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]);
341 * SequenceFeature on sequence and dataset sequence; returns that on
344 * Note JAL-2046: spurious: we have no use case for this at the moment.
345 * This test also buggy - as sf2.equals(sf), no new feature is added
347 SequenceFeature sf2 = new SequenceFeature();
348 sq.getDatasetSequence().addSequenceFeature(sf2);
349 sfs = sq.getSequenceFeatures();
350 assertEquals(1, sfs.length);
351 assertSame(sf, sfs[0]);
354 * SequenceFeature on dataset sequence only
355 * Note JAL-2046: spurious: we have no use case for setting a non-dataset sequence's feature array to null at the moment.
357 sq.setSequenceFeatures(null);
358 assertNull(sq.getDatasetSequence().getSequenceFeatures());
361 * Corrupt case - no SequenceFeature, dataset's dataset is the original
362 * sequence. Test shows no infinite loop results.
364 sq.getDatasetSequence().setSequenceFeatures(null);
366 * is there a usecase for this ? setDatasetSequence should throw an error if
367 * this actually occurs.
371 sq.getDatasetSequence().setDatasetSequence(sq); // loop!
372 Assert.fail("Expected Error to be raised when calling setDatasetSequence with self reference");
373 } catch (IllegalArgumentException e)
375 // TODO Jalview error/exception class for raising implementation errors
376 assertTrue(e.getMessage().toLowerCase()
377 .contains("implementation error"));
379 assertNull(sq.getSequenceFeatures());
383 * Test the method that returns an array, indexed by sequence position, whose
384 * entries are the residue positions at the sequence position (or to the right
387 @Test(groups = { "Functional" })
388 public void testFindPositionMap()
391 * Note: Javadoc for findPosition says it returns the residue position to
392 * the left of a gapped position; in fact it returns the position to the
393 * right. Also it returns a non-existent residue position for a gap beyond
396 Sequence sq = new Sequence("TestSeq", "AB.C-D E.");
397 int[] map = sq.findPositionMap();
398 assertEquals(Arrays.toString(new int[] { 1, 2, 3, 3, 4, 4, 5, 5, 6 }),
399 Arrays.toString(map));
403 * Test for getSubsequence
405 @Test(groups = { "Functional" })
406 public void testGetSubsequence()
408 SequenceI sq = new Sequence("TestSeq", "ABCDEFG");
409 sq.createDatasetSequence();
411 // positions are base 0, end position is exclusive
412 SequenceI subseq = sq.getSubSequence(2, 4);
414 assertEquals("CD", subseq.getSequenceAsString());
415 // start/end are base 1 positions
416 assertEquals(3, subseq.getStart());
417 assertEquals(4, subseq.getEnd());
418 // subsequence shares the full dataset sequence
419 assertSame(sq.getDatasetSequence(), subseq.getDatasetSequence());
423 * test createDatasetSequence behaves to doc
425 @Test(groups = { "Functional" })
426 public void testCreateDatasetSequence()
428 SequenceI sq = new Sequence("my","ASDASD");
429 assertNull(sq.getDatasetSequence());
430 SequenceI rds = sq.createDatasetSequence();
432 assertNull(rds.getDatasetSequence());
433 assertEquals(sq.getDatasetSequence(), rds);
437 * Test for deriveSequence applied to a sequence with a dataset
439 @Test(groups = { "Functional" })
440 public void testDeriveSequence_existingDataset()
442 Sequence sq = new Sequence("Seq1", "CD");
443 sq.setDatasetSequence(new Sequence("Seq1", "ABCDEF"));
444 sq.getDatasetSequence().addSequenceFeature(
445 new SequenceFeature("", "", 1, 2, 0f, null));
449 sq.setDescription("Test sequence description..");
450 sq.setVamsasId("TestVamsasId");
451 sq.addDBRef(new DBRefEntry("PDB", "version0", "1TST"));
453 sq.addDBRef(new DBRefEntry("PDB", "version1", "1PDB"));
454 sq.addDBRef(new DBRefEntry("PDB", "version2", "2PDB"));
455 sq.addDBRef(new DBRefEntry("PDB", "version3", "3PDB"));
456 sq.addDBRef(new DBRefEntry("PDB", "version4", "4PDB"));
458 sq.addPDBId(new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1"));
459 sq.addPDBId(new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1"));
460 sq.addPDBId(new PDBEntry("2PDB", "A", Type.MMCIF, "filePath/test2"));
461 sq.addPDBId(new PDBEntry("2PDB", "B", Type.MMCIF, "filePath/test2"));
463 // these are the same as ones already added
464 DBRefEntry pdb1pdb = new DBRefEntry("PDB", "version1", "1PDB");
465 DBRefEntry pdb2pdb = new DBRefEntry("PDB", "version2", "2PDB");
468 List<DBRefEntry> primRefs = Arrays.asList(new DBRefEntry[] { pdb1pdb,
471 sq.getDatasetSequence().addDBRef(pdb1pdb); // should do nothing
472 sq.getDatasetSequence().addDBRef(pdb2pdb); // should do nothing
473 sq.getDatasetSequence().addDBRef(
474 new DBRefEntry("PDB", "version3", "3PDB")); // should do nothing
475 sq.getDatasetSequence().addDBRef(
476 new DBRefEntry("PDB", "version4", "4PDB")); // should do nothing
478 PDBEntry pdbe1a=new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1");
479 PDBEntry pdbe1b = new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1");
480 PDBEntry pdbe2a=new PDBEntry("2PDB", "A", Type.MMCIF, "filePath/test2");
481 PDBEntry pdbe2b = new PDBEntry("2PDB", "B", Type.MMCIF, "filePath/test2");
482 sq.getDatasetSequence().addPDBId(
484 sq.getDatasetSequence().addPDBId(
486 sq.getDatasetSequence().addPDBId(pdbe2a);
487 sq.getDatasetSequence().addPDBId(pdbe2b);
490 * test we added pdb entries to the dataset sequence
492 Assert.assertEquals(sq.getDatasetSequence().getAllPDBEntries(), Arrays
493 .asList(new PDBEntry[] { pdbe1a, pdbe1b, pdbe2a, pdbe2b }),
494 "PDB Entries were not found on dataset sequence.");
497 * we should recover a pdb entry that is on the dataset sequence via PDBEntry
499 Assert.assertEquals(pdbe1a,
500 sq.getDatasetSequence().getPDBEntry("1PDB"),
501 "PDB Entry '1PDB' not found on dataset sequence via getPDBEntry.");
502 ArrayList<Annotation> annotsList = new ArrayList<Annotation>();
503 System.out.println(">>>>>> " + sq.getSequenceAsString().length());
504 annotsList.add(new Annotation("A", "A", 'X', 0.1f));
505 annotsList.add(new Annotation("A", "A", 'X', 0.1f));
506 Annotation[] annots = annotsList.toArray(new Annotation[0]);
507 sq.addAlignmentAnnotation(new AlignmentAnnotation("Test annot",
508 "Test annot description", annots));
509 sq.getDatasetSequence().addAlignmentAnnotation(
510 new AlignmentAnnotation("Test annot", "Test annot description",
512 Assert.assertEquals(sq.getDescription(), "Test sequence description..");
513 Assert.assertEquals(sq.getDBRefs().length, 5); // DBRefs are on dataset
515 Assert.assertEquals(sq.getAllPDBEntries().size(), 4);
516 Assert.assertNotNull(sq.getAnnotation());
517 Assert.assertEquals(sq.getAnnotation()[0].annotations.length, 2);
518 Assert.assertEquals(sq.getDatasetSequence().getDBRefs().length, 5); // same
521 Assert.assertEquals(sq.getDatasetSequence().getAllPDBEntries().size(),
523 Assert.assertNotNull(sq.getDatasetSequence().getAnnotation());
525 Sequence derived = (Sequence) sq.deriveSequence();
527 Assert.assertEquals(derived.getDescription(),
528 "Test sequence description..");
529 Assert.assertEquals(derived.getDBRefs().length, 5); // come from dataset
530 Assert.assertEquals(derived.getAllPDBEntries().size(), 4);
531 Assert.assertNotNull(derived.getAnnotation());
532 Assert.assertEquals(derived.getAnnotation()[0].annotations.length, 2);
533 Assert.assertEquals(derived.getDatasetSequence().getDBRefs().length, 5);
534 Assert.assertEquals(derived.getDatasetSequence().getAllPDBEntries()
536 Assert.assertNotNull(derived.getDatasetSequence().getAnnotation());
538 assertEquals("CD", derived.getSequenceAsString());
539 assertSame(sq.getDatasetSequence(), derived.getDatasetSequence());
541 assertNull(sq.sequenceFeatures);
542 assertNull(derived.sequenceFeatures);
543 // derived sequence should access dataset sequence features
544 assertNotNull(sq.getSequenceFeatures());
545 assertArrayEquals(sq.getSequenceFeatures(),
546 derived.getSequenceFeatures());
549 * verify we have primary db refs *just* for PDB IDs with associated
553 assertEquals(primRefs, sq.getPrimaryDBRefs());
554 assertEquals(primRefs, sq.getDatasetSequence().getPrimaryDBRefs());
556 assertEquals(sq.getPrimaryDBRefs(), derived.getPrimaryDBRefs());
561 * Test for deriveSequence applied to an ungapped sequence with no dataset
563 @Test(groups = { "Functional" })
564 public void testDeriveSequence_noDatasetUngapped()
566 SequenceI sq = new Sequence("Seq1", "ABCDEF");
567 assertEquals(1, sq.getStart());
568 assertEquals(6, sq.getEnd());
569 SequenceI derived = sq.deriveSequence();
570 assertEquals("ABCDEF", derived.getSequenceAsString());
571 assertEquals("ABCDEF", derived.getDatasetSequence()
572 .getSequenceAsString());
576 * Test for deriveSequence applied to a gapped sequence with no dataset
578 @Test(groups = { "Functional" })
579 public void testDeriveSequence_noDatasetGapped()
581 SequenceI sq = new Sequence("Seq1", "AB-C.D EF");
582 assertEquals(1, sq.getStart());
583 assertEquals(6, sq.getEnd());
584 assertNull(sq.getDatasetSequence());
585 SequenceI derived = sq.deriveSequence();
586 assertEquals("AB-C.D EF", derived.getSequenceAsString());
587 assertEquals("ABCDEF", derived.getDatasetSequence()
588 .getSequenceAsString());
591 @Test(groups = { "Functional" })
592 public void testCopyConstructor_noDataset()
594 SequenceI seq1 = new Sequence("Seq1", "AB-C.D EF");
595 seq1.setDescription("description");
596 seq1.addAlignmentAnnotation(new AlignmentAnnotation("label", "desc",
598 seq1.addSequenceFeature(new SequenceFeature("type", "desc", 22, 33,
600 seq1.addPDBId(new PDBEntry("1A70", "B", Type.PDB, "File"));
601 seq1.addDBRef(new DBRefEntry("EMBL", "1.2", "AZ12345"));
603 SequenceI copy = new Sequence(seq1);
605 assertNull(copy.getDatasetSequence());
607 verifyCopiedSequence(seq1, copy);
609 // copy has a copy of the DBRefEntry
610 // this is murky - DBrefs are only copied for dataset sequences
611 // where the test for 'dataset sequence' is 'dataset is null'
612 // but that doesn't distinguish it from an aligned sequence
613 // which has not yet generated a dataset sequence
614 // NB getDBRef looks inside dataset sequence if not null
615 DBRefEntry[] dbrefs = copy.getDBRefs();
616 assertEquals(1, dbrefs.length);
617 assertFalse(dbrefs[0] == seq1.getDBRefs()[0]);
618 assertTrue(dbrefs[0].equals(seq1.getDBRefs()[0]));
621 @Test(groups = { "Functional" })
622 public void testCopyConstructor_withDataset()
624 SequenceI seq1 = new Sequence("Seq1", "AB-C.D EF");
625 seq1.createDatasetSequence();
626 seq1.setDescription("description");
627 seq1.addAlignmentAnnotation(new AlignmentAnnotation("label", "desc",
629 // JAL-2046 - what is the contract for using a derived sequence's
630 // addSequenceFeature ?
631 seq1.addSequenceFeature(new SequenceFeature("type", "desc", 22, 33,
633 seq1.addPDBId(new PDBEntry("1A70", "B", Type.PDB, "File"));
634 // here we add DBRef to the dataset sequence:
635 seq1.getDatasetSequence().addDBRef(
636 new DBRefEntry("EMBL", "1.2", "AZ12345"));
638 SequenceI copy = new Sequence(seq1);
640 assertNotNull(copy.getDatasetSequence());
641 assertSame(copy.getDatasetSequence(), seq1.getDatasetSequence());
643 verifyCopiedSequence(seq1, copy);
645 // getDBRef looks inside dataset sequence and this is shared,
646 // so holds the same dbref objects
647 DBRefEntry[] dbrefs = copy.getDBRefs();
648 assertEquals(1, dbrefs.length);
649 assertSame(dbrefs[0], seq1.getDBRefs()[0]);
653 * Helper to make assertions about a copied sequence
658 protected void verifyCopiedSequence(SequenceI seq1, SequenceI copy)
660 // verify basic properties:
661 assertEquals(copy.getName(), seq1.getName());
662 assertEquals(copy.getDescription(), seq1.getDescription());
663 assertEquals(copy.getStart(), seq1.getStart());
664 assertEquals(copy.getEnd(), seq1.getEnd());
665 assertEquals(copy.getSequenceAsString(), seq1.getSequenceAsString());
667 // copy has a copy of the annotation:
668 AlignmentAnnotation[] anns = copy.getAnnotation();
669 assertEquals(1, anns.length);
670 assertFalse(anns[0] == seq1.getAnnotation()[0]);
671 assertEquals(anns[0].label, seq1.getAnnotation()[0].label);
672 assertEquals(anns[0].description, seq1.getAnnotation()[0].description);
673 assertEquals(anns[0].score, seq1.getAnnotation()[0].score);
675 // copy has a copy of the sequence feature:
676 SequenceFeature[] sfs = copy.getSequenceFeatures();
677 assertEquals(1, sfs.length);
678 if (seq1.getDatasetSequence()!=null && copy.getDatasetSequence()==seq1.getDatasetSequence()) {
679 assertTrue(sfs[0] == seq1.getSequenceFeatures()[0]);
681 assertFalse(sfs[0] == seq1.getSequenceFeatures()[0]);
683 assertTrue(sfs[0].equals(seq1.getSequenceFeatures()[0]));
685 // copy has a copy of the PDB entry
686 Vector<PDBEntry> pdbs = copy.getAllPDBEntries();
687 assertEquals(1, pdbs.size());
688 assertFalse(pdbs.get(0) == seq1.getAllPDBEntries().get(0));
689 assertTrue(pdbs.get(0).equals(seq1.getAllPDBEntries().get(0)));
692 @Test(groups = "Functional")
693 public void testGetCharAt()
695 SequenceI sq = new Sequence("", "abcde");
696 assertEquals('a', sq.getCharAt(0));
697 assertEquals('e', sq.getCharAt(4));
698 assertEquals(' ', sq.getCharAt(5));
699 assertEquals(' ', sq.getCharAt(-1));
703 * Tests for adding (or updating) dbrefs
705 * @see DBRefEntry#updateFrom(DBRefEntry)
707 @Test(groups = { "Functional" })
708 public void testAddDBRef()
710 SequenceI sq = new Sequence("", "abcde");
711 assertNull(sq.getDBRefs());
712 DBRefEntry dbref = new DBRefEntry("Uniprot", "1", "P00340");
714 assertEquals(1, sq.getDBRefs().length);
715 assertSame(dbref, sq.getDBRefs()[0]);
718 * change of version - new entry
720 DBRefEntry dbref2 = new DBRefEntry("Uniprot", "2", "P00340");
722 assertEquals(2, sq.getDBRefs().length);
723 assertSame(dbref, sq.getDBRefs()[0]);
724 assertSame(dbref2, sq.getDBRefs()[1]);
727 * matches existing entry - not added
729 sq.addDBRef(new DBRefEntry("UNIPROT", "1", "p00340"));
730 assertEquals(2, sq.getDBRefs().length);
733 * different source = new entry
735 DBRefEntry dbref3 = new DBRefEntry("UniRef", "1", "p00340");
737 assertEquals(3, sq.getDBRefs().length);
738 assertSame(dbref3, sq.getDBRefs()[2]);
741 * different ref = new entry
743 DBRefEntry dbref4 = new DBRefEntry("UniRef", "1", "p00341");
745 assertEquals(4, sq.getDBRefs().length);
746 assertSame(dbref4, sq.getDBRefs()[3]);
749 * matching ref with a mapping - map updated
751 DBRefEntry dbref5 = new DBRefEntry("UniRef", "1", "p00341");
752 Mapping map = new Mapping(new MapList(new int[] { 1, 3 }, new int[] {
756 assertEquals(4, sq.getDBRefs().length);
757 assertSame(dbref4, sq.getDBRefs()[3]);
758 assertSame(map, dbref4.getMap());
761 * 'real' version replaces "0" version
763 dbref2.setVersion("0");
764 DBRefEntry dbref6 = new DBRefEntry(dbref2.getSource(), "3",
765 dbref2.getAccessionId());
767 assertEquals(4, sq.getDBRefs().length);
768 assertSame(dbref2, sq.getDBRefs()[1]);
769 assertEquals("3", dbref2.getVersion());
772 * 'real' version replaces "source:0" version
774 dbref3.setVersion("Uniprot:0");
775 DBRefEntry dbref7 = new DBRefEntry(dbref3.getSource(), "3",
776 dbref3.getAccessionId());
778 assertEquals(4, sq.getDBRefs().length);
779 assertSame(dbref3, sq.getDBRefs()[2]);
780 assertEquals("3", dbref2.getVersion());
783 @Test(groups = { "Functional" })
784 public void testGetPrimaryDBRefs_peptide()
786 SequenceI sq = new Sequence("aseq", "ASDFKYLMQPRST", 10, 22);
789 List<DBRefEntry> primaryDBRefs = sq.getPrimaryDBRefs();
790 assertTrue(primaryDBRefs.isEmpty());
793 sq.setDBRefs(new DBRefEntry[] {});
794 primaryDBRefs = sq.getPrimaryDBRefs();
795 assertTrue(primaryDBRefs.isEmpty());
798 DBRefEntry upentry1 = new DBRefEntry("UNIPROT", "0", "Q04760");
799 sq.addDBRef(upentry1);
801 // primary - uniprot with congruent map
802 DBRefEntry upentry2 = new DBRefEntry("UNIPROT", "0", "Q04762");
803 upentry2.setMap(new Mapping(null, new MapList(new int[] { 10, 22 },
804 new int[] { 10, 22 }, 1, 1)));
805 sq.addDBRef(upentry2);
807 // primary - uniprot with map of enclosing sequence
808 DBRefEntry upentry3 = new DBRefEntry("UNIPROT", "0", "Q04763");
809 upentry3.setMap(new Mapping(null, new MapList(new int[] { 8, 24 },
810 new int[] { 8, 24 }, 1, 1)));
811 sq.addDBRef(upentry3);
813 // not primary - uniprot with map of sub-sequence (5')
814 DBRefEntry upentry4 = new DBRefEntry("UNIPROT", "0", "Q04764");
815 upentry4.setMap(new Mapping(null, new MapList(new int[] { 10, 18 },
816 new int[] { 10, 18 }, 1, 1)));
817 sq.addDBRef(upentry4);
819 // not primary - uniprot with map that overlaps 3'
820 DBRefEntry upentry5 = new DBRefEntry("UNIPROT", "0", "Q04765");
821 upentry5.setMap(new Mapping(null, new MapList(new int[] { 12, 22 },
822 new int[] { 12, 22 }, 1, 1)));
823 sq.addDBRef(upentry5);
825 // not primary - uniprot with map to different coordinates frame
826 DBRefEntry upentry6 = new DBRefEntry("UNIPROT", "0", "Q04766");
827 upentry6.setMap(new Mapping(null, new MapList(new int[] { 12, 18 },
828 new int[] { 112, 118 }, 1, 1)));
829 sq.addDBRef(upentry6);
831 // not primary - dbref to 'non-core' database
832 DBRefEntry upentry7 = new DBRefEntry("Pfam", "0", "PF00903");
833 sq.addDBRef(upentry7);
835 // primary - type is PDB
836 DBRefEntry pdbentry = new DBRefEntry("PDB", "0", "1qip");
837 sq.addDBRef(pdbentry);
839 // not primary - PDBEntry has no file
840 sq.addDBRef(new DBRefEntry("PDB", "0", "1AAA"));
842 // not primary - no PDBEntry
843 sq.addDBRef(new DBRefEntry("PDB", "0", "1DDD"));
845 // add corroborating PDB entry for primary DBref -
846 // needs to have a file as well as matching ID
847 // note PDB ID is not treated as case sensitive
848 sq.addPDBId(new PDBEntry("1QIP", null, Type.PDB, new File("/blah")
851 // not valid DBRef - no file..
852 sq.addPDBId(new PDBEntry("1AAA", null, null, null));
854 primaryDBRefs = sq.getPrimaryDBRefs();
855 assertEquals(4, primaryDBRefs.size());
856 assertTrue("Couldn't find simple primary reference (UNIPROT)",
857 primaryDBRefs.contains(upentry1));
858 assertTrue("Couldn't find mapped primary reference (UNIPROT)",
859 primaryDBRefs.contains(upentry2));
860 assertTrue("Couldn't find mapped context reference (UNIPROT)",
861 primaryDBRefs.contains(upentry3));
862 assertTrue("Couldn't find expected PDB primary reference",
863 primaryDBRefs.contains(pdbentry));
866 @Test(groups = { "Functional" })
867 public void testGetPrimaryDBRefs_nucleotide()
869 SequenceI sq = new Sequence("aseq", "TGATCACTCGACTAGCATCAGCATA", 10, 34);
872 DBRefEntry dbr1 = new DBRefEntry("ENSEMBL", "0", "ENSG1234");
875 // not primary - Ensembl 'transcript' mapping of sub-sequence
876 DBRefEntry dbr2 = new DBRefEntry("ENSEMBL", "0", "ENST1234");
877 dbr2.setMap(new Mapping(null, new MapList(new int[] { 15, 25 },
878 new int[] { 1, 11 }, 1, 1)));
881 // primary - EMBL with congruent map
882 DBRefEntry dbr3 = new DBRefEntry("EMBL", "0", "J1234");
883 dbr3.setMap(new Mapping(null, new MapList(new int[] { 10, 34 },
884 new int[] { 10, 34 }, 1, 1)));
887 // not primary - to non-core database
888 DBRefEntry dbr4 = new DBRefEntry("CCDS", "0", "J1234");
891 // not primary - to protein
892 DBRefEntry dbr5 = new DBRefEntry("UNIPROT", "0", "Q87654");
895 List<DBRefEntry> primaryDBRefs = sq.getPrimaryDBRefs();
896 assertEquals(2, primaryDBRefs.size());
897 assertTrue(primaryDBRefs.contains(dbr1));
898 assertTrue(primaryDBRefs.contains(dbr3));
902 * Test the method that updates the list of PDBEntry from any new DBRefEntry
905 @Test(groups = { "Functional" })
906 public void testUpdatePDBIds()
908 PDBEntry pdbe1 = new PDBEntry("3A6S", null, null, null);
910 seq.addDBRef(new DBRefEntry("Ensembl", "8", "ENST1234"));
911 seq.addDBRef(new DBRefEntry("PDB", "0", "1A70"));
912 seq.addDBRef(new DBRefEntry("PDB", "0", "4BQGa"));
913 seq.addDBRef(new DBRefEntry("PDB", "0", "3a6sB"));
914 // 7 is not a valid chain code:
915 seq.addDBRef(new DBRefEntry("PDB", "0", "2GIS7"));
918 List<PDBEntry> pdbIds = seq.getAllPDBEntries();
919 assertEquals(4, pdbIds.size());
920 assertSame(pdbe1, pdbIds.get(0));
921 // chain code got added to 3A6S:
922 assertEquals("B", pdbe1.getChainCode());
923 assertEquals("1A70", pdbIds.get(1).getId());
924 // 4BQGA is parsed into id + chain
925 assertEquals("4BQG", pdbIds.get(2).getId());
926 assertEquals("a", pdbIds.get(2).getChainCode());
927 assertEquals("2GIS7", pdbIds.get(3).getId());
928 assertNull(pdbIds.get(3).getChainCode());
932 * Test the method that either adds a pdbid or updates an existing one
934 @Test(groups = { "Functional" })
935 public void testAddPDBId()
937 PDBEntry pdbe = new PDBEntry("3A6S", null, null, null);
939 assertEquals(1, seq.getAllPDBEntries().size());
940 assertSame(pdbe, seq.getPDBEntry("3A6S"));
941 assertSame(pdbe, seq.getPDBEntry("3a6s")); // case-insensitive
943 // add the same entry
945 assertEquals(1, seq.getAllPDBEntries().size());
946 assertSame(pdbe, seq.getPDBEntry("3A6S"));
948 // add an identical entry
949 seq.addPDBId(new PDBEntry("3A6S", null, null, null));
950 assertEquals(1, seq.getAllPDBEntries().size());
951 assertSame(pdbe, seq.getPDBEntry("3A6S"));
953 // add a different entry
954 PDBEntry pdbe2 = new PDBEntry("1A70", null, null, null);
956 assertEquals(2, seq.getAllPDBEntries().size());
957 assertSame(pdbe, seq.getAllPDBEntries().get(0));
958 assertSame(pdbe2, seq.getAllPDBEntries().get(1));
960 // update pdbe with chain code, file, type
961 PDBEntry pdbe3 = new PDBEntry("3a6s", "A", Type.PDB, "filepath");
963 assertEquals(2, seq.getAllPDBEntries().size());
964 assertSame(pdbe, seq.getAllPDBEntries().get(0)); // updated in situ
965 assertEquals("3A6S", pdbe.getId()); // unchanged
966 assertEquals("A", pdbe.getChainCode()); // updated
967 assertEquals(Type.PDB.toString(), pdbe.getType()); // updated
968 assertEquals("filepath", pdbe.getFile()); // updated
969 assertSame(pdbe2, seq.getAllPDBEntries().get(1));
971 // add with a different file path
972 PDBEntry pdbe4 = new PDBEntry("3a6s", "A", Type.PDB, "filepath2");
974 assertEquals(3, seq.getAllPDBEntries().size());
975 assertSame(pdbe4, seq.getAllPDBEntries().get(2));
977 // add with a different chain code
978 PDBEntry pdbe5 = new PDBEntry("3a6s", "B", Type.PDB, "filepath");
980 assertEquals(4, seq.getAllPDBEntries().size());
981 assertSame(pdbe5, seq.getAllPDBEntries().get(3));
985 groups = { "Functional" },
986 expectedExceptions = { IllegalArgumentException.class })
987 public void testSetDatasetSequence_toSelf()
989 seq.setDatasetSequence(seq);
993 groups = { "Functional" },
994 expectedExceptions = { IllegalArgumentException.class })
995 public void testSetDatasetSequence_cascading()
997 SequenceI seq2 = new Sequence("Seq2", "xyz");
998 seq2.createDatasetSequence();
999 seq.setDatasetSequence(seq2);