Coverage Report
File Alignment.java
Coverage histogram
30% of files have more coverage
Classes
| Class | Line # | Actions | |||
|---|---|---|---|---|---|
| Alignment | 51 | 629 | 325 |
Contributing tests
This file is covered by 565 tests.
.
Source view
| 1 | /* | |
| 2 | * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$) | |
| 3 | * Copyright (C) $$Year-Rel$$ The Jalview Authors | |
| 4 | * | |
| 5 | * This file is part of Jalview. | |
| 6 | * | |
| 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. | |
| 11 | * | |
| 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. | |
| 16 | * | |
| 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. | |
| 20 | */ | |
| 21 | package jalview.datamodel; | |
| 22 | ||
| 23 | import java.util.ArrayList; | |
| 24 | import java.util.Arrays; | |
| 25 | import java.util.BitSet; | |
| 26 | import java.util.Collection; | |
| 27 | import java.util.Collections; | |
| 28 | import java.util.Enumeration; | |
| 29 | import java.util.HashSet; | |
| 30 | import java.util.Hashtable; | |
| 31 | import java.util.Iterator; | |
| 32 | import java.util.List; | |
| 33 | import java.util.Map; | |
| 34 | import java.util.Set; | |
| 35 | import java.util.Vector; | |
| 36 | ||
| 37 | import jalview.analysis.AlignmentUtils; | |
| 38 | import jalview.datamodel.AlignedCodonFrame.SequenceToSequenceMapping; | |
| 39 | import jalview.io.FastaFile; | |
| 40 | import jalview.util.Comparison; | |
| 41 | import jalview.util.LinkedIdentityHashSet; | |
| 42 | import jalview.util.MessageManager; | |
| 43 | ||
| 44 | /** | |
| 45 | * Data structure to hold and manipulate a multiple sequence alignment | |
| 46 | */ | |
| 47 | /** | |
| 48 | * @author JimP | |
| 49 | * | |
| 50 | */ | |
| 51 | public class Alignment implements AlignmentI, AutoCloseable | |
| 52 | { | |
| 53 | private Alignment dataset; | |
| 54 | ||
| 55 | private List<SequenceI> sequences; | |
| 56 | ||
| 57 | protected List<SequenceGroup> groups; | |
| 58 | ||
| 59 | protected char gapCharacter = '-'; | |
| 60 | ||
| 61 | private boolean nucleotide = true; | |
| 62 | ||
| 63 | public boolean hasRNAStructure = false; | |
| 64 | ||
| 65 | public AlignmentAnnotation[] annotations; | |
| 66 | ||
| 67 | HiddenSequences hiddenSequences; | |
| 68 | ||
| 69 | HiddenColumns hiddenCols; | |
| 70 | ||
| 71 | public Hashtable alignmentProperties; | |
| 72 | ||
| 73 | private List<AlignedCodonFrame> codonFrameList; | |
| 74 | ||
| 75 | 1849 |  private void initAlignment(SequenceI[] seqs) |
| 76 | { | |
| 77 | 1849 | groups = Collections.synchronizedList(new ArrayList<SequenceGroup>()); |
| 78 | 1849 | hiddenSequences = new HiddenSequences(this); |
| 79 | 1849 | hiddenCols = new HiddenColumns(); |
| 80 | 1849 | codonFrameList = new ArrayList<>(); |
| 81 | ||
| 82 | 1849 | nucleotide = Comparison.isNucleotide(seqs); |
| 83 | ||
| 84 | 1849 | sequences = Collections.synchronizedList(new ArrayList<SequenceI>()); |
| 85 | ||
| 86 | 35095 | for (int i = 0; i < seqs.length; i++) |
| 87 | { | |
| 88 | 33246 | sequences.add(seqs[i]); |
| 89 | } | |
| 90 | ||
| 91 | } | |
| 92 | ||
| 93 | /** | |
| 94 | * Make a 'copy' alignment - sequences have new copies of features and | |
| 95 | * annotations, but share the original dataset sequences. | |
| 96 | */ | |
| 97 | 4 | public Alignment(AlignmentI al) |
| 98 | { | |
| 99 | 4 | SequenceI[] seqs = al.getSequencesArray(); |
| 100 | 19 | for (int i = 0; i < seqs.length; i++) |
| 101 | { | |
| 102 | 15 | seqs[i] = new Sequence(seqs[i]); |
| 103 | } | |
| 104 | ||
| 105 | 4 | initAlignment(seqs); |
| 106 | ||
| 107 | /* | |
| 108 | * Share the same dataset sequence mappings (if any). | |
| 109 | */ | |
| 110 | 4 | if (dataset == null && al.getDataset() == null) |
| 111 | { | |
| 112 | 1 | this.setCodonFrames(al.getCodonFrames()); |
| 113 | } | |
| 114 | } | |
| 115 | ||
| 116 | /** | |
| 117 | * Make an alignment from an array of Sequences. | |
| 118 | * | |
| 119 | * @param sequences | |
| 120 | */ | |
| 121 | 1843 | public Alignment(SequenceI[] seqs) |
| 122 | { | |
| 123 | 1843 | initAlignment(seqs); |
| 124 | } | |
| 125 | ||
| 126 | /** | |
| 127 | * Make a new alignment from an array of SeqCigars | |
| 128 | * | |
| 129 | * @param seqs | |
| 130 | * SeqCigar[] | |
| 131 | */ | |
| 132 | 2 | public Alignment(SeqCigar[] alseqs) |
| 133 | { | |
| 134 | 2 | SequenceI[] seqs = SeqCigar.createAlignmentSequences(alseqs, |
| 135 | gapCharacter, new HiddenColumns(), null); | |
| 136 | 2 | initAlignment(seqs); |
| 137 | } | |
| 138 | ||
| 139 | /** | |
| 140 | * Make a new alignment from an CigarArray JBPNote - can only do this when | |
| 141 | * compactAlignment does not contain hidden regions. JBPNote - must also check | |
| 142 | * that compactAlignment resolves to a set of SeqCigars - or construct them | |
| 143 | * appropriately. | |
| 144 | * | |
| 145 | * @param compactAlignment | |
| 146 | * CigarArray | |
| 147 | */ | |
| 148 | 0 | public static AlignmentI createAlignment(CigarArray compactAlignment) |
| 149 | { | |
| 150 | 0 | throw new Error(MessageManager |
| 151 | .getString("error.alignment_cigararray_not_implemented")); | |
| 152 | // this(compactAlignment.refCigars); | |
| 153 | } | |
| 154 | ||
| 155 | 76199 | @Override |
| 156 | public List<SequenceI> getSequences() | |
| 157 | { | |
| 158 | 76199 | return sequences; |
| 159 | } | |
| 160 | ||
| 161 | 13 | @Override |
| 162 | public List<SequenceI> getSequences( | |
| 163 | Map<SequenceI, SequenceCollectionI> hiddenReps) | |
| 164 | { | |
| 165 | // TODO: in jalview 2.8 we don't do anything with hiddenreps - fix design to | |
| 166 | // work on this. | |
| 167 | 13 | return sequences; |
| 168 | } | |
| 169 | ||
| 170 | 33551 | @Override |
| 171 | public SequenceI[] getSequencesArray() | |
| 172 | { | |
| 173 | 33551 | if (sequences == null) |
| 174 | { | |
| 175 | 0 | return null; |
| 176 | } | |
| 177 | 33551 | synchronized (sequences) |
| 178 | { | |
| 179 | 33551 | return sequences.toArray(new SequenceI[sequences.size()]); |
| 180 | } | |
| 181 | } | |
| 182 | ||
| 183 | /** | |
| 184 | * Returns a map of lists of sequences keyed by sequence name. | |
| 185 | * | |
| 186 | * @return | |
| 187 | */ | |
| 188 | 0 | @Override |
| 189 | public Map<String, List<SequenceI>> getSequencesByName() | |
| 190 | { | |
| 191 | 0 | return AlignmentUtils.getSequencesByName(this); |
| 192 | } | |
| 193 | ||
| 194 | 29325109 | @Override |
| 195 | public SequenceI getSequenceAt(int i) | |
| 196 | { | |
| 197 | 29325111 | synchronized (sequences) |
| 198 | { | |
| 199 | ||
| 200 | 29325120 | if (i > -1 && i < sequences.size()) |
| 201 | { | |
| 202 | 29325112 | return sequences.get(i); |
| 203 | } | |
| 204 | } | |
| 205 | ||
| 206 | 7 | return null; |
| 207 | } | |
| 208 | ||
| 209 | 2618 | @Override |
| 210 | public SequenceI getSequenceAtAbsoluteIndex(int i) | |
| 211 | { | |
| 212 | 2618 | SequenceI seq = null; |
| 213 | 2618 | if (getHiddenSequences().getSize() > 0) |
| 214 | { | |
| 215 | 1715 | seq = getHiddenSequences().getHiddenSequence(i); |
| 216 | 1715 | if (seq == null) |
| 217 | { | |
| 218 | // didn't find the sequence in the hidden sequences, get it from the | |
| 219 | // alignment | |
| 220 | 1715 | int index = getHiddenSequences().findIndexWithoutHiddenSeqs(i); |
| 221 | 1715 | seq = getSequenceAt(index); |
| 222 | } | |
| 223 | } | |
| 224 | else | |
| 225 | { | |
| 226 | 903 | seq = getSequenceAt(i); |
| 227 | } | |
| 228 | 2618 | return seq; |
| 229 | } | |
| 230 | ||
| 231 | /** | |
| 232 | * Adds a sequence to the alignment. Recalculates maxLength and size. Note | |
| 233 | * this currently does not recalculate whether or not the alignment is | |
| 234 | * nucleotide, so mixed alignments may have undefined behaviour. | |
| 235 | * | |
| 236 | * @param snew | |
| 237 | */ | |
| 238 | 14981 | @Override |
| 239 | public void addSequence(SequenceI snew) | |
| 240 | { | |
| 241 | 14981 | if (dataset != null) |
| 242 | { | |
| 243 | ||
| 244 | // maintain dataset integrity | |
| 245 | 68 | SequenceI dsseq = snew.getDatasetSequence(); |
| 246 | 68 | if (dsseq == null) |
| 247 | { | |
| 248 | // derive new sequence | |
| 249 | 5 | SequenceI adding = snew.deriveSequence(); |
| 250 | 5 | snew = adding; |
| 251 | 5 | dsseq = snew.getDatasetSequence(); |
| 252 | } | |
| 253 | 68 | if (getDataset().findIndex(dsseq) == -1) |
| 254 | { | |
| 255 | 65 | getDataset().addSequence(dsseq); |
| 256 | } | |
| 257 | ||
| 258 | } | |
| 259 | 14981 | if (sequences == null) |
| 260 | { | |
| 261 | 0 | initAlignment(new SequenceI[] { snew }); |
| 262 | } | |
| 263 | else | |
| 264 | { | |
| 265 | 14981 | synchronized (sequences) |
| 266 | { | |
| 267 | 14981 | sequences.add(snew); |
| 268 | } | |
| 269 | } | |
| 270 | 14981 | if (hiddenSequences != null) |
| 271 | { | |
| 272 | 14981 | hiddenSequences.adjustHeightSequenceAdded(); |
| 273 | } | |
| 274 | } | |
| 275 | ||
| 276 | 76 | @Override |
| 277 | public SequenceI replaceSequenceAt(int i, SequenceI snew) | |
| 278 | { | |
| 279 | 76 | synchronized (sequences) |
| 280 | { | |
| 281 | 76 | if (sequences.size() > i) |
| 282 | { | |
| 283 | 76 | return sequences.set(i, snew); |
| 284 | ||
| 285 | } | |
| 286 | else | |
| 287 | { | |
| 288 | 0 | sequences.add(snew); |
| 289 | 0 | hiddenSequences.adjustHeightSequenceAdded(); |
| 290 | } | |
| 291 | 0 | return null; |
| 292 | } | |
| 293 | } | |
| 294 | ||
| 295 | /** | |
| 296 | * DOCUMENT ME! | |
| 297 | * | |
| 298 | * @return DOCUMENT ME! | |
| 299 | */ | |
| 300 | 10086 | @Override |
| 301 | public List<SequenceGroup> getGroups() | |
| 302 | { | |
| 303 | 10086 | return groups; |
| 304 | } | |
| 305 | ||
| 306 | 0 | @Override |
| 307 | public void close() | |
| 308 | { | |
| 309 | 0 | if (getDataset() != null) |
| 310 | { | |
| 311 | 0 | try |
| 312 | { | |
| 313 | 0 | getDataset().removeAlignmentRef(); |
| 314 | } catch (Throwable e) | |
| 315 | { | |
| 316 | 0 | e.printStackTrace(); |
| 317 | } | |
| 318 | } | |
| 319 | ||
| 320 | 0 | nullReferences(); |
| 321 | } | |
| 322 | ||
| 323 | /** | |
| 324 | * Defensively nulls out references in case this object is not garbage | |
| 325 | * collected | |
| 326 | */ | |
| 327 | 0 | void nullReferences() |
| 328 | { | |
| 329 | 0 | dataset = null; |
| 330 | 0 | sequences = null; |
| 331 | 0 | groups = null; |
| 332 | 0 | annotations = null; |
| 333 | 0 | hiddenSequences = null; |
| 334 | } | |
| 335 | ||
| 336 | /** | |
| 337 | * decrement the alignmentRefs counter by one and null references if it goes | |
| 338 | * to zero. | |
| 339 | * | |
| 340 | * @throws Throwable | |
| 341 | */ | |
| 342 | 0 | private void removeAlignmentRef() throws Throwable |
| 343 | { | |
| 344 | 0 | if (--alignmentRefs == 0) |
| 345 | { | |
| 346 | 0 | nullReferences(); |
| 347 | } | |
| 348 | } | |
| 349 | ||
| 350 | 96 | @Override |
| 351 | public void deleteSequence(SequenceI s) | |
| 352 | { | |
| 353 | 96 | synchronized (sequences) |
| 354 | { | |
| 355 | 96 | deleteSequence(findIndex(s)); |
| 356 | } | |
| 357 | } | |
| 358 | ||
| 359 | 101 | @Override |
| 360 | public void deleteSequence(int i) | |
| 361 | { | |
| 362 | 101 | synchronized (sequences) |
| 363 | { | |
| 364 | 101 | if (i > -1 && i < getHeight()) |
| 365 | { | |
| 366 | 99 | sequences.remove(i); |
| 367 | 99 | hiddenSequences.adjustHeightSequenceDeleted(i); |
| 368 | } | |
| 369 | } | |
| 370 | } | |
| 371 | ||
| 372 | 530 | @Override |
| 373 | public void deleteHiddenSequence(int i) | |
| 374 | { | |
| 375 | 530 | synchronized (sequences) |
| 376 | { | |
| 377 | 530 | if (i > -1 && i < getHeight()) |
| 378 | { | |
| 379 | 530 | sequences.remove(i); |
| 380 | } | |
| 381 | } | |
| 382 | } | |
| 383 | ||
| 384 | /* | |
| 385 | * (non-Javadoc) | |
| 386 | * | |
| 387 | * @see jalview.datamodel.AlignmentI#findGroup(jalview.datamodel.SequenceI) | |
| 388 | */ | |
| 389 | 19 | @Override |
| 390 | public SequenceGroup findGroup(SequenceI seq, int position) | |
| 391 | { | |
| 392 | 19 | synchronized (groups) |
| 393 | { | |
| 394 | 19 | for (SequenceGroup sg : groups) |
| 395 | { | |
| 396 | 23 | if (sg.getSequences(null).contains(seq)) |
| 397 | { | |
| 398 | 16 | if (position >= sg.getStartRes() && position <= sg.getEndRes()) |
| 399 | { | |
| 400 | 10 | return sg; |
| 401 | } | |
| 402 | } | |
| 403 | } | |
| 404 | } | |
| 405 | 9 | return null; |
| 406 | } | |
| 407 | ||
| 408 | /* | |
| 409 | * (non-Javadoc) | |
| 410 | * | |
| 411 | * @see | |
| 412 | * jalview.datamodel.AlignmentI#findAllGroups(jalview.datamodel.SequenceI) | |
| 413 | */ | |
| 414 | 87304 | @Override |
| 415 | public SequenceGroup[] findAllGroups(SequenceI s) | |
| 416 | { | |
| 417 | 87305 | ArrayList<SequenceGroup> temp = new ArrayList<>(); |
| 418 | ||
| 419 | 87305 | synchronized (groups) |
| 420 | { | |
| 421 | 87364 | int gSize = groups.size(); |
| 422 | 95238 | for (int i = 0; i < gSize; i++) |
| 423 | { | |
| 424 | 7874 | SequenceGroup sg = groups.get(i); |
| 425 | 7874 | if (sg == null || sg.getSequences() == null) |
| 426 | { | |
| 427 | 0 | this.deleteGroup(sg); |
| 428 | 0 | gSize--; |
| 429 | 0 | continue; |
| 430 | } | |
| 431 | ||
| 432 | 7874 | if (sg.getSequences().contains(s)) |
| 433 | { | |
| 434 | 5175 | temp.add(sg); |
| 435 | } | |
| 436 | } | |
| 437 | } | |
| 438 | 87364 | SequenceGroup[] ret = new SequenceGroup[temp.size()]; |
| 439 | 87363 | return temp.toArray(ret); |
| 440 | } | |
| 441 | ||
| 442 | /** */ | |
| 443 | 131 | @Override |
| 444 | public void addGroup(SequenceGroup sg) | |
| 445 | { | |
| 446 | 131 | synchronized (groups) |
| 447 | { | |
| 448 | 131 | if (!groups.contains(sg)) |
| 449 | { | |
| 450 | 122 | if (hiddenSequences.getSize() > 0) |
| 451 | { | |
| 452 | 0 | int i, iSize = sg.getSize(); |
| 453 | 0 | for (i = 0; i < iSize; i++) |
| 454 | { | |
| 455 | 0 | if (!sequences.contains(sg.getSequenceAt(i))) |
| 456 | { | |
| 457 | 0 | sg.deleteSequence(sg.getSequenceAt(i), false); |
| 458 | 0 | iSize--; |
| 459 | 0 | i--; |
| 460 | } | |
| 461 | } | |
| 462 | ||
| 463 | 0 | if (sg.getSize() < 1) |
| 464 | { | |
| 465 | 0 | return; |
| 466 | } | |
| 467 | } | |
| 468 | 122 | sg.setContext(this, true); |
| 469 | 122 | groups.add(sg); |
| 470 | } | |
| 471 | } | |
| 472 | } | |
| 473 | ||
| 474 | /** | |
| 475 | * remove any annotation that references gp | |
| 476 | * | |
| 477 | * @param gp | |
| 478 | * (if null, removes all group associated annotation) | |
| 479 | */ | |
| 480 | 1 | private void removeAnnotationForGroup(SequenceGroup gp) |
| 481 | { | |
| 482 | 1 | if (annotations == null || annotations.length == 0) |
| 483 | { | |
| 484 | 0 | return; |
| 485 | } | |
| 486 | // remove annotation very quickly | |
| 487 | 1 | AlignmentAnnotation[] t, |
| 488 | todelete = new AlignmentAnnotation[annotations.length], | |
| 489 | tokeep = new AlignmentAnnotation[annotations.length]; | |
| 490 | 1 | int i, p, k; |
| 491 | 1 | if (gp == null) |
| 492 | { | |
| 493 | 70 | for (i = 0, p = 0, k = 0; i < annotations.length; i++) |
| 494 | { | |
| 495 | 69 | if (annotations[i].groupRef != null) |
| 496 | { | |
| 497 | 0 | todelete[p++] = annotations[i]; |
| 498 | } | |
| 499 | else | |
| 500 | { | |
| 501 | 69 | tokeep[k++] = annotations[i]; |
| 502 | } | |
| 503 | } | |
| 504 | } | |
| 505 | else | |
| 506 | { | |
| 507 | 0 | for (i = 0, p = 0, k = 0; i < annotations.length; i++) |
| 508 | { | |
| 509 | 0 | if (annotations[i].groupRef == gp) |
| 510 | { | |
| 511 | 0 | todelete[p++] = annotations[i]; |
| 512 | } | |
| 513 | else | |
| 514 | { | |
| 515 | 0 | tokeep[k++] = annotations[i]; |
| 516 | } | |
| 517 | } | |
| 518 | } | |
| 519 | 1 | if (p > 0) |
| 520 | { | |
| 521 | // clear out the group associated annotation. | |
| 522 | 0 | for (i = 0; i < p; i++) |
| 523 | { | |
| 524 | 0 | unhookAnnotation(todelete[i]); |
| 525 | 0 | todelete[i] = null; |
| 526 | } | |
| 527 | 0 | t = new AlignmentAnnotation[k]; |
| 528 | 0 | for (i = 0; i < k; i++) |
| 529 | { | |
| 530 | 0 | t[i] = tokeep[i]; |
| 531 | } | |
| 532 | 0 | annotations = t; |
| 533 | } | |
| 534 | } | |
| 535 | ||
| 536 | 1 | @Override |
| 537 | public void deleteAllGroups() | |
| 538 | { | |
| 539 | 1 | synchronized (groups) |
| 540 | { | |
| 541 | 1 | if (annotations != null) |
| 542 | { | |
| 543 | 1 | removeAnnotationForGroup(null); |
| 544 | } | |
| 545 | 1 | for (SequenceGroup sg : groups) |
| 546 | { | |
| 547 | 0 | sg.setContext(null, false); |
| 548 | } | |
| 549 | 1 | groups.clear(); |
| 550 | } | |
| 551 | } | |
| 552 | ||
| 553 | /** */ | |
| 554 | 0 | @Override |
| 555 | public void deleteGroup(SequenceGroup g) | |
| 556 | { | |
| 557 | 0 | synchronized (groups) |
| 558 | { | |
| 559 | 0 | if (groups.contains(g)) |
| 560 | { | |
| 561 | 0 | removeAnnotationForGroup(g); |
| 562 | 0 | groups.remove(g); |
| 563 | 0 | g.setContext(null, false); |
| 564 | } | |
| 565 | } | |
| 566 | } | |
| 567 | ||
| 568 | /** */ | |
| 569 | 397 | @Override |
| 570 | public SequenceI findName(String name) | |
| 571 | { | |
| 572 | 397 | return findName(name, false); |
| 573 | } | |
| 574 | ||
| 575 | /* | |
| 576 | * (non-Javadoc) | |
| 577 | * | |
| 578 | * @see jalview.datamodel.AlignmentI#findName(java.lang.String, boolean) | |
| 579 | */ | |
| 580 | 1503 | @Override |
| 581 | public SequenceI findName(String token, boolean b) | |
| 582 | { | |
| 583 | 1503 | return findName(null, token, b); |
| 584 | } | |
| 585 | ||
| 586 | /* | |
| 587 | * (non-Javadoc) | |
| 588 | * | |
| 589 | * @see jalview.datamodel.AlignmentI#findName(SequenceI, java.lang.String, | |
| 590 | * boolean) | |
| 591 | */ | |
| 592 | 2267 | @Override |
| 593 | public SequenceI findName(SequenceI startAfter, String token, boolean b) | |
| 594 | { | |
| 595 | ||
| 596 | 2267 | int i = 0; |
| 597 | 2267 | SequenceI sq = null; |
| 598 | 2267 | String sqname = null; |
| 599 | 2267 | int nseq = sequences.size(); |
| 600 | 2267 | if (startAfter != null) |
| 601 | { | |
| 602 | // try to find the sequence in the alignment | |
| 603 | 764 | boolean matched = false; |
| 604 | 6689 | while (i < nseq) |
| 605 | { | |
| 606 | 6674 | if (getSequenceAt(i++) == startAfter) |
| 607 | { | |
| 608 | 749 | matched = true; |
| 609 | 749 | break; |
| 610 | } | |
| 611 | } | |
| 612 | 764 | if (!matched) |
| 613 | { | |
| 614 | 15 | i = 0; |
| 615 | } | |
| 616 | } | |
| 617 | 18753 | while (i < nseq) |
| 618 | { | |
| 619 | 17950 | sq = getSequenceAt(i); |
| 620 | 17950 | sqname = sq.getName(); |
| 621 | 17950 | if (sqname.equals(token) // exact match |
| 622 | || (b && // allow imperfect matches - case varies | |
| 623 | (sqname.equalsIgnoreCase(token)))) | |
| 624 | { | |
| 625 | 1464 | return getSequenceAt(i); |
| 626 | } | |
| 627 | ||
| 628 | 16486 | i++; |
| 629 | } | |
| 630 | ||
| 631 | 803 | return null; |
| 632 | } | |
| 633 | ||
| 634 | 22 | @Override |
| 635 | public SequenceI[] findSequenceMatch(String name) | |
| 636 | { | |
| 637 | 22 | Vector matches = new Vector(); |
| 638 | 22 | int i = 0; |
| 639 | ||
| 640 | 493 | while (i < sequences.size()) |
| 641 | { | |
| 642 | 471 | if (getSequenceAt(i).getName().equals(name)) |
| 643 | { | |
| 644 | 5 | matches.addElement(getSequenceAt(i)); |
| 645 | } | |
| 646 | 471 | i++; |
| 647 | } | |
| 648 | ||
| 649 | 22 | SequenceI[] result = new SequenceI[matches.size()]; |
| 650 | 27 | for (i = 0; i < result.length; i++) |
| 651 | { | |
| 652 | 5 | result[i] = (SequenceI) matches.elementAt(i); |
| 653 | } | |
| 654 | ||
| 655 | 22 | return result; |
| 656 | ||
| 657 | } | |
| 658 | ||
| 659 | /* | |
| 660 | * (non-Javadoc) | |
| 661 | * | |
| 662 | * @see jalview.datamodel.AlignmentI#findIndex(jalview.datamodel.SequenceI) | |
| 663 | */ | |
| 664 | 17583 | @Override |
| 665 | public int findIndex(SequenceI s) | |
| 666 | { | |
| 667 | 17583 | int i = 0; |
| 668 | ||
| 669 | 27330988 | while (i < sequences.size()) |
| 670 | { | |
| 671 | 27316191 | if (s == getSequenceAt(i)) |
| 672 | { | |
| 673 | 2786 | return i; |
| 674 | } | |
| 675 | ||
| 676 | 27313405 | i++; |
| 677 | } | |
| 678 | ||
| 679 | 14797 | return -1; |
| 680 | } | |
| 681 | ||
| 682 | /* | |
| 683 | * (non-Javadoc) | |
| 684 | * | |
| 685 | * @see | |
| 686 | * jalview.datamodel.AlignmentI#findIndex(jalview.datamodel.SearchResults) | |
| 687 | */ | |
| 688 | 5 | @Override |
| 689 | public int findIndex(SearchResultsI results) | |
| 690 | { | |
| 691 | 5 | int i = 0; |
| 692 | ||
| 693 | 29 | while (i < sequences.size()) |
| 694 | { | |
| 695 | 29 | if (results.involvesSequence(getSequenceAt(i))) |
| 696 | { | |
| 697 | 5 | return i; |
| 698 | } | |
| 699 | 24 | i++; |
| 700 | } | |
| 701 | 0 | return -1; |
| 702 | } | |
| 703 | ||
| 704 | 76083 | @Override |
| 705 | public int getHeight() | |
| 706 | { | |
| 707 | 76083 | return sequences.size(); |
| 708 | } | |
| 709 | ||
| 710 | 10 | @Override |
| 711 | public int getAbsoluteHeight() | |
| 712 | { | |
| 713 | 10 | return sequences.size() + getHiddenSequences().getSize(); |
| 714 | } | |
| 715 | ||
| 716 | 22067 | @Override |
| 717 | public int getWidth() | |
| 718 | { | |
| 719 | 22067 | int maxLength = -1; |
| 720 | ||
| 721 | 1728372 | for (int i = 0; i < sequences.size(); i++) |
| 722 | { | |
| 723 | 1706305 | maxLength = Math.max(maxLength, getSequenceAt(i).getLength()); |
| 724 | } | |
| 725 | 22067 | return maxLength; |
| 726 | } | |
| 727 | ||
| 728 | 8859 | @Override |
| 729 | public int getVisibleWidth() | |
| 730 | { | |
| 731 | 8859 | int w = getWidth(); |
| 732 | 8859 | if (hiddenCols != null) |
| 733 | { | |
| 734 | 8859 | w -= hiddenCols.getSize(); |
| 735 | } | |
| 736 | 8859 | return w; |
| 737 | } | |
| 738 | ||
| 739 | /** | |
| 740 | * DOCUMENT ME! | |
| 741 | * | |
| 742 | * @param gc | |
| 743 | * DOCUMENT ME! | |
| 744 | */ | |
| 745 | 566 | @Override |
| 746 | public void setGapCharacter(char gc) | |
| 747 | { | |
| 748 | 566 | gapCharacter = gc; |
| 749 | 566 | synchronized (sequences) |
| 750 | { | |
| 751 | 566 | for (SequenceI seq : sequences) |
| 752 | { | |
| 753 | 4784 | seq.setSequence(seq.getSequenceAsString().replace('.', gc) |
| 754 | .replace('-', gc).replace(' ', gc)); | |
| 755 | } | |
| 756 | } | |
| 757 | } | |
| 758 | ||
| 759 | /** | |
| 760 | * DOCUMENT ME! | |
| 761 | * | |
| 762 | * @return DOCUMENT ME! | |
| 763 | */ | |
| 764 | 436 | @Override |
| 765 | public char getGapCharacter() | |
| 766 | { | |
| 767 | 436 | return gapCharacter; |
| 768 | } | |
| 769 | ||
| 770 | /* | |
| 771 | * (non-Javadoc) | |
| 772 | * | |
| 773 | * @see jalview.datamodel.AlignmentI#isAligned() | |
| 774 | */ | |
| 775 | 0 | @Override |
| 776 | public boolean isAligned() | |
| 777 | { | |
| 778 | 0 | return isAligned(false); |
| 779 | } | |
| 780 | ||
| 781 | /* | |
| 782 | * (non-Javadoc) | |
| 783 | * | |
| 784 | * @see jalview.datamodel.AlignmentI#isAligned(boolean) | |
| 785 | */ | |
| 786 | 0 | @Override |
| 787 | public boolean isAligned(boolean includeHidden) | |
| 788 | { | |
| 789 | 0 | int width = getWidth(); |
| 790 | 0 | if (hiddenSequences == null || hiddenSequences.getSize() == 0) |
| 791 | { | |
| 792 | 0 | includeHidden = true; // no hidden sequences to check against. |
| 793 | } | |
| 794 | 0 | for (int i = 0; i < sequences.size(); i++) |
| 795 | { | |
| 796 | 0 | if (includeHidden || !hiddenSequences.isHidden(getSequenceAt(i))) |
| 797 | { | |
| 798 | 0 | if (getSequenceAt(i).getLength() != width) |
| 799 | { | |
| 800 | 0 | return false; |
| 801 | } | |
| 802 | } | |
| 803 | } | |
| 804 | ||
| 805 | 0 | return true; |
| 806 | } | |
| 807 | ||
| 808 | 0 | @Override |
| 809 | public boolean isHidden(int alignmentIndex) | |
| 810 | { | |
| 811 | 0 | return (getHiddenSequences().getHiddenSequence(alignmentIndex) != null); |
| 812 | } | |
| 813 | ||
| 814 | /** | |
| 815 | * Delete all annotations, including auto-calculated if the flag is set true. | |
| 816 | * Returns true if at least one annotation was deleted, else false. | |
| 817 | * | |
| 818 | * @param includingAutoCalculated | |
| 819 | * @return | |
| 820 | */ | |
| 821 | 3 | @Override |
| 822 | public boolean deleteAllAnnotations(boolean includingAutoCalculated) | |
| 823 | { | |
| 824 | 3 | boolean result = false; |
| 825 | 3 | for (AlignmentAnnotation alan : getAlignmentAnnotation()) |
| 826 | { | |
| 827 | 11 | if (!alan.autoCalculated || includingAutoCalculated) |
| 828 | { | |
| 829 | 10 | deleteAnnotation(alan); |
| 830 | 10 | result = true; |
| 831 | } | |
| 832 | } | |
| 833 | 3 | return result; |
| 834 | } | |
| 835 | ||
| 836 | /* | |
| 837 | * (non-Javadoc) | |
| 838 | * | |
| 839 | * @seejalview.datamodel.AlignmentI#deleteAnnotation(jalview.datamodel. | |
| 840 | * AlignmentAnnotation) | |
| 841 | */ | |
| 842 | 10 | @Override |
| 843 | public boolean deleteAnnotation(AlignmentAnnotation aa) | |
| 844 | { | |
| 845 | 10 | return deleteAnnotation(aa, true); |
| 846 | } | |
| 847 | ||
| 848 | 249 | @Override |
| 849 | public boolean deleteAnnotation(AlignmentAnnotation aa, boolean unhook) | |
| 850 | { | |
| 851 | 249 | int aSize = 1; |
| 852 | ||
| 853 | 249 | if (annotations != null) |
| 854 | { | |
| 855 | 249 | aSize = annotations.length; |
| 856 | } | |
| 857 | ||
| 858 | 249 | if (aSize < 1) |
| 859 | { | |
| 860 | 0 | return false; |
| 861 | } | |
| 862 | ||
| 863 | 249 | AlignmentAnnotation[] temp = new AlignmentAnnotation[aSize - 1]; |
| 864 | ||
| 865 | 249 | boolean swap = false; |
| 866 | 249 | int tIndex = 0; |
| 867 | ||
| 868 | 2415 | for (int i = 0; i < aSize; i++) |
| 869 | { | |
| 870 | 2166 | if (annotations[i] == aa) |
| 871 | { | |
| 872 | 249 | swap = true; |
| 873 | 249 | continue; |
| 874 | } | |
| 875 | 1917 | if (tIndex < temp.length) |
| 876 | { | |
| 877 | 1917 | temp[tIndex++] = annotations[i]; |
| 878 | } | |
| 879 | } | |
| 880 | ||
| 881 | 249 | if (swap) |
| 882 | { | |
| 883 | 249 | annotations = temp; |
| 884 | 249 | if (unhook) |
| 885 | { | |
| 886 | 10 | unhookAnnotation(aa); |
| 887 | } | |
| 888 | } | |
| 889 | 249 | return swap; |
| 890 | } | |
| 891 | ||
| 892 | /** | |
| 893 | * remove any object references associated with this annotation | |
| 894 | * | |
| 895 | * @param aa | |
| 896 | */ | |
| 897 | 10 | private void unhookAnnotation(AlignmentAnnotation aa) |
| 898 | { | |
| 899 | 10 | if (aa.sequenceRef != null) |
| 900 | { | |
| 901 | 9 | aa.sequenceRef.removeAlignmentAnnotation(aa); |
| 902 | } | |
| 903 | 10 | if (aa.groupRef != null) |
| 904 | { | |
| 905 | // probably need to do more here in the future (post 2.5.0) | |
| 906 | 0 | aa.groupRef = null; |
| 907 | } | |
| 908 | } | |
| 909 | ||
| 910 | /* | |
| 911 | * (non-Javadoc) | |
| 912 | * | |
| 913 | * @seejalview.datamodel.AlignmentI#addAnnotation(jalview.datamodel. | |
| 914 | * AlignmentAnnotation) | |
| 915 | */ | |
| 916 | 3997 | @Override |
| 917 | public void addAnnotation(AlignmentAnnotation aa) | |
| 918 | { | |
| 919 | 3997 | addAnnotation(aa, -1); |
| 920 | } | |
| 921 | ||
| 922 | /* | |
| 923 | * (non-Javadoc) | |
| 924 | * | |
| 925 | * @seejalview.datamodel.AlignmentI#addAnnotation(jalview.datamodel. | |
| 926 | * AlignmentAnnotation, int) | |
| 927 | */ | |
| 928 | 4260 | @Override |
| 929 | public void addAnnotation(AlignmentAnnotation aa, int pos) | |
| 930 | { | |
| 931 | 4260 | if (aa.getRNAStruc() != null) |
| 932 | { | |
| 933 | 422 | hasRNAStructure = true; |
| 934 | } | |
| 935 | ||
| 936 | 4260 | int aSize = 1; |
| 937 | 4260 | if (annotations != null) |
| 938 | { | |
| 939 | 3561 | aSize = annotations.length + 1; |
| 940 | } | |
| 941 | ||
| 942 | 4260 | AlignmentAnnotation[] temp = new AlignmentAnnotation[aSize]; |
| 943 | 4260 | int i = 0; |
| 944 | 4260 | if (pos == -1 || pos >= aSize) |
| 945 | { | |
| 946 | 3997 | temp[aSize - 1] = aa; |
| 947 | } | |
| 948 | else | |
| 949 | { | |
| 950 | 263 | temp[pos] = aa; |
| 951 | } | |
| 952 | 4260 | if (aSize > 1) |
| 953 | { | |
| 954 | 3540 | int p = 0; |
| 955 | 45489 | for (i = 0; i < (aSize - 1); i++, p++) |
| 956 | { | |
| 957 | 41949 | if (p == pos) |
| 958 | { | |
| 959 | 96 | p++; |
| 960 | } | |
| 961 | 41949 | if (p < temp.length) |
| 962 | { | |
| 963 | 41949 | temp[p] = annotations[i]; |
| 964 | } | |
| 965 | } | |
| 966 | } | |
| 967 | ||
| 968 | 4260 | annotations = temp; |
| 969 | } | |
| 970 | ||
| 971 | 257 | @Override |
| 972 | public void setAnnotationIndex(AlignmentAnnotation aa, int index) | |
| 973 | { | |
| 974 | 257 | if (aa == null || annotations == null || annotations.length - 1 < index) |
| 975 | { | |
| 976 | 0 | return; |
| 977 | } | |
| 978 | ||
| 979 | 257 | int aSize = annotations.length; |
| 980 | 257 | AlignmentAnnotation[] temp = new AlignmentAnnotation[aSize]; |
| 981 | ||
| 982 | 257 | temp[index] = aa; |
| 983 | ||
| 984 | 3558 | for (int i = 0; i < aSize; i++) |
| 985 | { | |
| 986 | 3301 | if (i == index) |
| 987 | { | |
| 988 | 257 | continue; |
| 989 | } | |
| 990 | ||
| 991 | 3044 | if (i < index) |
| 992 | { | |
| 993 | 2771 | temp[i] = annotations[i]; |
| 994 | } | |
| 995 | else | |
| 996 | { | |
| 997 | 273 | temp[i] = annotations[i - 1]; |
| 998 | } | |
| 999 | } | |
| 1000 | ||
| 1001 | 257 | annotations = temp; |
| 1002 | } | |
| 1003 | ||
| 1004 | 57201 | @Override |
| 1005 | /** | |
| 1006 | * returns all annotation on the alignment | |
| 1007 | */ | |
| 1008 | public AlignmentAnnotation[] getAlignmentAnnotation() | |
| 1009 | { | |
| 1010 | 57201 | return annotations; |
| 1011 | } | |
| 1012 | ||
| 1013 | 18606 | @Override |
| 1014 | public boolean isNucleotide() | |
| 1015 | { | |
| 1016 | 18606 | return nucleotide; |
| 1017 | } | |
| 1018 | ||
| 1019 | 1072 | @Override |
| 1020 | public boolean hasRNAStructure() | |
| 1021 | { | |
| 1022 | // TODO can it happen that structure is removed from alignment? | |
| 1023 | 1072 | return hasRNAStructure; |
| 1024 | } | |
| 1025 | ||
| 1026 | 671 | @Override |
| 1027 | public void setDataset(AlignmentI data) | |
| 1028 | { | |
| 1029 | 671 | if (dataset == null && data == null) |
| 1030 | { | |
| 1031 | 586 | createDatasetAlignment(); |
| 1032 | } | |
| 1033 | 85 | else if (dataset == null && data != null) |
| 1034 | { | |
| 1035 | 70 | if (data == this) |
| 1036 | { | |
| 1037 | 1 | throw new IllegalArgumentException("Circular dataset reference"); |
| 1038 | } | |
| 1039 | 69 | if (!(data instanceof Alignment)) |
| 1040 | { | |
| 1041 | 0 | throw new Error( |
| 1042 | "Implementation Error: jalview.datamodel.Alignment does not yet support other implementations of AlignmentI as its dataset reference"); | |
| 1043 | } | |
| 1044 | 69 | dataset = (Alignment) data; |
| 1045 | 910 | for (int i = 0; i < getHeight(); i++) |
| 1046 | { | |
| 1047 | 841 | SequenceI currentSeq = getSequenceAt(i); |
| 1048 | 841 | SequenceI dsq = currentSeq.getDatasetSequence(); |
| 1049 | 841 | if (dsq == null) |
| 1050 | { | |
| 1051 | 0 | dsq = currentSeq.createDatasetSequence(); |
| 1052 | 0 | dataset.addSequence(dsq); |
| 1053 | } | |
| 1054 | else | |
| 1055 | { | |
| 1056 | 841 | while (dsq.getDatasetSequence() != null) |
| 1057 | { | |
| 1058 | 0 | dsq = dsq.getDatasetSequence(); |
| 1059 | } | |
| 1060 | 841 | if (dataset.findIndex(dsq) == -1) |
| 1061 | { | |
| 1062 | 0 | dataset.addSequence(dsq); |
| 1063 | } | |
| 1064 | } | |
| 1065 | } | |
| 1066 | } | |
| 1067 | 670 | dataset.addAlignmentRef(); |
| 1068 | } | |
| 1069 | ||
| 1070 | /** | |
| 1071 | * add dataset sequences to seq for currentSeq and any sequences it references | |
| 1072 | */ | |
| 1073 | 4263 | private void resolveAndAddDatasetSeq(SequenceI currentSeq, |
| 1074 | Set<SequenceI> seqs, boolean createDatasetSequence) | |
| 1075 | { | |
| 1076 | 4263 | SequenceI alignedSeq = currentSeq; |
| 1077 | 4263 | if (currentSeq.getDatasetSequence() != null) |
| 1078 | { | |
| 1079 | 822 | currentSeq = currentSeq.getDatasetSequence(); |
| 1080 | } | |
| 1081 | else | |
| 1082 | { | |
| 1083 | 3441 | if (createDatasetSequence) |
| 1084 | { | |
| 1085 | 3441 | currentSeq = currentSeq.createDatasetSequence(); |
| 1086 | } | |
| 1087 | } | |
| 1088 | ||
| 1089 | 4263 | List<SequenceI> toProcess = new ArrayList<>(); |
| 1090 | 4263 | toProcess.add(currentSeq); |
| 1091 | 8532 | while (toProcess.size() > 0) |
| 1092 | { | |
| 1093 | // use a queue ? | |
| 1094 | 4269 | SequenceI curDs = toProcess.remove(0); |
| 1095 | ||
| 1096 | 4269 | if (!seqs.add(curDs)) |
| 1097 | { | |
| 1098 | 109 | continue; |
| 1099 | } | |
| 1100 | // iterate over database references, making sure we add forward referenced | |
| 1101 | // sequences | |
| 1102 | 4160 | if (curDs.getDBRefs() != null) |
| 1103 | { | |
| 1104 | 572 | for (DBRefEntry dbr : curDs.getDBRefs()) |
| 1105 | { | |
| 1106 | 778 | if (dbr.getMap() != null && dbr.getMap().getTo() != null) |
| 1107 | { | |
| 1108 | 6 | if (dbr.getMap().getTo() == alignedSeq) |
| 1109 | { | |
| 1110 | /* | |
| 1111 | * update mapping to be to the newly created dataset sequence | |
| 1112 | */ | |
| 1113 | 2 | dbr.getMap().setTo(currentSeq); |
| 1114 | } | |
| 1115 | 6 | if (dbr.getMap().getTo().getDatasetSequence() != null) |
| 1116 | { | |
| 1117 | 0 | throw new Error("Implementation error: Map.getTo() for dbref " |
| 1118 | + dbr + " from " + curDs.getName() | |
| 1119 | + " is not a dataset sequence."); | |
| 1120 | } | |
| 1121 | // we recurse to add all forward references to dataset sequences via | |
| 1122 | // DBRefs/etc | |
| 1123 | 6 | toProcess.add(dbr.getMap().getTo()); |
| 1124 | } | |
| 1125 | } | |
| 1126 | } | |
| 1127 | } | |
| 1128 | } | |
| 1129 | ||
| 1130 | /** | |
| 1131 | * Creates a new dataset for this alignment. Can only be done once - if | |
| 1132 | * dataset is not null this will not be performed. | |
| 1133 | */ | |
| 1134 | 601 | public void createDatasetAlignment() |
| 1135 | { | |
| 1136 | 601 | if (dataset != null) |
| 1137 | { | |
| 1138 | 0 | return; |
| 1139 | } | |
| 1140 | // try to avoid using SequenceI.equals at this stage, it will be expensive | |
| 1141 | 601 | Set<SequenceI> seqs = new LinkedIdentityHashSet<>(); |
| 1142 | ||
| 1143 | 4864 | for (int i = 0; i < getHeight(); i++) |
| 1144 | { | |
| 1145 | 4263 | SequenceI currentSeq = getSequenceAt(i); |
| 1146 | 4263 | resolveAndAddDatasetSeq(currentSeq, seqs, true); |
| 1147 | } | |
| 1148 | ||
| 1149 | // verify all mappings are in dataset | |
| 1150 | 601 | for (AlignedCodonFrame cf : codonFrameList) |
| 1151 | { | |
| 1152 | 3 | for (SequenceToSequenceMapping ssm : cf.getMappings()) |
| 1153 | { | |
| 1154 | 1 | if (!seqs.contains(ssm.getFromSeq())) |
| 1155 | { | |
| 1156 | 0 | resolveAndAddDatasetSeq(ssm.getFromSeq(), seqs, false); |
| 1157 | } | |
| 1158 | 1 | if (!seqs.contains(ssm.getMapping().getTo())) |
| 1159 | { | |
| 1160 | 0 | resolveAndAddDatasetSeq(ssm.getMapping().getTo(), seqs, false); |
| 1161 | } | |
| 1162 | } | |
| 1163 | } | |
| 1164 | // finally construct dataset | |
| 1165 | 601 | dataset = new Alignment(seqs.toArray(new SequenceI[seqs.size()])); |
| 1166 | // move mappings to the dataset alignment | |
| 1167 | 601 | dataset.codonFrameList = this.codonFrameList; |
| 1168 | 601 | this.codonFrameList = null; |
| 1169 | } | |
| 1170 | ||
| 1171 | /** | |
| 1172 | * reference count for number of alignments referencing this one. | |
| 1173 | */ | |
| 1174 | int alignmentRefs = 0; | |
| 1175 | ||
| 1176 | /** | |
| 1177 | * increase reference count to this alignment. | |
| 1178 | */ | |
| 1179 | 670 | private void addAlignmentRef() |
| 1180 | { | |
| 1181 | 670 | alignmentRefs++; |
| 1182 | } | |
| 1183 | ||
| 1184 | 3025 | @Override |
| 1185 | public Alignment getDataset() | |
| 1186 | { | |
| 1187 | 3025 | return dataset; |
| 1188 | } | |
| 1189 | ||
| 1190 | 730 | @Override |
| 1191 | public boolean padGaps() | |
| 1192 | { | |
| 1193 | 730 | boolean modified = false; |
| 1194 | ||
| 1195 | // Remove excess gaps from the end of alignment | |
| 1196 | 730 | int maxLength = -1; |
| 1197 | ||
| 1198 | 730 | SequenceI current; |
| 1199 | 730 | int nseq = sequences.size(); |
| 1200 | 6218 | for (int i = 0; i < nseq; i++) |
| 1201 | { | |
| 1202 | 5488 | current = getSequenceAt(i); |
| 1203 | 14550 | for (int j = current.getLength(); j > maxLength; j--) |
| 1204 | { | |
| 1205 | 10096 | if (j > maxLength |
| 1206 | && !jalview.util.Comparison.isGap(current.getCharAt(j))) | |
| 1207 | { | |
| 1208 | 1034 | maxLength = j; |
| 1209 | 1034 | break; |
| 1210 | } | |
| 1211 | } | |
| 1212 | } | |
| 1213 | ||
| 1214 | 730 | maxLength++; |
| 1215 | ||
| 1216 | 730 | int cLength; |
| 1217 | 6218 | for (int i = 0; i < nseq; i++) |
| 1218 | { | |
| 1219 | 5488 | current = getSequenceAt(i); |
| 1220 | 5488 | cLength = current.getLength(); |
| 1221 | ||
| 1222 | 5488 | if (cLength < maxLength) |
| 1223 | { | |
| 1224 | 75 | current.insertCharAt(cLength, maxLength - cLength, gapCharacter); |
| 1225 | 75 | modified = true; |
| 1226 | } | |
| 1227 | 5413 | else if (current.getLength() > maxLength) |
| 1228 | { | |
| 1229 | 2 | current.deleteChars(maxLength, current.getLength()); |
| 1230 | } | |
| 1231 | } | |
| 1232 | 730 | return modified; |
| 1233 | } | |
| 1234 | ||
| 1235 | /** | |
| 1236 | * Justify the sequences to the left or right by deleting and inserting gaps | |
| 1237 | * before the initial residue or after the terminal residue | |
| 1238 | * | |
| 1239 | * @param right | |
| 1240 | * true if alignment padded to right, false to justify to left | |
| 1241 | * @return true if alignment was changed | |
| 1242 | */ | |
| 1243 | 0 | @Override |
| 1244 | public boolean justify(boolean right) | |
| 1245 | { | |
| 1246 | 0 | boolean modified = false; |
| 1247 | ||
| 1248 | // Remove excess gaps from the end of alignment | |
| 1249 | 0 | int maxLength = -1; |
| 1250 | 0 | int ends[] = new int[sequences.size() * 2]; |
| 1251 | 0 | SequenceI current; |
| 1252 | 0 | for (int i = 0; i < sequences.size(); i++) |
| 1253 | { | |
| 1254 | 0 | current = getSequenceAt(i); |
| 1255 | // This should really be a sequence method | |
| 1256 | 0 | ends[i * 2] = current.findIndex(current.getStart()); |
| 1257 | 0 | ends[i * 2 + 1] = current |
| 1258 | .findIndex(current.getStart() + current.getLength()); | |
| 1259 | 0 | boolean hitres = false; |
| 1260 | 0 | for (int j = 0, rs = 0, ssiz = current.getLength(); j < ssiz; j++) |
| 1261 | { | |
| 1262 | 0 | if (!jalview.util.Comparison.isGap(current.getCharAt(j))) |
| 1263 | { | |
| 1264 | 0 | if (!hitres) |
| 1265 | { | |
| 1266 | 0 | ends[i * 2] = j; |
| 1267 | 0 | hitres = true; |
| 1268 | } | |
| 1269 | else | |
| 1270 | { | |
| 1271 | 0 | ends[i * 2 + 1] = j; |
| 1272 | 0 | if (j - ends[i * 2] > maxLength) |
| 1273 | { | |
| 1274 | 0 | maxLength = j - ends[i * 2]; |
| 1275 | } | |
| 1276 | } | |
| 1277 | } | |
| 1278 | } | |
| 1279 | } | |
| 1280 | ||
| 1281 | 0 | maxLength++; |
| 1282 | // now edit the flanking gaps to justify to either left or right | |
| 1283 | 0 | int cLength, extent, diff; |
| 1284 | 0 | for (int i = 0; i < sequences.size(); i++) |
| 1285 | { | |
| 1286 | 0 | current = getSequenceAt(i); |
| 1287 | ||
| 1288 | 0 | cLength = 1 + ends[i * 2 + 1] - ends[i * 2]; |
| 1289 | 0 | diff = maxLength - cLength; // number of gaps to indent |
| 1290 | 0 | extent = current.getLength(); |
| 1291 | 0 | if (right) |
| 1292 | { | |
| 1293 | // right justify | |
| 1294 | 0 | if (extent > ends[i * 2 + 1]) |
| 1295 | { | |
| 1296 | 0 | current.deleteChars(ends[i * 2 + 1] + 1, extent); |
| 1297 | 0 | modified = true; |
| 1298 | } | |
| 1299 | 0 | if (ends[i * 2] > diff) |
| 1300 | { | |
| 1301 | 0 | current.deleteChars(0, ends[i * 2] - diff); |
| 1302 | 0 | modified = true; |
| 1303 | } | |
| 1304 | else | |
| 1305 | { | |
| 1306 | 0 | if (ends[i * 2] < diff) |
| 1307 | { | |
| 1308 | 0 | current.insertCharAt(0, diff - ends[i * 2], gapCharacter); |
| 1309 | 0 | modified = true; |
| 1310 | } | |
| 1311 | } | |
| 1312 | } | |
| 1313 | else | |
| 1314 | { | |
| 1315 | // left justify | |
| 1316 | 0 | if (ends[i * 2] > 0) |
| 1317 | { | |
| 1318 | 0 | current.deleteChars(0, ends[i * 2]); |
| 1319 | 0 | modified = true; |
| 1320 | 0 | ends[i * 2 + 1] -= ends[i * 2]; |
| 1321 | 0 | extent -= ends[i * 2]; |
| 1322 | } | |
| 1323 | 0 | if (extent > maxLength) |
| 1324 | { | |
| 1325 | 0 | current.deleteChars(maxLength + 1, extent); |
| 1326 | 0 | modified = true; |
| 1327 | } | |
| 1328 | else | |
| 1329 | { | |
| 1330 | 0 | if (extent < maxLength) |
| 1331 | { | |
| 1332 | 0 | current.insertCharAt(extent, maxLength - extent, gapCharacter); |
| 1333 | 0 | modified = true; |
| 1334 | } | |
| 1335 | } | |
| 1336 | } | |
| 1337 | } | |
| 1338 | 0 | return modified; |
| 1339 | } | |
| 1340 | ||
| 1341 | 16519 | @Override |
| 1342 | public HiddenSequences getHiddenSequences() | |
| 1343 | { | |
| 1344 | 16519 | return hiddenSequences; |
| 1345 | } | |
| 1346 | ||
| 1347 | 28250 | @Override |
| 1348 | public HiddenColumns getHiddenColumns() | |
| 1349 | { | |
| 1350 | 28250 | return hiddenCols; |
| 1351 | } | |
| 1352 | ||
| 1353 | 0 | @Override |
| 1354 | public CigarArray getCompactAlignment() | |
| 1355 | { | |
| 1356 | 0 | synchronized (sequences) |
| 1357 | { | |
| 1358 | 0 | SeqCigar alseqs[] = new SeqCigar[sequences.size()]; |
| 1359 | 0 | int i = 0; |
| 1360 | 0 | for (SequenceI seq : sequences) |
| 1361 | { | |
| 1362 | 0 | alseqs[i++] = new SeqCigar(seq); |
| 1363 | } | |
| 1364 | 0 | CigarArray cal = new CigarArray(alseqs); |
| 1365 | 0 | cal.addOperation(CigarArray.M, getWidth()); |
| 1366 | 0 | return cal; |
| 1367 | } | |
| 1368 | } | |
| 1369 | ||
| 1370 | 143 | @Override |
| 1371 | public void setProperty(Object key, Object value) | |
| 1372 | { | |
| 1373 | 143 | if (alignmentProperties == null) |
| 1374 | { | |
| 1375 | 15 | alignmentProperties = new Hashtable(); |
| 1376 | } | |
| 1377 | ||
| 1378 | 143 | alignmentProperties.put(key, value); |
| 1379 | } | |
| 1380 | ||
| 1381 | 0 | @Override |
| 1382 | public Object getProperty(Object key) | |
| 1383 | { | |
| 1384 | 0 | if (alignmentProperties != null) |
| 1385 | { | |
| 1386 | 0 | return alignmentProperties.get(key); |
| 1387 | } | |
| 1388 | else | |
| 1389 | { | |
| 1390 | 0 | return null; |
| 1391 | } | |
| 1392 | } | |
| 1393 | ||
| 1394 | 368 | @Override |
| 1395 | public Hashtable getProperties() | |
| 1396 | { | |
| 1397 | 368 | return alignmentProperties; |
| 1398 | } | |
| 1399 | ||
| 1400 | /** | |
| 1401 | * Adds the given mapping to the stored set. Note this may be held on the | |
| 1402 | * dataset alignment. | |
| 1403 | */ | |
| 1404 | 81 | @Override |
| 1405 | public void addCodonFrame(AlignedCodonFrame codons) | |
| 1406 | { | |
| 1407 | 81 | List<AlignedCodonFrame> acfs = getCodonFrames(); |
| 1408 | 81 | if (codons != null && acfs != null && !acfs.contains(codons)) |
| 1409 | { | |
| 1410 | 78 | acfs.add(codons); |
| 1411 | } | |
| 1412 | } | |
| 1413 | ||
| 1414 | /* | |
| 1415 | * (non-Javadoc) | |
| 1416 | * | |
| 1417 | * @see | |
| 1418 | * jalview.datamodel.AlignmentI#getCodonFrame(jalview.datamodel.SequenceI) | |
| 1419 | */ | |
| 1420 | 53 | @Override |
| 1421 | public List<AlignedCodonFrame> getCodonFrame(SequenceI seq) | |
| 1422 | { | |
| 1423 | 53 | if (seq == null) |
| 1424 | { | |
| 1425 | 0 | return null; |
| 1426 | } | |
| 1427 | 53 | List<AlignedCodonFrame> cframes = new ArrayList<>(); |
| 1428 | 53 | for (AlignedCodonFrame acf : getCodonFrames()) |
| 1429 | { | |
| 1430 | 105 | if (acf.involvesSequence(seq)) |
| 1431 | { | |
| 1432 | 46 | cframes.add(acf); |
| 1433 | } | |
| 1434 | } | |
| 1435 | 53 | return cframes; |
| 1436 | } | |
| 1437 | ||
| 1438 | /** | |
| 1439 | * Sets the codon frame mappings (replacing any existing mappings). Note the | |
| 1440 | * mappings are set on the dataset alignment instead if there is one. | |
| 1441 | * | |
| 1442 | * @see jalview.datamodel.AlignmentI#setCodonFrames() | |
| 1443 | */ | |
| 1444 | 52 | @Override |
| 1445 | public void setCodonFrames(List<AlignedCodonFrame> acfs) | |
| 1446 | { | |
| 1447 | 52 | if (dataset != null) |
| 1448 | { | |
| 1449 | 24 | dataset.setCodonFrames(acfs); |
| 1450 | } | |
| 1451 | else | |
| 1452 | { | |
| 1453 | 28 | this.codonFrameList = acfs; |
| 1454 | } | |
| 1455 | } | |
| 1456 | ||
| 1457 | /** | |
| 1458 | * Returns the set of codon frame mappings. Any changes to the returned set | |
| 1459 | * will affect the alignment. The mappings are held on (and read from) the | |
| 1460 | * dataset alignment if there is one. | |
| 1461 | * | |
| 1462 | * @see jalview.datamodel.AlignmentI#getCodonFrames() | |
| 1463 | */ | |
| 1464 | 7853 | @Override |
| 1465 | public List<AlignedCodonFrame> getCodonFrames() | |
| 1466 | { | |
| 1467 | // TODO: Fix this method to fix failing AlignedCodonFrame tests | |
| 1468 | // this behaviour is currently incorrect. method should return codon frames | |
| 1469 | // for just the alignment, | |
| 1470 | // selected from dataset | |
| 1471 | 7853 | return dataset != null ? dataset.getCodonFrames() : codonFrameList; |
| 1472 | } | |
| 1473 | ||
| 1474 | /** | |
| 1475 | * Removes the given mapping from the stored set. Note that the mappings are | |
| 1476 | * held on the dataset alignment if there is one. | |
| 1477 | */ | |
| 1478 | 0 | @Override |
| 1479 | public boolean removeCodonFrame(AlignedCodonFrame codons) | |
| 1480 | { | |
| 1481 | 0 | List<AlignedCodonFrame> acfs = getCodonFrames(); |
| 1482 | 0 | if (codons == null || acfs == null) |
| 1483 | { | |
| 1484 | 0 | return false; |
| 1485 | } | |
| 1486 | 0 | return acfs.remove(codons); |
| 1487 | } | |
| 1488 | ||
| 1489 | 1 | @Override |
| 1490 | public void append(AlignmentI toappend) | |
| 1491 | { | |
| 1492 | // TODO JAL-1270 needs test coverage | |
| 1493 | // currently tested for use in jalview.gui.SequenceFetcher | |
| 1494 | 1 | char oldc = toappend.getGapCharacter(); |
| 1495 | 1 | boolean samegap = oldc == getGapCharacter(); |
| 1496 | 1 | boolean hashidden = toappend.getHiddenSequences() != null |
| 1497 | && toappend.getHiddenSequences().hiddenSequences != null; | |
| 1498 | // get all sequences including any hidden ones | |
| 1499 | 1 | List<SequenceI> sqs = (hashidden) |
| 1500 | ? toappend.getHiddenSequences().getFullAlignment() | |
| 1501 | .getSequences() | |
| 1502 | : toappend.getSequences(); | |
| 1503 | 1 | if (sqs != null) |
| 1504 | { | |
| 1505 | // avoid self append deadlock by | |
| 1506 | 1 | List<SequenceI> toappendsq = new ArrayList<>(); |
| 1507 | 1 | synchronized (sqs) |
| 1508 | { | |
| 1509 | 1 | for (SequenceI addedsq : sqs) |
| 1510 | { | |
| 1511 | 1 | if (!samegap) |
| 1512 | { | |
| 1513 | 1 | addedsq.replace(oldc, gapCharacter); |
| 1514 | } | |
| 1515 | 1 | toappendsq.add(addedsq); |
| 1516 | } | |
| 1517 | } | |
| 1518 | 1 | for (SequenceI addedsq : toappendsq) |
| 1519 | { | |
| 1520 | 1 | addSequence(addedsq); |
| 1521 | } | |
| 1522 | } | |
| 1523 | 1 | AlignmentAnnotation[] alan = toappend.getAlignmentAnnotation(); |
| 1524 | 1 | for (int a = 0; alan != null && a < alan.length; a++) |
| 1525 | { | |
| 1526 | 0 | addAnnotation(alan[a]); |
| 1527 | } | |
| 1528 | ||
| 1529 | // use add method | |
| 1530 | 1 | getCodonFrames().addAll(toappend.getCodonFrames()); |
| 1531 | ||
| 1532 | 1 | List<SequenceGroup> sg = toappend.getGroups(); |
| 1533 | 1 | if (sg != null) |
| 1534 | { | |
| 1535 | 1 | for (SequenceGroup _sg : sg) |
| 1536 | { | |
| 1537 | 0 | addGroup(_sg); |
| 1538 | } | |
| 1539 | } | |
| 1540 | 1 | if (toappend.getHiddenSequences() != null) |
| 1541 | { | |
| 1542 | 1 | HiddenSequences hs = toappend.getHiddenSequences(); |
| 1543 | 1 | if (hiddenSequences == null) |
| 1544 | { | |
| 1545 | 0 | hiddenSequences = new HiddenSequences(this); |
| 1546 | } | |
| 1547 | 1 | if (hs.hiddenSequences != null) |
| 1548 | { | |
| 1549 | 0 | for (int s = 0; s < hs.hiddenSequences.length; s++) |
| 1550 | { | |
| 1551 | // hide the newly appended sequence in the alignment | |
| 1552 | 0 | if (hs.hiddenSequences[s] != null) |
| 1553 | { | |
| 1554 | 0 | hiddenSequences.hideSequence(hs.hiddenSequences[s]); |
| 1555 | } | |
| 1556 | } | |
| 1557 | } | |
| 1558 | } | |
| 1559 | 1 | if (toappend.getProperties() != null) |
| 1560 | { | |
| 1561 | // we really can't do very much here - just try to concatenate strings | |
| 1562 | // where property collisions occur. | |
| 1563 | 0 | Enumeration key = toappend.getProperties().keys(); |
| 1564 | 0 | while (key.hasMoreElements()) |
| 1565 | { | |
| 1566 | 0 | Object k = key.nextElement(); |
| 1567 | 0 | Object ourval = this.getProperty(k); |
| 1568 | 0 | Object toapprop = toappend.getProperty(k); |
| 1569 | 0 | if (ourval != null) |
| 1570 | { | |
| 1571 | 0 | if (ourval.getClass().equals(toapprop.getClass()) |
| 1572 | && !ourval.equals(toapprop)) | |
| 1573 | { | |
| 1574 | 0 | if (ourval instanceof String) |
| 1575 | { | |
| 1576 | // append strings | |
| 1577 | 0 | this.setProperty(k, |
| 1578 | ((String) ourval) + "; " + ((String) toapprop)); | |
| 1579 | } | |
| 1580 | else | |
| 1581 | { | |
| 1582 | 0 | if (ourval instanceof Vector) |
| 1583 | { | |
| 1584 | // append vectors | |
| 1585 | 0 | Enumeration theirv = ((Vector) toapprop).elements(); |
| 1586 | 0 | while (theirv.hasMoreElements()) |
| 1587 | { | |
| 1588 | 0 | ((Vector) ourval).addElement(theirv); |
| 1589 | } | |
| 1590 | } | |
| 1591 | } | |
| 1592 | } | |
| 1593 | } | |
| 1594 | else | |
| 1595 | { | |
| 1596 | // just add new property directly | |
| 1597 | 0 | setProperty(k, toapprop); |
| 1598 | } | |
| 1599 | ||
| 1600 | } | |
| 1601 | } | |
| 1602 | } | |
| 1603 | ||
| 1604 | 19 | @Override |
| 1605 | public AlignmentAnnotation findOrCreateAnnotation(String name, | |
| 1606 | String calcId, boolean autoCalc, SequenceI seqRef, | |
| 1607 | SequenceGroup groupRef) | |
| 1608 | { | |
| 1609 | 19 | if (annotations != null) |
| 1610 | { | |
| 1611 | 18 | for (AlignmentAnnotation annot : getAlignmentAnnotation()) |
| 1612 | { | |
| 1613 | 189 | if (annot.autoCalculated == autoCalc && (name.equals(annot.label)) |
| 1614 | && (calcId == null || annot.getCalcId().equals(calcId)) | |
| 1615 | && annot.sequenceRef == seqRef | |
| 1616 | && annot.groupRef == groupRef) | |
| 1617 | { | |
| 1618 | 1 | return annot; |
| 1619 | } | |
| 1620 | } | |
| 1621 | } | |
| 1622 | 18 | AlignmentAnnotation annot = new AlignmentAnnotation(name, name, |
| 1623 | new Annotation[1], 0f, 0f, AlignmentAnnotation.BAR_GRAPH); | |
| 1624 | 18 | annot.hasText = false; |
| 1625 | 18 | if (calcId != null) |
| 1626 | { | |
| 1627 | 17 | annot.setCalcId(new String(calcId)); |
| 1628 | } | |
| 1629 | 18 | annot.autoCalculated = autoCalc; |
| 1630 | 18 | if (seqRef != null) |
| 1631 | { | |
| 1632 | 16 | annot.setSequenceRef(seqRef); |
| 1633 | } | |
| 1634 | 18 | annot.groupRef = groupRef; |
| 1635 | 18 | addAnnotation(annot); |
| 1636 | ||
| 1637 | 18 | return annot; |
| 1638 | } | |
| 1639 | ||
| 1640 | 529 | @Override |
| 1641 | public Iterable<AlignmentAnnotation> findAnnotation(String calcId) | |
| 1642 | { | |
| 1643 | 529 | AlignmentAnnotation[] alignmentAnnotation = getAlignmentAnnotation(); |
| 1644 | 529 | if (alignmentAnnotation != null) |
| 1645 | { | |
| 1646 | 520 | return AlignmentAnnotation.findAnnotation( |
| 1647 | Arrays.asList(getAlignmentAnnotation()), calcId); | |
| 1648 | } | |
| 1649 | 9 | return Arrays.asList(new AlignmentAnnotation[] {}); |
| 1650 | } | |
| 1651 | ||
| 1652 | 201 | @Override |
| 1653 | public Iterable<AlignmentAnnotation> findAnnotations(SequenceI seq, | |
| 1654 | String calcId, String label) | |
| 1655 | { | |
| 1656 | 201 | return annotations == null ? null |
| 1657 | : AlignmentAnnotation.findAnnotations( | |
| 1658 | Arrays.asList(getAlignmentAnnotation()), seq, calcId, | |
| 1659 | label); | |
| 1660 | } | |
| 1661 | ||
| 1662 | 0 | @Override |
| 1663 | public void moveSelectedSequencesByOne(SequenceGroup sg, | |
| 1664 | Map<SequenceI, SequenceCollectionI> map, boolean up) | |
| 1665 | { | |
| 1666 | 0 | synchronized (sequences) |
| 1667 | { | |
| 1668 | 0 | if (up) |
| 1669 | { | |
| 1670 | ||
| 1671 | 0 | for (int i = 1, iSize = sequences.size(); i < iSize; i++) |
| 1672 | { | |
| 1673 | 0 | SequenceI seq = sequences.get(i); |
| 1674 | 0 | if (!sg.getSequences(map).contains(seq)) |
| 1675 | { | |
| 1676 | 0 | continue; |
| 1677 | } | |
| 1678 | ||
| 1679 | 0 | SequenceI temp = sequences.get(i - 1); |
| 1680 | 0 | if (sg.getSequences(null).contains(temp)) |
| 1681 | { | |
| 1682 | 0 | continue; |
| 1683 | } | |
| 1684 | ||
| 1685 | 0 | sequences.set(i, temp); |
| 1686 | 0 | sequences.set(i - 1, seq); |
| 1687 | } | |
| 1688 | } | |
| 1689 | else | |
| 1690 | { | |
| 1691 | 0 | for (int i = sequences.size() - 2; i > -1; i--) |
| 1692 | { | |
| 1693 | 0 | SequenceI seq = sequences.get(i); |
| 1694 | 0 | if (!sg.getSequences(map).contains(seq)) |
| 1695 | { | |
| 1696 | 0 | continue; |
| 1697 | } | |
| 1698 | ||
| 1699 | 0 | SequenceI temp = sequences.get(i + 1); |
| 1700 | 0 | if (sg.getSequences(map).contains(temp)) |
| 1701 | { | |
| 1702 | 0 | continue; |
| 1703 | } | |
| 1704 | ||
| 1705 | 0 | sequences.set(i, temp); |
| 1706 | 0 | sequences.set(i + 1, seq); |
| 1707 | } | |
| 1708 | } | |
| 1709 | ||
| 1710 | } | |
| 1711 | } | |
| 1712 | ||
| 1713 | 0 | @Override |
| 1714 | public void validateAnnotation(AlignmentAnnotation alignmentAnnotation) | |
| 1715 | { | |
| 1716 | 0 | alignmentAnnotation.validateRangeAndDisplay(); |
| 1717 | 0 | if (isNucleotide() && alignmentAnnotation.isValidStruc()) |
| 1718 | { | |
| 1719 | 0 | hasRNAStructure = true; |
| 1720 | } | |
| 1721 | } | |
| 1722 | ||
| 1723 | private SequenceI seqrep = null; | |
| 1724 | ||
| 1725 | /** | |
| 1726 | * | |
| 1727 | * @return the representative sequence for this group | |
| 1728 | */ | |
| 1729 | 19126 | @Override |
| 1730 | public SequenceI getSeqrep() | |
| 1731 | { | |
| 1732 | 19126 | return seqrep; |
| 1733 | } | |
| 1734 | ||
| 1735 | /** | |
| 1736 | * set the representative sequence for this group. Note - this affects the | |
| 1737 | * interpretation of the Hidereps attribute. | |
| 1738 | * | |
| 1739 | * @param seqrep | |
| 1740 | * the seqrep to set (null means no sequence representative) | |
| 1741 | */ | |
| 1742 | 200 | @Override |
| 1743 | public void setSeqrep(SequenceI seqrep) | |
| 1744 | { | |
| 1745 | 200 | this.seqrep = seqrep; |
| 1746 | } | |
| 1747 | ||
| 1748 | /** | |
| 1749 | * | |
| 1750 | * @return true if group has a sequence representative | |
| 1751 | */ | |
| 1752 | 23902 | @Override |
| 1753 | public boolean hasSeqrep() | |
| 1754 | { | |
| 1755 | 23902 | return seqrep != null; |
| 1756 | } | |
| 1757 | ||
| 1758 | 31 | @Override |
| 1759 | public int getEndRes() | |
| 1760 | { | |
| 1761 | 31 | return getWidth() - 1; |
| 1762 | } | |
| 1763 | ||
| 1764 | 31 | @Override |
| 1765 | public int getStartRes() | |
| 1766 | { | |
| 1767 | 31 | return 0; |
| 1768 | } | |
| 1769 | ||
| 1770 | /* | |
| 1771 | * In the case of AlignmentI - returns the dataset for the alignment, if set | |
| 1772 | * (non-Javadoc) | |
| 1773 | * | |
| 1774 | * @see jalview.datamodel.AnnotatedCollectionI#getContext() | |
| 1775 | */ | |
| 1776 | 552 | @Override |
| 1777 | public AnnotatedCollectionI getContext() | |
| 1778 | { | |
| 1779 | 552 | return dataset; |
| 1780 | } | |
| 1781 | ||
| 1782 | /** | |
| 1783 | * Align this alignment like the given (mapped) one. | |
| 1784 | */ | |
| 1785 | 4 | @Override |
| 1786 | public int alignAs(AlignmentI al) | |
| 1787 | { | |
| 1788 | /* | |
| 1789 | * Currently retains unmapped gaps (in introns), regaps mapped regions | |
| 1790 | * (exons) | |
| 1791 | */ | |
| 1792 | 4 | return alignAs(al, false, true); |
| 1793 | } | |
| 1794 | ||
| 1795 | /** | |
| 1796 | * Align this alignment 'the same as' the given one. Mapped sequences only are | |
| 1797 | * realigned. If both of the same type (nucleotide/protein) then align both | |
| 1798 | * identically. If this is nucleotide and the other is protein, make 3 gaps | |
| 1799 | * for each gap in the protein sequences. If this is protein and the other is | |
| 1800 | * nucleotide, insert a gap for each 3 gaps (or part thereof) between | |
| 1801 | * nucleotide bases. If this is protein and the other is nucleotide, gaps | |
| 1802 | * protein to match the relative ordering of codons in the nucleotide. | |
| 1803 | * | |
| 1804 | * Parameters control whether gaps in exon (mapped) and intron (unmapped) | |
| 1805 | * regions are preserved. Gaps that connect introns to exons are treated | |
| 1806 | * conservatively, i.e. only preserved if both intron and exon gaps are | |
| 1807 | * preserved. TODO: check caveats below where the implementation fails | |
| 1808 | * | |
| 1809 | * @param al | |
| 1810 | * - must have same dataset, and sequences in al must have equivalent | |
| 1811 | * dataset sequence and start/end bounds under given mapping | |
| 1812 | * @param preserveMappedGaps | |
| 1813 | * if true, gaps within and between mapped codons are preserved | |
| 1814 | * @param preserveUnmappedGaps | |
| 1815 | * if true, gaps within and between unmapped codons are preserved | |
| 1816 | */ | |
| 1817 | // @Override | |
| 1818 | 10 | public int alignAs(AlignmentI al, boolean preserveMappedGaps, |
| 1819 | boolean preserveUnmappedGaps) | |
| 1820 | { | |
| 1821 | // TODO should this method signature be the one in the interface? | |
| 1822 | // JBPComment - yes - neither flag is used, so should be deleted. | |
| 1823 | 10 | boolean thisIsNucleotide = this.isNucleotide(); |
| 1824 | 10 | boolean thatIsProtein = !al.isNucleotide(); |
| 1825 | 10 | if (!thatIsProtein && !thisIsNucleotide) |
| 1826 | { | |
| 1827 | 3 | return AlignmentUtils.alignProteinAsDna(this, al); |
| 1828 | } | |
| 1829 | 7 | else if (thatIsProtein && thisIsNucleotide) |
| 1830 | { | |
| 1831 | 4 | return AlignmentUtils.alignCdsAsProtein(this, al); |
| 1832 | } | |
| 1833 | 3 | return AlignmentUtils.alignAs(this, al); |
| 1834 | } | |
| 1835 | ||
| 1836 | /** | |
| 1837 | * Returns the alignment in Fasta format. Behaviour of this method is not | |
| 1838 | * guaranteed between versions. | |
| 1839 | */ | |
| 1840 | 3 | @Override |
| 1841 | public String toString() | |
| 1842 | { | |
| 1843 | 3 | return new FastaFile().print(getSequencesArray(), true); |
| 1844 | } | |
| 1845 | ||
| 1846 | /** | |
| 1847 | * Returns the set of distinct sequence names. No ordering is guaranteed. | |
| 1848 | */ | |
| 1849 | 44 | @Override |
| 1850 | public Set<String> getSequenceNames() | |
| 1851 | { | |
| 1852 | 44 | Set<String> names = new HashSet<>(); |
| 1853 | 44 | for (SequenceI seq : getSequences()) |
| 1854 | { | |
| 1855 | 420 | names.add(seq.getName()); |
| 1856 | } | |
| 1857 | 44 | return names; |
| 1858 | } | |
| 1859 | ||
| 1860 | 331 | @Override |
| 1861 | public boolean hasValidSequence() | |
| 1862 | { | |
| 1863 | 331 | boolean hasValidSeq = false; |
| 1864 | 331 | for (SequenceI seq : getSequences()) |
| 1865 | { | |
| 1866 | 331 | if ((seq.getEnd() - seq.getStart()) > 0) |
| 1867 | { | |
| 1868 | 331 | hasValidSeq = true; |
| 1869 | 331 | break; |
| 1870 | } | |
| 1871 | } | |
| 1872 | 331 | return hasValidSeq; |
| 1873 | } | |
| 1874 | ||
| 1875 | /** | |
| 1876 | * Update any mappings to 'virtual' sequences to compatible real ones, if | |
| 1877 | * present in the added sequences. Returns a count of mappings updated. | |
| 1878 | * | |
| 1879 | * @param seqs | |
| 1880 | * @return | |
| 1881 | */ | |
| 1882 | 21 | @Override |
| 1883 | public int realiseMappings(List<SequenceI> seqs) | |
| 1884 | { | |
| 1885 | 21 | int count = 0; |
| 1886 | 21 | for (SequenceI seq : seqs) |
| 1887 | { | |
| 1888 | 58 | for (AlignedCodonFrame mapping : getCodonFrames()) |
| 1889 | { | |
| 1890 | 0 | count += mapping.realiseWith(seq); |
| 1891 | } | |
| 1892 | } | |
| 1893 | 21 | return count; |
| 1894 | } | |
| 1895 | ||
| 1896 | /** | |
| 1897 | * Returns the first AlignedCodonFrame that has a mapping between the given | |
| 1898 | * dataset sequences | |
| 1899 | * | |
| 1900 | * @param mapFrom | |
| 1901 | * @param mapTo | |
| 1902 | * @return | |
| 1903 | */ | |
| 1904 | 38 | @Override |
| 1905 | public AlignedCodonFrame getMapping(SequenceI mapFrom, SequenceI mapTo) | |
| 1906 | { | |
| 1907 | 38 | for (AlignedCodonFrame acf : getCodonFrames()) |
| 1908 | { | |
| 1909 | 13 | if (acf.getAaForDnaSeq(mapFrom) == mapTo) |
| 1910 | { | |
| 1911 | 12 | return acf; |
| 1912 | } | |
| 1913 | } | |
| 1914 | 26 | return null; |
| 1915 | } | |
| 1916 | ||
| 1917 | 42 | @Override |
| 1918 | public boolean setHiddenColumns(HiddenColumns cols) | |
| 1919 | { | |
| 1920 | 42 | boolean changed = cols == null ? hiddenCols != null |
| 1921 | : !cols.equals(hiddenCols); | |
| 1922 | 42 | hiddenCols = cols; |
| 1923 | 42 | return changed; |
| 1924 | } | |
| 1925 | ||
| 1926 | 0 | @Override |
| 1927 | public void setupJPredAlignment() | |
| 1928 | { | |
| 1929 | 0 | SequenceI repseq = getSequenceAt(0); |
| 1930 | 0 | setSeqrep(repseq); |
| 1931 | 0 | HiddenColumns cs = new HiddenColumns(); |
| 1932 | 0 | cs.hideList(repseq.getInsertions()); |
| 1933 | 0 | setHiddenColumns(cs); |
| 1934 | } | |
| 1935 | ||
| 1936 | 2 | @Override |
| 1937 | public HiddenColumns propagateInsertions(SequenceI profileseq, | |
| 1938 | AlignmentView input) | |
| 1939 | { | |
| 1940 | 2 | int profsqpos = 0; |
| 1941 | ||
| 1942 | 2 | char gc = getGapCharacter(); |
| 1943 | 2 | Object[] alandhidden = input.getAlignmentAndHiddenColumns(gc); |
| 1944 | 2 | HiddenColumns nview = (HiddenColumns) alandhidden[1]; |
| 1945 | 2 | SequenceI origseq = ((SequenceI[]) alandhidden[0])[profsqpos]; |
| 1946 | 2 | return propagateInsertions(profileseq, origseq, nview); |
| 1947 | } | |
| 1948 | ||
| 1949 | /** | |
| 1950 | * | |
| 1951 | * @param profileseq | |
| 1952 | * sequence in al which corresponds to origseq | |
| 1953 | * @param al | |
| 1954 | * alignment which is to have gaps inserted into it | |
| 1955 | * @param origseq | |
| 1956 | * sequence corresponding to profileseq which defines gap map for | |
| 1957 | * modifying al | |
| 1958 | */ | |
| 1959 | 2 | private HiddenColumns propagateInsertions(SequenceI profileseq, |
| 1960 | SequenceI origseq, HiddenColumns hc) | |
| 1961 | { | |
| 1962 | // take the set of hidden columns, and the set of gaps in origseq, | |
| 1963 | // and remove all the hidden gaps from hiddenColumns | |
| 1964 | ||
| 1965 | // first get the gaps as a Bitset | |
| 1966 | // then calculate hidden ^ not(gap) | |
| 1967 | 2 | BitSet gaps = origseq.gapBitset(); |
| 1968 | 2 | hc.andNot(gaps); |
| 1969 | ||
| 1970 | // for each sequence in the alignment, except the profile sequence, | |
| 1971 | // insert gaps corresponding to each hidden region but where each hidden | |
| 1972 | // column region is shifted backwards by the number of preceding visible | |
| 1973 | // gaps update hidden columns at the same time | |
| 1974 | 2 | HiddenColumns newhidden = new HiddenColumns(); |
| 1975 | ||
| 1976 | 2 | int numGapsBefore = 0; |
| 1977 | 2 | int gapPosition = 0; |
| 1978 | 2 | Iterator<int[]> it = hc.iterator(); |
| 1979 | 4 | while (it.hasNext()) |
| 1980 | { | |
| 1981 | 2 | int[] region = it.next(); |
| 1982 | ||
| 1983 | // get region coordinates accounting for gaps | |
| 1984 | // we can rely on gaps not being *in* hidden regions because we already | |
| 1985 | // removed those | |
| 1986 | 26 | while (gapPosition < region[0]) |
| 1987 | { | |
| 1988 | 24 | gapPosition++; |
| 1989 | 24 | if (gaps.get(gapPosition)) |
| 1990 | { | |
| 1991 | 8 | numGapsBefore++; |
| 1992 | } | |
| 1993 | } | |
| 1994 | ||
| 1995 | 2 | int left = region[0] - numGapsBefore; |
| 1996 | 2 | int right = region[1] - numGapsBefore; |
| 1997 | ||
| 1998 | 2 | newhidden.hideColumns(left, right); |
| 1999 | 2 | padGaps(left, right, profileseq); |
| 2000 | } | |
| 2001 | 2 | return newhidden; |
| 2002 | } | |
| 2003 | ||
| 2004 | /** | |
| 2005 | * Pad gaps in all sequences in alignment except profileseq | |
| 2006 | * | |
| 2007 | * @param left | |
| 2008 | * position of first gap to insert | |
| 2009 | * @param right | |
| 2010 | * position of last gap to insert | |
| 2011 | * @param profileseq | |
| 2012 | * sequence not to pad | |
| 2013 | */ | |
| 2014 | 2 | private void padGaps(int left, int right, SequenceI profileseq) |
| 2015 | { | |
| 2016 | 2 | char gc = getGapCharacter(); |
| 2017 | ||
| 2018 | // make a string with number of gaps = length of hidden region | |
| 2019 | 2 | StringBuilder sb = new StringBuilder(); |
| 2020 | 7 | for (int g = 0; g < right - left + 1; g++) |
| 2021 | { | |
| 2022 | 5 | sb.append(gc); |
| 2023 | } | |
| 2024 | ||
| 2025 | // loop over the sequences and pad with gaps where required | |
| 2026 | 22 | for (int s = 0, ns = getHeight(); s < ns; s++) |
| 2027 | { | |
| 2028 | 20 | SequenceI sqobj = getSequenceAt(s); |
| 2029 | 20 | if ((sqobj != profileseq) && (sqobj.getLength() >= left)) |
| 2030 | { | |
| 2031 | 15 | String sq = sqobj.getSequenceAsString(); |
| 2032 | 15 | sqobj.setSequence( |
| 2033 | sq.substring(0, left) + sb.toString() + sq.substring(left)); | |
| 2034 | } | |
| 2035 | } | |
| 2036 | } | |
| 2037 | ||
| 2038 | //// | |
| 2039 | //// Contact Matrix Holder Boilerplate | |
| 2040 | //// | |
| 2041 | ContactMapHolder cmholder = new ContactMapHolder(); | |
| 2042 | ||
| 2043 | 21 | @Override |
| 2044 | public Collection<ContactMatrixI> getContactMaps() | |
| 2045 | { | |
| 2046 | 21 | return cmholder.getContactMaps(); |
| 2047 | } | |
| 2048 | ||
| 2049 | 151 | @Override |
| 2050 | public ContactMatrixI getContactMatrixFor(AlignmentAnnotation _aa) | |
| 2051 | { | |
| 2052 | 151 | ContactMatrixI cm = cmholder.getContactMatrixFor(_aa); |
| 2053 | 151 | if (cm == null && _aa.groupRef != null) |
| 2054 | { | |
| 2055 | 0 | cm = _aa.groupRef.getContactMatrixFor(_aa); |
| 2056 | } | |
| 2057 | 151 | if (cm == null && _aa.sequenceRef != null) |
| 2058 | { | |
| 2059 | 151 | cm = _aa.sequenceRef.getContactMatrixFor(_aa); |
| 2060 | 151 | if (cm == null && _aa.sequenceRef.getDatasetSequence() != null) |
| 2061 | { | |
| 2062 | // TODO fix up this logic and unify with getContactListFor | |
| 2063 | 0 | cm = _aa.sequenceRef.getDatasetSequence().getContactMatrixFor(_aa); |
| 2064 | } | |
| 2065 | } | |
| 2066 | 151 | return cm; |
| 2067 | } | |
| 2068 | ||
| 2069 | 4491 | @Override |
| 2070 | public ContactListI getContactListFor(AlignmentAnnotation _aa, int column) | |
| 2071 | { | |
| 2072 | 4491 | if (_aa.annotations == null || column >= _aa.annotations.length |
| 2073 | || column < 0) | |
| 2074 | { | |
| 2075 | 1 | return null; |
| 2076 | } | |
| 2077 | 4490 | ContactListI cl = cmholder.getContactListFor(_aa, column); |
| 2078 | 4490 | if (cl == null && _aa.groupRef != null) |
| 2079 | { | |
| 2080 | 0 | cl = _aa.groupRef.getContactListFor(_aa, column); |
| 2081 | } | |
| 2082 | 4490 | if (cl == null && _aa.sequenceRef != null) |
| 2083 | { | |
| 2084 | 4490 | if (_aa.annotations[column] != null) |
| 2085 | { | |
| 2086 | // sequence associated | |
| 2087 | 4490 | cl = _aa.sequenceRef.getContactListFor(_aa, column); |
| 2088 | 4490 | if (cl == null && _aa.sequenceRef.getDatasetSequence() != null) |
| 2089 | { | |
| 2090 | 0 | int spos = _aa.sequenceRef.findPosition(column); |
| 2091 | 0 | if (spos >= _aa.sequenceRef.getStart() |
| 2092 | && spos <= 1 + _aa.sequenceRef.getEnd()) | |
| 2093 | { | |
| 2094 | 0 | cl = _aa.sequenceRef.getDatasetSequence().getContactListFor(_aa, |
| 2095 | spos - _aa.sequenceRef.getStart()); | |
| 2096 | } | |
| 2097 | } | |
| 2098 | } | |
| 2099 | } | |
| 2100 | 4490 | return cl; |
| 2101 | } | |
| 2102 | ||
| 2103 | 0 | @Override |
| 2104 | public AlignmentAnnotation addContactList(ContactMatrixI cm) | |
| 2105 | { | |
| 2106 | 0 | AlignmentAnnotation aa = cmholder.addContactList(cm); |
| 2107 | ||
| 2108 | 0 | Annotation _aa[] = new Annotation[getWidth()]; |
| 2109 | 0 | for (int i = 0; i < _aa.length; _aa[i++] = new Annotation(0.0f)) |
| 2110 | { | |
| 2111 | 0 | ; |
| 2112 | } | |
| 2113 | 0 | aa.annotations = _aa; |
| 2114 | 0 | addAnnotation(aa); |
| 2115 | 0 | return aa; |
| 2116 | } | |
| 2117 | ||
| 2118 | 0 | @Override |
| 2119 | public void addContactListFor(AlignmentAnnotation annotation, | |
| 2120 | ContactMatrixI cm) | |
| 2121 | { | |
| 2122 | 0 | cmholder.addContactListFor(annotation, cm); |
| 2123 | ||
| 2124 | } | |
| 2125 | ||
| 2126 | 4 | @Override |
| 2127 | public boolean isSecondaryStructurePresent() | |
| 2128 | { | |
| 2129 | 4 | if (annotations == null || annotations.length == 0) |
| 2130 | { | |
| 2131 | 1 | return false; |
| 2132 | } | |
| 2133 | 3 | boolean hasSeqRef = false; |
| 2134 | // TODO - move this to its own method | |
| 2135 | 7 | for (int a = 0; !hasSeqRef && a < annotations.length; a++) |
| 2136 | { | |
| 2137 | 4 | if (annotations[a] != null && annotations[a].sequenceRef != null) |
| 2138 | { | |
| 2139 | 2 | hasSeqRef = true; |
| 2140 | } | |
| 2141 | } | |
| 2142 | ||
| 2143 | // TODO - JAL-4399 needs to be made efficient if called repeatedly | |
| 2144 | 3 | return hasSeqRef |
| 2145 | && AlignmentUtils.isSecondaryStructurePresent(annotations); | |
| 2146 | } | |
| 2147 | } |