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;
31 import jalview.commands.EditCommand;
32 import jalview.commands.EditCommand.Action;
33 import jalview.datamodel.PDBEntry.Type;
34 import jalview.gui.JvOptionPane;
35 import jalview.util.MapList;
38 import java.util.ArrayList;
39 import java.util.Arrays;
40 import java.util.BitSet;
41 import java.util.List;
42 import java.util.Vector;
44 import junit.extensions.PA;
46 import org.testng.Assert;
47 import org.testng.annotations.BeforeClass;
48 import org.testng.annotations.BeforeMethod;
49 import org.testng.annotations.Test;
51 public class SequenceTest
54 @BeforeClass(alwaysRun = true)
55 public void setUpJvOptionPane()
57 JvOptionPane.setInteractiveMode(false);
58 JvOptionPane.setMockResponse(JvOptionPane.CANCEL_OPTION);
63 @BeforeMethod(alwaysRun = true)
66 seq = new Sequence("FER1", "AKPNGVL");
69 @Test(groups = { "Functional" })
70 public void testInsertGapsAndGapmaps()
72 SequenceI aseq = seq.deriveSequence();
73 aseq.insertCharAt(2, 3, '-');
74 aseq.insertCharAt(6, 3, '-');
75 assertEquals("Gap insertions not correct", "AK---P---NGVL",
76 aseq.getSequenceAsString());
77 List<int[]> gapInt = aseq.getInsertions();
78 assertEquals("Gap interval 1 start wrong", 2, gapInt.get(0)[0]);
79 assertEquals("Gap interval 1 end wrong", 4, gapInt.get(0)[1]);
80 assertEquals("Gap interval 2 start wrong", 6, gapInt.get(1)[0]);
81 assertEquals("Gap interval 2 end wrong", 8, gapInt.get(1)[1]);
83 BitSet gapfield = aseq.getInsertionsAsBits();
84 BitSet expectedgaps = new BitSet();
85 expectedgaps.set(2, 5);
86 expectedgaps.set(6, 9);
88 assertEquals(6, expectedgaps.cardinality());
90 assertEquals("getInsertionsAsBits didn't mark expected number of gaps",
91 6, gapfield.cardinality());
93 assertEquals("getInsertionsAsBits not correct.", expectedgaps, gapfield);
96 @Test(groups = ("Functional"))
97 public void testIsProtein()
100 assertTrue(new Sequence("prot", "ASDFASDFASDF").isProtein());
102 assertFalse(new Sequence("prot", "ACGTACGTACGT").isProtein());
104 SequenceI sq = new Sequence("prot", "ACGUACGUACGU");
105 assertFalse(sq.isProtein());
106 // change sequence, should trigger an update of cached result
107 sq.setSequence("ASDFASDFADSF");
108 assertTrue(sq.isProtein());
110 * in situ change of sequence doesn't change hashcode :-O
111 * (sequence should not expose internal implementation)
113 for (int i = 0; i < sq.getSequence().length; i++)
115 sq.getSequence()[i] = "acgtu".charAt(i % 5);
117 assertTrue(sq.isProtein()); // but it isn't
120 @Test(groups = { "Functional" })
121 public void testGetAnnotation()
123 // initial state returns null not an empty array
124 assertNull(seq.getAnnotation());
125 AlignmentAnnotation ann = addAnnotation("label1", "desc1", "calcId1",
127 AlignmentAnnotation[] anns = seq.getAnnotation();
128 assertEquals(1, anns.length);
129 assertSame(ann, anns[0]);
131 // removing all annotations reverts array to null
132 seq.removeAlignmentAnnotation(ann);
133 assertNull(seq.getAnnotation());
136 @Test(groups = { "Functional" })
137 public void testGetAnnotation_forLabel()
139 AlignmentAnnotation ann1 = addAnnotation("label1", "desc1", "calcId1",
141 addAnnotation("label2", "desc2", "calcId2", 1f);
142 AlignmentAnnotation ann3 = addAnnotation("label1", "desc3", "calcId3",
144 AlignmentAnnotation[] anns = seq.getAnnotation("label1");
145 assertEquals(2, anns.length);
146 assertSame(ann1, anns[0]);
147 assertSame(ann3, anns[1]);
150 private AlignmentAnnotation addAnnotation(String label,
151 String description, String calcId, float value)
153 final AlignmentAnnotation annotation = new AlignmentAnnotation(label,
155 annotation.setCalcId(calcId);
156 seq.addAlignmentAnnotation(annotation);
160 @Test(groups = { "Functional" })
161 public void testGetAlignmentAnnotations_forCalcIdAndLabel()
163 addAnnotation("label1", "desc1", "calcId1", 1f);
164 AlignmentAnnotation ann2 = addAnnotation("label2", "desc2", "calcId2",
166 addAnnotation("label2", "desc3", "calcId3", 1f);
167 AlignmentAnnotation ann4 = addAnnotation("label2", "desc3", "calcId2",
169 addAnnotation("label5", "desc3", null, 1f);
170 addAnnotation(null, "desc3", "calcId3", 1f);
172 List<AlignmentAnnotation> anns = seq.getAlignmentAnnotations("calcId2",
174 assertEquals(2, anns.size());
175 assertSame(ann2, anns.get(0));
176 assertSame(ann4, anns.get(1));
178 assertTrue(seq.getAlignmentAnnotations("calcId2", "label3").isEmpty());
179 assertTrue(seq.getAlignmentAnnotations("calcId3", "label5").isEmpty());
180 assertTrue(seq.getAlignmentAnnotations("calcId2", null).isEmpty());
181 assertTrue(seq.getAlignmentAnnotations(null, "label3").isEmpty());
182 assertTrue(seq.getAlignmentAnnotations(null, null).isEmpty());
186 * Tests for addAlignmentAnnotation. Note this method has the side-effect of
187 * setting the sequenceRef on the annotation. Adding the same annotation twice
190 @Test(groups = { "Functional" })
191 public void testAddAlignmentAnnotation()
193 assertNull(seq.getAnnotation());
194 final AlignmentAnnotation annotation = new AlignmentAnnotation("a",
196 assertNull(annotation.sequenceRef);
197 seq.addAlignmentAnnotation(annotation);
198 assertSame(seq, annotation.sequenceRef);
199 AlignmentAnnotation[] anns = seq.getAnnotation();
200 assertEquals(1, anns.length);
201 assertSame(annotation, anns[0]);
203 // re-adding does nothing
204 seq.addAlignmentAnnotation(annotation);
205 anns = seq.getAnnotation();
206 assertEquals(1, anns.length);
207 assertSame(annotation, anns[0]);
209 // an identical but different annotation can be added
210 final AlignmentAnnotation annotation2 = new AlignmentAnnotation("a",
212 seq.addAlignmentAnnotation(annotation2);
213 anns = seq.getAnnotation();
214 assertEquals(2, anns.length);
215 assertSame(annotation, anns[0]);
216 assertSame(annotation2, anns[1]);
219 @Test(groups = { "Functional" })
220 public void testGetStartGetEnd()
222 SequenceI sq = new Sequence("test", "ABCDEF");
223 assertEquals(1, sq.getStart());
224 assertEquals(6, sq.getEnd());
226 sq = new Sequence("test", "--AB-C-DEF--");
227 assertEquals(1, sq.getStart());
228 assertEquals(6, sq.getEnd());
230 sq = new Sequence("test", "----");
231 assertEquals(1, sq.getStart());
232 assertEquals(0, sq.getEnd()); // ??
236 * Tests for the method that returns an alignment column position (base 1) for
237 * a given sequence position (base 1).
239 @Test(groups = { "Functional" })
240 public void testFindIndex()
243 * call sequenceChanged() after each test to invalidate any cursor,
244 * forcing the 1-arg findIndex to be executed
246 SequenceI sq = new Sequence("test", "ABCDEF");
247 assertEquals(0, sq.findIndex(0));
248 sq.sequenceChanged();
249 assertEquals(1, sq.findIndex(1));
250 sq.sequenceChanged();
251 assertEquals(5, sq.findIndex(5));
252 sq.sequenceChanged();
253 assertEquals(6, sq.findIndex(6));
254 sq.sequenceChanged();
255 assertEquals(6, sq.findIndex(9));
257 sq = new Sequence("test/8-13", "-A--B-C-D-E-F--");
258 assertEquals(2, sq.findIndex(8));
259 sq.sequenceChanged();
260 assertEquals(5, sq.findIndex(9));
261 sq.sequenceChanged();
262 assertEquals(7, sq.findIndex(10));
264 // before start returns 0
265 sq.sequenceChanged();
266 assertEquals(0, sq.findIndex(0));
267 sq.sequenceChanged();
268 assertEquals(0, sq.findIndex(-1));
270 // beyond end returns last residue column
271 sq.sequenceChanged();
272 assertEquals(13, sq.findIndex(99));
276 * Tests for the method that returns a dataset sequence position (start..) for
277 * an aligned column position (base 0).
279 @Test(groups = { "Functional" })
280 public void testFindPosition()
283 * call sequenceChanged() after each test to invalidate any cursor,
284 * forcing the 1-arg findPosition to be executed
286 SequenceI sq = new Sequence("test/8-13", "ABCDEF");
287 assertEquals(8, sq.findPosition(0));
288 // Sequence should now hold a cursor at [8, 0]
289 SequenceCursor cursor = (SequenceCursor) PA.getValue(sq, "cursor");
290 int token = (int) PA.getValue(sq, "changeCount");
291 assertEquals(new SequenceCursor(sq, 8, 1, token), cursor);
293 sq.sequenceChanged();
296 * find F13 at column offset 5, cursor should update to [13, 6]
298 assertEquals(13, sq.findPosition(5));
299 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
300 assertEquals(++token, (int) PA.getValue(sq, "changeCount"));
301 assertEquals(new SequenceCursor(sq, 13, 6, token), cursor);
303 // assertEquals(-1, seq.findPosition(6)); // fails
305 sq = new Sequence("test/8-11", "AB-C-D--");
306 token = (int) PA.getValue(sq, "changeCount"); // 0
307 assertEquals(8, sq.findPosition(0));
308 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
309 assertEquals(new SequenceCursor(sq, 8, 1, token), cursor);
311 sq.sequenceChanged();
312 assertEquals(9, sq.findPosition(1));
313 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
314 assertEquals(new SequenceCursor(sq, 9, 2, ++token), cursor);
316 sq.sequenceChanged();
317 // gap position 'finds' residue to the right (not the left as per javadoc)
318 // cursor is set to the last residue position found [B 2]
319 assertEquals(10, sq.findPosition(2));
320 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
321 assertEquals(new SequenceCursor(sq, 9, 2, ++token), cursor);
323 sq.sequenceChanged();
324 assertEquals(10, sq.findPosition(3));
325 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
326 assertEquals(new SequenceCursor(sq, 10, 4, ++token), cursor);
328 sq.sequenceChanged();
329 // column[4] is the gap after C - returns D11
330 // cursor is set to [C 4]
331 assertEquals(11, sq.findPosition(4));
332 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
333 assertEquals(new SequenceCursor(sq, 10, 4, ++token), cursor);
335 sq.sequenceChanged();
336 assertEquals(11, sq.findPosition(5)); // D
337 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
338 assertEquals(new SequenceCursor(sq, 11, 6, ++token), cursor);
340 sq.sequenceChanged();
341 // returns 1 more than sequence length if off the end ?!?
342 assertEquals(12, sq.findPosition(6));
344 sq.sequenceChanged();
345 assertEquals(12, sq.findPosition(7));
347 sq = new Sequence("test/8-13", "--AB-C-DEF--");
348 assertEquals(8, sq.findPosition(0));
350 sq.sequenceChanged();
351 assertEquals(8, sq.findPosition(1));
353 sq.sequenceChanged();
354 assertEquals(8, sq.findPosition(2));
356 sq.sequenceChanged();
357 assertEquals(9, sq.findPosition(3));
359 sq.sequenceChanged();
360 assertEquals(10, sq.findPosition(4));
362 sq.sequenceChanged();
363 assertEquals(10, sq.findPosition(5));
365 sq.sequenceChanged();
366 assertEquals(11, sq.findPosition(6));
368 sq.sequenceChanged();
369 assertEquals(11, sq.findPosition(7));
371 sq.sequenceChanged();
372 assertEquals(12, sq.findPosition(8));
374 sq.sequenceChanged();
375 assertEquals(13, sq.findPosition(9));
377 sq.sequenceChanged();
378 assertEquals(14, sq.findPosition(10));
381 * findPosition for column beyond sequence length
382 * returns 1 more than last residue position
384 sq.sequenceChanged();
385 assertEquals(14, sq.findPosition(11));
386 sq.sequenceChanged();
387 assertEquals(14, sq.findPosition(99));
390 @Test(groups = { "Functional" })
391 public void testDeleteChars()
396 SequenceI sq = new Sequence("test", "ABCDEF");
397 assertNull(PA.getValue(sq, "datasetSequence"));
398 assertEquals(1, sq.getStart());
399 assertEquals(6, sq.getEnd());
400 sq.deleteChars(2, 3);
401 assertEquals("ABDEF", sq.getSequenceAsString());
402 assertEquals(1, sq.getStart());
403 assertEquals(5, sq.getEnd());
404 assertNull(PA.getValue(sq, "datasetSequence"));
409 sq = new Sequence("test", "ABCDEF");
410 sq.deleteChars(0, 2);
411 assertEquals("CDEF", sq.getSequenceAsString());
412 assertEquals(3, sq.getStart());
413 assertEquals(6, sq.getEnd());
414 assertNull(PA.getValue(sq, "datasetSequence"));
419 sq = new Sequence("test", "ABCDEF");
420 sq.deleteChars(4, 6);
421 assertEquals("ABCD", sq.getSequenceAsString());
422 assertEquals(1, sq.getStart());
423 assertEquals(4, sq.getEnd());
424 assertNull(PA.getValue(sq, "datasetSequence"));
427 @Test(groups = { "Functional" })
428 public void testDeleteChars_withDbRefsAndFeatures()
431 * internal delete - new dataset sequence created
432 * gets a copy of any dbrefs
434 SequenceI sq = new Sequence("test", "ABCDEF");
435 sq.createDatasetSequence();
436 DBRefEntry dbr1 = new DBRefEntry("Uniprot", "0", "a123");
438 Object ds = PA.getValue(sq, "datasetSequence");
440 assertEquals(1, sq.getStart());
441 assertEquals(6, sq.getEnd());
442 sq.deleteChars(2, 3);
443 assertEquals("ABDEF", sq.getSequenceAsString());
444 assertEquals(1, sq.getStart());
445 assertEquals(5, sq.getEnd());
446 Object newDs = PA.getValue(sq, "datasetSequence");
447 assertNotNull(newDs);
448 assertNotSame(ds, newDs);
449 assertNotNull(sq.getDBRefs());
450 assertEquals(1, sq.getDBRefs().length);
451 assertNotSame(dbr1, sq.getDBRefs()[0]);
452 assertEquals(dbr1, sq.getDBRefs()[0]);
455 * internal delete with sequence features
456 * (failure case for JAL-2541)
458 sq = new Sequence("test", "ABCDEF");
459 sq.createDatasetSequence();
460 SequenceFeature sf1 = new SequenceFeature("Cath", "desc", 2, 4, 2f,
462 sq.addSequenceFeature(sf1);
463 ds = PA.getValue(sq, "datasetSequence");
465 assertEquals(1, sq.getStart());
466 assertEquals(6, sq.getEnd());
467 sq.deleteChars(2, 4);
468 assertEquals("ABEF", sq.getSequenceAsString());
469 assertEquals(1, sq.getStart());
470 assertEquals(4, sq.getEnd());
471 newDs = PA.getValue(sq, "datasetSequence");
472 assertNotNull(newDs);
473 assertNotSame(ds, newDs);
474 List<SequenceFeature> sfs = sq.getSequenceFeatures();
475 assertEquals(1, sfs.size());
476 assertNotSame(sf1, sfs.get(0));
477 assertEquals(sf1, sfs.get(0));
480 * delete at start - no new dataset sequence created
481 * any sequence features remain as before
483 sq = new Sequence("test", "ABCDEF");
484 sq.createDatasetSequence();
485 ds = PA.getValue(sq, "datasetSequence");
486 sf1 = new SequenceFeature("Cath", "desc", 2, 4, 2f, "CathGroup");
487 sq.addSequenceFeature(sf1);
488 sq.deleteChars(0, 2);
489 assertEquals("CDEF", sq.getSequenceAsString());
490 assertEquals(3, sq.getStart());
491 assertEquals(6, sq.getEnd());
492 assertSame(ds, PA.getValue(sq, "datasetSequence"));
493 sfs = sq.getSequenceFeatures();
495 assertEquals(1, sfs.size());
496 assertSame(sf1, sfs.get(0));
499 * delete at end - no new dataset sequence created
500 * any dbrefs remain as before
502 sq = new Sequence("test", "ABCDEF");
503 sq.createDatasetSequence();
504 ds = PA.getValue(sq, "datasetSequence");
505 dbr1 = new DBRefEntry("Uniprot", "0", "a123");
507 sq.deleteChars(4, 6);
508 assertEquals("ABCD", sq.getSequenceAsString());
509 assertEquals(1, sq.getStart());
510 assertEquals(4, sq.getEnd());
511 assertSame(ds, PA.getValue(sq, "datasetSequence"));
512 assertNotNull(sq.getDBRefs());
513 assertEquals(1, sq.getDBRefs().length);
514 assertSame(dbr1, sq.getDBRefs()[0]);
517 @Test(groups = { "Functional" })
518 public void testInsertCharAt()
520 // non-static methods:
521 SequenceI sq = new Sequence("test", "ABCDEF");
522 sq.insertCharAt(0, 'z');
523 assertEquals("zABCDEF", sq.getSequenceAsString());
524 sq.insertCharAt(2, 2, 'x');
525 assertEquals("zAxxBCDEF", sq.getSequenceAsString());
527 // for static method see StringUtilsTest
531 * Test the method that returns an array of aligned sequence positions where
532 * the array index is the data sequence position (both base 0).
534 @Test(groups = { "Functional" })
535 public void testGapMap()
537 SequenceI sq = new Sequence("test", "-A--B-CD-E--F-");
538 sq.createDatasetSequence();
539 assertEquals("[1, 4, 6, 7, 9, 12]", Arrays.toString(sq.gapMap()));
543 * Test the method that gets sequence features, either from the sequence or
546 @Test(groups = { "Functional" })
547 public void testGetSequenceFeatures()
549 SequenceI sq = new Sequence("test", "GATCAT");
550 sq.createDatasetSequence();
552 assertTrue(sq.getSequenceFeatures().isEmpty());
555 * SequenceFeature on sequence
557 SequenceFeature sf = new SequenceFeature("Cath", "desc", 2, 4, 2f, null);
558 sq.addSequenceFeature(sf);
559 List<SequenceFeature> sfs = sq.getSequenceFeatures();
560 assertEquals(1, sfs.size());
561 assertSame(sf, sfs.get(0));
564 * SequenceFeature on sequence and dataset sequence; returns that on
567 * Note JAL-2046: spurious: we have no use case for this at the moment.
568 * This test also buggy - as sf2.equals(sf), no new feature is added
570 SequenceFeature sf2 = new SequenceFeature("Cath", "desc", 2, 4, 2f,
572 sq.getDatasetSequence().addSequenceFeature(sf2);
573 sfs = sq.getSequenceFeatures();
574 assertEquals(1, sfs.size());
575 assertSame(sf, sfs.get(0));
578 * SequenceFeature on dataset sequence only
579 * Note JAL-2046: spurious: we have no use case for setting a non-dataset sequence's feature array to null at the moment.
581 sq.setSequenceFeatures(null);
582 assertTrue(sq.getDatasetSequence().getSequenceFeatures().isEmpty());
585 * Corrupt case - no SequenceFeature, dataset's dataset is the original
586 * sequence. Test shows no infinite loop results.
588 sq.getDatasetSequence().setSequenceFeatures(null);
590 * is there a usecase for this ? setDatasetSequence should throw an error if
591 * this actually occurs.
595 sq.getDatasetSequence().setDatasetSequence(sq); // loop!
596 Assert.fail("Expected Error to be raised when calling setDatasetSequence with self reference");
597 } catch (IllegalArgumentException e)
599 // TODO Jalview error/exception class for raising implementation errors
600 assertTrue(e.getMessage().toLowerCase()
601 .contains("implementation error"));
603 assertTrue(sq.getSequenceFeatures().isEmpty());
607 * Test the method that returns an array, indexed by sequence position, whose
608 * entries are the residue positions at the sequence position (or to the right
611 @Test(groups = { "Functional" })
612 public void testFindPositionMap()
615 * Note: Javadoc for findPosition says it returns the residue position to
616 * the left of a gapped position; in fact it returns the position to the
617 * right. Also it returns a non-existent residue position for a gap beyond
620 Sequence sq = new Sequence("TestSeq", "AB.C-D E.");
621 int[] map = sq.findPositionMap();
622 assertEquals(Arrays.toString(new int[] { 1, 2, 3, 3, 4, 4, 5, 5, 6 }),
623 Arrays.toString(map));
627 * Test for getSubsequence
629 @Test(groups = { "Functional" })
630 public void testGetSubsequence()
632 SequenceI sq = new Sequence("TestSeq", "ABCDEFG");
633 sq.createDatasetSequence();
635 // positions are base 0, end position is exclusive
636 SequenceI subseq = sq.getSubSequence(2, 4);
638 assertEquals("CD", subseq.getSequenceAsString());
639 // start/end are base 1 positions
640 assertEquals(3, subseq.getStart());
641 assertEquals(4, subseq.getEnd());
642 // subsequence shares the full dataset sequence
643 assertSame(sq.getDatasetSequence(), subseq.getDatasetSequence());
647 * test createDatasetSequence behaves to doc
649 @Test(groups = { "Functional" })
650 public void testCreateDatasetSequence()
652 SequenceI sq = new Sequence("my", "ASDASD");
653 sq.addSequenceFeature(new SequenceFeature("type", "desc", 1, 10, 1f,
655 sq.addDBRef(new DBRefEntry("source", "version", "accession"));
656 assertNull(sq.getDatasetSequence());
657 assertNotNull(PA.getValue(sq, "sequenceFeatureStore"));
658 assertNotNull(PA.getValue(sq, "dbrefs"));
660 SequenceI rds = sq.createDatasetSequence();
662 assertNull(rds.getDatasetSequence());
663 assertSame(sq.getDatasetSequence(), rds);
665 // sequence features and dbrefs transferred to dataset sequence
666 assertNull(PA.getValue(sq, "sequenceFeatureStore"));
667 assertNull(PA.getValue(sq, "dbrefs"));
668 assertNotNull(PA.getValue(rds, "sequenceFeatureStore"));
669 assertNotNull(PA.getValue(rds, "dbrefs"));
673 * Test for deriveSequence applied to a sequence with a dataset
675 @Test(groups = { "Functional" })
676 public void testDeriveSequence_existingDataset()
678 Sequence sq = new Sequence("Seq1", "CD");
679 sq.setDatasetSequence(new Sequence("Seq1", "ABCDEF"));
680 sq.getDatasetSequence().addSequenceFeature(
681 new SequenceFeature("", "", 1, 2, 0f, null));
685 sq.setDescription("Test sequence description..");
686 sq.setVamsasId("TestVamsasId");
687 sq.addDBRef(new DBRefEntry("PDB", "version0", "1TST"));
689 sq.addDBRef(new DBRefEntry("PDB", "version1", "1PDB"));
690 sq.addDBRef(new DBRefEntry("PDB", "version2", "2PDB"));
691 sq.addDBRef(new DBRefEntry("PDB", "version3", "3PDB"));
692 sq.addDBRef(new DBRefEntry("PDB", "version4", "4PDB"));
694 sq.addPDBId(new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1"));
695 sq.addPDBId(new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1"));
696 sq.addPDBId(new PDBEntry("2PDB", "A", Type.MMCIF, "filePath/test2"));
697 sq.addPDBId(new PDBEntry("2PDB", "B", Type.MMCIF, "filePath/test2"));
699 // these are the same as ones already added
700 DBRefEntry pdb1pdb = new DBRefEntry("PDB", "version1", "1PDB");
701 DBRefEntry pdb2pdb = new DBRefEntry("PDB", "version2", "2PDB");
703 List<DBRefEntry> primRefs = Arrays.asList(new DBRefEntry[] { pdb1pdb,
706 sq.getDatasetSequence().addDBRef(pdb1pdb); // should do nothing
707 sq.getDatasetSequence().addDBRef(pdb2pdb); // should do nothing
708 sq.getDatasetSequence().addDBRef(
709 new DBRefEntry("PDB", "version3", "3PDB")); // should do nothing
710 sq.getDatasetSequence().addDBRef(
711 new DBRefEntry("PDB", "version4", "4PDB")); // should do nothing
713 PDBEntry pdbe1a = new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1");
714 PDBEntry pdbe1b = new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1");
715 PDBEntry pdbe2a = new PDBEntry("2PDB", "A", Type.MMCIF,
717 PDBEntry pdbe2b = new PDBEntry("2PDB", "B", Type.MMCIF,
719 sq.getDatasetSequence().addPDBId(pdbe1a);
720 sq.getDatasetSequence().addPDBId(pdbe1b);
721 sq.getDatasetSequence().addPDBId(pdbe2a);
722 sq.getDatasetSequence().addPDBId(pdbe2b);
725 * test we added pdb entries to the dataset sequence
727 Assert.assertEquals(sq.getDatasetSequence().getAllPDBEntries(), Arrays
728 .asList(new PDBEntry[] { pdbe1a, pdbe1b, pdbe2a, pdbe2b }),
729 "PDB Entries were not found on dataset sequence.");
732 * we should recover a pdb entry that is on the dataset sequence via PDBEntry
734 Assert.assertEquals(pdbe1a,
735 sq.getDatasetSequence().getPDBEntry("1PDB"),
736 "PDB Entry '1PDB' not found on dataset sequence via getPDBEntry.");
737 ArrayList<Annotation> annotsList = new ArrayList<Annotation>();
738 System.out.println(">>>>>> " + sq.getSequenceAsString().length());
739 annotsList.add(new Annotation("A", "A", 'X', 0.1f));
740 annotsList.add(new Annotation("A", "A", 'X', 0.1f));
741 Annotation[] annots = annotsList.toArray(new Annotation[0]);
742 sq.addAlignmentAnnotation(new AlignmentAnnotation("Test annot",
743 "Test annot description", annots));
744 sq.getDatasetSequence().addAlignmentAnnotation(
745 new AlignmentAnnotation("Test annot", "Test annot description",
747 Assert.assertEquals(sq.getDescription(), "Test sequence description..");
748 Assert.assertEquals(sq.getDBRefs().length, 5); // DBRefs are on dataset
750 Assert.assertEquals(sq.getAllPDBEntries().size(), 4);
751 Assert.assertNotNull(sq.getAnnotation());
752 Assert.assertEquals(sq.getAnnotation()[0].annotations.length, 2);
753 Assert.assertEquals(sq.getDatasetSequence().getDBRefs().length, 5); // same
756 Assert.assertEquals(sq.getDatasetSequence().getAllPDBEntries().size(),
758 Assert.assertNotNull(sq.getDatasetSequence().getAnnotation());
760 Sequence derived = (Sequence) sq.deriveSequence();
762 Assert.assertEquals(derived.getDescription(),
763 "Test sequence description..");
764 Assert.assertEquals(derived.getDBRefs().length, 5); // come from dataset
765 Assert.assertEquals(derived.getAllPDBEntries().size(), 4);
766 Assert.assertNotNull(derived.getAnnotation());
767 Assert.assertEquals(derived.getAnnotation()[0].annotations.length, 2);
768 Assert.assertEquals(derived.getDatasetSequence().getDBRefs().length, 5);
769 Assert.assertEquals(derived.getDatasetSequence().getAllPDBEntries()
771 Assert.assertNotNull(derived.getDatasetSequence().getAnnotation());
773 assertEquals("CD", derived.getSequenceAsString());
774 assertSame(sq.getDatasetSequence(), derived.getDatasetSequence());
776 // derived sequence should access dataset sequence features
777 assertNotNull(sq.getSequenceFeatures());
778 assertEquals(sq.getSequenceFeatures(), derived.getSequenceFeatures());
781 * verify we have primary db refs *just* for PDB IDs with associated
785 assertEquals(primRefs, sq.getPrimaryDBRefs());
786 assertEquals(primRefs, sq.getDatasetSequence().getPrimaryDBRefs());
788 assertEquals(sq.getPrimaryDBRefs(), derived.getPrimaryDBRefs());
793 * Test for deriveSequence applied to an ungapped sequence with no dataset
795 @Test(groups = { "Functional" })
796 public void testDeriveSequence_noDatasetUngapped()
798 SequenceI sq = new Sequence("Seq1", "ABCDEF");
799 assertEquals(1, sq.getStart());
800 assertEquals(6, sq.getEnd());
801 SequenceI derived = sq.deriveSequence();
802 assertEquals("ABCDEF", derived.getSequenceAsString());
803 assertEquals("ABCDEF", derived.getDatasetSequence()
804 .getSequenceAsString());
808 * Test for deriveSequence applied to a gapped sequence with no dataset
810 @Test(groups = { "Functional" })
811 public void testDeriveSequence_noDatasetGapped()
813 SequenceI sq = new Sequence("Seq1", "AB-C.D EF");
814 assertEquals(1, sq.getStart());
815 assertEquals(6, sq.getEnd());
816 assertNull(sq.getDatasetSequence());
817 SequenceI derived = sq.deriveSequence();
818 assertEquals("AB-C.D EF", derived.getSequenceAsString());
819 assertEquals("ABCDEF", derived.getDatasetSequence()
820 .getSequenceAsString());
823 @Test(groups = { "Functional" })
824 public void testCopyConstructor_noDataset()
826 SequenceI seq1 = new Sequence("Seq1", "AB-C.D EF");
827 seq1.setDescription("description");
828 seq1.addAlignmentAnnotation(new AlignmentAnnotation("label", "desc",
830 seq1.addSequenceFeature(new SequenceFeature("type", "desc", 22, 33,
832 seq1.addPDBId(new PDBEntry("1A70", "B", Type.PDB, "File"));
833 seq1.addDBRef(new DBRefEntry("EMBL", "1.2", "AZ12345"));
835 SequenceI copy = new Sequence(seq1);
837 assertNull(copy.getDatasetSequence());
839 verifyCopiedSequence(seq1, copy);
841 // copy has a copy of the DBRefEntry
842 // this is murky - DBrefs are only copied for dataset sequences
843 // where the test for 'dataset sequence' is 'dataset is null'
844 // but that doesn't distinguish it from an aligned sequence
845 // which has not yet generated a dataset sequence
846 // NB getDBRef looks inside dataset sequence if not null
847 DBRefEntry[] dbrefs = copy.getDBRefs();
848 assertEquals(1, dbrefs.length);
849 assertFalse(dbrefs[0] == seq1.getDBRefs()[0]);
850 assertTrue(dbrefs[0].equals(seq1.getDBRefs()[0]));
853 @Test(groups = { "Functional" })
854 public void testCopyConstructor_withDataset()
856 SequenceI seq1 = new Sequence("Seq1", "AB-C.D EF");
857 seq1.createDatasetSequence();
858 seq1.setDescription("description");
859 seq1.addAlignmentAnnotation(new AlignmentAnnotation("label", "desc",
861 // JAL-2046 - what is the contract for using a derived sequence's
862 // addSequenceFeature ?
863 seq1.addSequenceFeature(new SequenceFeature("type", "desc", 22, 33,
865 seq1.addPDBId(new PDBEntry("1A70", "B", Type.PDB, "File"));
866 // here we add DBRef to the dataset sequence:
867 seq1.getDatasetSequence().addDBRef(
868 new DBRefEntry("EMBL", "1.2", "AZ12345"));
870 SequenceI copy = new Sequence(seq1);
872 assertNotNull(copy.getDatasetSequence());
873 assertSame(copy.getDatasetSequence(), seq1.getDatasetSequence());
875 verifyCopiedSequence(seq1, copy);
877 // getDBRef looks inside dataset sequence and this is shared,
878 // so holds the same dbref objects
879 DBRefEntry[] dbrefs = copy.getDBRefs();
880 assertEquals(1, dbrefs.length);
881 assertSame(dbrefs[0], seq1.getDBRefs()[0]);
885 * Helper to make assertions about a copied sequence
890 protected void verifyCopiedSequence(SequenceI seq1, SequenceI copy)
892 // verify basic properties:
893 assertEquals(copy.getName(), seq1.getName());
894 assertEquals(copy.getDescription(), seq1.getDescription());
895 assertEquals(copy.getStart(), seq1.getStart());
896 assertEquals(copy.getEnd(), seq1.getEnd());
897 assertEquals(copy.getSequenceAsString(), seq1.getSequenceAsString());
899 // copy has a copy of the annotation:
900 AlignmentAnnotation[] anns = copy.getAnnotation();
901 assertEquals(1, anns.length);
902 assertFalse(anns[0] == seq1.getAnnotation()[0]);
903 assertEquals(anns[0].label, seq1.getAnnotation()[0].label);
904 assertEquals(anns[0].description, seq1.getAnnotation()[0].description);
905 assertEquals(anns[0].score, seq1.getAnnotation()[0].score);
907 // copy has a copy of the sequence feature:
908 List<SequenceFeature> sfs = copy.getSequenceFeatures();
909 assertEquals(1, sfs.size());
910 if (seq1.getDatasetSequence() != null
911 && copy.getDatasetSequence() == seq1.getDatasetSequence())
913 assertSame(sfs.get(0), seq1.getSequenceFeatures().get(0));
917 assertNotSame(sfs.get(0), seq1.getSequenceFeatures().get(0));
919 assertEquals(sfs.get(0), seq1.getSequenceFeatures().get(0));
921 // copy has a copy of the PDB entry
922 Vector<PDBEntry> pdbs = copy.getAllPDBEntries();
923 assertEquals(1, pdbs.size());
924 assertFalse(pdbs.get(0) == seq1.getAllPDBEntries().get(0));
925 assertTrue(pdbs.get(0).equals(seq1.getAllPDBEntries().get(0)));
928 @Test(groups = "Functional")
929 public void testGetCharAt()
931 SequenceI sq = new Sequence("", "abcde");
932 assertEquals('a', sq.getCharAt(0));
933 assertEquals('e', sq.getCharAt(4));
934 assertEquals(' ', sq.getCharAt(5));
935 assertEquals(' ', sq.getCharAt(-1));
938 @Test(groups = { "Functional" })
939 public void testAddSequenceFeatures()
941 SequenceI sq = new Sequence("", "abcde");
942 // type may not be null
943 assertFalse(sq.addSequenceFeature(new SequenceFeature(null, "desc", 4,
945 assertTrue(sq.addSequenceFeature(new SequenceFeature("Cath", "desc", 4,
947 // can't add a duplicate feature
948 assertFalse(sq.addSequenceFeature(new SequenceFeature("Cath", "desc",
950 // can add a different feature
951 assertTrue(sq.addSequenceFeature(new SequenceFeature("Scop", "desc", 4,
952 8, 0f, null))); // different type
953 assertTrue(sq.addSequenceFeature(new SequenceFeature("Cath",
954 "description", 4, 8, 0f, null)));// different description
955 assertTrue(sq.addSequenceFeature(new SequenceFeature("Cath", "desc", 3,
956 8, 0f, null))); // different start position
957 assertTrue(sq.addSequenceFeature(new SequenceFeature("Cath", "desc", 4,
958 9, 0f, null))); // different end position
959 assertTrue(sq.addSequenceFeature(new SequenceFeature("Cath", "desc", 4,
960 8, 1f, null))); // different score
961 assertTrue(sq.addSequenceFeature(new SequenceFeature("Cath", "desc", 4,
962 8, Float.NaN, null))); // score NaN
963 assertTrue(sq.addSequenceFeature(new SequenceFeature("Cath", "desc", 4,
964 8, 0f, "Metal"))); // different group
965 assertEquals(8, sq.getFeatures().getAllFeatures().size());
969 * Tests for adding (or updating) dbrefs
971 * @see DBRefEntry#updateFrom(DBRefEntry)
973 @Test(groups = { "Functional" })
974 public void testAddDBRef()
976 SequenceI sq = new Sequence("", "abcde");
977 assertNull(sq.getDBRefs());
978 DBRefEntry dbref = new DBRefEntry("Uniprot", "1", "P00340");
980 assertEquals(1, sq.getDBRefs().length);
981 assertSame(dbref, sq.getDBRefs()[0]);
984 * change of version - new entry
986 DBRefEntry dbref2 = new DBRefEntry("Uniprot", "2", "P00340");
988 assertEquals(2, sq.getDBRefs().length);
989 assertSame(dbref, sq.getDBRefs()[0]);
990 assertSame(dbref2, sq.getDBRefs()[1]);
993 * matches existing entry - not added
995 sq.addDBRef(new DBRefEntry("UNIPROT", "1", "p00340"));
996 assertEquals(2, sq.getDBRefs().length);
999 * different source = new entry
1001 DBRefEntry dbref3 = new DBRefEntry("UniRef", "1", "p00340");
1002 sq.addDBRef(dbref3);
1003 assertEquals(3, sq.getDBRefs().length);
1004 assertSame(dbref3, sq.getDBRefs()[2]);
1007 * different ref = new entry
1009 DBRefEntry dbref4 = new DBRefEntry("UniRef", "1", "p00341");
1010 sq.addDBRef(dbref4);
1011 assertEquals(4, sq.getDBRefs().length);
1012 assertSame(dbref4, sq.getDBRefs()[3]);
1015 * matching ref with a mapping - map updated
1017 DBRefEntry dbref5 = new DBRefEntry("UniRef", "1", "p00341");
1018 Mapping map = new Mapping(new MapList(new int[] { 1, 3 }, new int[] {
1021 sq.addDBRef(dbref5);
1022 assertEquals(4, sq.getDBRefs().length);
1023 assertSame(dbref4, sq.getDBRefs()[3]);
1024 assertSame(map, dbref4.getMap());
1027 * 'real' version replaces "0" version
1029 dbref2.setVersion("0");
1030 DBRefEntry dbref6 = new DBRefEntry(dbref2.getSource(), "3",
1031 dbref2.getAccessionId());
1032 sq.addDBRef(dbref6);
1033 assertEquals(4, sq.getDBRefs().length);
1034 assertSame(dbref2, sq.getDBRefs()[1]);
1035 assertEquals("3", dbref2.getVersion());
1038 * 'real' version replaces "source:0" version
1040 dbref3.setVersion("Uniprot:0");
1041 DBRefEntry dbref7 = new DBRefEntry(dbref3.getSource(), "3",
1042 dbref3.getAccessionId());
1043 sq.addDBRef(dbref7);
1044 assertEquals(4, sq.getDBRefs().length);
1045 assertSame(dbref3, sq.getDBRefs()[2]);
1046 assertEquals("3", dbref2.getVersion());
1049 @Test(groups = { "Functional" })
1050 public void testGetPrimaryDBRefs_peptide()
1052 SequenceI sq = new Sequence("aseq", "ASDFKYLMQPRST", 10, 22);
1055 List<DBRefEntry> primaryDBRefs = sq.getPrimaryDBRefs();
1056 assertTrue(primaryDBRefs.isEmpty());
1059 sq.setDBRefs(new DBRefEntry[] {});
1060 primaryDBRefs = sq.getPrimaryDBRefs();
1061 assertTrue(primaryDBRefs.isEmpty());
1063 // primary - uniprot
1064 DBRefEntry upentry1 = new DBRefEntry("UNIPROT", "0", "Q04760");
1065 sq.addDBRef(upentry1);
1067 // primary - uniprot with congruent map
1068 DBRefEntry upentry2 = new DBRefEntry("UNIPROT", "0", "Q04762");
1069 upentry2.setMap(new Mapping(null, new MapList(new int[] { 10, 22 },
1070 new int[] { 10, 22 }, 1, 1)));
1071 sq.addDBRef(upentry2);
1073 // primary - uniprot with map of enclosing sequence
1074 DBRefEntry upentry3 = new DBRefEntry("UNIPROT", "0", "Q04763");
1075 upentry3.setMap(new Mapping(null, new MapList(new int[] { 8, 24 },
1076 new int[] { 8, 24 }, 1, 1)));
1077 sq.addDBRef(upentry3);
1079 // not primary - uniprot with map of sub-sequence (5')
1080 DBRefEntry upentry4 = new DBRefEntry("UNIPROT", "0", "Q04764");
1081 upentry4.setMap(new Mapping(null, new MapList(new int[] { 10, 18 },
1082 new int[] { 10, 18 }, 1, 1)));
1083 sq.addDBRef(upentry4);
1085 // not primary - uniprot with map that overlaps 3'
1086 DBRefEntry upentry5 = new DBRefEntry("UNIPROT", "0", "Q04765");
1087 upentry5.setMap(new Mapping(null, new MapList(new int[] { 12, 22 },
1088 new int[] { 12, 22 }, 1, 1)));
1089 sq.addDBRef(upentry5);
1091 // not primary - uniprot with map to different coordinates frame
1092 DBRefEntry upentry6 = new DBRefEntry("UNIPROT", "0", "Q04766");
1093 upentry6.setMap(new Mapping(null, new MapList(new int[] { 12, 18 },
1094 new int[] { 112, 118 }, 1, 1)));
1095 sq.addDBRef(upentry6);
1097 // not primary - dbref to 'non-core' database
1098 DBRefEntry upentry7 = new DBRefEntry("Pfam", "0", "PF00903");
1099 sq.addDBRef(upentry7);
1101 // primary - type is PDB
1102 DBRefEntry pdbentry = new DBRefEntry("PDB", "0", "1qip");
1103 sq.addDBRef(pdbentry);
1105 // not primary - PDBEntry has no file
1106 sq.addDBRef(new DBRefEntry("PDB", "0", "1AAA"));
1108 // not primary - no PDBEntry
1109 sq.addDBRef(new DBRefEntry("PDB", "0", "1DDD"));
1111 // add corroborating PDB entry for primary DBref -
1112 // needs to have a file as well as matching ID
1113 // note PDB ID is not treated as case sensitive
1114 sq.addPDBId(new PDBEntry("1QIP", null, Type.PDB, new File("/blah")
1117 // not valid DBRef - no file..
1118 sq.addPDBId(new PDBEntry("1AAA", null, null, null));
1120 primaryDBRefs = sq.getPrimaryDBRefs();
1121 assertEquals(4, primaryDBRefs.size());
1122 assertTrue("Couldn't find simple primary reference (UNIPROT)",
1123 primaryDBRefs.contains(upentry1));
1124 assertTrue("Couldn't find mapped primary reference (UNIPROT)",
1125 primaryDBRefs.contains(upentry2));
1126 assertTrue("Couldn't find mapped context reference (UNIPROT)",
1127 primaryDBRefs.contains(upentry3));
1128 assertTrue("Couldn't find expected PDB primary reference",
1129 primaryDBRefs.contains(pdbentry));
1132 @Test(groups = { "Functional" })
1133 public void testGetPrimaryDBRefs_nucleotide()
1135 SequenceI sq = new Sequence("aseq", "TGATCACTCGACTAGCATCAGCATA", 10, 34);
1137 // primary - Ensembl
1138 DBRefEntry dbr1 = new DBRefEntry("ENSEMBL", "0", "ENSG1234");
1141 // not primary - Ensembl 'transcript' mapping of sub-sequence
1142 DBRefEntry dbr2 = new DBRefEntry("ENSEMBL", "0", "ENST1234");
1143 dbr2.setMap(new Mapping(null, new MapList(new int[] { 15, 25 },
1144 new int[] { 1, 11 }, 1, 1)));
1147 // primary - EMBL with congruent map
1148 DBRefEntry dbr3 = new DBRefEntry("EMBL", "0", "J1234");
1149 dbr3.setMap(new Mapping(null, new MapList(new int[] { 10, 34 },
1150 new int[] { 10, 34 }, 1, 1)));
1153 // not primary - to non-core database
1154 DBRefEntry dbr4 = new DBRefEntry("CCDS", "0", "J1234");
1157 // not primary - to protein
1158 DBRefEntry dbr5 = new DBRefEntry("UNIPROT", "0", "Q87654");
1161 List<DBRefEntry> primaryDBRefs = sq.getPrimaryDBRefs();
1162 assertEquals(2, primaryDBRefs.size());
1163 assertTrue(primaryDBRefs.contains(dbr1));
1164 assertTrue(primaryDBRefs.contains(dbr3));
1168 * Test the method that updates the list of PDBEntry from any new DBRefEntry
1171 @Test(groups = { "Functional" })
1172 public void testUpdatePDBIds()
1174 PDBEntry pdbe1 = new PDBEntry("3A6S", null, null, null);
1175 seq.addPDBId(pdbe1);
1176 seq.addDBRef(new DBRefEntry("Ensembl", "8", "ENST1234"));
1177 seq.addDBRef(new DBRefEntry("PDB", "0", "1A70"));
1178 seq.addDBRef(new DBRefEntry("PDB", "0", "4BQGa"));
1179 seq.addDBRef(new DBRefEntry("PDB", "0", "3a6sB"));
1180 // 7 is not a valid chain code:
1181 seq.addDBRef(new DBRefEntry("PDB", "0", "2GIS7"));
1184 List<PDBEntry> pdbIds = seq.getAllPDBEntries();
1185 assertEquals(4, pdbIds.size());
1186 assertSame(pdbe1, pdbIds.get(0));
1187 // chain code got added to 3A6S:
1188 assertEquals("B", pdbe1.getChainCode());
1189 assertEquals("1A70", pdbIds.get(1).getId());
1190 // 4BQGA is parsed into id + chain
1191 assertEquals("4BQG", pdbIds.get(2).getId());
1192 assertEquals("a", pdbIds.get(2).getChainCode());
1193 assertEquals("2GIS7", pdbIds.get(3).getId());
1194 assertNull(pdbIds.get(3).getChainCode());
1198 * Test the method that either adds a pdbid or updates an existing one
1200 @Test(groups = { "Functional" })
1201 public void testAddPDBId()
1203 PDBEntry pdbe = new PDBEntry("3A6S", null, null, null);
1205 assertEquals(1, seq.getAllPDBEntries().size());
1206 assertSame(pdbe, seq.getPDBEntry("3A6S"));
1207 assertSame(pdbe, seq.getPDBEntry("3a6s")); // case-insensitive
1209 // add the same entry
1211 assertEquals(1, seq.getAllPDBEntries().size());
1212 assertSame(pdbe, seq.getPDBEntry("3A6S"));
1214 // add an identical entry
1215 seq.addPDBId(new PDBEntry("3A6S", null, null, null));
1216 assertEquals(1, seq.getAllPDBEntries().size());
1217 assertSame(pdbe, seq.getPDBEntry("3A6S"));
1219 // add a different entry
1220 PDBEntry pdbe2 = new PDBEntry("1A70", null, null, null);
1221 seq.addPDBId(pdbe2);
1222 assertEquals(2, seq.getAllPDBEntries().size());
1223 assertSame(pdbe, seq.getAllPDBEntries().get(0));
1224 assertSame(pdbe2, seq.getAllPDBEntries().get(1));
1226 // update pdbe with chain code, file, type
1227 PDBEntry pdbe3 = new PDBEntry("3a6s", "A", Type.PDB, "filepath");
1228 seq.addPDBId(pdbe3);
1229 assertEquals(2, seq.getAllPDBEntries().size());
1230 assertSame(pdbe, seq.getAllPDBEntries().get(0)); // updated in situ
1231 assertEquals("3A6S", pdbe.getId()); // unchanged
1232 assertEquals("A", pdbe.getChainCode()); // updated
1233 assertEquals(Type.PDB.toString(), pdbe.getType()); // updated
1234 assertEquals("filepath", pdbe.getFile()); // updated
1235 assertSame(pdbe2, seq.getAllPDBEntries().get(1));
1237 // add with a different file path
1238 PDBEntry pdbe4 = new PDBEntry("3a6s", "A", Type.PDB, "filepath2");
1239 seq.addPDBId(pdbe4);
1240 assertEquals(3, seq.getAllPDBEntries().size());
1241 assertSame(pdbe4, seq.getAllPDBEntries().get(2));
1243 // add with a different chain code
1244 PDBEntry pdbe5 = new PDBEntry("3a6s", "B", Type.PDB, "filepath");
1245 seq.addPDBId(pdbe5);
1246 assertEquals(4, seq.getAllPDBEntries().size());
1247 assertSame(pdbe5, seq.getAllPDBEntries().get(3));
1251 groups = { "Functional" },
1252 expectedExceptions = { IllegalArgumentException.class })
1253 public void testSetDatasetSequence_toSelf()
1255 seq.setDatasetSequence(seq);
1259 groups = { "Functional" },
1260 expectedExceptions = { IllegalArgumentException.class })
1261 public void testSetDatasetSequence_cascading()
1263 SequenceI seq2 = new Sequence("Seq2", "xyz");
1264 seq2.createDatasetSequence();
1265 seq.setDatasetSequence(seq2);
1268 @Test(groups = { "Functional" })
1269 public void testFindFeatures()
1271 SequenceI sq = new Sequence("test/8-16", "-ABC--DEF--GHI--");
1272 sq.createDatasetSequence();
1274 assertTrue(sq.findFeatures(1, 99).isEmpty());
1276 // add non-positional feature
1277 SequenceFeature sf0 = new SequenceFeature("Cath", "desc", 0, 0, 2f,
1279 sq.addSequenceFeature(sf0);
1280 // add feature on BCD
1281 SequenceFeature sf1 = new SequenceFeature("Cath", "desc", 9, 11, 2f,
1283 sq.addSequenceFeature(sf1);
1284 // add feature on DE
1285 SequenceFeature sf2 = new SequenceFeature("Cath", "desc", 11, 12, 2f,
1287 sq.addSequenceFeature(sf2);
1288 // add contact feature at [B, H]
1289 SequenceFeature sf3 = new SequenceFeature("Disulphide bond", "desc", 9,
1292 sq.addSequenceFeature(sf3);
1293 // add contact feature at [F, G]
1294 SequenceFeature sf4 = new SequenceFeature("Disulfide Bond", "desc", 13,
1297 sq.addSequenceFeature(sf4);
1299 // no features in columns 1-2 (-A)
1300 List<SequenceFeature> found = sq.findFeatures(1, 2);
1301 assertTrue(found.isEmpty());
1303 // columns 1-6 (-ABC--) includes BCD and B/H feature but not DE
1304 found = sq.findFeatures(1, 6);
1305 assertEquals(2, found.size());
1306 assertTrue(found.contains(sf1));
1307 assertTrue(found.contains(sf3));
1309 // columns 5-6 (--) includes (enclosing) BCD but not (contact) B/H feature
1310 found = sq.findFeatures(5, 6);
1311 assertEquals(1, found.size());
1312 assertTrue(found.contains(sf1));
1314 // columns 7-10 (DEF-) includes BCD, DE, F/G but not B/H feature
1315 found = sq.findFeatures(7, 10);
1316 assertEquals(3, found.size());
1317 assertTrue(found.contains(sf1));
1318 assertTrue(found.contains(sf2));
1319 assertTrue(found.contains(sf4));
1322 @Test(groups = { "Functional" })
1323 public void testFindIndex_withCursor()
1325 Sequence sq = new Sequence("test/8-13", "-A--BCD-EF--");
1328 assertEquals(10, sq.findIndex(13, new SequenceCursor(sq, 8, 2, 0)));
1331 assertEquals(2, sq.findIndex(8, new SequenceCursor(sq, 13, 10, 0)));
1334 assertEquals(6, sq.findIndex(10, new SequenceCursor(sq, 10, 6, 0)));
1337 @Test(groups = { "Functional" })
1338 public void testFindPosition_withCursor()
1340 Sequence sq = new Sequence("test/8-13", "-A--BCD-EF--");
1342 // find F pos given A
1343 assertEquals(13, sq.findPosition(10, new SequenceCursor(sq, 8, 2, 0)));
1344 int token = (int) PA.getValue(sq, "changeCount"); // 0
1345 SequenceCursor cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1346 assertEquals(new SequenceCursor(sq, 13, 10, token), cursor);
1348 // find A pos given F
1349 assertEquals(8, sq.findPosition(2, new SequenceCursor(sq, 13, 10, 0)));
1350 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1351 assertEquals(new SequenceCursor(sq, 8, 2, token), cursor);
1353 // find C pos given C
1354 assertEquals(10, sq.findPosition(6, new SequenceCursor(sq, 10, 6, 0)));
1355 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1356 assertEquals(new SequenceCursor(sq, 10, 6, token), cursor);
1358 // now the grey area - what residue position for a gapped column? JAL-2562
1360 // find 'residue' for column 3 given cursor for D (so working left)
1361 // returns B9; cursor is updated to [B 5]
1362 assertEquals(9, sq.findPosition(3, new SequenceCursor(sq, 11, 7, 0)));
1363 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1364 assertEquals(new SequenceCursor(sq, 9, 5, token), cursor);
1366 // find 'residue' for column 8 given cursor for D (so working right)
1367 // returns E12; cursor is updated to [D 7]
1368 assertEquals(12, sq.findPosition(8, new SequenceCursor(sq, 11, 7, 0)));
1369 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1370 assertEquals(new SequenceCursor(sq, 11, 7, token), cursor);
1372 // find 'residue' for column 12 given cursor for B
1373 // returns 1 more than last residue position; cursor is updated to [F 10]
1374 assertEquals(14, sq.findPosition(12, new SequenceCursor(sq, 9, 5, 0)));
1375 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1376 assertEquals(new SequenceCursor(sq, 13, 10, token), cursor);
1379 * findPosition for column beyond length of sequence
1380 * returns 1 more than the last residue position
1381 * cursor is set to last real residue position [F 10]
1383 assertEquals(14, sq.findPosition(99, new SequenceCursor(sq, 8, 2, 0)));
1384 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1385 assertEquals(new SequenceCursor(sq, 13, 10, token), cursor);
1388 * and the case without a trailing gap
1390 sq = new Sequence("test/8-13", "-A--BCD-EF");
1391 // first find C from A
1392 assertEquals(10, sq.findPosition(6, new SequenceCursor(sq, 8, 2, 0)));
1393 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1394 assertEquals(new SequenceCursor(sq, 10, 6, token), cursor);
1395 // now 'find' 99 from C
1396 // cursor is set to [F 10]
1397 assertEquals(14, sq.findPosition(99, cursor));
1398 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1399 assertEquals(new SequenceCursor(sq, 13, 10, token), cursor);
1403 public void testIsValidCursor()
1405 Sequence sq = new Sequence("Seq", "ABC--DE-F", 8, 13);
1406 assertFalse(sq.isValidCursor(null));
1409 * cursor is valid if it has valid sequence ref and changeCount token
1410 * and positions within the range of the sequence
1412 int changeCount = (int) PA.getValue(sq, "changeCount");
1413 SequenceCursor cursor = new SequenceCursor(sq, 13, 1, changeCount);
1414 assertTrue(sq.isValidCursor(cursor));
1417 * column position outside [0 - length-1] is rejected
1419 cursor = new SequenceCursor(sq, 13, -1, changeCount);
1420 assertFalse(sq.isValidCursor(cursor));
1421 cursor = new SequenceCursor(sq, 13, 9, changeCount);
1422 assertFalse(sq.isValidCursor(cursor));
1423 cursor = new SequenceCursor(sq, 7, 8, changeCount);
1424 assertFalse(sq.isValidCursor(cursor));
1425 cursor = new SequenceCursor(sq, 14, 2, changeCount);
1426 assertFalse(sq.isValidCursor(cursor));
1429 * wrong sequence is rejected
1431 cursor = new SequenceCursor(null, 13, 1, changeCount);
1432 assertFalse(sq.isValidCursor(cursor));
1433 cursor = new SequenceCursor(new Sequence("Seq", "abc"), 13, 1,
1435 assertFalse(sq.isValidCursor(cursor));
1438 * wrong token value is rejected
1440 cursor = new SequenceCursor(sq, 13, 1, changeCount + 1);
1441 assertFalse(sq.isValidCursor(cursor));
1442 cursor = new SequenceCursor(sq, 13, 1, changeCount - 1);
1443 assertFalse(sq.isValidCursor(cursor));
1446 @Test(groups = { "Functional" })
1447 public void testFindPosition_withCursorAndEdits()
1449 Sequence sq = new Sequence("test/8-13", "-A--BCD-EF--");
1451 // find F pos given A
1452 assertEquals(13, sq.findPosition(10, new SequenceCursor(sq, 8, 2, 0)));
1453 int token = (int) PA.getValue(sq, "changeCount"); // 0
1454 SequenceCursor cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1455 assertEquals(new SequenceCursor(sq, 13, 10, token), cursor);
1458 * setSequence should invalidate the cursor cached by the sequence
1460 sq.setSequence("-A-BCD-EF---"); // one gap removed
1461 assertEquals(8, sq.getStart()); // sanity check
1462 assertEquals(11, sq.findPosition(5)); // D11
1463 // cursor should now be at [D 6]
1464 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1465 assertEquals(new SequenceCursor(sq, 11, 6, ++token), cursor);
1468 * deleteChars should invalidate the cached cursor
1470 sq.deleteChars(2, 5); // delete -BC
1471 assertEquals("-AD-EF---", sq.getSequenceAsString());
1472 assertEquals(8, sq.getStart()); // sanity check
1473 assertEquals(10, sq.findPosition(4)); // E10
1474 // cursor should now be at [E 5]
1475 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1476 assertEquals(new SequenceCursor(sq, 10, 5, ++token), cursor);
1479 * Edit to insert gaps should invalidate the cached cursor
1480 * insert 2 gaps at column[3] to make -AD---EF---
1482 SequenceI[] seqs = new SequenceI[] { sq };
1483 AlignmentI al = new Alignment(seqs);
1484 new EditCommand().appendEdit(Action.INSERT_GAP, seqs, 3, 2, al, true);
1485 assertEquals("-AD---EF---", sq.getSequenceAsString());
1486 assertEquals(10, sq.findPosition(4)); // E10
1487 // cursor should now be at [D 3]
1488 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1489 assertEquals(new SequenceCursor(sq, 9, 3, ++token), cursor);
1492 * insertCharAt should invalidate the cached cursor
1493 * insert CC at column[4] to make -AD-CC--EF---
1495 sq.insertCharAt(4, 2, 'C');
1496 assertEquals("-AD-CC--EF---", sq.getSequenceAsString());
1497 assertEquals(13, sq.findPosition(9)); // F13
1498 // cursor should now be at [F 10]
1499 cursor = (SequenceCursor) PA.getValue(sq, "cursor");
1500 assertEquals(new SequenceCursor(sq, 13, 10, ++token), cursor);