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.
21 package jalview.datamodel;
23 import jalview.util.MapList;
25 import java.util.Iterator;
26 import java.util.NoSuchElementException;
27 import java.util.Vector;
32 * An iterator that serves the aligned codon positions (with their protein
38 public class AlignedCodonIterator implements Iterator<AlignedCodon>
41 * The gap character used in the aligned sequence
43 private final char gap;
46 * The characters of the aligned sequence e.g. "-cGT-ACgTG-"
48 private final char[] alignedSeq;
51 * the sequence start residue
56 * Next position (base 0) in the aligned sequence
58 private int alignedColumn = 0;
61 * Count of bases up to and including alignedColumn position
63 private int alignedBases = 0;
66 * [start, end] from ranges (base 1)
68 private Iterator<int[]> fromRanges;
71 * [start, end] to ranges (base 1)
73 private Iterator<int[]> toRanges;
76 * The current [start, end] (base 1) from range
78 private int[] currentFromRange = null;
81 * The current [start, end] (base 1) to range
83 private int[] currentToRange = null;
86 * The next 'from' position (base 1) to process
88 private int fromPosition = 0;
91 * The next 'to' position (base 1) to process
93 private int toPosition = 0;
99 * the aligned sequence
102 public AlignedCodonIterator(SequenceI seq, char gapChar)
104 this.alignedSeq = seq.getSequence();
105 this.start = seq.getStart();
107 fromRanges = map.getFromRanges().iterator();
108 toRanges = map.getToRanges().iterator();
109 if (fromRanges.hasNext())
111 currentFromRange = fromRanges.next();
112 fromPosition = currentFromRange[0];
114 if (toRanges.hasNext())
116 currentToRange = toRanges.next();
117 toPosition = currentToRange[0];
122 * Returns true unless we have already traversed the whole mapping.
125 public boolean hasNext()
127 if (fromRanges.hasNext())
131 if (currentFromRange == null || fromPosition >= currentFromRange[1])
139 * Returns the next codon's aligned positions, and translated value.
141 * @throws NoSuchElementException
142 * if hasNext() would have returned false
143 * @throws IncompleteCodonException
144 * if not enough mapped bases are left to make up a codon
147 public AlignedCodon next() throws IncompleteCodonException
151 throw new NoSuchElementException();
154 int[] codon = getNextCodon();
155 int[] alignedCodon = getAlignedCodon(codon);
157 String peptide = getPeptide();
158 return new AlignedCodon(alignedCodon[0], alignedCodon[1],
159 alignedCodon[2], peptide);
163 * Retrieve the translation as the 'mapped to' position in the mapped to
168 private String getPeptide()
170 // TODO should ideally handle toRatio other than 1 as well...
171 // i.e. code like getNextCodon()
172 if (toPosition <= currentToRange[1])
174 SequenceI seq = Mapping.this.to;
175 char pep = seq.getSequence()[toPosition - seq.getStart()];
177 return String.valueOf(pep);
179 if (!toRanges.hasNext())
181 throw new NoSuchElementException("Ran out of peptide at position "
184 currentToRange = toRanges.next();
185 toPosition = currentToRange[0];
190 * Get the (base 1) dataset positions for the next codon in the mapping.
192 * @throws IncompleteCodonException
193 * if less than 3 remaining bases are mapped
195 private int[] getNextCodon()
197 int[] codon = new int[3];
200 while (codonbase < 3)
202 if (fromPosition <= currentFromRange[1])
205 * Add next position from the current start-end range
207 codon[codonbase++] = fromPosition++;
212 * Move to the next range - if there is one
214 if (!fromRanges.hasNext())
216 throw new IncompleteCodonException();
218 currentFromRange = fromRanges.next();
219 fromPosition = currentFromRange[0];
226 * Get the aligned column positions (base 0) for the given sequence
227 * positions (base 1), by counting ungapped characters in the aligned
233 private int[] getAlignedCodon(int[] codon)
235 int[] aligned = new int[codon.length];
236 for (int i = 0; i < codon.length; i++)
238 aligned[i] = getAlignedColumn(codon[i]);
244 * Get the aligned column position (base 0) for the given sequence position
250 private int getAlignedColumn(int sequencePos)
253 * allow for offset e.g. treat pos 8 as 2 if sequence starts at 7
255 int truePos = sequencePos - (start - 1);
256 while (alignedBases < truePos && alignedColumn < alignedSeq.length)
258 if (alignedSeq[alignedColumn++] != gap)
263 return alignedColumn - 1;
275 * Contains the start-end pairs mapping from the associated sequence to the
276 * sequence in the database coordinate system. It also takes care of step
277 * difference between coordinate systems.
282 * The sequence that map maps the associated sequence to (if any).
286 public Mapping(MapList map)
292 public Mapping(SequenceI to, MapList map)
299 * create a new mapping from
302 * the sequence being mapped
304 * int[] {start,end,start,end} series on associated sequence
306 * int[] {start,end,...} ranges on the reference frame being mapped
309 * step size on associated sequence
311 * step size on mapped frame
313 public Mapping(SequenceI to, int[] exon, int[] is, int i, int j)
315 this(to, new MapList(exon, is, i, j));
319 * create a duplicate (and independent) mapping object with the same reference
320 * to any SequenceI being mapped to.
324 public Mapping(Mapping map2)
326 if (map2 != this && map2 != null)
328 if (map2.map != null)
330 map = new MapList(map2.map);
339 public MapList getMap()
348 public void setMap(MapList map)
354 * Equals that compares both the to references and MapList mappings.
360 public boolean equals(Object o)
362 // TODO should override Object.hashCode() to ensure that equal objects have
364 if (o == null || !(o instanceof Mapping))
368 Mapping other = (Mapping) o;
377 if ((map != null && other.map == null)
378 || (map == null && other.map != null))
382 if ((map == null && other.map == null) || map.equals(other.map))
390 * get the 'initial' position in the associated sequence for a position in the
391 * mapped reference frame
396 public int getPosition(int mpos)
400 int[] mp = map.shiftTo(mpos);
410 * gets boundary in direction of mapping
413 * in mapped reference frame
414 * @return int{start, end} positions in associated sequence (in direction of
417 public int[] getWord(int mpos)
421 return map.getToWord(mpos);
427 * width of mapped unit in associated sequence
430 public int getWidth()
434 return map.getFromRatio();
440 * width of unit in mapped reference frame
444 public int getMappedWidth()
448 return map.getToRatio();
454 * get mapped position in the associated reference frame for position pos in
455 * the associated sequence.
460 public int getMappedPosition(int pos)
464 int[] mp = map.shiftFrom(pos);
473 public int[] getMappedWord(int pos)
477 int[] mp = map.shiftFrom(pos);
480 return new int[] { mp[0], mp[0] + mp[2] * (map.getToRatio() - 1) };
487 * locates the region of feature f in the associated sequence's reference
491 * @return one or more features corresponding to f
493 public SequenceFeature[] locateFeature(SequenceFeature f)
496 { // f.getBegin()!=f.getEnd()) {
499 int[] frange = map.locateInFrom(f.getBegin(), f.getEnd());
502 // JBPNote - this isprobably not the right thing to doJBPHack
505 SequenceFeature[] vf = new SequenceFeature[frange.length / 2];
506 for (int i = 0, v = 0; i < frange.length; i += 2, v++)
508 vf[v] = new SequenceFeature(f);
509 vf[v].setBegin(frange[i]);
510 vf[v].setEnd(frange[i + 1]);
511 if (frange.length > 2)
513 vf[v].setDescription(f.getDescription() + "\nPart " + (v + 1));
521 int[] word = getWord(f.getBegin());
522 if (word[0] < word[1])
530 word = getWord(f.getEnd());
531 if (word[0] > word[1])
540 // give up and just return the feature.
541 return new SequenceFeature[] { f };
545 * return a series of contigs on the associated sequence corresponding to the
546 * from,to interval on the mapped reference frame
550 * @return int[] { from_i, to_i for i=1 to n contiguous regions in the
551 * associated sequence}
553 public int[] locateRange(int from, int to)
559 from = (map.getToLowest() < from) ? from : map.getToLowest();
560 to = (map.getToHighest() > to) ? to : map.getToHighest();
568 from = (map.getToHighest() > from) ? from : map.getToHighest();
569 to = (map.getToLowest() < to) ? to : map.getToLowest();
575 return map.locateInFrom(from, to);
577 return new int[] { from, to };
581 * return a series of mapped contigs mapped from a range on the associated
588 public int[] locateMappedRange(int from, int to)
595 from = (map.getFromLowest() < from) ? from : map.getFromLowest();
596 to = (map.getFromHighest() > to) ? to : map.getFromHighest();
604 from = (map.getFromHighest() > from) ? from : map.getFromHighest();
605 to = (map.getFromLowest() < to) ? to : map.getFromLowest();
611 return map.locateInTo(from, to);
613 return new int[] { from, to };
617 * return a new mapping object with a maplist modifed to only map the visible
618 * regions defined by viscontigs.
623 public Mapping intersectVisContigs(int[] viscontigs)
625 Mapping copy = new Mapping(this);
630 Vector toRange = new Vector();
631 Vector fromRange = new Vector();
632 for (int vc = 0; vc < viscontigs.length; vc += 2)
634 // find a mapped range in this visible region
635 int[] mpr = locateMappedRange(1 + viscontigs[vc],
636 viscontigs[vc + 1] - 1);
639 for (int m = 0; m < mpr.length; m += 2)
641 toRange.addElement(new int[] { mpr[m], mpr[m + 1] });
642 int[] xpos = locateRange(mpr[m], mpr[m + 1]);
643 for (int x = 0; x < xpos.length; x += 2)
645 fromRange.addElement(new int[] { xpos[x], xpos[x + 1] });
650 int[] from = new int[fromRange.size() * 2];
651 int[] to = new int[toRange.size() * 2];
653 for (int f = 0, fSize = fromRange.size(); f < fSize; f++)
655 r = (int[]) fromRange.elementAt(f);
657 from[f * 2 + 1] = r[1];
659 for (int f = 0, fSize = toRange.size(); f < fSize; f++)
661 r = (int[]) toRange.elementAt(f);
663 to[f * 2 + 1] = r[1];
665 copy.setMap(new MapList(from, to, map.getFromRatio(), map
672 * get the sequence being mapped to - if any
674 * @return null or a dataset sequence
676 public SequenceI getTo()
682 * set the dataset sequence being mapped to if any
686 public void setTo(SequenceI tto)
694 * @see java.lang.Object#finalize()
696 protected void finalize() throws Throwable
703 public Iterator<AlignedCodon> getCodonIterator(SequenceI seq, char gapChar)
705 return new AlignedCodonIterator(seq, gapChar);