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.assertNull;
27 import static org.testng.AssertJUnit.assertSame;
28 import static org.testng.AssertJUnit.assertTrue;
29 import static org.testng.internal.junit.ArrayAsserts.assertArrayEquals;
31 import jalview.datamodel.PDBEntry.Type;
32 import jalview.util.MapList;
35 import java.util.ArrayList;
36 import java.util.Arrays;
37 import java.util.List;
38 import java.util.Vector;
40 import org.testng.Assert;
41 import org.testng.annotations.BeforeMethod;
42 import org.testng.annotations.Test;
44 public class SequenceTest
48 @BeforeMethod(alwaysRun = true)
51 seq = new Sequence("FER1", "AKPNGVL");
54 @Test(groups = { "Functional" })
55 public void testInsertGapsAndGapmaps()
57 SequenceI aseq = seq.deriveSequence();
58 aseq.insertCharAt(2, 3, '-');
59 aseq.insertCharAt(6, 3, '-');
60 assertEquals("Gap insertions not correct", "AK---P---NGVL",
61 aseq.getSequenceAsString());
62 List<int[]> gapInt = aseq.getInsertions();
63 assertEquals("Gap interval 1 start wrong", 2, gapInt.get(0)[0]);
64 assertEquals("Gap interval 1 end wrong", 4, gapInt.get(0)[1]);
65 assertEquals("Gap interval 2 start wrong", 6, gapInt.get(1)[0]);
66 assertEquals("Gap interval 2 end wrong", 8, gapInt.get(1)[1]);
69 @Test(groups = ("Functional"))
70 public void testIsProtein()
73 assertTrue(new Sequence("prot", "ASDFASDFASDF").isProtein());
75 assertFalse(new Sequence("prot", "ACGTACGTACGT").isProtein());
77 SequenceI sq = new Sequence("prot", "ACGUACGUACGU");
78 assertFalse(sq.isProtein());
79 // change sequence, should trigger an update of cached result
80 sq.setSequence("ASDFASDFADSF");
81 assertTrue(sq.isProtein());
83 * in situ change of sequence doesn't change hashcode :-O
84 * (sequence should not expose internal implementation)
86 for (int i = 0; i < sq.getSequence().length; i++)
88 sq.getSequence()[i] = "acgtu".charAt(i % 5);
90 assertTrue(sq.isProtein()); // but it isn't
93 @Test(groups = { "Functional" })
94 public void testGetAnnotation()
96 // initial state returns null not an empty array
97 assertNull(seq.getAnnotation());
98 AlignmentAnnotation ann = addAnnotation("label1", "desc1", "calcId1",
100 AlignmentAnnotation[] anns = seq.getAnnotation();
101 assertEquals(1, anns.length);
102 assertSame(ann, anns[0]);
104 // removing all annotations reverts array to null
105 seq.removeAlignmentAnnotation(ann);
106 assertNull(seq.getAnnotation());
109 @Test(groups = { "Functional" })
110 public void testGetAnnotation_forLabel()
112 AlignmentAnnotation ann1 = addAnnotation("label1", "desc1", "calcId1",
114 addAnnotation("label2", "desc2", "calcId2", 1f);
115 AlignmentAnnotation ann3 = addAnnotation("label1", "desc3", "calcId3",
117 AlignmentAnnotation[] anns = seq.getAnnotation("label1");
118 assertEquals(2, anns.length);
119 assertSame(ann1, anns[0]);
120 assertSame(ann3, anns[1]);
123 private AlignmentAnnotation addAnnotation(String label,
124 String description, String calcId, float value)
126 final AlignmentAnnotation annotation = new AlignmentAnnotation(label,
128 annotation.setCalcId(calcId);
129 seq.addAlignmentAnnotation(annotation);
133 @Test(groups = { "Functional" })
134 public void testGetAlignmentAnnotations_forCalcIdAndLabel()
136 addAnnotation("label1", "desc1", "calcId1", 1f);
137 AlignmentAnnotation ann2 = addAnnotation("label2", "desc2", "calcId2",
139 addAnnotation("label2", "desc3", "calcId3", 1f);
140 AlignmentAnnotation ann4 = addAnnotation("label2", "desc3", "calcId2",
142 addAnnotation("label5", "desc3", null, 1f);
143 addAnnotation(null, "desc3", "calcId3", 1f);
145 List<AlignmentAnnotation> anns = seq.getAlignmentAnnotations("calcId2",
147 assertEquals(2, anns.size());
148 assertSame(ann2, anns.get(0));
149 assertSame(ann4, anns.get(1));
151 assertTrue(seq.getAlignmentAnnotations("calcId2", "label3").isEmpty());
152 assertTrue(seq.getAlignmentAnnotations("calcId3", "label5").isEmpty());
153 assertTrue(seq.getAlignmentAnnotations("calcId2", null).isEmpty());
154 assertTrue(seq.getAlignmentAnnotations(null, "label3").isEmpty());
155 assertTrue(seq.getAlignmentAnnotations(null, null).isEmpty());
159 * Tests for addAlignmentAnnotation. Note this method has the side-effect of
160 * setting the sequenceRef on the annotation. Adding the same annotation twice
163 @Test(groups = { "Functional" })
164 public void testAddAlignmentAnnotation()
166 assertNull(seq.getAnnotation());
167 final AlignmentAnnotation annotation = new AlignmentAnnotation("a",
169 assertNull(annotation.sequenceRef);
170 seq.addAlignmentAnnotation(annotation);
171 assertSame(seq, annotation.sequenceRef);
172 AlignmentAnnotation[] anns = seq.getAnnotation();
173 assertEquals(1, anns.length);
174 assertSame(annotation, anns[0]);
176 // re-adding does nothing
177 seq.addAlignmentAnnotation(annotation);
178 anns = seq.getAnnotation();
179 assertEquals(1, anns.length);
180 assertSame(annotation, anns[0]);
182 // an identical but different annotation can be added
183 final AlignmentAnnotation annotation2 = new AlignmentAnnotation("a",
185 seq.addAlignmentAnnotation(annotation2);
186 anns = seq.getAnnotation();
187 assertEquals(2, anns.length);
188 assertSame(annotation, anns[0]);
189 assertSame(annotation2, anns[1]);
192 @Test(groups = { "Functional" })
193 public void testGetStartGetEnd()
195 SequenceI sq = new Sequence("test", "ABCDEF");
196 assertEquals(1, sq.getStart());
197 assertEquals(6, sq.getEnd());
199 sq = new Sequence("test", "--AB-C-DEF--");
200 assertEquals(1, sq.getStart());
201 assertEquals(6, sq.getEnd());
203 sq = new Sequence("test", "----");
204 assertEquals(1, sq.getStart());
205 assertEquals(0, sq.getEnd()); // ??
209 * Tests for the method that returns an alignment column position (base 1) for
210 * a given sequence position (base 1).
212 @Test(groups = { "Functional" })
213 public void testFindIndex()
215 SequenceI sq = new Sequence("test", "ABCDEF");
216 assertEquals(0, sq.findIndex(0));
217 assertEquals(1, sq.findIndex(1));
218 assertEquals(5, sq.findIndex(5));
219 assertEquals(6, sq.findIndex(6));
220 assertEquals(6, sq.findIndex(9));
222 sq = new Sequence("test", "-A--B-C-D-E-F--");
223 assertEquals(2, sq.findIndex(1));
224 assertEquals(5, sq.findIndex(2));
225 assertEquals(7, sq.findIndex(3));
227 // before start returns 0
228 assertEquals(0, sq.findIndex(0));
229 assertEquals(0, sq.findIndex(-1));
231 // beyond end returns last residue column
232 assertEquals(13, sq.findIndex(99));
237 * Tests for the method that returns a dataset sequence position (base 1) for
238 * an aligned column position (base 0).
240 @Test(groups = { "Functional" })
241 public void testFindPosition()
243 SequenceI sq = new Sequence("test", "ABCDEF");
244 assertEquals(1, sq.findPosition(0));
245 assertEquals(6, sq.findPosition(5));
246 // assertEquals(-1, seq.findPosition(6)); // fails
248 sq = new Sequence("test", "AB-C-D--");
249 assertEquals(1, sq.findPosition(0));
250 assertEquals(2, sq.findPosition(1));
251 // gap position 'finds' residue to the right (not the left as per javadoc)
252 assertEquals(3, sq.findPosition(2));
253 assertEquals(3, sq.findPosition(3));
254 assertEquals(4, sq.findPosition(4));
255 assertEquals(4, sq.findPosition(5));
256 // returns 1 more than sequence length if off the end ?!?
257 assertEquals(5, sq.findPosition(6));
258 assertEquals(5, sq.findPosition(7));
260 sq = new Sequence("test", "--AB-C-DEF--");
261 assertEquals(1, sq.findPosition(0));
262 assertEquals(1, sq.findPosition(1));
263 assertEquals(1, sq.findPosition(2));
264 assertEquals(2, sq.findPosition(3));
265 assertEquals(3, sq.findPosition(4));
266 assertEquals(3, sq.findPosition(5));
267 assertEquals(4, sq.findPosition(6));
268 assertEquals(4, sq.findPosition(7));
269 assertEquals(5, sq.findPosition(8));
270 assertEquals(6, sq.findPosition(9));
271 assertEquals(7, sq.findPosition(10));
272 assertEquals(7, sq.findPosition(11));
275 @Test(groups = { "Functional" })
276 public void testDeleteChars()
278 SequenceI sq = new Sequence("test", "ABCDEF");
279 assertEquals(1, sq.getStart());
280 assertEquals(6, sq.getEnd());
281 sq.deleteChars(2, 3);
282 assertEquals("ABDEF", sq.getSequenceAsString());
283 assertEquals(1, sq.getStart());
284 assertEquals(5, sq.getEnd());
286 sq = new Sequence("test", "ABCDEF");
287 sq.deleteChars(0, 2);
288 assertEquals("CDEF", sq.getSequenceAsString());
289 assertEquals(3, sq.getStart());
290 assertEquals(6, sq.getEnd());
293 @Test(groups = { "Functional" })
294 public void testInsertCharAt()
296 // non-static methods:
297 SequenceI sq = new Sequence("test", "ABCDEF");
298 sq.insertCharAt(0, 'z');
299 assertEquals("zABCDEF", sq.getSequenceAsString());
300 sq.insertCharAt(2, 2, 'x');
301 assertEquals("zAxxBCDEF", sq.getSequenceAsString());
303 // for static method see StringUtilsTest
307 * Test the method that returns an array of aligned sequence positions where
308 * the array index is the data sequence position (both base 0).
310 @Test(groups = { "Functional" })
311 public void testGapMap()
313 SequenceI sq = new Sequence("test", "-A--B-CD-E--F-");
314 sq.createDatasetSequence();
315 assertEquals("[1, 4, 6, 7, 9, 12]", Arrays.toString(sq.gapMap()));
319 * Test the method that gets sequence features, either from the sequence or
322 @Test(groups = { "Functional" })
323 public void testGetSequenceFeatures()
325 SequenceI sq = new Sequence("test", "GATCAT");
326 sq.createDatasetSequence();
328 assertNull(sq.getSequenceFeatures());
331 * SequenceFeature on sequence
333 SequenceFeature sf = new SequenceFeature();
334 sq.addSequenceFeature(sf);
335 SequenceFeature[] sfs = sq.getSequenceFeatures();
336 assertEquals(1, sfs.length);
337 assertSame(sf, sfs[0]);
340 * SequenceFeature on sequence and dataset sequence; returns that on
343 * Note JAL-2046: spurious: we have no use case for this at the moment.
344 * This test also buggy - as sf2.equals(sf), no new feature is added
346 SequenceFeature sf2 = new SequenceFeature();
347 sq.getDatasetSequence().addSequenceFeature(sf2);
348 sfs = sq.getSequenceFeatures();
349 assertEquals(1, sfs.length);
350 assertSame(sf, sfs[0]);
353 * SequenceFeature on dataset sequence only
354 * Note JAL-2046: spurious: we have no use case for setting a non-dataset sequence's feature array to null at the moment.
356 sq.setSequenceFeatures(null);
357 assertNull(sq.getDatasetSequence().getSequenceFeatures());
360 * Corrupt case - no SequenceFeature, dataset's dataset is the original
361 * sequence. Test shows no infinite loop results.
363 sq.getDatasetSequence().setSequenceFeatures(null);
365 * is there a usecase for this ? setDatasetSequence should throw an error if
366 * this actually occurs.
370 sq.getDatasetSequence().setDatasetSequence(sq); // loop!
371 Assert.fail("Expected Error to be raised when calling setDatasetSequence with self reference");
372 } catch (IllegalArgumentException e)
374 // TODO Jalview error/exception class for raising implementation errors
375 assertTrue(e.getMessage().toLowerCase()
376 .contains("implementation error"));
378 assertNull(sq.getSequenceFeatures());
382 * Test the method that returns an array, indexed by sequence position, whose
383 * entries are the residue positions at the sequence position (or to the right
386 @Test(groups = { "Functional" })
387 public void testFindPositionMap()
390 * Note: Javadoc for findPosition says it returns the residue position to
391 * the left of a gapped position; in fact it returns the position to the
392 * right. Also it returns a non-existent residue position for a gap beyond
395 Sequence sq = new Sequence("TestSeq", "AB.C-D E.");
396 int[] map = sq.findPositionMap();
397 assertEquals(Arrays.toString(new int[] { 1, 2, 3, 3, 4, 4, 5, 5, 6 }),
398 Arrays.toString(map));
402 * Test for getSubsequence
404 @Test(groups = { "Functional" })
405 public void testGetSubsequence()
407 SequenceI sq = new Sequence("TestSeq", "ABCDEFG");
408 sq.createDatasetSequence();
410 // positions are base 0, end position is exclusive
411 SequenceI subseq = sq.getSubSequence(2, 4);
413 assertEquals("CD", subseq.getSequenceAsString());
414 // start/end are base 1 positions
415 assertEquals(3, subseq.getStart());
416 assertEquals(4, subseq.getEnd());
417 // subsequence shares the full dataset sequence
418 assertSame(sq.getDatasetSequence(), subseq.getDatasetSequence());
422 * test createDatasetSequence behaves to doc
424 @Test(groups = { "Functional" })
425 public void testCreateDatasetSequence()
427 SequenceI sq = new Sequence("my", "ASDASD");
428 assertNull(sq.getDatasetSequence());
429 SequenceI rds = sq.createDatasetSequence();
431 assertNull(rds.getDatasetSequence());
432 assertEquals(sq.getDatasetSequence(), rds);
436 * Test for deriveSequence applied to a sequence with a dataset
438 @Test(groups = { "Functional" })
439 public void testDeriveSequence_existingDataset()
441 Sequence sq = new Sequence("Seq1", "CD");
442 sq.setDatasetSequence(new Sequence("Seq1", "ABCDEF"));
443 sq.getDatasetSequence().addSequenceFeature(
444 new SequenceFeature("", "", 1, 2, 0f, null));
448 sq.setDescription("Test sequence description..");
449 sq.setVamsasId("TestVamsasId");
450 sq.addDBRef(new DBRefEntry("PDB", "version0", "1TST"));
452 sq.addDBRef(new DBRefEntry("PDB", "version1", "1PDB"));
453 sq.addDBRef(new DBRefEntry("PDB", "version2", "2PDB"));
454 sq.addDBRef(new DBRefEntry("PDB", "version3", "3PDB"));
455 sq.addDBRef(new DBRefEntry("PDB", "version4", "4PDB"));
457 sq.addPDBId(new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1"));
458 sq.addPDBId(new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1"));
459 sq.addPDBId(new PDBEntry("2PDB", "A", Type.MMCIF, "filePath/test2"));
460 sq.addPDBId(new PDBEntry("2PDB", "B", Type.MMCIF, "filePath/test2"));
462 // these are the same as ones already added
463 DBRefEntry pdb1pdb = new DBRefEntry("PDB", "version1", "1PDB");
464 DBRefEntry pdb2pdb = new DBRefEntry("PDB", "version2", "2PDB");
466 List<DBRefEntry> primRefs = Arrays.asList(new DBRefEntry[] { pdb1pdb,
469 sq.getDatasetSequence().addDBRef(pdb1pdb); // should do nothing
470 sq.getDatasetSequence().addDBRef(pdb2pdb); // should do nothing
471 sq.getDatasetSequence().addDBRef(
472 new DBRefEntry("PDB", "version3", "3PDB")); // should do nothing
473 sq.getDatasetSequence().addDBRef(
474 new DBRefEntry("PDB", "version4", "4PDB")); // should do nothing
476 PDBEntry pdbe1a = new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1");
477 PDBEntry pdbe1b = new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1");
478 PDBEntry pdbe2a = new PDBEntry("2PDB", "A", Type.MMCIF,
480 PDBEntry pdbe2b = new PDBEntry("2PDB", "B", Type.MMCIF,
482 sq.getDatasetSequence().addPDBId(pdbe1a);
483 sq.getDatasetSequence().addPDBId(pdbe1b);
484 sq.getDatasetSequence().addPDBId(pdbe2a);
485 sq.getDatasetSequence().addPDBId(pdbe2b);
488 * test we added pdb entries to the dataset sequence
490 Assert.assertEquals(sq.getDatasetSequence().getAllPDBEntries(), Arrays
491 .asList(new PDBEntry[] { pdbe1a, pdbe1b, pdbe2a, pdbe2b }),
492 "PDB Entries were not found on dataset sequence.");
495 * we should recover a pdb entry that is on the dataset sequence via PDBEntry
497 Assert.assertEquals(pdbe1a,
498 sq.getDatasetSequence().getPDBEntry("1PDB"),
499 "PDB Entry '1PDB' not found on dataset sequence via getPDBEntry.");
500 ArrayList<Annotation> annotsList = new ArrayList<Annotation>();
501 System.out.println(">>>>>> " + sq.getSequenceAsString().length());
502 annotsList.add(new Annotation("A", "A", 'X', 0.1f));
503 annotsList.add(new Annotation("A", "A", 'X', 0.1f));
504 Annotation[] annots = annotsList.toArray(new Annotation[0]);
505 sq.addAlignmentAnnotation(new AlignmentAnnotation("Test annot",
506 "Test annot description", annots));
507 sq.getDatasetSequence().addAlignmentAnnotation(
508 new AlignmentAnnotation("Test annot", "Test annot description",
510 Assert.assertEquals(sq.getDescription(), "Test sequence description..");
511 Assert.assertEquals(sq.getDBRefs().length, 5); // DBRefs are on dataset
513 Assert.assertEquals(sq.getAllPDBEntries().size(), 4);
514 Assert.assertNotNull(sq.getAnnotation());
515 Assert.assertEquals(sq.getAnnotation()[0].annotations.length, 2);
516 Assert.assertEquals(sq.getDatasetSequence().getDBRefs().length, 5); // same
519 Assert.assertEquals(sq.getDatasetSequence().getAllPDBEntries().size(),
521 Assert.assertNotNull(sq.getDatasetSequence().getAnnotation());
523 Sequence derived = (Sequence) sq.deriveSequence();
525 Assert.assertEquals(derived.getDescription(),
526 "Test sequence description..");
527 Assert.assertEquals(derived.getDBRefs().length, 5); // come from dataset
528 Assert.assertEquals(derived.getAllPDBEntries().size(), 4);
529 Assert.assertNotNull(derived.getAnnotation());
530 Assert.assertEquals(derived.getAnnotation()[0].annotations.length, 2);
531 Assert.assertEquals(derived.getDatasetSequence().getDBRefs().length, 5);
532 Assert.assertEquals(derived.getDatasetSequence().getAllPDBEntries()
534 Assert.assertNotNull(derived.getDatasetSequence().getAnnotation());
536 assertEquals("CD", derived.getSequenceAsString());
537 assertSame(sq.getDatasetSequence(), derived.getDatasetSequence());
539 assertNull(sq.sequenceFeatures);
540 assertNull(derived.sequenceFeatures);
541 // derived sequence should access dataset sequence features
542 assertNotNull(sq.getSequenceFeatures());
543 assertArrayEquals(sq.getSequenceFeatures(),
544 derived.getSequenceFeatures());
547 * verify we have primary db refs *just* for PDB IDs with associated
551 assertEquals(primRefs, sq.getPrimaryDBRefs());
552 assertEquals(primRefs, sq.getDatasetSequence().getPrimaryDBRefs());
554 assertEquals(sq.getPrimaryDBRefs(), derived.getPrimaryDBRefs());
559 * Test for deriveSequence applied to an ungapped sequence with no dataset
561 @Test(groups = { "Functional" })
562 public void testDeriveSequence_noDatasetUngapped()
564 SequenceI sq = new Sequence("Seq1", "ABCDEF");
565 assertEquals(1, sq.getStart());
566 assertEquals(6, sq.getEnd());
567 SequenceI derived = sq.deriveSequence();
568 assertEquals("ABCDEF", derived.getSequenceAsString());
569 assertEquals("ABCDEF", derived.getDatasetSequence()
570 .getSequenceAsString());
574 * Test for deriveSequence applied to a gapped sequence with no dataset
576 @Test(groups = { "Functional" })
577 public void testDeriveSequence_noDatasetGapped()
579 SequenceI sq = new Sequence("Seq1", "AB-C.D EF");
580 assertEquals(1, sq.getStart());
581 assertEquals(6, sq.getEnd());
582 assertNull(sq.getDatasetSequence());
583 SequenceI derived = sq.deriveSequence();
584 assertEquals("AB-C.D EF", derived.getSequenceAsString());
585 assertEquals("ABCDEF", derived.getDatasetSequence()
586 .getSequenceAsString());
589 @Test(groups = { "Functional" })
590 public void testCopyConstructor_noDataset()
592 SequenceI seq1 = new Sequence("Seq1", "AB-C.D EF");
593 seq1.setDescription("description");
594 seq1.addAlignmentAnnotation(new AlignmentAnnotation("label", "desc",
596 seq1.addSequenceFeature(new SequenceFeature("type", "desc", 22, 33,
598 seq1.addPDBId(new PDBEntry("1A70", "B", Type.PDB, "File"));
599 seq1.addDBRef(new DBRefEntry("EMBL", "1.2", "AZ12345"));
601 SequenceI copy = new Sequence(seq1);
603 assertNull(copy.getDatasetSequence());
605 verifyCopiedSequence(seq1, copy);
607 // copy has a copy of the DBRefEntry
608 // this is murky - DBrefs are only copied for dataset sequences
609 // where the test for 'dataset sequence' is 'dataset is null'
610 // but that doesn't distinguish it from an aligned sequence
611 // which has not yet generated a dataset sequence
612 // NB getDBRef looks inside dataset sequence if not null
613 DBRefEntry[] dbrefs = copy.getDBRefs();
614 assertEquals(1, dbrefs.length);
615 assertFalse(dbrefs[0] == seq1.getDBRefs()[0]);
616 assertTrue(dbrefs[0].equals(seq1.getDBRefs()[0]));
619 @Test(groups = { "Functional" })
620 public void testCopyConstructor_withDataset()
622 SequenceI seq1 = new Sequence("Seq1", "AB-C.D EF");
623 seq1.createDatasetSequence();
624 seq1.setDescription("description");
625 seq1.addAlignmentAnnotation(new AlignmentAnnotation("label", "desc",
627 // JAL-2046 - what is the contract for using a derived sequence's
628 // addSequenceFeature ?
629 seq1.addSequenceFeature(new SequenceFeature("type", "desc", 22, 33,
631 seq1.addPDBId(new PDBEntry("1A70", "B", Type.PDB, "File"));
632 // here we add DBRef to the dataset sequence:
633 seq1.getDatasetSequence().addDBRef(
634 new DBRefEntry("EMBL", "1.2", "AZ12345"));
636 SequenceI copy = new Sequence(seq1);
638 assertNotNull(copy.getDatasetSequence());
639 assertSame(copy.getDatasetSequence(), seq1.getDatasetSequence());
641 verifyCopiedSequence(seq1, copy);
643 // getDBRef looks inside dataset sequence and this is shared,
644 // so holds the same dbref objects
645 DBRefEntry[] dbrefs = copy.getDBRefs();
646 assertEquals(1, dbrefs.length);
647 assertSame(dbrefs[0], seq1.getDBRefs()[0]);
651 * Helper to make assertions about a copied sequence
656 protected void verifyCopiedSequence(SequenceI seq1, SequenceI copy)
658 // verify basic properties:
659 assertEquals(copy.getName(), seq1.getName());
660 assertEquals(copy.getDescription(), seq1.getDescription());
661 assertEquals(copy.getStart(), seq1.getStart());
662 assertEquals(copy.getEnd(), seq1.getEnd());
663 assertEquals(copy.getSequenceAsString(), seq1.getSequenceAsString());
665 // copy has a copy of the annotation:
666 AlignmentAnnotation[] anns = copy.getAnnotation();
667 assertEquals(1, anns.length);
668 assertFalse(anns[0] == seq1.getAnnotation()[0]);
669 assertEquals(anns[0].label, seq1.getAnnotation()[0].label);
670 assertEquals(anns[0].description, seq1.getAnnotation()[0].description);
671 assertEquals(anns[0].score, seq1.getAnnotation()[0].score);
673 // copy has a copy of the sequence feature:
674 SequenceFeature[] sfs = copy.getSequenceFeatures();
675 assertEquals(1, sfs.length);
676 if (seq1.getDatasetSequence() != null
677 && copy.getDatasetSequence() == seq1.getDatasetSequence())
679 assertTrue(sfs[0] == seq1.getSequenceFeatures()[0]);
683 assertFalse(sfs[0] == seq1.getSequenceFeatures()[0]);
685 assertTrue(sfs[0].equals(seq1.getSequenceFeatures()[0]));
687 // copy has a copy of the PDB entry
688 Vector<PDBEntry> pdbs = copy.getAllPDBEntries();
689 assertEquals(1, pdbs.size());
690 assertFalse(pdbs.get(0) == seq1.getAllPDBEntries().get(0));
691 assertTrue(pdbs.get(0).equals(seq1.getAllPDBEntries().get(0)));
694 @Test(groups = "Functional")
695 public void testGetCharAt()
697 SequenceI sq = new Sequence("", "abcde");
698 assertEquals('a', sq.getCharAt(0));
699 assertEquals('e', sq.getCharAt(4));
700 assertEquals(' ', sq.getCharAt(5));
701 assertEquals(' ', sq.getCharAt(-1));
705 * Tests for adding (or updating) dbrefs
707 * @see DBRefEntry#updateFrom(DBRefEntry)
709 @Test(groups = { "Functional" })
710 public void testAddDBRef()
712 SequenceI sq = new Sequence("", "abcde");
713 assertNull(sq.getDBRefs());
714 DBRefEntry dbref = new DBRefEntry("Uniprot", "1", "P00340");
716 assertEquals(1, sq.getDBRefs().length);
717 assertSame(dbref, sq.getDBRefs()[0]);
720 * change of version - new entry
722 DBRefEntry dbref2 = new DBRefEntry("Uniprot", "2", "P00340");
724 assertEquals(2, sq.getDBRefs().length);
725 assertSame(dbref, sq.getDBRefs()[0]);
726 assertSame(dbref2, sq.getDBRefs()[1]);
729 * matches existing entry - not added
731 sq.addDBRef(new DBRefEntry("UNIPROT", "1", "p00340"));
732 assertEquals(2, sq.getDBRefs().length);
735 * different source = new entry
737 DBRefEntry dbref3 = new DBRefEntry("UniRef", "1", "p00340");
739 assertEquals(3, sq.getDBRefs().length);
740 assertSame(dbref3, sq.getDBRefs()[2]);
743 * different ref = new entry
745 DBRefEntry dbref4 = new DBRefEntry("UniRef", "1", "p00341");
747 assertEquals(4, sq.getDBRefs().length);
748 assertSame(dbref4, sq.getDBRefs()[3]);
751 * matching ref with a mapping - map updated
753 DBRefEntry dbref5 = new DBRefEntry("UniRef", "1", "p00341");
754 Mapping map = new Mapping(new MapList(new int[] { 1, 3 }, new int[] {
758 assertEquals(4, sq.getDBRefs().length);
759 assertSame(dbref4, sq.getDBRefs()[3]);
760 assertSame(map, dbref4.getMap());
763 * 'real' version replaces "0" version
765 dbref2.setVersion("0");
766 DBRefEntry dbref6 = new DBRefEntry(dbref2.getSource(), "3",
767 dbref2.getAccessionId());
769 assertEquals(4, sq.getDBRefs().length);
770 assertSame(dbref2, sq.getDBRefs()[1]);
771 assertEquals("3", dbref2.getVersion());
774 * 'real' version replaces "source:0" version
776 dbref3.setVersion("Uniprot:0");
777 DBRefEntry dbref7 = new DBRefEntry(dbref3.getSource(), "3",
778 dbref3.getAccessionId());
780 assertEquals(4, sq.getDBRefs().length);
781 assertSame(dbref3, sq.getDBRefs()[2]);
782 assertEquals("3", dbref2.getVersion());
785 @Test(groups = { "Functional" })
786 public void testGetPrimaryDBRefs_peptide()
788 SequenceI sq = new Sequence("aseq", "ASDFKYLMQPRST", 10, 22);
791 List<DBRefEntry> primaryDBRefs = sq.getPrimaryDBRefs();
792 assertTrue(primaryDBRefs.isEmpty());
795 sq.setDBRefs(new DBRefEntry[] {});
796 primaryDBRefs = sq.getPrimaryDBRefs();
797 assertTrue(primaryDBRefs.isEmpty());
800 DBRefEntry upentry1 = new DBRefEntry("UNIPROT", "0", "Q04760");
801 sq.addDBRef(upentry1);
803 // primary - uniprot with congruent map
804 DBRefEntry upentry2 = new DBRefEntry("UNIPROT", "0", "Q04762");
805 upentry2.setMap(new Mapping(null, new MapList(new int[] { 10, 22 },
806 new int[] { 10, 22 }, 1, 1)));
807 sq.addDBRef(upentry2);
809 // primary - uniprot with map of enclosing sequence
810 DBRefEntry upentry3 = new DBRefEntry("UNIPROT", "0", "Q04763");
811 upentry3.setMap(new Mapping(null, new MapList(new int[] { 8, 24 },
812 new int[] { 8, 24 }, 1, 1)));
813 sq.addDBRef(upentry3);
815 // not primary - uniprot with map of sub-sequence (5')
816 DBRefEntry upentry4 = new DBRefEntry("UNIPROT", "0", "Q04764");
817 upentry4.setMap(new Mapping(null, new MapList(new int[] { 10, 18 },
818 new int[] { 10, 18 }, 1, 1)));
819 sq.addDBRef(upentry4);
821 // not primary - uniprot with map that overlaps 3'
822 DBRefEntry upentry5 = new DBRefEntry("UNIPROT", "0", "Q04765");
823 upentry5.setMap(new Mapping(null, new MapList(new int[] { 12, 22 },
824 new int[] { 12, 22 }, 1, 1)));
825 sq.addDBRef(upentry5);
827 // not primary - uniprot with map to different coordinates frame
828 DBRefEntry upentry6 = new DBRefEntry("UNIPROT", "0", "Q04766");
829 upentry6.setMap(new Mapping(null, new MapList(new int[] { 12, 18 },
830 new int[] { 112, 118 }, 1, 1)));
831 sq.addDBRef(upentry6);
833 // not primary - dbref to 'non-core' database
834 DBRefEntry upentry7 = new DBRefEntry("Pfam", "0", "PF00903");
835 sq.addDBRef(upentry7);
837 // primary - type is PDB
838 DBRefEntry pdbentry = new DBRefEntry("PDB", "0", "1qip");
839 sq.addDBRef(pdbentry);
841 // not primary - PDBEntry has no file
842 sq.addDBRef(new DBRefEntry("PDB", "0", "1AAA"));
844 // not primary - no PDBEntry
845 sq.addDBRef(new DBRefEntry("PDB", "0", "1DDD"));
847 // add corroborating PDB entry for primary DBref -
848 // needs to have a file as well as matching ID
849 // note PDB ID is not treated as case sensitive
850 sq.addPDBId(new PDBEntry("1QIP", null, Type.PDB, new File("/blah")
853 // not valid DBRef - no file..
854 sq.addPDBId(new PDBEntry("1AAA", null, null, null));
856 primaryDBRefs = sq.getPrimaryDBRefs();
857 assertEquals(4, primaryDBRefs.size());
858 assertTrue("Couldn't find simple primary reference (UNIPROT)",
859 primaryDBRefs.contains(upentry1));
860 assertTrue("Couldn't find mapped primary reference (UNIPROT)",
861 primaryDBRefs.contains(upentry2));
862 assertTrue("Couldn't find mapped context reference (UNIPROT)",
863 primaryDBRefs.contains(upentry3));
864 assertTrue("Couldn't find expected PDB primary reference",
865 primaryDBRefs.contains(pdbentry));
868 @Test(groups = { "Functional" })
869 public void testGetPrimaryDBRefs_nucleotide()
871 SequenceI sq = new Sequence("aseq", "TGATCACTCGACTAGCATCAGCATA", 10, 34);
874 DBRefEntry dbr1 = new DBRefEntry("ENSEMBL", "0", "ENSG1234");
877 // not primary - Ensembl 'transcript' mapping of sub-sequence
878 DBRefEntry dbr2 = new DBRefEntry("ENSEMBL", "0", "ENST1234");
879 dbr2.setMap(new Mapping(null, new MapList(new int[] { 15, 25 },
880 new int[] { 1, 11 }, 1, 1)));
883 // primary - EMBL with congruent map
884 DBRefEntry dbr3 = new DBRefEntry("EMBL", "0", "J1234");
885 dbr3.setMap(new Mapping(null, new MapList(new int[] { 10, 34 },
886 new int[] { 10, 34 }, 1, 1)));
889 // not primary - to non-core database
890 DBRefEntry dbr4 = new DBRefEntry("CCDS", "0", "J1234");
893 // not primary - to protein
894 DBRefEntry dbr5 = new DBRefEntry("UNIPROT", "0", "Q87654");
897 List<DBRefEntry> primaryDBRefs = sq.getPrimaryDBRefs();
898 assertEquals(2, primaryDBRefs.size());
899 assertTrue(primaryDBRefs.contains(dbr1));
900 assertTrue(primaryDBRefs.contains(dbr3));
904 * Test the method that updates the list of PDBEntry from any new DBRefEntry
907 @Test(groups = { "Functional" })
908 public void testUpdatePDBIds()
910 PDBEntry pdbe1 = new PDBEntry("3A6S", null, null, null);
912 seq.addDBRef(new DBRefEntry("Ensembl", "8", "ENST1234"));
913 seq.addDBRef(new DBRefEntry("PDB", "0", "1A70"));
914 seq.addDBRef(new DBRefEntry("PDB", "0", "4BQGa"));
915 seq.addDBRef(new DBRefEntry("PDB", "0", "3a6sB"));
916 // 7 is not a valid chain code:
917 seq.addDBRef(new DBRefEntry("PDB", "0", "2GIS7"));
920 List<PDBEntry> pdbIds = seq.getAllPDBEntries();
921 assertEquals(4, pdbIds.size());
922 assertSame(pdbe1, pdbIds.get(0));
923 // chain code got added to 3A6S:
924 assertEquals("B", pdbe1.getChainCode());
925 assertEquals("1A70", pdbIds.get(1).getId());
926 // 4BQGA is parsed into id + chain
927 assertEquals("4BQG", pdbIds.get(2).getId());
928 assertEquals("a", pdbIds.get(2).getChainCode());
929 assertEquals("2GIS7", pdbIds.get(3).getId());
930 assertNull(pdbIds.get(3).getChainCode());
934 * Test the method that either adds a pdbid or updates an existing one
936 @Test(groups = { "Functional" })
937 public void testAddPDBId()
939 PDBEntry pdbe = new PDBEntry("3A6S", null, null, null);
941 assertEquals(1, seq.getAllPDBEntries().size());
942 assertSame(pdbe, seq.getPDBEntry("3A6S"));
943 assertSame(pdbe, seq.getPDBEntry("3a6s")); // case-insensitive
945 // add the same entry
947 assertEquals(1, seq.getAllPDBEntries().size());
948 assertSame(pdbe, seq.getPDBEntry("3A6S"));
950 // add an identical entry
951 seq.addPDBId(new PDBEntry("3A6S", null, null, null));
952 assertEquals(1, seq.getAllPDBEntries().size());
953 assertSame(pdbe, seq.getPDBEntry("3A6S"));
955 // add a different entry
956 PDBEntry pdbe2 = new PDBEntry("1A70", null, null, null);
958 assertEquals(2, seq.getAllPDBEntries().size());
959 assertSame(pdbe, seq.getAllPDBEntries().get(0));
960 assertSame(pdbe2, seq.getAllPDBEntries().get(1));
962 // update pdbe with chain code, file, type
963 PDBEntry pdbe3 = new PDBEntry("3a6s", "A", Type.PDB, "filepath");
965 assertEquals(2, seq.getAllPDBEntries().size());
966 assertSame(pdbe, seq.getAllPDBEntries().get(0)); // updated in situ
967 assertEquals("3A6S", pdbe.getId()); // unchanged
968 assertEquals("A", pdbe.getChainCode()); // updated
969 assertEquals(Type.PDB.toString(), pdbe.getType()); // updated
970 assertEquals("filepath", pdbe.getFile()); // updated
971 assertSame(pdbe2, seq.getAllPDBEntries().get(1));
973 // add with a different file path
974 PDBEntry pdbe4 = new PDBEntry("3a6s", "A", Type.PDB, "filepath2");
976 assertEquals(3, seq.getAllPDBEntries().size());
977 assertSame(pdbe4, seq.getAllPDBEntries().get(2));
979 // add with a different chain code
980 PDBEntry pdbe5 = new PDBEntry("3a6s", "B", Type.PDB, "filepath");
982 assertEquals(4, seq.getAllPDBEntries().size());
983 assertSame(pdbe5, seq.getAllPDBEntries().get(3));
987 groups = { "Functional" },
988 expectedExceptions = { IllegalArgumentException.class })
989 public void testSetDatasetSequence_toSelf()
991 seq.setDatasetSequence(seq);
995 groups = { "Functional" },
996 expectedExceptions = { IllegalArgumentException.class })
997 public void testSetDatasetSequence_cascading()
999 SequenceI seq2 = new Sequence("Seq2", "xyz");
1000 seq2.createDatasetSequence();
1001 seq.setDatasetSequence(seq2);