalised feature scores to RESNUM indicating start/end of sequence
429 // sf.setScore(offset+count);
431 // System.out.println("PDB Sequence is :\nSequence = " + seq);
432 // System.out.println("No of residues = " + residues.size());
434 if (StructureImportSettings.isShowSeqFeatures())
436 for (i = 0, iSize = resFeatures.size(); i < iSize; i++)
438 sequence.addSequenceFeature(resFeatures.elementAt(i));
439 resFeatures.setElementAt(null, i);
442 if (visibleChainAnnotation)
444 Annotation[] annots = new Annotation[resAnnotation.size()];
446 for (i = 0, iSize = annots.length; i < iSize; i++)
448 annots[i] = resAnnotation.elementAt(i);
449 if (annots[i].value > max)
451 max = annots[i].value;
453 resAnnotation.setElementAt(null, i);
456 AlignmentAnnotation tfactorann = new AlignmentAnnotation(
457 "Temperature Factor", "Temperature Factor for " + pdbid + id,
458 annots, 0, max, AlignmentAnnotation.LINE_GRAPH);
459 tfactorann.setSequenceRef(sequence);
460 sequence.addAlignmentAnnotation(tfactorann);
465 * Colour start/end of bonds by charge
467 * <li>ASP and GLU red</li>
468 * <li>LYS and ARG blue</li>
469 * <li>CYS yellow</li>
470 * <li>others light gray</li>
473 public void setChargeColours()
477 if (b.at1 != null && b.at2 != null)
479 b.startCol = getChargeColour(b.at1.resName);
480 b.endCol = getChargeColour(b.at2.resName);
484 b.startCol = Color.gray;
485 b.endCol = Color.gray;
490 public static Color getChargeColour(String resName)
492 Color result = Color.lightGray;
493 if ("ASP".equals(resName) || "GLU".equals(resName))
497 else if ("LYS".equals(resName) || "ARG".equals(resName))
501 else if ("CYS".equals(resName))
503 result = Color.yellow;
509 * Sets the start/end colours of bonds to those of the start/end atoms
510 * according to the specified colour scheme. Note: currently only works for
515 public void setChainColours(ColourSchemeI cs)
522 index = ResidueProperties.aa3Hash.get(b.at1.resName).intValue();
523 b.startCol = cs.findColour(ResidueProperties.aa[index].charAt(0),
526 index = ResidueProperties.aa3Hash.get(b.at2.resName).intValue();
527 b.endCol = cs.findColour(ResidueProperties.aa[index].charAt(0), 0,
530 } catch (Exception e)
532 b.startCol = Color.gray;
533 b.endCol = Color.gray;
538 public void setChainColours(Color col)
548 * copy any sequence annotation onto the sequence mapped using the provided
552 * - positional mapping between destination sequence and pdb resnum
554 * - mapping between destination sequence and local chain
556 public void transferResidueAnnotation(StructureMapping mapping,
557 jalview.datamodel.Mapping sqmpping)
559 SequenceI sq = mapping.getSequence();
563 while (dsq.getDatasetSequence() != null)
565 dsq = dsq.getDatasetSequence();
567 // any annotation will be transferred onto the dataset sequence
569 if (shadow != null && shadow.getAnnotation() != null)
572 for (AlignmentAnnotation ana : shadow.getAnnotation())
574 List<AlignmentAnnotation> transfer = sq.getAlignmentAnnotations(
575 ana.getCalcId(), ana.label);
576 if (transfer == null || transfer.size() == 0)
578 ana = new AlignmentAnnotation(ana);
579 ana.liftOver(sequence, shadowMap);
580 ana.liftOver(dsq, sqmpping);
581 dsq.addAlignmentAnnotation(ana);
591 if (sequence != null && sequence.getAnnotation() != null)
593 for (AlignmentAnnotation ana : sequence.getAnnotation())
595 List<AlignmentAnnotation> transfer = dsq
596 .getAlignmentAnnotations(ana.getCalcId(), ana.label);
597 if (transfer == null || transfer.size() == 0)
599 ana = new AlignmentAnnotation(ana);
600 ana.liftOver(dsq, sqmpping);
601 dsq.addAlignmentAnnotation(ana);
602 // mapping.transfer(ana);
613 // Useful for debugging mappings - adds annotation for mapped position
614 float min = -1, max = 0;
615 Annotation[] an = new Annotation[sq.getEnd() - sq.getStart() + 1];
616 for (int i = sq.getStart(), j = sq.getEnd(), k = 0; i <= j; i++, k++)
618 int prn = mapping.getPDBResNum(k + 1);
620 an[k] = new Annotation(prn);
638 sq.addAlignmentAnnotation(new AlignmentAnnotation("PDB.RESNUM",
639 "PDB Residue Numbering for " + this.pdbid + ":" + this.id,
640 an, min, max, AlignmentAnnotation.LINE_GRAPH));