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 * Copies over the RESNUM seqfeatures from the internal chain sequence to the
175 * The Status of the transferred annotation
177 public void transferRESNUMFeatures(SequenceI seq,
181 while (sq != null && sq.getDatasetSequence() != null)
183 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;
201 List<SequenceFeature> features = sequence.getSequenceFeatures();
202 for (SequenceFeature feature : features)
204 if (feature.getFeatureGroup() != null
205 && feature.getFeatureGroup().equals(pdbid))
207 int newBegin = 1 + residues.elementAt(feature.getBegin() - offset).atoms
208 .elementAt(0).alignmentMapping;
209 int newEnd = 1 + residues.elementAt(feature.getEnd() - offset).atoms
210 .elementAt(0).alignmentMapping;
211 SequenceFeature tx = new SequenceFeature(feature, newBegin, newEnd,
212 feature.getFeatureGroup(), feature.getScore());
214 + ((tx.getStatus() == null || tx.getStatus().length() == 0) ? ""
215 : ":" + tx.getStatus()));
216 if (tx.begin != 0 && tx.end != 0)
218 sq.addSequenceFeature(tx);
225 * Traverses the list of residues and constructs bonds where CA-to-CA atoms or
226 * P-to-P atoms are found. Also sets the 'isNa' flag if more than 99% of
227 * residues contain a P not a CA.
229 public void makeCaBondList()
233 for (int i = 0; i < (residues.size() - 1); i++)
235 Residue tmpres = residues.elementAt(i);
236 Residue tmpres2 = residues.elementAt(i + 1);
237 Atom at1 = tmpres.findAtom("CA");
238 Atom at2 = tmpres2.findAtom("CA");
240 if ((at1 == null) && (at2 == null))
243 at1 = tmpres.findAtom("P");
244 at2 = tmpres2.findAtom("P");
246 if ((at1 != null) && (at2 != null))
248 if (at1.chain.equals(at2.chain))
259 System.out.println("not found " + i);
264 * If > 99% 'P', flag as nucleotide; note the count doesn't include the last
267 if (residues.size() > 1 && (numNa / (residues.size() - 1) > 0.99))
274 * Construct a bond from atom1 to atom2 and add it to the list of bonds for
280 public void makeBond(Atom at1, Atom at2)
282 bonds.addElement(new Bond(at1, at2));
286 * Traverses the list of atoms and
288 * <li>constructs a list of Residues, each containing all the atoms that share
289 * the same residue number</li>
290 * <li>adds a RESNUM sequence feature for each position</li>
291 * <li>creates the sequence string</li>
292 * <li>determines if nucleotide</li>
293 * <li>saves the residue number of the first atom as 'offset'</li>
294 * <li>adds temp factor annotation if the flag is set to do so</li>
297 * @param visibleChainAnnotation
299 public void makeResidueList(boolean visibleChainAnnotation)
303 boolean deoxyn = false;
304 boolean nucleotide = false;
305 StringBuilder seq = new StringBuilder(256);
306 Vector<SequenceFeature> resFeatures = new Vector<SequenceFeature>();
307 Vector<Annotation> resAnnotation = new Vector<Annotation>();
308 int i, iSize = atoms.size() - 1;
311 for (i = 0; i <= iSize; i++)
313 Atom tmp = atoms.elementAt(i);
314 resNumber = tmp.resNumber;
315 insCode = tmp.insCode;
325 Vector<Atom> resAtoms = new Vector<Atom>();
326 // Add atoms to a vector while the residue number
327 // remains the same as the first atom's resNumber (res)
328 while ((resNumber == res) && (ins == insCode) && (i < atoms.size()))
330 resAtoms.add(atoms.elementAt(i));
333 if (i < atoms.size())
335 resNumber = atoms.elementAt(i).resNumber;
336 insCode = atoms.elementAt(i).insCode;
344 // We need this to keep in step with the outer for i = loop
347 // Add inserted residues as features to the base residue
348 Atom currAtom = resAtoms.get(0);
349 if (currAtom.insCode != ' '
350 && !residues.isEmpty()
351 && residues.lastElement().atoms.get(0).resNumber == currAtom.resNumber)
353 String desc = currAtom.resName + ":" + currAtom.resNumIns + " "
355 SequenceFeature sf = new SequenceFeature("INSERTION", desc, offset
356 + count - 1, offset + count - 1, "PDB_INS");
357 resFeatures.addElement(sf);
358 residues.lastElement().atoms.addAll(resAtoms);
362 // Make a new Residue object with the new atoms vector
363 residues.addElement(new Residue(resAtoms, resNumber - 1, count));
365 Residue tmpres = residues.lastElement();
366 Atom tmpat = tmpres.atoms.get(0);
367 // Make A new SequenceFeature for the current residue numbering
368 String desc = tmpat.resName
369 + ":" + tmpat.resNumIns + " " + pdbid + id;
370 SequenceFeature sf = new SequenceFeature(RESNUM_FEATURE, desc,
371 offset + count, offset + count, pdbid);
372 resFeatures.addElement(sf);
373 resAnnotation.addElement(new Annotation(tmpat.tfactor));
374 // Keep totting up the sequence
376 if ((symbol = ResidueProperties.getAA3Hash().get(tmpat.resName)) == null)
378 String nucname = tmpat.resName.trim();
379 // use the aaIndex rather than call 'toLower' - which would take a bit
381 deoxyn = nucname.length() == 2
382 && ResidueProperties.aaIndex[nucname.charAt(0)] == ResidueProperties.aaIndex['D'];
383 if (tmpat.name.equalsIgnoreCase("CA")
384 || ResidueProperties.nucleotideIndex[nucname
385 .charAt((deoxyn ? 1 : 0))] == -1)
387 char r = ResidueProperties
388 .getSingleCharacterCode(ResidueProperties
389 .getCanonicalAminoAcid(tmpat.resName));
390 seq.append(r == '0' ? 'X' : r);
391 // System.err.println("PDBReader:Null aa3Hash for " +
398 seq.append(nucname.charAt((deoxyn ? 1 : 0)));
406 .println("Warning: mixed nucleotide and amino acid chain.. its gonna do bad things to you!");
408 seq.append(ResidueProperties.aa[((Integer) symbol).intValue()]);
419 sequence = new Sequence(id, seq.toString(), offset, resNumber - 1); // Note:
423 // Add normalised feature scores to RESNUM indicating start/end of sequence
424 // sf.setScore(offset+count);
426 // System.out.println("PDB Sequence is :\nSequence = " + seq);
427 // System.out.println("No of residues = " + residues.size());
429 if (StructureImportSettings.isShowSeqFeatures())
431 for (i = 0, iSize = resFeatures.size(); i < iSize; i++)
433 sequence.addSequenceFeature(resFeatures.elementAt(i));
434 resFeatures.setElementAt(null, i);
437 if (visibleChainAnnotation)
439 Annotation[] annots = new Annotation[resAnnotation.size()];
441 for (i = 0, iSize = annots.length; i < iSize; i++)
443 annots[i] = resAnnotation.elementAt(i);
444 if (annots[i].value > max)
446 max = annots[i].value;
448 resAnnotation.setElementAt(null, i);
451 AlignmentAnnotation tfactorann = new AlignmentAnnotation(
452 "Temperature Factor", "Temperature Factor for " + pdbid + id,
453 annots, 0, max, AlignmentAnnotation.LINE_GRAPH);
454 tfactorann.setSequenceRef(sequence);
455 sequence.addAlignmentAnnotation(tfactorann);
460 * Colour start/end of bonds by charge
462 * <li>ASP and GLU red</li>
463 * <li>LYS and ARG blue</li>
464 * <li>CYS yellow</li>
465 * <li>others light gray</li>
468 public void setChargeColours()
472 if (b.at1 != null && b.at2 != null)
474 b.startCol = getChargeColour(b.at1.resName);
475 b.endCol = getChargeColour(b.at2.resName);
479 b.startCol = Color.gray;
480 b.endCol = Color.gray;
485 public static Color getChargeColour(String resName)
487 Color result = Color.lightGray;
488 if ("ASP".equals(resName) || "GLU".equals(resName))
492 else if ("LYS".equals(resName) || "ARG".equals(resName))
496 else if ("CYS".equals(resName))
498 result = Color.yellow;
504 * Sets the start/end colours of bonds to those of the start/end atoms
505 * according to the specified colour scheme. Note: currently only works for
510 public void setChainColours(ColourSchemeI cs)
517 index = ResidueProperties.aa3Hash.get(b.at1.resName).intValue();
518 b.startCol = cs.findColour(ResidueProperties.aa[index].charAt(0),
521 index = ResidueProperties.aa3Hash.get(b.at2.resName).intValue();
522 b.endCol = cs.findColour(ResidueProperties.aa[index].charAt(0), 0,
525 } catch (Exception e)
527 b.startCol = Color.gray;
528 b.endCol = Color.gray;
533 public void setChainColours(Color col)
543 * copy any sequence annotation onto the sequence mapped using the provided
547 * - positional mapping between destination sequence and pdb resnum
549 * - mapping between destination sequence and local chain
551 public void transferResidueAnnotation(StructureMapping mapping,
552 jalview.datamodel.Mapping sqmpping)
554 SequenceI sq = mapping.getSequence();
558 while (dsq.getDatasetSequence() != null)
560 dsq = dsq.getDatasetSequence();
562 // any annotation will be transferred onto the dataset sequence
564 if (shadow != null && shadow.getAnnotation() != null)
567 for (AlignmentAnnotation ana : shadow.getAnnotation())
569 List<AlignmentAnnotation> transfer = sq.getAlignmentAnnotations(
570 ana.getCalcId(), ana.label);
571 if (transfer == null || transfer.size() == 0)
573 ana = new AlignmentAnnotation(ana);
574 ana.liftOver(sequence, shadowMap);
575 ana.liftOver(dsq, sqmpping);
576 dsq.addAlignmentAnnotation(ana);
586 if (sequence != null && sequence.getAnnotation() != null)
588 for (AlignmentAnnotation ana : sequence.getAnnotation())
590 List<AlignmentAnnotation> transfer = dsq
591 .getAlignmentAnnotations(ana.getCalcId(), ana.label);
592 if (transfer == null || transfer.size() == 0)
594 ana = new AlignmentAnnotation(ana);
595 ana.liftOver(dsq, sqmpping);
596 dsq.addAlignmentAnnotation(ana);
597 // mapping.transfer(ana);
608 // Useful for debugging mappings - adds annotation for mapped position
609 float min = -1, max = 0;
610 Annotation[] an = new Annotation[sq.getEnd() - sq.getStart() + 1];
611 for (int i = sq.getStart(), j = sq.getEnd(), k = 0; i <= j; i++, k++)
613 int prn = mapping.getPDBResNum(k + 1);
615 an[k] = new Annotation(prn);
633 sq.addAlignmentAnnotation(new AlignmentAnnotation("PDB.RESNUM",
634 "PDB Residue Numbering for " + this.pdbid + ":" + this.id,
635 an, min, max, AlignmentAnnotation.LINE_GRAPH));