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 static org.testng.AssertJUnit.assertEquals;
24 import static org.testng.AssertJUnit.assertFalse;
25 import static org.testng.AssertJUnit.assertNotNull;
26 import static org.testng.AssertJUnit.assertNotSame;
27 import static org.testng.AssertJUnit.assertNull;
28 import static org.testng.AssertJUnit.assertSame;
29 import static org.testng.AssertJUnit.assertTrue;
32 import java.util.ArrayList;
33 import java.util.Arrays;
34 import java.util.BitSet;
35 import java.util.Iterator;
36 import java.util.List;
37 import java.util.Locale;
38 import java.util.Vector;
40 import org.testng.Assert;
41 import org.testng.annotations.BeforeClass;
42 import org.testng.annotations.BeforeMethod;
43 import org.testng.annotations.Test;
45 import jalview.analysis.AlignmentGenerator;
46 import jalview.bin.Cache;
47 import jalview.commands.EditCommand;
48 import jalview.commands.EditCommand.Action;
49 import jalview.datamodel.PDBEntry.Type;
50 import jalview.gui.JvOptionPane;
51 import jalview.util.MapList;
52 import junit.extensions.PA;
54 public class SequenceTest
56 @BeforeClass(alwaysRun = true)
57 public void setUpJvOptionPane()
59 JvOptionPane.setInteractiveMode(false);
60 JvOptionPane.setMockResponse(JvOptionPane.CANCEL_OPTION);
63 @BeforeMethod(alwaysRun = true)
64 public void loadProperties()
66 Cache.loadProperties("test/jalview/util/comparisonTestProps.jvprops");
71 @BeforeMethod(alwaysRun = true)
74 seq = new Sequence("FER1", "AKPNGVL");
77 @Test(groups = { "Functional" })
78 public void testInsertGapsAndGapmaps()
80 SequenceI aseq = seq.deriveSequence();
81 aseq.insertCharAt(2, 3, '-');
82 aseq.insertCharAt(6, 3, '-');
83 assertEquals("Gap insertions not correct", "AK---P---NGVL",
84 aseq.getSequenceAsString());
85 List<int[]> gapInt = aseq.getInsertions();
86 assertEquals("Gap interval 1 start wrong", 2, gapInt.get(0)[0]);
87 assertEquals("Gap interval 1 end wrong", 4, gapInt.get(0)[1]);
88 assertEquals("Gap interval 2 start wrong", 6, gapInt.get(1)[0]);
89 assertEquals("Gap interval 2 end wrong", 8, gapInt.get(1)[1]);
91 BitSet gapfield = aseq.getInsertionsAsBits();
92 BitSet expectedgaps = new BitSet();
93 expectedgaps.set(2, 5);
94 expectedgaps.set(6, 9);
96 assertEquals(6, expectedgaps.cardinality());
98 assertEquals("getInsertionsAsBits didn't mark expected number of gaps",
99 6, gapfield.cardinality());
101 assertEquals("getInsertionsAsBits not correct.", expectedgaps,
105 @Test(groups = ("Functional"))
106 public void testIsProtein()
109 assertTrue(new Sequence("prot", "ASDFASDFASDF").isProtein());
111 assertFalse(new Sequence("prot", "ACGTACGTACGT").isProtein());
113 SequenceI sq = new Sequence("prot", "ACGUACGUACGU");
114 assertFalse(sq.isProtein());
115 // change sequence, should trigger an update of cached result
116 sq.setSequence("ASDFASDFADSF");
117 assertTrue(sq.isProtein());
120 @Test(groups = ("Functional"))
121 public void testIsProteinWithXorNAmbiguityCodes()
123 // test Protein with N - poly asparagine
124 assertTrue(new Sequence("prot", "ASDFASDFASDFNNNNNNNNN").isProtein());
125 assertTrue(new Sequence("prot", "NNNNNNNNNNNNNNNNNNNNN").isProtein());
126 // test Protein with X
127 assertTrue(new Sequence("prot", "ASDFASDFASDFXXXXXXXXX").isProtein());
129 assertFalse(new Sequence("prot", "ACGTACGTACGTXXXXXXXX").isProtein());
130 // short sequence is nucleotide only if 50% is nucleotide and remaining N/X
131 // is either N or X only
132 assertTrue(new Sequence("prot", "ACGTACGTACGTXN").isProtein());
134 assertFalse(new Sequence("prot", "ACGTACGTACGTNNNNNNNN").isProtein());
136 assertFalse(new Sequence("prot", "ACGUACGUACGUACTGACAXX").isProtein());
137 assertFalse(new Sequence("prot", "ACGUACGUACGUXXXXXXXXX").isProtein());
138 assertFalse(new Sequence("prot", "ACGUACGUACGUNNNNNNNNN").isProtein());
141 @Test(groups = { "Functional" })
142 public void testGetAnnotation()
144 // initial state returns null not an empty array
145 assertNull(seq.getAnnotation());
146 AlignmentAnnotation ann = addAnnotation("label1", "desc1", "calcId1",
148 AlignmentAnnotation[] anns = seq.getAnnotation();
149 assertEquals(1, anns.length);
150 assertSame(ann, anns[0]);
152 // removing all annotations reverts array to null
153 seq.removeAlignmentAnnotation(ann);
154 assertNull(seq.getAnnotation());
157 @Test(groups = { "Functional" })
158 public void testGetAnnotation_forLabel()
160 AlignmentAnnotation ann1 = addAnnotation("label1", "desc1", "calcId1",
162 addAnnotation("label2", "desc2", "calcId2", 1f);
163 AlignmentAnnotation ann3 = addAnnotation("label1", "desc3", "calcId3",
165 AlignmentAnnotation[] anns = seq.getAnnotation("label1");
166 assertEquals(2, anns.length);
167 assertSame(ann1, anns[0]);
168 assertSame(ann3, anns[1]);
171 private AlignmentAnnotation addAnnotation(String label,
172 String description, String calcId, float value)
174 final AlignmentAnnotation annotation = new AlignmentAnnotation(label,
176 annotation.setCalcId(calcId);
177 seq.addAlignmentAnnotation(annotation);
181 @Test(groups = { "Functional" })
182 public void testGetAlignmentAnnotations_forCalcIdAndLabel()
184 addAnnotation("label1", "desc1", "calcId1", 1f);
185 AlignmentAnnotation ann2 = addAnnotation("label2", "desc2", "calcId2",
187 addAnnotation("label2", "desc3", "calcId3", 1f);
188 AlignmentAnnotation ann4 = addAnnotation("label2", "desc3", "calcId2",
190 addAnnotation("label5", "desc3", null, 1f);
191 addAnnotation(null, "desc3", "calcId3", 1f);
193 List<AlignmentAnnotation> anns = seq.getAlignmentAnnotations("calcId2",
195 assertEquals(2, anns.size());
196 assertSame(ann2, anns.get(0));
197 assertSame(ann4, anns.get(1));
199 assertTrue(seq.getAlignmentAnnotations("calcId2", "label3").isEmpty());
200 assertTrue(seq.getAlignmentAnnotations("calcId3", "label5").isEmpty());
201 assertTrue(seq.getAlignmentAnnotations("calcId2", null).isEmpty());
202 assertTrue(seq.getAlignmentAnnotations(null, "label3").isEmpty());
203 assertTrue(seq.getAlignmentAnnotations(null, null).isEmpty());
206 @Test(groups = { "Functional" })
207 public void testGetAlignmentAnnotations_forCalcIdLabelAndDescription()
209 addAnnotation("label1", "desc1", "calcId1", 1f);
210 AlignmentAnnotation ann2 = addAnnotation("label2", "desc2", "calcId2",
212 addAnnotation("label2", "desc3", "calcId3", 1f);
213 AlignmentAnnotation ann4 = addAnnotation("label2", "desc3", "calcId2",
215 addAnnotation("label5", "desc3", null, 1f);
216 addAnnotation(null, "desc3", "calcId3", 1f);
218 List<AlignmentAnnotation> anns = seq.getAlignmentAnnotations("calcId2",
220 assertEquals(1, anns.size());
221 assertSame(ann4, anns.get(0));
223 * null matching should fail
225 assertTrue(seq.getAlignmentAnnotations("calcId3", "label2", null)
228 assertTrue(seq.getAlignmentAnnotations("calcId2", "label3", null)
230 assertTrue(seq.getAlignmentAnnotations("calcId3", "label5", null)
233 seq.getAlignmentAnnotations("calcId2", null, null).isEmpty());
234 assertTrue(seq.getAlignmentAnnotations(null, "label3", null).isEmpty());
235 assertTrue(seq.getAlignmentAnnotations(null, null, null).isEmpty());
239 * Tests for addAlignmentAnnotation. Note this method has the side-effect of
240 * setting the sequenceRef on the annotation. Adding the same annotation twice
243 @Test(groups = { "Functional" })
244 public void testAddAlignmentAnnotation()
246 assertNull(seq.getAnnotation());
247 final AlignmentAnnotation annotation = new AlignmentAnnotation("a", "b",
249 assertNull(annotation.sequenceRef);
250 seq.addAlignmentAnnotation(annotation);
251 assertSame(seq, annotation.sequenceRef);
252 AlignmentAnnotation[] anns = seq.getAnnotation();
253 assertEquals(1, anns.length);
254 assertSame(annotation, anns[0]);
256 // re-adding does nothing
257 seq.addAlignmentAnnotation(annotation);
258 anns = seq.getAnnotation();
259 assertEquals(1, anns.length);
260 assertSame(annotation, anns[0]);
262 // an identical but different annotation can be added
263 final AlignmentAnnotation annotation2 = new AlignmentAnnotation("a",
265 seq.addAlignmentAnnotation(annotation2);
266 anns = seq.getAnnotation();
267 assertEquals(2, anns.length);
268 assertSame(annotation, anns[0]);
269 assertSame(annotation2, anns[1]);
272 @Test(groups = { "Functional" })
273 public void testGetStartGetEnd()
275 SequenceI sq = new Sequence("test", "ABCDEF");
276 assertEquals(1, sq.getStart());
277 assertEquals(6, sq.getEnd());
279 sq = new Sequence("test", "--AB-C-DEF--");
280 assertEquals(1, sq.getStart());
281 assertEquals(6, sq.getEnd());
283 sq = new Sequence("test", "----");
284 assertEquals(1, sq.getStart());
285 assertEquals(0, sq.getEnd()); // ??
289 * Tests for the method that returns an alignment column position (base 1) for
290 * a given sequence position (base 1).
292 @Test(groups = { "Functional" })
293 public void testFindIndex()
296 * call sequenceChanged() after each test to invalidate any cursor,
297 * forcing the 1-arg findIndex to be executed
299 SequenceI sq = new Sequence("test", "ABCDEF");
300 assertEquals(0, sq.findIndex(0));
301 sq.sequenceChanged();
302 assertEquals(1, sq.findIndex(1));
303 sq.sequenceChanged();
304 assertEquals(5, sq.findIndex(5));
305 sq.sequenceChanged();
306 assertEquals(6, sq.findIndex(6));
307 sq.sequenceChanged();
308 assertEquals(6, sq.findIndex(9));
310 final String aligned = "-A--B-C-D-E-F--";
311 assertEquals(15, aligned.length());
312 sq = new Sequence("test/8-13", aligned);
313 assertEquals(2, sq.findIndex(8));
314 sq.sequenceChanged();
315 assertEquals(5, sq.findIndex(9));
316 sq.sequenceChanged();
317 assertEquals(7, sq.findIndex(10));
319 // before start returns 0
320 sq.sequenceChanged();
321 assertEquals(0, sq.findIndex(0));
322 sq.sequenceChanged();
323 assertEquals(0, sq.findIndex(-1));
325 // beyond end returns last residue column
326 sq.sequenceChanged();
327 assertEquals(13, sq.findIndex(99));
330 * residue before sequence 'end' but beyond end of sequence returns
331 * length of sequence (last column) (rightly or wrongly!)
333 sq = new Sequence("test/8-15", "A-B-C-"); // trailing gap case
334 assertEquals(6, sq.getLength());
335 sq.sequenceChanged();
336 assertEquals(sq.getLength(), sq.findIndex(14));
337 sq = new Sequence("test/8-99", "-A--B-C-D"); // trailing residue case
338 sq.sequenceChanged();
339 assertEquals(sq.getLength(), sq.findIndex(65));
342 * residue after sequence 'start' but before first residue returns
343 * zero (before first column) (rightly or wrongly!)
345 sq = new Sequence("test/8-15", "-A-B-C-"); // leading gap case
346 sq.sequenceChanged();
347 assertEquals(0, sq.findIndex(3));
348 sq = new Sequence("test/8-15", "A-B-C-"); // leading residue case
349 sq.sequenceChanged();
350 assertEquals(0, sq.findIndex(2));
353 @Test(groups = { "Functional" })
354 public void testFindPositions()
356 SequenceI sq = new Sequence("test/8-13", "-ABC---DE-F--");
361 assertNull(sq.findPositions(6, 5));
362 assertNull(sq.findPositions(0, 5));
363 assertNull(sq.findPositions(-1, 5));
368 assertNull(sq.findPositions(1, 1)); // 1-based columns
369 assertNull(sq.findPositions(5, 5));
370 assertNull(sq.findPositions(5, 6));
371 assertNull(sq.findPositions(5, 7));
374 * all ungapped ranges
376 assertEquals(new Range(8, 8), sq.findPositions(2, 2)); // A
377 assertEquals(new Range(8, 9), sq.findPositions(2, 3)); // AB
378 assertEquals(new Range(8, 10), sq.findPositions(2, 4)); // ABC
379 assertEquals(new Range(9, 10), sq.findPositions(3, 4)); // BC
382 * gap to ungapped range
384 assertEquals(new Range(8, 10), sq.findPositions(1, 4)); // ABC
385 assertEquals(new Range(11, 12), sq.findPositions(6, 9)); // DE
388 * ungapped to gapped range
390 assertEquals(new Range(10, 10), sq.findPositions(4, 5)); // C
391 assertEquals(new Range(9, 13), sq.findPositions(3, 11)); // BCDEF
394 * ungapped to ungapped enclosing gaps
396 assertEquals(new Range(10, 11), sq.findPositions(4, 8)); // CD
397 assertEquals(new Range(8, 13), sq.findPositions(2, 11)); // ABCDEF
400 * gapped to gapped enclosing ungapped
402 assertEquals(new Range(8, 10), sq.findPositions(1, 5)); // ABC
403 assertEquals(new Range(11, 12), sq.findPositions(5, 10)); // DE
404 assertEquals(new Range(8, 13), sq.findPositions(1, 13)); // the lot
405 assertEquals(new Range(8, 13), sq.findPositions(1, 99));
409 * Tests for the method that returns a dataset sequence position (start..) for
410 * an aligned column position (base 0).
412 @Test(groups = { "Functional" })
413 public void testFindPosition()
416 * call sequenceChanged() after each test to invalidate any cursor,
417 * forcing the 1-arg findPosition to be executed
419 SequenceI sq = new Sequence("test/8-13", "ABCDEF");
420 assertEquals(8, sq.findPosition(0));
421 // Sequence should now hold a cursor at [8, 0]
422 assertEquals("test:Pos8:Col1:startCol1:endCol0:tok1",
423 PA.getValue(sq, "cursor").toString());
424 SequenceCursor cursor = (SequenceCursor) PA.getValue(sq, "cursor");
425 int token = (int) PA.getValue(sq, "changeCount");
426 assertEquals(new SequenceCursor(sq, 8, 1, token), cursor);
428 sq.sequenceChanged();
431 * find F13 at column offset 5, cursor should update to [13, 6]
432 * endColumn is found and saved in cursor
434 assertEquals(13, sq.findPosition(5));
435 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
436 assertEquals(++token, (int) PA.getValue(sq, "changeCount"));
437 assertEquals(new SequenceCursor(sq, 13, 6, token), cursor);
438 assertEquals("test:Pos13:Col6:startCol1:endCol6:tok2",
439 PA.getValue(sq, "cursor").toString());
441 // assertEquals(-1, seq.findPosition(6)); // fails
443 sq = new Sequence("test/8-11", "AB-C-D--");
444 token = (int) PA.getValue(sq, "changeCount"); // 1 for setStart
445 assertEquals(8, sq.findPosition(0));
446 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
447 assertEquals(new SequenceCursor(sq, 8, 1, token), cursor);
448 assertEquals("test:Pos8:Col1:startCol1:endCol0:tok1",
449 PA.getValue(sq, "cursor").toString());
451 sq.sequenceChanged();
452 assertEquals(9, sq.findPosition(1));
453 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
454 assertEquals(new SequenceCursor(sq, 9, 2, ++token), cursor);
455 assertEquals("test:Pos9:Col2:startCol1:endCol0:tok2",
456 PA.getValue(sq, "cursor").toString());
458 sq.sequenceChanged();
459 // gap position 'finds' residue to the right (not the left as per javadoc)
460 // cursor is set to the last residue position found [B 2]
461 assertEquals(10, sq.findPosition(2));
462 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
463 assertEquals(new SequenceCursor(sq, 9, 2, ++token), cursor);
464 assertEquals("test:Pos9:Col2:startCol1:endCol0:tok3",
465 PA.getValue(sq, "cursor").toString());
467 sq.sequenceChanged();
468 assertEquals(10, sq.findPosition(3));
469 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
470 assertEquals(new SequenceCursor(sq, 10, 4, ++token), cursor);
471 assertEquals("test:Pos10:Col4:startCol1:endCol0:tok4",
472 PA.getValue(sq, "cursor").toString());
474 sq.sequenceChanged();
475 // column[4] is the gap after C - returns D11
476 // cursor is set to [C 4]
477 assertEquals(11, sq.findPosition(4));
478 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
479 assertEquals(new SequenceCursor(sq, 10, 4, ++token), cursor);
480 assertEquals("test:Pos10:Col4:startCol1:endCol0:tok5",
481 PA.getValue(sq, "cursor").toString());
483 sq.sequenceChanged();
484 assertEquals(11, sq.findPosition(5)); // D
485 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
486 assertEquals(new SequenceCursor(sq, 11, 6, ++token), cursor);
487 // lastCol has been found and saved in the cursor
488 assertEquals("test:Pos11:Col6:startCol1:endCol6:tok6",
489 PA.getValue(sq, "cursor").toString());
491 sq.sequenceChanged();
492 // returns 1 more than sequence length if off the end ?!?
493 assertEquals(12, sq.findPosition(6));
495 sq.sequenceChanged();
496 assertEquals(12, sq.findPosition(7));
499 * first findPosition should also set firstResCol in cursor
501 sq = new Sequence("test/8-13", "--AB-C-DEF--");
502 assertEquals(8, sq.findPosition(0));
503 assertNull(PA.getValue(sq, "cursor"));
504 assertEquals(1, PA.getValue(sq, "changeCount"));
506 sq.sequenceChanged();
507 assertEquals(8, sq.findPosition(1));
508 assertNull(PA.getValue(sq, "cursor"));
510 sq.sequenceChanged();
511 assertEquals(8, sq.findPosition(2));
512 assertEquals("test:Pos8:Col3:startCol3:endCol0:tok3",
513 PA.getValue(sq, "cursor").toString());
515 sq.sequenceChanged();
516 assertEquals(9, sq.findPosition(3));
517 assertEquals("test:Pos9:Col4:startCol3:endCol0:tok4",
518 PA.getValue(sq, "cursor").toString());
520 sq.sequenceChanged();
521 // column[4] is a gap, returns next residue pos (C10)
522 // cursor is set to last residue found [B]
523 assertEquals(10, sq.findPosition(4));
524 assertEquals("test:Pos9:Col4:startCol3:endCol0:tok5",
525 PA.getValue(sq, "cursor").toString());
527 sq.sequenceChanged();
528 assertEquals(10, sq.findPosition(5));
529 assertEquals("test:Pos10:Col6:startCol3:endCol0:tok6",
530 PA.getValue(sq, "cursor").toString());
532 sq.sequenceChanged();
533 // column[6] is a gap, returns next residue pos (D11)
534 // cursor is set to last residue found [C]
535 assertEquals(11, sq.findPosition(6));
536 assertEquals("test:Pos10:Col6:startCol3:endCol0:tok7",
537 PA.getValue(sq, "cursor").toString());
539 sq.sequenceChanged();
540 assertEquals(11, sq.findPosition(7));
541 assertEquals("test:Pos11:Col8:startCol3:endCol0:tok8",
542 PA.getValue(sq, "cursor").toString());
544 sq.sequenceChanged();
545 assertEquals(12, sq.findPosition(8));
546 assertEquals("test:Pos12:Col9:startCol3:endCol0:tok9",
547 PA.getValue(sq, "cursor").toString());
550 * when the last residue column is found, it is set in the cursor
552 sq.sequenceChanged();
553 assertEquals(13, sq.findPosition(9));
554 assertEquals("test:Pos13:Col10:startCol3:endCol10:tok10",
555 PA.getValue(sq, "cursor").toString());
557 sq.sequenceChanged();
558 assertEquals(14, sq.findPosition(10));
559 assertEquals("test:Pos13:Col10:startCol3:endCol10:tok11",
560 PA.getValue(sq, "cursor").toString());
563 * findPosition for column beyond sequence length
564 * returns 1 more than last residue position
566 sq.sequenceChanged();
567 assertEquals(14, sq.findPosition(11));
568 assertEquals("test:Pos13:Col10:startCol3:endCol10:tok12",
569 PA.getValue(sq, "cursor").toString());
571 sq.sequenceChanged();
572 assertEquals(14, sq.findPosition(99));
573 assertEquals("test:Pos13:Col10:startCol3:endCol10:tok13",
574 PA.getValue(sq, "cursor").toString());
577 * gapped sequence ending in non-gap
579 sq = new Sequence("test/8-13", "--AB-C-DEF");
580 assertEquals(13, sq.findPosition(9));
581 assertEquals("test:Pos13:Col10:startCol3:endCol10:tok1",
582 PA.getValue(sq, "cursor").toString());
583 sq.sequenceChanged();
584 assertEquals(12, sq.findPosition(8)); // E12
585 // sequenceChanged() invalidates cursor.lastResidueColumn
586 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
587 assertEquals("test:Pos12:Col9:startCol3:endCol0:tok2",
589 // findPosition with cursor accepts base 1 column values
590 assertEquals(13, ((Sequence) sq).findPosition(10, cursor));
591 assertEquals(13, sq.findPosition(9)); // F13
592 // lastResidueColumn has now been found and saved in cursor
593 assertEquals("test:Pos13:Col10:startCol3:endCol10:tok2",
594 PA.getValue(sq, "cursor").toString());
597 @Test(groups = { "Functional" })
598 public void testDeleteChars()
603 SequenceI sq = new Sequence("test", "ABCDEF");
604 assertNull(PA.getValue(sq, "datasetSequence"));
605 assertEquals(1, sq.getStart());
606 assertEquals(6, sq.getEnd());
607 sq.deleteChars(2, 3);
608 assertEquals("ABDEF", sq.getSequenceAsString());
609 assertEquals(1, sq.getStart());
610 assertEquals(5, sq.getEnd());
611 assertNull(PA.getValue(sq, "datasetSequence"));
616 sq = new Sequence("test", "ABCDEF");
617 sq.deleteChars(0, 2);
618 assertEquals("CDEF", sq.getSequenceAsString());
619 assertEquals(3, sq.getStart());
620 assertEquals(6, sq.getEnd());
621 assertNull(PA.getValue(sq, "datasetSequence"));
623 sq = new Sequence("test", "ABCDE");
624 sq.deleteChars(0, 3);
625 assertEquals("DE", sq.getSequenceAsString());
626 assertEquals(4, sq.getStart());
627 assertEquals(5, sq.getEnd());
628 assertNull(PA.getValue(sq, "datasetSequence"));
633 sq = new Sequence("test", "ABCDEF");
634 sq.deleteChars(4, 6);
635 assertEquals("ABCD", sq.getSequenceAsString());
636 assertEquals(1, sq.getStart());
637 assertEquals(4, sq.getEnd());
638 assertNull(PA.getValue(sq, "datasetSequence"));
641 * delete more positions than there are
643 sq = new Sequence("test/8-11", "ABCD");
644 sq.deleteChars(0, 99);
645 assertEquals("", sq.getSequenceAsString());
646 assertEquals(12, sq.getStart()); // = findPosition(99) ?!?
647 assertEquals(11, sq.getEnd());
649 sq = new Sequence("test/8-11", "----");
650 sq.deleteChars(0, 99); // ArrayIndexOutOfBoundsException <= 2.10.2
651 assertEquals("", sq.getSequenceAsString());
652 assertEquals(8, sq.getStart());
653 assertEquals(11, sq.getEnd());
656 @Test(groups = { "Functional" })
657 public void testDeleteChars_withDbRefsAndFeatures()
660 * internal delete - new dataset sequence created
661 * gets a copy of any dbrefs
663 SequenceI sq = new Sequence("test", "ABCDEF");
664 sq.createDatasetSequence();
665 DBRefEntry dbr1 = new DBRefEntry("Uniprot", "0", "a123");
667 Object ds = PA.getValue(sq, "datasetSequence");
669 assertEquals(1, sq.getStart());
670 assertEquals(6, sq.getEnd());
671 sq.deleteChars(2, 3);
672 assertEquals("ABDEF", sq.getSequenceAsString());
673 assertEquals(1, sq.getStart());
674 assertEquals(5, sq.getEnd());
675 Object newDs = PA.getValue(sq, "datasetSequence");
676 assertNotNull(newDs);
677 assertNotSame(ds, newDs);
678 assertNotNull(sq.getDBRefs());
679 assertEquals(1, sq.getDBRefs().size());
680 assertNotSame(dbr1, sq.getDBRefs().get(0));
681 assertEquals(dbr1, sq.getDBRefs().get(0));
684 * internal delete with sequence features
685 * (failure case for JAL-2541)
687 sq = new Sequence("test", "ABCDEF");
688 sq.createDatasetSequence();
689 SequenceFeature sf1 = new SequenceFeature("Cath", "desc", 2, 4, 2f,
691 sq.addSequenceFeature(sf1);
692 ds = PA.getValue(sq, "datasetSequence");
694 assertEquals(1, sq.getStart());
695 assertEquals(6, sq.getEnd());
696 sq.deleteChars(2, 4);
697 assertEquals("ABEF", sq.getSequenceAsString());
698 assertEquals(1, sq.getStart());
699 assertEquals(4, sq.getEnd());
700 newDs = PA.getValue(sq, "datasetSequence");
701 assertNotNull(newDs);
702 assertNotSame(ds, newDs);
703 List<SequenceFeature> sfs = sq.getSequenceFeatures();
704 assertEquals(1, sfs.size());
705 assertNotSame(sf1, sfs.get(0));
706 assertEquals(sf1, sfs.get(0));
709 * delete at start - no new dataset sequence created
710 * any sequence features remain as before
712 sq = new Sequence("test", "ABCDEF");
713 sq.createDatasetSequence();
714 ds = PA.getValue(sq, "datasetSequence");
715 sf1 = new SequenceFeature("Cath", "desc", 2, 4, 2f, "CathGroup");
716 sq.addSequenceFeature(sf1);
717 sq.deleteChars(0, 2);
718 assertEquals("CDEF", sq.getSequenceAsString());
719 assertEquals(3, sq.getStart());
720 assertEquals(6, sq.getEnd());
721 assertSame(ds, PA.getValue(sq, "datasetSequence"));
722 sfs = sq.getSequenceFeatures();
724 assertEquals(1, sfs.size());
725 assertSame(sf1, sfs.get(0));
728 * delete at end - no new dataset sequence created
729 * any dbrefs remain as before
731 sq = new Sequence("test", "ABCDEF");
732 sq.createDatasetSequence();
733 ds = PA.getValue(sq, "datasetSequence");
734 dbr1 = new DBRefEntry("Uniprot", "0", "a123");
736 sq.deleteChars(4, 6);
737 assertEquals("ABCD", sq.getSequenceAsString());
738 assertEquals(1, sq.getStart());
739 assertEquals(4, sq.getEnd());
740 assertSame(ds, PA.getValue(sq, "datasetSequence"));
741 assertNotNull(sq.getDBRefs());
742 assertEquals(1, sq.getDBRefs().size());
743 assertSame(dbr1, sq.getDBRefs().get(0));
746 @Test(groups = { "Functional" })
747 public void testInsertCharAt()
749 // non-static methods:
750 SequenceI sq = new Sequence("test", "ABCDEF");
751 sq.insertCharAt(0, 'z');
752 assertEquals("zABCDEF", sq.getSequenceAsString());
753 sq.insertCharAt(2, 2, 'x');
754 assertEquals("zAxxBCDEF", sq.getSequenceAsString());
756 // for static method see StringUtilsTest
760 * Test the method that returns an array of aligned sequence positions where
761 * the array index is the data sequence position (both base 0).
763 @Test(groups = { "Functional" })
764 public void testGapMap()
766 SequenceI sq = new Sequence("test", "-A--B-CD-E--F-");
767 sq.createDatasetSequence();
768 assertEquals("[1, 4, 6, 7, 9, 12]", Arrays.toString(sq.gapMap()));
772 * Test the method that gets sequence features, either from the sequence or
775 @Test(groups = { "Functional" })
776 public void testGetSequenceFeatures()
778 SequenceI sq = new Sequence("test", "GATCAT");
779 sq.createDatasetSequence();
781 assertTrue(sq.getSequenceFeatures().isEmpty());
784 * SequenceFeature on sequence
786 SequenceFeature sf = new SequenceFeature("Cath", "desc", 2, 4, 2f,
788 sq.addSequenceFeature(sf);
789 List<SequenceFeature> sfs = sq.getSequenceFeatures();
790 assertEquals(1, sfs.size());
791 assertSame(sf, sfs.get(0));
794 * SequenceFeature on sequence and dataset sequence; returns that on
797 * Note JAL-2046: spurious: we have no use case for this at the moment.
798 * This test also buggy - as sf2.equals(sf), no new feature is added
800 SequenceFeature sf2 = new SequenceFeature("Cath", "desc", 2, 4, 2f,
802 sq.getDatasetSequence().addSequenceFeature(sf2);
803 sfs = sq.getSequenceFeatures();
804 assertEquals(1, sfs.size());
805 assertSame(sf, sfs.get(0));
808 * SequenceFeature on dataset sequence only
809 * Note JAL-2046: spurious: we have no use case for setting a non-dataset sequence's feature array to null at the moment.
811 sq.setSequenceFeatures(null);
812 assertTrue(sq.getDatasetSequence().getSequenceFeatures().isEmpty());
815 * Corrupt case - no SequenceFeature, dataset's dataset is the original
816 * sequence. Test shows no infinite loop results.
818 sq.getDatasetSequence().setSequenceFeatures(null);
820 * is there a usecase for this ? setDatasetSequence should throw an error if
821 * this actually occurs.
825 sq.getDatasetSequence().setDatasetSequence(sq); // loop!
827 "Expected Error to be raised when calling setDatasetSequence with self reference");
828 } catch (IllegalArgumentException e)
830 // TODO Jalview error/exception class for raising implementation errors
831 assertTrue(e.getMessage().toLowerCase(Locale.ROOT)
832 .contains("implementation error"));
834 assertTrue(sq.getSequenceFeatures().isEmpty());
838 * Test the method that returns an array, indexed by sequence position, whose
839 * entries are the residue positions at the sequence position (or to the right
842 @Test(groups = { "Functional" })
843 public void testFindPositionMap()
846 * Note: Javadoc for findPosition says it returns the residue position to
847 * the left of a gapped position; in fact it returns the position to the
848 * right. Also it returns a non-existent residue position for a gap beyond
851 Sequence sq = new Sequence("TestSeq", "AB.C-D E.");
852 int[] map = sq.findPositionMap();
853 assertEquals(Arrays.toString(new int[] { 1, 2, 3, 3, 4, 4, 5, 5, 6 }),
854 Arrays.toString(map));
858 * Test for getSubsequence
860 @Test(groups = { "Functional" })
861 public void testGetSubsequence()
863 SequenceI sq = new Sequence("TestSeq", "ABCDEFG");
864 sq.createDatasetSequence();
866 // positions are base 0, end position is exclusive
867 SequenceI subseq = sq.getSubSequence(2, 4);
869 assertEquals("CD", subseq.getSequenceAsString());
870 // start/end are base 1 positions
871 assertEquals(3, subseq.getStart());
872 assertEquals(4, subseq.getEnd());
873 // subsequence shares the full dataset sequence
874 assertSame(sq.getDatasetSequence(), subseq.getDatasetSequence());
878 * test createDatasetSequence behaves to doc
880 @Test(groups = { "Functional" })
881 public void testCreateDatasetSequence()
883 SequenceI sq = new Sequence("my", "ASDASD");
884 sq.addSequenceFeature(
885 new SequenceFeature("type", "desc", 1, 10, 1f, "group"));
886 sq.addDBRef(new DBRefEntry("source", "version", "accession"));
887 assertNull(sq.getDatasetSequence());
888 assertNotNull(PA.getValue(sq, "sequenceFeatureStore"));
889 assertNotNull(PA.getValue(sq, "dbrefs"));
891 SequenceI rds = sq.createDatasetSequence();
893 assertNull(rds.getDatasetSequence());
894 assertSame(sq.getDatasetSequence(), rds);
896 // sequence features and dbrefs transferred to dataset sequence
897 assertNull(PA.getValue(sq, "sequenceFeatureStore"));
898 assertNull(PA.getValue(sq, "dbrefs"));
899 assertNotNull(PA.getValue(rds, "sequenceFeatureStore"));
900 assertNotNull(PA.getValue(rds, "dbrefs"));
904 * Test for deriveSequence applied to a sequence with a dataset
906 @Test(groups = { "Functional" })
907 public void testDeriveSequence_existingDataset()
909 Sequence sq = new Sequence("Seq1", "CD");
910 sq.setDatasetSequence(new Sequence("Seq1", "ABCDEF"));
911 sq.getDatasetSequence().addSequenceFeature(
912 new SequenceFeature("", "", 1, 2, 0f, null));
916 sq.setDescription("Test sequence description..");
917 sq.setVamsasId("TestVamsasId");
918 sq.addDBRef(new DBRefEntry("PDB", "version0", "1TST"));
920 sq.addDBRef(new DBRefEntry("PDB", "version1", "1PDB"));
921 sq.addDBRef(new DBRefEntry("PDB", "version2", "2PDB"));
922 sq.addDBRef(new DBRefEntry("PDB", "version3", "3PDB"));
923 sq.addDBRef(new DBRefEntry("PDB", "version4", "4PDB"));
925 sq.addPDBId(new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1"));
926 sq.addPDBId(new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1"));
927 sq.addPDBId(new PDBEntry("2PDB", "A", Type.MMCIF, "filePath/test2"));
928 sq.addPDBId(new PDBEntry("2PDB", "B", Type.MMCIF, "filePath/test2"));
930 // these are the same as ones already added
931 DBRefEntry pdb1pdb = new DBRefEntry("PDB", "version1", "1PDB");
932 DBRefEntry pdb2pdb = new DBRefEntry("PDB", "version2", "2PDB");
934 List<DBRefEntry> primRefs = Arrays
935 .asList(new DBRefEntry[]
936 { pdb1pdb, pdb2pdb });
938 sq.getDatasetSequence().addDBRef(pdb1pdb); // should do nothing
939 sq.getDatasetSequence().addDBRef(pdb2pdb); // should do nothing
940 sq.getDatasetSequence()
941 .addDBRef(new DBRefEntry("PDB", "version3", "3PDB")); // should do
943 sq.getDatasetSequence()
944 .addDBRef(new DBRefEntry("PDB", "version4", "4PDB")); // should do
947 PDBEntry pdbe1a = new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1");
948 PDBEntry pdbe1b = new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1");
949 PDBEntry pdbe2a = new PDBEntry("2PDB", "A", Type.MMCIF,
951 PDBEntry pdbe2b = new PDBEntry("2PDB", "B", Type.MMCIF,
953 sq.getDatasetSequence().addPDBId(pdbe1a);
954 sq.getDatasetSequence().addPDBId(pdbe1b);
955 sq.getDatasetSequence().addPDBId(pdbe2a);
956 sq.getDatasetSequence().addPDBId(pdbe2b);
959 * test we added pdb entries to the dataset sequence
961 Assert.assertEquals(sq.getDatasetSequence().getAllPDBEntries(),
962 Arrays.asList(new PDBEntry[]
963 { pdbe1a, pdbe1b, pdbe2a, pdbe2b }),
964 "PDB Entries were not found on dataset sequence.");
967 * we should recover a pdb entry that is on the dataset sequence via PDBEntry
969 Assert.assertEquals(pdbe1a, sq.getDatasetSequence().getPDBEntry("1PDB"),
970 "PDB Entry '1PDB' not found on dataset sequence via getPDBEntry.");
971 ArrayList<Annotation> annotsList = new ArrayList<>();
972 System.out.println(">>>>>> " + sq.getSequenceAsString().length());
973 annotsList.add(new Annotation("A", "A", 'X', 0.1f));
974 annotsList.add(new Annotation("A", "A", 'X', 0.1f));
975 Annotation[] annots = annotsList.toArray(new Annotation[0]);
976 sq.addAlignmentAnnotation(new AlignmentAnnotation("Test annot",
977 "Test annot description", annots));
978 sq.getDatasetSequence().addAlignmentAnnotation(new AlignmentAnnotation(
979 "Test annot", "Test annot description", annots));
980 Assert.assertEquals(sq.getDescription(), "Test sequence description..");
981 Assert.assertEquals(sq.getDBRefs().size(), 5); // DBRefs are on dataset
983 Assert.assertEquals(sq.getAllPDBEntries().size(), 4);
984 Assert.assertNotNull(sq.getAnnotation());
985 Assert.assertEquals(sq.getAnnotation()[0].annotations.length, 2);
986 Assert.assertEquals(sq.getDatasetSequence().getDBRefs().size(), 5); // same
989 Assert.assertEquals(sq.getDatasetSequence().getAllPDBEntries().size(),
991 Assert.assertNotNull(sq.getDatasetSequence().getAnnotation());
993 Sequence derived = (Sequence) sq.deriveSequence();
995 Assert.assertEquals(derived.getDescription(),
996 "Test sequence description..");
997 Assert.assertEquals(derived.getDBRefs().size(), 5); // come from dataset
998 Assert.assertEquals(derived.getAllPDBEntries().size(), 4);
999 Assert.assertNotNull(derived.getAnnotation());
1000 Assert.assertEquals(derived.getAnnotation()[0].annotations.length, 2);
1001 Assert.assertEquals(derived.getDatasetSequence().getDBRefs().size(), 5);
1002 Assert.assertEquals(
1003 derived.getDatasetSequence().getAllPDBEntries().size(), 4);
1004 Assert.assertNotNull(derived.getDatasetSequence().getAnnotation());
1006 assertEquals("CD", derived.getSequenceAsString());
1007 assertSame(sq.getDatasetSequence(), derived.getDatasetSequence());
1009 // derived sequence should access dataset sequence features
1010 assertNotNull(sq.getSequenceFeatures());
1011 assertEquals(sq.getSequenceFeatures(), derived.getSequenceFeatures());
1014 * verify we have primary db refs *just* for PDB IDs with associated
1018 assertEquals(primRefs, sq.getPrimaryDBRefs());
1019 assertEquals(primRefs, sq.getDatasetSequence().getPrimaryDBRefs());
1021 assertEquals(sq.getPrimaryDBRefs(), derived.getPrimaryDBRefs());
1026 * Test for deriveSequence applied to an ungapped sequence with no dataset
1028 @Test(groups = { "Functional" })
1029 public void testDeriveSequence_noDatasetUngapped()
1031 SequenceI sq = new Sequence("Seq1", "ABCDEF");
1032 assertEquals(1, sq.getStart());
1033 assertEquals(6, sq.getEnd());
1034 SequenceI derived = sq.deriveSequence();
1035 assertEquals("ABCDEF", derived.getSequenceAsString());
1036 assertEquals("ABCDEF",
1037 derived.getDatasetSequence().getSequenceAsString());
1041 * Test for deriveSequence applied to a gapped sequence with no dataset
1043 @Test(groups = { "Functional" })
1044 public void testDeriveSequence_noDatasetGapped()
1046 SequenceI sq = new Sequence("Seq1", "AB-C.D EF");
1047 assertEquals(1, sq.getStart());
1048 assertEquals(6, sq.getEnd());
1049 assertNull(sq.getDatasetSequence());
1050 SequenceI derived = sq.deriveSequence();
1051 assertEquals("AB-C.D EF", derived.getSequenceAsString());
1052 assertEquals("ABCDEF",
1053 derived.getDatasetSequence().getSequenceAsString());
1056 @Test(groups = { "Functional" })
1057 public void testCopyConstructor_noDataset()
1059 SequenceI seq1 = new Sequence("Seq1", "AB-C.D EF");
1060 seq1.setDescription("description");
1061 seq1.addAlignmentAnnotation(
1062 new AlignmentAnnotation("label", "desc", 1.3d));
1063 seq1.addSequenceFeature(
1064 new SequenceFeature("type", "desc", 22, 33, 12.4f, "group"));
1065 seq1.addPDBId(new PDBEntry("1A70", "B", Type.PDB, "File"));
1066 seq1.addDBRef(new DBRefEntry("EMBL", "1.2", "AZ12345"));
1068 SequenceI copy = new Sequence(seq1);
1070 assertNull(copy.getDatasetSequence());
1072 verifyCopiedSequence(seq1, copy);
1074 // copy has a copy of the DBRefEntry
1075 // this is murky - DBrefs are only copied for dataset sequences
1076 // where the test for 'dataset sequence' is 'dataset is null'
1077 // but that doesn't distinguish it from an aligned sequence
1078 // which has not yet generated a dataset sequence
1079 // NB getDBRef looks inside dataset sequence if not null
1080 List<DBRefEntry> dbrefs = copy.getDBRefs();
1081 assertEquals(1, dbrefs.size());
1082 assertFalse(dbrefs.get(0) == seq1.getDBRefs().get(0));
1083 assertTrue(dbrefs.get(0).equals(seq1.getDBRefs().get(0)));
1086 @Test(groups = { "Functional" })
1087 public void testCopyConstructor_withDataset()
1089 SequenceI seq1 = new Sequence("Seq1", "AB-C.D EF");
1090 seq1.createDatasetSequence();
1091 seq1.setDescription("description");
1092 seq1.addAlignmentAnnotation(
1093 new AlignmentAnnotation("label", "desc", 1.3d));
1094 // JAL-2046 - what is the contract for using a derived sequence's
1095 // addSequenceFeature ?
1096 seq1.addSequenceFeature(
1097 new SequenceFeature("type", "desc", 22, 33, 12.4f, "group"));
1098 seq1.addPDBId(new PDBEntry("1A70", "B", Type.PDB, "File"));
1099 // here we add DBRef to the dataset sequence:
1100 seq1.getDatasetSequence()
1101 .addDBRef(new DBRefEntry("EMBL", "1.2", "AZ12345"));
1103 SequenceI copy = new Sequence(seq1);
1105 assertNotNull(copy.getDatasetSequence());
1106 assertSame(copy.getDatasetSequence(), seq1.getDatasetSequence());
1108 verifyCopiedSequence(seq1, copy);
1110 // getDBRef looks inside dataset sequence and this is shared,
1111 // so holds the same dbref objects
1112 List<DBRefEntry> dbrefs = copy.getDBRefs();
1113 assertEquals(1, dbrefs.size());
1114 assertSame(dbrefs.get(0), seq1.getDBRefs().get(0));
1118 * Helper to make assertions about a copied sequence
1123 protected void verifyCopiedSequence(SequenceI seq1, SequenceI copy)
1125 // verify basic properties:
1126 assertEquals(copy.getName(), seq1.getName());
1127 assertEquals(copy.getDescription(), seq1.getDescription());
1128 assertEquals(copy.getStart(), seq1.getStart());
1129 assertEquals(copy.getEnd(), seq1.getEnd());
1130 assertEquals(copy.getSequenceAsString(), seq1.getSequenceAsString());
1132 // copy has a copy of the annotation:
1133 AlignmentAnnotation[] anns = copy.getAnnotation();
1134 assertEquals(1, anns.length);
1135 assertFalse(anns[0] == seq1.getAnnotation()[0]);
1136 assertEquals(anns[0].label, seq1.getAnnotation()[0].label);
1137 assertEquals(anns[0].description, seq1.getAnnotation()[0].description);
1138 assertEquals(anns[0].score, seq1.getAnnotation()[0].score);
1140 // copy has a copy of the sequence feature:
1141 List<SequenceFeature> sfs = copy.getSequenceFeatures();
1142 assertEquals(1, sfs.size());
1143 if (seq1.getDatasetSequence() != null
1144 && copy.getDatasetSequence() == seq1.getDatasetSequence())
1146 assertSame(sfs.get(0), seq1.getSequenceFeatures().get(0));
1150 assertNotSame(sfs.get(0), seq1.getSequenceFeatures().get(0));
1152 assertEquals(sfs.get(0), seq1.getSequenceFeatures().get(0));
1154 // copy has a copy of the PDB entry
1155 Vector<PDBEntry> pdbs = copy.getAllPDBEntries();
1156 assertEquals(1, pdbs.size());
1157 assertFalse(pdbs.get(0) == seq1.getAllPDBEntries().get(0));
1158 assertTrue(pdbs.get(0).equals(seq1.getAllPDBEntries().get(0)));
1161 @Test(groups = "Functional")
1162 public void testGetCharAt()
1164 SequenceI sq = new Sequence("", "abcde");
1165 assertEquals('a', sq.getCharAt(0));
1166 assertEquals('e', sq.getCharAt(4));
1167 assertEquals(' ', sq.getCharAt(5));
1168 assertEquals(' ', sq.getCharAt(-1));
1171 @Test(groups = { "Functional" })
1172 public void testAddSequenceFeatures()
1174 SequenceI sq = new Sequence("", "abcde");
1175 // type may not be null
1176 assertFalse(sq.addSequenceFeature(
1177 new SequenceFeature(null, "desc", 4, 8, 0f, null)));
1178 assertTrue(sq.addSequenceFeature(
1179 new SequenceFeature("Cath", "desc", 4, 8, 0f, null)));
1180 // can't add a duplicate feature
1181 assertFalse(sq.addSequenceFeature(
1182 new SequenceFeature("Cath", "desc", 4, 8, 0f, null)));
1183 // can add a different feature
1184 assertTrue(sq.addSequenceFeature(
1185 new SequenceFeature("Scop", "desc", 4, 8, 0f, null))); // different
1187 assertTrue(sq.addSequenceFeature(
1188 new SequenceFeature("Cath", "description", 4, 8, 0f, null)));// different
1190 assertTrue(sq.addSequenceFeature(
1191 new SequenceFeature("Cath", "desc", 3, 8, 0f, null))); // different
1194 assertTrue(sq.addSequenceFeature(
1195 new SequenceFeature("Cath", "desc", 4, 9, 0f, null))); // different
1198 assertTrue(sq.addSequenceFeature(
1199 new SequenceFeature("Cath", "desc", 4, 8, 1f, null))); // different
1201 assertTrue(sq.addSequenceFeature(
1202 new SequenceFeature("Cath", "desc", 4, 8, Float.NaN, null))); // score
1204 assertTrue(sq.addSequenceFeature(
1205 new SequenceFeature("Cath", "desc", 4, 8, 0f, "Metal"))); // different
1207 assertEquals(8, sq.getFeatures().getAllFeatures().size());
1211 * Tests for adding (or updating) dbrefs
1213 * @see DBRefEntry#updateFrom(DBRefEntry)
1215 @Test(groups = { "Functional" })
1216 public void testAddDBRef()
1218 SequenceI sq = new Sequence("", "abcde");
1219 assertNull(sq.getDBRefs());
1220 DBRefEntry dbref = new DBRefEntry("Uniprot", "1", "P00340");
1222 assertEquals(1, sq.getDBRefs().size());
1223 assertSame(dbref, sq.getDBRefs().get(0));
1226 * change of version - new entry
1228 DBRefEntry dbref2 = new DBRefEntry("Uniprot", "2", "P00340");
1229 sq.addDBRef(dbref2);
1230 assertEquals(2, sq.getDBRefs().size());
1231 assertSame(dbref, sq.getDBRefs().get(0));
1232 assertSame(dbref2, sq.getDBRefs().get(1));
1235 * matches existing entry - not added
1237 sq.addDBRef(new DBRefEntry("UNIPROT", "1", "p00340"));
1238 assertEquals(2, sq.getDBRefs().size());
1241 * different source = new entry
1243 DBRefEntry dbref3 = new DBRefEntry("UniRef", "1", "p00340");
1244 sq.addDBRef(dbref3);
1245 assertEquals(3, sq.getDBRefs().size());
1246 assertSame(dbref3, sq.getDBRefs().get(2));
1249 * different ref = new entry
1251 DBRefEntry dbref4 = new DBRefEntry("UniRef", "1", "p00341");
1252 sq.addDBRef(dbref4);
1253 assertEquals(4, sq.getDBRefs().size());
1254 assertSame(dbref4, sq.getDBRefs().get(3));
1257 * matching ref with a mapping - map updated
1259 DBRefEntry dbref5 = new DBRefEntry("UniRef", "1", "p00341");
1260 Mapping map = new Mapping(
1261 new MapList(new int[]
1262 { 1, 3 }, new int[] { 1, 1 }, 3, 1));
1264 sq.addDBRef(dbref5);
1265 assertEquals(4, sq.getDBRefs().size());
1266 assertSame(dbref4, sq.getDBRefs().get(3));
1267 assertSame(map, dbref4.getMap());
1270 * 'real' version replaces "0" version
1272 dbref2.setVersion("0");
1273 DBRefEntry dbref6 = new DBRefEntry(dbref2.getSource(), "3",
1274 dbref2.getAccessionId());
1275 sq.addDBRef(dbref6);
1276 assertEquals(4, sq.getDBRefs().size());
1277 assertSame(dbref2, sq.getDBRefs().get(1));
1278 assertEquals("3", dbref2.getVersion());
1281 * 'real' version replaces "source:0" version
1283 dbref3.setVersion("Uniprot:0");
1284 DBRefEntry dbref7 = new DBRefEntry(dbref3.getSource(), "3",
1285 dbref3.getAccessionId());
1286 sq.addDBRef(dbref7);
1287 assertEquals(4, sq.getDBRefs().size());
1288 assertSame(dbref3, sq.getDBRefs().get(2));
1289 assertEquals("3", dbref2.getVersion());
1292 @Test(groups = { "Functional" })
1293 public void testGetPrimaryDBRefs_peptide()
1295 SequenceI sq = new Sequence("aseq", "ASDFKYLMQPRST", 10, 22);
1298 List<DBRefEntry> primaryDBRefs = sq.getPrimaryDBRefs();
1299 assertTrue(primaryDBRefs.isEmpty());
1303 primaryDBRefs = sq.getPrimaryDBRefs();
1304 assertTrue(primaryDBRefs.isEmpty());
1306 // primary - uniprot
1307 DBRefEntry upentry1 = new DBRefEntry("UNIPROT", "0", "Q04760");
1308 sq.addDBRef(upentry1);
1310 // primary - uniprot with congruent map
1311 DBRefEntry upentry2 = new DBRefEntry("UNIPROT", "0", "Q04762");
1313 new Mapping(null, new MapList(new int[]
1314 { 10, 22 }, new int[] { 10, 22 }, 1, 1)));
1315 sq.addDBRef(upentry2);
1317 // primary - uniprot with map of enclosing sequence
1318 DBRefEntry upentry3 = new DBRefEntry("UNIPROT", "0", "Q04763");
1320 new Mapping(null, new MapList(new int[]
1321 { 8, 24 }, new int[] { 8, 24 }, 1, 1)));
1322 sq.addDBRef(upentry3);
1324 // not primary - uniprot with map of sub-sequence (5')
1325 DBRefEntry upentry4 = new DBRefEntry("UNIPROT", "0", "Q04764");
1327 new Mapping(null, new MapList(new int[]
1328 { 10, 18 }, new int[] { 10, 18 }, 1, 1)));
1329 sq.addDBRef(upentry4);
1331 // not primary - uniprot with map that overlaps 3'
1332 DBRefEntry upentry5 = new DBRefEntry("UNIPROT", "0", "Q04765");
1334 new Mapping(null, new MapList(new int[]
1335 { 12, 22 }, new int[] { 12, 22 }, 1, 1)));
1336 sq.addDBRef(upentry5);
1338 // not primary - uniprot with map to different coordinates frame
1339 DBRefEntry upentry6 = new DBRefEntry("UNIPROT", "0", "Q04766");
1341 new Mapping(null, new MapList(new int[]
1342 { 12, 18 }, new int[] { 112, 118 }, 1, 1)));
1343 sq.addDBRef(upentry6);
1345 // not primary - dbref to 'non-core' database
1346 DBRefEntry upentry7 = new DBRefEntry("Pfam", "0", "PF00903");
1347 sq.addDBRef(upentry7);
1349 // primary - type is PDB
1350 DBRefEntry pdbentry = new DBRefEntry("PDB", "0", "1qip");
1351 sq.addDBRef(pdbentry);
1353 // not primary - PDBEntry has no file
1354 sq.addDBRef(new DBRefEntry("PDB", "0", "1AAA"));
1356 // not primary - no PDBEntry
1357 sq.addDBRef(new DBRefEntry("PDB", "0", "1DDD"));
1359 // add corroborating PDB entry for primary DBref -
1360 // needs to have a file as well as matching ID
1361 // note PDB ID is not treated as case sensitive
1362 sq.addPDBId(new PDBEntry("1QIP", null, Type.PDB,
1363 new File("/blah").toString()));
1365 // not valid DBRef - no file..
1366 sq.addPDBId(new PDBEntry("1AAA", null, null, null));
1368 primaryDBRefs = sq.getPrimaryDBRefs();
1369 assertEquals(4, primaryDBRefs.size());
1370 assertTrue("Couldn't find simple primary reference (UNIPROT)",
1371 primaryDBRefs.contains(upentry1));
1372 assertTrue("Couldn't find mapped primary reference (UNIPROT)",
1373 primaryDBRefs.contains(upentry2));
1374 assertTrue("Couldn't find mapped context reference (UNIPROT)",
1375 primaryDBRefs.contains(upentry3));
1376 assertTrue("Couldn't find expected PDB primary reference",
1377 primaryDBRefs.contains(pdbentry));
1380 @Test(groups = { "Functional" })
1381 public void testGetPrimaryDBRefs_nucleotide()
1383 SequenceI sq = new Sequence("aseq", "TGATCACTCGACTAGCATCAGCATA", 10,
1386 // primary - Ensembl
1387 DBRefEntry dbr1 = new DBRefEntry("ENSEMBL", "0", "ENSG1234");
1390 // not primary - Ensembl 'transcript' mapping of sub-sequence
1391 DBRefEntry dbr2 = new DBRefEntry("ENSEMBL", "0", "ENST1234");
1393 new Mapping(null, new MapList(new int[]
1394 { 15, 25 }, new int[] { 1, 11 }, 1, 1)));
1397 // primary - EMBL with congruent map
1398 DBRefEntry dbr3 = new DBRefEntry("EMBL", "0", "J1234");
1400 new Mapping(null, new MapList(new int[]
1401 { 10, 34 }, new int[] { 10, 34 }, 1, 1)));
1404 // not primary - to non-core database
1405 DBRefEntry dbr4 = new DBRefEntry("CCDS", "0", "J1234");
1408 // not primary - to protein
1409 DBRefEntry dbr5 = new DBRefEntry("UNIPROT", "0", "Q87654");
1412 List<DBRefEntry> primaryDBRefs = sq.getPrimaryDBRefs();
1413 assertEquals(2, primaryDBRefs.size());
1414 assertTrue(primaryDBRefs.contains(dbr1));
1415 assertTrue(primaryDBRefs.contains(dbr3));
1419 * Test the method that updates the list of PDBEntry from any new DBRefEntry
1422 @Test(groups = { "Functional" })
1423 public void testUpdatePDBIds()
1425 PDBEntry pdbe1 = new PDBEntry("3A6S", null, null, null);
1426 seq.addPDBId(pdbe1);
1427 seq.addDBRef(new DBRefEntry("Ensembl", "8", "ENST1234"));
1428 seq.addDBRef(new DBRefEntry("PDB", "0", "1A70"));
1429 seq.addDBRef(new DBRefEntry("PDB", "0", "4BQGa"));
1430 seq.addDBRef(new DBRefEntry("PDB", "0", "3a6sB"));
1431 // 7 is not a valid chain code:
1432 seq.addDBRef(new DBRefEntry("PDB", "0", "2GIS7"));
1435 List<PDBEntry> pdbIds = seq.getAllPDBEntries();
1436 assertEquals(4, pdbIds.size());
1437 assertSame(pdbe1, pdbIds.get(0));
1438 // chain code got added to 3A6S:
1439 assertEquals("B", pdbe1.getChainCode());
1440 assertEquals("1A70", pdbIds.get(1).getId());
1441 // 4BQGA is parsed into id + chain
1442 assertEquals("4BQG", pdbIds.get(2).getId());
1443 assertEquals("a", pdbIds.get(2).getChainCode());
1444 assertEquals("2GIS7", pdbIds.get(3).getId());
1445 assertNull(pdbIds.get(3).getChainCode());
1449 * Test the method that either adds a pdbid or updates an existing one
1451 @Test(groups = { "Functional" })
1452 public void testAddPDBId()
1454 PDBEntry pdbe = new PDBEntry("3A6S", null, null, null);
1456 assertEquals(1, seq.getAllPDBEntries().size());
1457 assertSame(pdbe, seq.getPDBEntry("3A6S"));
1458 assertSame(pdbe, seq.getPDBEntry("3a6s")); // case-insensitive
1460 // add the same entry
1462 assertEquals(1, seq.getAllPDBEntries().size());
1463 assertSame(pdbe, seq.getPDBEntry("3A6S"));
1465 // add an identical entry
1466 seq.addPDBId(new PDBEntry("3A6S", null, null, null));
1467 assertEquals(1, seq.getAllPDBEntries().size());
1468 assertSame(pdbe, seq.getPDBEntry("3A6S"));
1470 // add a different entry
1471 PDBEntry pdbe2 = new PDBEntry("1A70", null, null, null);
1472 seq.addPDBId(pdbe2);
1473 assertEquals(2, seq.getAllPDBEntries().size());
1474 assertSame(pdbe, seq.getAllPDBEntries().get(0));
1475 assertSame(pdbe2, seq.getAllPDBEntries().get(1));
1477 // update pdbe with chain code, file, type
1478 PDBEntry pdbe3 = new PDBEntry("3a6s", "A", Type.PDB, "filepath");
1479 seq.addPDBId(pdbe3);
1480 assertEquals(2, seq.getAllPDBEntries().size());
1481 assertSame(pdbe, seq.getAllPDBEntries().get(0)); // updated in situ
1482 assertEquals("3A6S", pdbe.getId()); // unchanged
1483 assertEquals("A", pdbe.getChainCode()); // updated
1484 assertEquals(Type.PDB.toString(), pdbe.getType()); // updated
1485 assertEquals("filepath", pdbe.getFile()); // updated
1486 assertSame(pdbe2, seq.getAllPDBEntries().get(1));
1488 // add with a different file path
1489 PDBEntry pdbe4 = new PDBEntry("3a6s", "A", Type.PDB, "filepath2");
1490 seq.addPDBId(pdbe4);
1491 assertEquals(3, seq.getAllPDBEntries().size());
1492 assertSame(pdbe4, seq.getAllPDBEntries().get(2));
1494 // add with a different chain code
1495 PDBEntry pdbe5 = new PDBEntry("3a6s", "B", Type.PDB, "filepath");
1496 seq.addPDBId(pdbe5);
1497 assertEquals(4, seq.getAllPDBEntries().size());
1498 assertSame(pdbe5, seq.getAllPDBEntries().get(3));
1500 // add with a fake pdbid
1501 // (models don't have an embedded ID)
1502 String realId = "RealIDQ";
1503 PDBEntry pdbe6 = new PDBEntry(realId, null, Type.PDB, "real/localpath");
1504 PDBEntry pdbe7 = new PDBEntry("RealID/real/localpath", "C", Type.MMCIF,
1506 pdbe7.setFakedPDBId(true);
1507 seq.addPDBId(pdbe6);
1508 assertEquals(5, seq.getAllPDBEntries().size());
1509 seq.addPDBId(pdbe7);
1510 assertEquals(5, seq.getAllPDBEntries().size());
1511 assertFalse(pdbe6.fakedPDBId());
1512 assertSame(pdbe6, seq.getAllPDBEntries().get(4));
1513 assertEquals("C", pdbe6.getChainCode());
1514 assertEquals(realId, pdbe6.getId());
1520 expectedExceptions =
1521 { IllegalArgumentException.class })
1522 public void testSetDatasetSequence_toSelf()
1524 seq.setDatasetSequence(seq);
1530 expectedExceptions =
1531 { IllegalArgumentException.class })
1532 public void testSetDatasetSequence_cascading()
1534 SequenceI seq2 = new Sequence("Seq2", "xyz");
1535 seq2.createDatasetSequence();
1536 seq.setDatasetSequence(seq2);
1539 @Test(groups = { "Functional" })
1540 public void testFindFeatures()
1542 SequenceI sq = new Sequence("test/8-16", "-ABC--DEF--GHI--");
1543 sq.createDatasetSequence();
1545 assertTrue(sq.findFeatures(1, 99).isEmpty());
1547 // add non-positional feature
1548 SequenceFeature sf0 = new SequenceFeature("Cath", "desc", 0, 0, 2f,
1550 sq.addSequenceFeature(sf0);
1551 // add feature on BCD
1552 SequenceFeature sfBCD = new SequenceFeature("Cath", "desc", 9, 11, 2f,
1554 sq.addSequenceFeature(sfBCD);
1555 // add feature on DE
1556 SequenceFeature sfDE = new SequenceFeature("Cath", "desc", 11, 12, 2f,
1558 sq.addSequenceFeature(sfDE);
1559 // add contact feature at [B, H]
1560 SequenceFeature sfContactBH = new SequenceFeature("Disulphide bond",
1561 "desc", 9, 15, 2f, null);
1562 sq.addSequenceFeature(sfContactBH);
1563 // add contact feature at [F, G]
1564 SequenceFeature sfContactFG = new SequenceFeature("Disulfide Bond",
1565 "desc", 13, 14, 2f, null);
1566 sq.addSequenceFeature(sfContactFG);
1567 // add single position feature at [I]
1568 SequenceFeature sfI = new SequenceFeature("Disulfide Bond", "desc", 16,
1570 sq.addSequenceFeature(sfI);
1572 // no features in columns 1-2 (-A)
1573 List<SequenceFeature> found = sq.findFeatures(1, 2);
1574 assertTrue(found.isEmpty());
1576 // columns 1-6 (-ABC--) includes BCD and B/H feature but not DE
1577 found = sq.findFeatures(1, 6);
1578 assertEquals(2, found.size());
1579 assertTrue(found.contains(sfBCD));
1580 assertTrue(found.contains(sfContactBH));
1582 // columns 5-6 (--) includes (enclosing) BCD but not (contact) B/H feature
1583 found = sq.findFeatures(5, 6);
1584 assertEquals(1, found.size());
1585 assertTrue(found.contains(sfBCD));
1587 // columns 7-10 (DEF-) includes BCD, DE, F/G but not B/H feature
1588 found = sq.findFeatures(7, 10);
1589 assertEquals(3, found.size());
1590 assertTrue(found.contains(sfBCD));
1591 assertTrue(found.contains(sfDE));
1592 assertTrue(found.contains(sfContactFG));
1594 // columns 10-11 (--) should find nothing
1595 found = sq.findFeatures(10, 11);
1596 assertEquals(0, found.size());
1598 // columns 14-14 (I) should find variant feature
1599 found = sq.findFeatures(14, 14);
1600 assertEquals(1, found.size());
1601 assertTrue(found.contains(sfI));
1604 @Test(groups = { "Functional" })
1605 public void testFindIndex_withCursor()
1607 Sequence sq = new Sequence("test/8-13", "-A--BCD-EF--");
1608 final int tok = (int) PA.getValue(sq, "changeCount");
1609 assertEquals(1, tok);
1611 // find F given A, check cursor is now at the found position
1612 assertEquals(10, sq.findIndex(13, new SequenceCursor(sq, 8, 2, tok)));
1613 SequenceCursor cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1614 assertEquals(13, cursor.residuePosition);
1615 assertEquals(10, cursor.columnPosition);
1618 assertEquals(2, sq.findIndex(8, new SequenceCursor(sq, 13, 10, tok)));
1619 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1620 assertEquals(8, cursor.residuePosition);
1621 assertEquals(2, cursor.columnPosition);
1623 // find C given C (no cursor update is done for this case)
1624 assertEquals(6, sq.findIndex(10, new SequenceCursor(sq, 10, 6, tok)));
1625 SequenceCursor cursor2 = (SequenceCursor) PA.getValue(sq, "cursor");
1626 assertSame(cursor2, cursor);
1629 * sequence 'end' beyond end of sequence returns length of sequence
1630 * (for compatibility with pre-cursor code)
1631 * - also verify the cursor is left in a valid state
1633 sq = new Sequence("test/8-99", "-A--B-C-D-E-F--"); // trailing gap case
1634 assertEquals(7, sq.findIndex(10)); // establishes a cursor
1635 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1636 assertEquals(10, cursor.residuePosition);
1637 assertEquals(7, cursor.columnPosition);
1638 assertEquals(sq.getLength(), sq.findIndex(65));
1639 cursor2 = (SequenceCursor) PA.getValue(sq, "cursor");
1640 assertSame(cursor, cursor2); // not updated for this case!
1642 sq = new Sequence("test/8-99", "-A--B-C-D-E-F"); // trailing residue case
1643 sq.findIndex(10); // establishes a cursor
1644 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1645 assertEquals(sq.getLength(), sq.findIndex(65));
1646 cursor2 = (SequenceCursor) PA.getValue(sq, "cursor");
1647 assertSame(cursor, cursor2); // not updated for this case!
1650 * residue after sequence 'start' but before first residue should return
1651 * zero (for compatibility with pre-cursor code)
1653 sq = new Sequence("test/8-15", "-A-B-C-"); // leading gap case
1654 sq.findIndex(10); // establishes a cursor
1655 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1656 assertEquals(0, sq.findIndex(3));
1657 cursor2 = (SequenceCursor) PA.getValue(sq, "cursor");
1658 assertSame(cursor, cursor2); // not updated for this case!
1660 sq = new Sequence("test/8-15", "A-B-C-"); // leading residue case
1661 sq.findIndex(10); // establishes a cursor
1662 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1663 assertEquals(0, sq.findIndex(2));
1664 cursor2 = (SequenceCursor) PA.getValue(sq, "cursor");
1665 assertSame(cursor, cursor2); // not updated for this case!
1668 @Test(groups = { "Functional" })
1669 public void testFindPosition_withCursor()
1671 Sequence sq = new Sequence("test/8-13", "-A--BCD-EF--");
1672 final int tok = (int) PA.getValue(sq, "changeCount");
1673 assertEquals(1, tok);
1675 // find F pos given A - lastCol gets set in cursor
1677 sq.findPosition(10, new SequenceCursor(sq, 8, 2, tok)));
1678 assertEquals("test:Pos13:Col10:startCol0:endCol10:tok1",
1679 PA.getValue(sq, "cursor").toString());
1681 // find A pos given F - first residue column is saved in cursor
1683 sq.findPosition(2, new SequenceCursor(sq, 13, 10, tok)));
1684 assertEquals("test:Pos8:Col2:startCol2:endCol10:tok1",
1685 PA.getValue(sq, "cursor").toString());
1687 // find C pos given C (neither startCol nor endCol is set)
1689 sq.findPosition(6, new SequenceCursor(sq, 10, 6, tok)));
1690 assertEquals("test:Pos10:Col6:startCol0:endCol0:tok1",
1691 PA.getValue(sq, "cursor").toString());
1693 // now the grey area - what residue position for a gapped column? JAL-2562
1695 // find 'residue' for column 3 given cursor for D (so working left)
1696 // returns B9; cursor is updated to [B 5]
1697 assertEquals(9, sq.findPosition(3, new SequenceCursor(sq, 11, 7, tok)));
1698 assertEquals("test:Pos9:Col5:startCol0:endCol0:tok1",
1699 PA.getValue(sq, "cursor").toString());
1701 // find 'residue' for column 8 given cursor for D (so working right)
1702 // returns E12; cursor is updated to [D 7]
1704 sq.findPosition(8, new SequenceCursor(sq, 11, 7, tok)));
1705 assertEquals("test:Pos11:Col7:startCol0:endCol0:tok1",
1706 PA.getValue(sq, "cursor").toString());
1708 // find 'residue' for column 12 given cursor for B
1709 // returns 1 more than last residue position; cursor is updated to [F 10]
1710 // lastCol position is saved in cursor
1712 sq.findPosition(12, new SequenceCursor(sq, 9, 5, tok)));
1713 assertEquals("test:Pos13:Col10:startCol0:endCol10:tok1",
1714 PA.getValue(sq, "cursor").toString());
1717 * findPosition for column beyond length of sequence
1718 * returns 1 more than the last residue position
1719 * cursor is set to last real residue position [F 10]
1722 sq.findPosition(99, new SequenceCursor(sq, 8, 2, tok)));
1723 assertEquals("test:Pos13:Col10:startCol0:endCol10:tok1",
1724 PA.getValue(sq, "cursor").toString());
1727 * and the case without a trailing gap
1729 sq = new Sequence("test/8-13", "-A--BCD-EF");
1730 // first find C from A
1731 assertEquals(10, sq.findPosition(6, new SequenceCursor(sq, 8, 2, tok)));
1732 SequenceCursor cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1733 assertEquals("test:Pos10:Col6:startCol0:endCol0:tok1",
1735 // now 'find' 99 from C
1736 // cursor is set to [F 10] and saved lastCol
1737 assertEquals(14, sq.findPosition(99, cursor));
1738 assertEquals("test:Pos13:Col10:startCol0:endCol10:tok1",
1739 PA.getValue(sq, "cursor").toString());
1743 public void testIsValidCursor()
1745 Sequence sq = new Sequence("Seq", "ABC--DE-F", 8, 13);
1746 assertFalse(sq.isValidCursor(null));
1749 * cursor is valid if it has valid sequence ref and changeCount token
1750 * and positions within the range of the sequence
1752 int changeCount = (int) PA.getValue(sq, "changeCount");
1753 SequenceCursor cursor = new SequenceCursor(sq, 13, 1, changeCount);
1754 assertTrue(sq.isValidCursor(cursor));
1757 * column position outside [0 - length] is rejected
1759 cursor = new SequenceCursor(sq, 13, -1, changeCount);
1760 assertFalse(sq.isValidCursor(cursor));
1761 cursor = new SequenceCursor(sq, 13, 10, changeCount);
1762 assertFalse(sq.isValidCursor(cursor));
1763 cursor = new SequenceCursor(sq, 7, 8, changeCount);
1764 assertFalse(sq.isValidCursor(cursor));
1765 cursor = new SequenceCursor(sq, 14, 2, changeCount);
1766 assertFalse(sq.isValidCursor(cursor));
1769 * wrong sequence is rejected
1771 cursor = new SequenceCursor(null, 13, 1, changeCount);
1772 assertFalse(sq.isValidCursor(cursor));
1773 cursor = new SequenceCursor(new Sequence("Seq", "abc"), 13, 1,
1775 assertFalse(sq.isValidCursor(cursor));
1778 * wrong token value is rejected
1780 cursor = new SequenceCursor(sq, 13, 1, changeCount + 1);
1781 assertFalse(sq.isValidCursor(cursor));
1782 cursor = new SequenceCursor(sq, 13, 1, changeCount - 1);
1783 assertFalse(sq.isValidCursor(cursor));
1786 @Test(groups = { "Functional" })
1787 public void testFindPosition_withCursorAndEdits()
1789 Sequence sq = new Sequence("test/8-13", "-A--BCD-EF--");
1791 // find F pos given A
1792 assertEquals(13, sq.findPosition(10, new SequenceCursor(sq, 8, 2, 0)));
1793 int token = (int) PA.getValue(sq, "changeCount"); // 0
1794 SequenceCursor cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1795 assertEquals(new SequenceCursor(sq, 13, 10, token), cursor);
1798 * setSequence should invalidate the cursor cached by the sequence
1800 sq.setSequence("-A-BCD-EF---"); // one gap removed
1801 assertEquals(8, sq.getStart()); // sanity check
1802 assertEquals(11, sq.findPosition(5)); // D11
1803 // cursor should now be at [D 6]
1804 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1805 assertEquals(new SequenceCursor(sq, 11, 6, ++token), cursor);
1806 assertEquals(0, cursor.lastColumnPosition); // not yet found
1807 assertEquals(13, sq.findPosition(8)); // E13
1808 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1809 assertEquals(9, cursor.lastColumnPosition); // found
1812 * deleteChars should invalidate the cached cursor
1814 sq.deleteChars(2, 5); // delete -BC
1815 assertEquals("-AD-EF---", sq.getSequenceAsString());
1816 assertEquals(8, sq.getStart()); // sanity check
1817 assertEquals(10, sq.findPosition(4)); // E10
1818 // cursor should now be at [E 5]
1819 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1820 assertEquals(new SequenceCursor(sq, 10, 5, ++token), cursor);
1823 * Edit to insert gaps should invalidate the cached cursor
1824 * insert 2 gaps at column[3] to make -AD---EF---
1826 SequenceI[] seqs = new SequenceI[] { sq };
1827 AlignmentI al = new Alignment(seqs);
1828 new EditCommand().appendEdit(Action.INSERT_GAP, seqs, 3, 2, al, true);
1829 assertEquals("-AD---EF---", sq.getSequenceAsString());
1830 assertEquals(10, sq.findPosition(4)); // E10
1831 // cursor should now be at [D 3]
1832 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1833 assertEquals(new SequenceCursor(sq, 9, 3, ++token), cursor);
1836 * insertCharAt should invalidate the cached cursor
1837 * insert CC at column[4] to make -AD-CC--EF---
1839 sq.insertCharAt(4, 2, 'C');
1840 assertEquals("-AD-CC--EF---", sq.getSequenceAsString());
1841 assertEquals(13, sq.findPosition(9)); // F13
1842 // cursor should now be at [F 10]
1843 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1844 assertEquals(new SequenceCursor(sq, 13, 10, ++token), cursor);
1847 * changing sequence start should invalidate cursor
1849 sq = new Sequence("test/8-13", "-A--BCD-EF--");
1850 assertEquals(8, sq.getStart());
1851 assertEquals(9, sq.findPosition(4)); // B(9)
1853 assertEquals(8, sq.findPosition(4)); // is now B(8)
1855 assertEquals(11, sq.findPosition(4)); // is now B(11)
1858 @Test(groups = { "Functional" })
1859 public void testGetSequence()
1861 String seqstring = "-A--BCD-EF--";
1862 Sequence sq = new Sequence("test/8-13", seqstring);
1863 sq.createDatasetSequence();
1864 assertTrue(Arrays.equals(sq.getSequence(), seqstring.toCharArray()));
1865 assertTrue(Arrays.equals(sq.getDatasetSequence().getSequence(),
1866 "ABCDEF".toCharArray()));
1868 // verify a copy of the sequence array is returned
1869 char[] theSeq = (char[]) PA.getValue(sq, "sequence");
1870 assertNotSame(theSeq, sq.getSequence());
1871 theSeq = (char[]) PA.getValue(sq.getDatasetSequence(), "sequence");
1872 assertNotSame(theSeq, sq.getDatasetSequence().getSequence());
1875 @Test(groups = { "Functional" })
1876 public void testReplace()
1878 String seqstring = "-A--BCD-EF--";
1879 SequenceI sq = new Sequence("test/8-13", seqstring);
1880 // changeCount is incremented for setStart
1881 assertEquals(1, PA.getValue(sq, "changeCount"));
1883 assertEquals(0, sq.replace('A', 'A')); // same char
1884 assertEquals(seqstring, sq.getSequenceAsString());
1885 assertEquals(1, PA.getValue(sq, "changeCount"));
1887 assertEquals(0, sq.replace('X', 'Y')); // not there
1888 assertEquals(seqstring, sq.getSequenceAsString());
1889 assertEquals(1, PA.getValue(sq, "changeCount"));
1891 assertEquals(1, sq.replace('A', 'K'));
1892 assertEquals("-K--BCD-EF--", sq.getSequenceAsString());
1893 assertEquals(2, PA.getValue(sq, "changeCount"));
1895 assertEquals(6, sq.replace('-', '.'));
1896 assertEquals(".K..BCD.EF..", sq.getSequenceAsString());
1897 assertEquals(3, PA.getValue(sq, "changeCount"));
1900 @Test(groups = { "Functional" })
1901 public void testGapBitset()
1903 SequenceI sq = new Sequence("test/8-13", "-ABC---DE-F--");
1904 BitSet bs = sq.gapBitset();
1905 BitSet expected = new BitSet();
1909 expected.set(11, 13);
1911 assertTrue(bs.equals(expected));
1915 public void testFindFeatures_largeEndPos()
1918 * imitate a PDB sequence where end is larger than end position
1920 SequenceI sq = new Sequence("test", "-ABC--DEF--", 1, 20);
1921 sq.createDatasetSequence();
1923 assertTrue(sq.findFeatures(1, 9).isEmpty());
1924 // should be no array bounds exception - JAL-2772
1925 assertTrue(sq.findFeatures(1, 15).isEmpty());
1927 // add feature on BCD
1928 SequenceFeature sfBCD = new SequenceFeature("Cath", "desc", 2, 4, 2f,
1930 sq.addSequenceFeature(sfBCD);
1932 // no features in columns 1-2 (-A)
1933 List<SequenceFeature> found = sq.findFeatures(1, 2);
1934 assertTrue(found.isEmpty());
1936 // columns 1-6 (-ABC--) includes BCD
1937 found = sq.findFeatures(1, 6);
1938 assertEquals(1, found.size());
1939 assertTrue(found.contains(sfBCD));
1941 // columns 10-11 (--) should find nothing
1942 found = sq.findFeatures(10, 11);
1943 assertEquals(0, found.size());
1946 @Test(groups = { "Functional" })
1947 public void testSetName()
1949 SequenceI sq = new Sequence("test", "-ABC---DE-F--");
1950 assertEquals("test", sq.getName());
1951 assertEquals(1, sq.getStart());
1952 assertEquals(6, sq.getEnd());
1954 sq.setName("testing");
1955 assertEquals("testing", sq.getName());
1957 sq.setName("test/8-10");
1958 assertEquals("test", sq.getName());
1959 assertEquals(8, sq.getStart());
1960 assertEquals(13, sq.getEnd()); // note end is recomputed
1962 sq.setName("testing/7-99");
1963 assertEquals("testing", sq.getName());
1964 assertEquals(7, sq.getStart());
1965 assertEquals(99, sq.getEnd()); // end may be beyond physical end
1968 assertEquals("", sq.getName());
1969 assertEquals(2, sq.getStart());
1970 assertEquals(7, sq.getEnd());
1972 sq.setName("test/"); // invalid
1973 assertEquals("test/", sq.getName());
1974 assertEquals(2, sq.getStart());
1975 assertEquals(7, sq.getEnd());
1977 sq.setName("test/6-13/7-99");
1978 assertEquals("test/6-13", sq.getName());
1979 assertEquals(7, sq.getStart());
1980 assertEquals(99, sq.getEnd());
1982 sq.setName("test/0-5"); // 0 is invalid - ignored
1983 assertEquals("test/0-5", sq.getName());
1984 assertEquals(7, sq.getStart());
1985 assertEquals(99, sq.getEnd());
1987 sq.setName("test/a-5"); // a is invalid - ignored
1988 assertEquals("test/a-5", sq.getName());
1989 assertEquals(7, sq.getStart());
1990 assertEquals(99, sq.getEnd());
1992 sq.setName("test/6-5"); // start > end is invalid - ignored
1993 assertEquals("test/6-5", sq.getName());
1994 assertEquals(7, sq.getStart());
1995 assertEquals(99, sq.getEnd());
1997 sq.setName("test/5"); // invalid - ignored
1998 assertEquals("test/5", sq.getName());
1999 assertEquals(7, sq.getStart());
2000 assertEquals(99, sq.getEnd());
2002 sq.setName("test/-5"); // invalid - ignored
2003 assertEquals("test/-5", sq.getName());
2004 assertEquals(7, sq.getStart());
2005 assertEquals(99, sq.getEnd());
2007 sq.setName("test/5-"); // invalid - ignored
2008 assertEquals("test/5-", sq.getName());
2009 assertEquals(7, sq.getStart());
2010 assertEquals(99, sq.getEnd());
2012 sq.setName("test/5-6-7"); // invalid - ignored
2013 assertEquals("test/5-6-7", sq.getName());
2014 assertEquals(7, sq.getStart());
2015 assertEquals(99, sq.getEnd());
2017 sq.setName(null); // invalid, gets converted to space
2018 assertEquals("", sq.getName());
2019 assertEquals(7, sq.getStart());
2020 assertEquals(99, sq.getEnd());
2023 @Test(groups = { "Functional" })
2024 public void testCheckValidRange()
2026 Sequence sq = new Sequence("test/7-12", "-ABC---DE-F--");
2027 assertEquals(7, sq.getStart());
2028 assertEquals(12, sq.getEnd());
2031 * checkValidRange ensures end is at least the last residue position
2033 PA.setValue(sq, "end", 2);
2034 sq.checkValidRange();
2035 assertEquals(12, sq.getEnd());
2038 * end may be beyond the last residue position
2040 PA.setValue(sq, "end", 22);
2041 sq.checkValidRange();
2042 assertEquals(22, sq.getEnd());
2045 @Test(groups = { "Functional" })
2046 public void testDeleteChars_withGaps()
2051 SequenceI sq = new Sequence("test/8-10", "A-B-C");
2052 sq.createDatasetSequence();
2053 assertEquals("ABC", sq.getDatasetSequence().getSequenceAsString());
2054 sq.deleteChars(1, 2); // delete first gap
2055 assertEquals("AB-C", sq.getSequenceAsString());
2056 assertEquals(8, sq.getStart());
2057 assertEquals(10, sq.getEnd());
2058 assertEquals("ABC", sq.getDatasetSequence().getSequenceAsString());
2061 * delete gaps and residues at start (no new dataset sequence)
2063 sq = new Sequence("test/8-10", "A-B-C");
2064 sq.createDatasetSequence();
2065 sq.deleteChars(0, 3); // delete A-B
2066 assertEquals("-C", sq.getSequenceAsString());
2067 assertEquals(10, sq.getStart());
2068 assertEquals(10, sq.getEnd());
2069 assertEquals("ABC", sq.getDatasetSequence().getSequenceAsString());
2072 * delete gaps and residues at end (no new dataset sequence)
2074 sq = new Sequence("test/8-10", "A-B-C");
2075 sq.createDatasetSequence();
2076 sq.deleteChars(2, 5); // delete B-C
2077 assertEquals("A-", sq.getSequenceAsString());
2078 assertEquals(8, sq.getStart());
2079 assertEquals(8, sq.getEnd());
2080 assertEquals("ABC", sq.getDatasetSequence().getSequenceAsString());
2083 * delete gaps and residues internally (new dataset sequence)
2084 * first delete from gap to residue
2086 sq = new Sequence("test/8-10", "A-B-C");
2087 sq.createDatasetSequence();
2088 sq.deleteChars(1, 3); // delete -B
2089 assertEquals("A-C", sq.getSequenceAsString());
2090 assertEquals(8, sq.getStart());
2091 assertEquals(9, sq.getEnd());
2092 assertEquals("AC", sq.getDatasetSequence().getSequenceAsString());
2093 assertEquals(8, sq.getDatasetSequence().getStart());
2094 assertEquals(9, sq.getDatasetSequence().getEnd());
2097 * internal delete from gap to gap
2099 sq = new Sequence("test/8-10", "A-B-C");
2100 sq.createDatasetSequence();
2101 sq.deleteChars(1, 4); // delete -B-
2102 assertEquals("AC", sq.getSequenceAsString());
2103 assertEquals(8, sq.getStart());
2104 assertEquals(9, sq.getEnd());
2105 assertEquals("AC", sq.getDatasetSequence().getSequenceAsString());
2106 assertEquals(8, sq.getDatasetSequence().getStart());
2107 assertEquals(9, sq.getDatasetSequence().getEnd());
2110 * internal delete from residue to residue
2112 sq = new Sequence("test/8-10", "A-B-C");
2113 sq.createDatasetSequence();
2114 sq.deleteChars(2, 3); // delete B
2115 assertEquals("A--C", sq.getSequenceAsString());
2116 assertEquals(8, sq.getStart());
2117 assertEquals(9, sq.getEnd());
2118 assertEquals("AC", sq.getDatasetSequence().getSequenceAsString());
2119 assertEquals(8, sq.getDatasetSequence().getStart());
2120 assertEquals(9, sq.getDatasetSequence().getEnd());
2124 * Test the code used to locate the reference sequence ruler origin
2126 @Test(groups = { "Functional" })
2127 public void testLocateVisibleStartofSequence()
2129 // create random alignment
2130 AlignmentGenerator gen = new AlignmentGenerator(false);
2131 AlignmentI al = gen.generate(50, 20, 123, 5, 5);
2133 HiddenColumns cs = al.getHiddenColumns();
2134 ColumnSelection colsel = new ColumnSelection();
2136 SequenceI seq = new Sequence("RefSeq", "-A-SD-ASD--E---");
2137 assertEquals(2, seq.findIndex(seq.getStart()));
2139 // no hidden columns
2140 assertEquals(seq.findIndex(seq.getStart()) - 1,
2141 seq.firstResidueOutsideIterator(cs.iterator()));
2143 // hidden column on gap after end of sequence - should not affect bounds
2144 colsel.hideSelectedColumns(13, al.getHiddenColumns());
2145 assertEquals(seq.findIndex(seq.getStart()) - 1,
2146 seq.firstResidueOutsideIterator(cs.iterator()));
2148 cs.revealAllHiddenColumns(colsel);
2149 // hidden column on gap before beginning of sequence - should vis bounds by
2151 colsel.hideSelectedColumns(0, al.getHiddenColumns());
2152 assertEquals(seq.findIndex(seq.getStart()) - 2,
2153 cs.absoluteToVisibleColumn(
2154 seq.firstResidueOutsideIterator(cs.iterator())));
2156 cs.revealAllHiddenColumns(colsel);
2157 // hide columns around most of sequence - leave one residue remaining
2158 cs.hideColumns(1, 3);
2159 cs.hideColumns(6, 11);
2161 Iterator<int[]> it = cs.getVisContigsIterator(0, 6, false);
2163 assertEquals("-D", seq.getSequenceStringFromIterator(it));
2164 // cs.getVisibleSequenceStrings(0, 5, new SequenceI[]
2167 assertEquals(4, seq.firstResidueOutsideIterator(cs.iterator()));
2168 cs.revealAllHiddenColumns(colsel);
2170 // hide whole sequence - should just get location of hidden region
2171 // containing sequence
2172 cs.hideColumns(1, 11);
2173 assertEquals(0, seq.firstResidueOutsideIterator(cs.iterator()));
2175 cs.revealAllHiddenColumns(colsel);
2176 cs.hideColumns(0, 15);
2177 assertEquals(0, seq.firstResidueOutsideIterator(cs.iterator()));
2179 SequenceI seq2 = new Sequence("RefSeq2", "-------A-SD-ASD--E---");
2181 cs.revealAllHiddenColumns(colsel);
2182 cs.hideColumns(7, 17);
2183 assertEquals(0, seq2.firstResidueOutsideIterator(cs.iterator()));
2185 cs.revealAllHiddenColumns(colsel);
2186 cs.hideColumns(3, 17);
2187 assertEquals(0, seq2.firstResidueOutsideIterator(cs.iterator()));
2189 cs.revealAllHiddenColumns(colsel);
2190 cs.hideColumns(3, 19);
2191 assertEquals(0, seq2.firstResidueOutsideIterator(cs.iterator()));
2193 cs.revealAllHiddenColumns(colsel);
2194 cs.hideColumns(0, 0);
2195 assertEquals(1, seq.firstResidueOutsideIterator(cs.iterator()));
2197 cs.revealAllHiddenColumns(colsel);
2198 cs.hideColumns(0, 1);
2199 assertEquals(3, seq.firstResidueOutsideIterator(cs.iterator()));
2201 cs.revealAllHiddenColumns(colsel);
2202 cs.hideColumns(0, 2);
2203 assertEquals(3, seq.firstResidueOutsideIterator(cs.iterator()));
2205 cs.revealAllHiddenColumns(colsel);
2206 cs.hideColumns(1, 1);
2207 assertEquals(3, seq.firstResidueOutsideIterator(cs.iterator()));
2209 cs.revealAllHiddenColumns(colsel);
2210 cs.hideColumns(1, 2);
2211 assertEquals(3, seq.firstResidueOutsideIterator(cs.iterator()));
2213 cs.revealAllHiddenColumns(colsel);
2214 cs.hideColumns(1, 3);
2215 assertEquals(4, seq.firstResidueOutsideIterator(cs.iterator()));
2217 cs.revealAllHiddenColumns(colsel);
2218 cs.hideColumns(0, 2);
2219 cs.hideColumns(5, 6);
2220 assertEquals(3, seq.firstResidueOutsideIterator(cs.iterator()));
2222 cs.revealAllHiddenColumns(colsel);
2223 cs.hideColumns(0, 2);
2224 cs.hideColumns(5, 6);
2225 cs.hideColumns(9, 10);
2226 assertEquals(3, seq.firstResidueOutsideIterator(cs.iterator()));
2228 cs.revealAllHiddenColumns(colsel);
2229 cs.hideColumns(0, 2);
2230 cs.hideColumns(7, 11);
2231 assertEquals(3, seq.firstResidueOutsideIterator(cs.iterator()));
2233 cs.revealAllHiddenColumns(colsel);
2234 cs.hideColumns(2, 4);
2235 cs.hideColumns(7, 11);
2236 assertEquals(1, seq.firstResidueOutsideIterator(cs.iterator()));
2238 cs.revealAllHiddenColumns(colsel);
2239 cs.hideColumns(2, 4);
2240 cs.hideColumns(7, 12);
2241 assertEquals(1, seq.firstResidueOutsideIterator(cs.iterator()));
2243 cs.revealAllHiddenColumns(colsel);
2244 cs.hideColumns(1, 11);
2245 assertEquals(0, seq.firstResidueOutsideIterator(cs.iterator()));
2247 cs.revealAllHiddenColumns(colsel);
2248 cs.hideColumns(0, 12);
2249 assertEquals(0, seq.firstResidueOutsideIterator(cs.iterator()));
2251 cs.revealAllHiddenColumns(colsel);
2252 cs.hideColumns(0, 4);
2253 cs.hideColumns(6, 12);
2254 assertEquals(0, seq.firstResidueOutsideIterator(cs.iterator()));
2256 cs.revealAllHiddenColumns(colsel);
2257 cs.hideColumns(0, 1);
2258 cs.hideColumns(3, 12);
2259 assertEquals(0, seq.firstResidueOutsideIterator(cs.iterator()));
2261 cs.revealAllHiddenColumns(colsel);
2262 cs.hideColumns(3, 14);
2263 cs.hideColumns(17, 19);
2264 assertEquals(0, seq2.firstResidueOutsideIterator(cs.iterator()));
2266 cs.revealAllHiddenColumns(colsel);
2267 cs.hideColumns(3, 7);
2268 cs.hideColumns(9, 14);
2269 cs.hideColumns(17, 19);
2270 assertEquals(0, seq2.firstResidueOutsideIterator(cs.iterator()));
2272 cs.revealAllHiddenColumns(colsel);
2273 cs.hideColumns(0, 1);
2274 cs.hideColumns(3, 4);
2275 cs.hideColumns(6, 8);
2276 cs.hideColumns(10, 12);
2277 assertEquals(0, seq.firstResidueOutsideIterator(cs.iterator()));
2281 @Test(groups = { "Functional" })
2282 public void testTransferAnnotation()
2284 Sequence origSeq = new Sequence("MYSEQ", "THISISASEQ");
2285 Sequence toSeq = new Sequence("MYSEQ", "THISISASEQ");
2286 origSeq.addDBRef(new DBRefEntry("UNIPROT", "0", "Q12345", null, true));
2287 toSeq.transferAnnotation(origSeq, null);
2288 assertTrue(toSeq.getDBRefs().size() == 1);
2290 assertTrue(toSeq.getDBRefs().get(0).isCanonical());
2292 // check for promotion of non-canonical
2293 // to canonical (e.g. fetch-db-refs on a jalview project pre 2.11.2)
2294 toSeq.setDBRefs(null);
2295 toSeq.addDBRef(new DBRefEntry("UNIPROT", "0", "Q12345", null, false));
2296 toSeq.transferAnnotation(origSeq, null);
2297 assertTrue(toSeq.getDBRefs().size() == 1);
2299 assertTrue("Promotion of non-canonical DBRefEntry failed",
2300 toSeq.getDBRefs().get(0).isCanonical());