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.
369 sq.getDatasetSequence().setDatasetSequence(sq); // loop!
370 assertNull(sq.getSequenceFeatures());
374 * Test the method that returns an array, indexed by sequence position, whose
375 * entries are the residue positions at the sequence position (or to the right
378 @Test(groups = { "Functional" })
379 public void testFindPositionMap()
382 * Note: Javadoc for findPosition says it returns the residue position to
383 * the left of a gapped position; in fact it returns the position to the
384 * right. Also it returns a non-existent residue position for a gap beyond
387 Sequence sq = new Sequence("TestSeq", "AB.C-D E.");
388 int[] map = sq.findPositionMap();
389 assertEquals(Arrays.toString(new int[] { 1, 2, 3, 3, 4, 4, 5, 5, 6 }),
390 Arrays.toString(map));
394 * Test for getSubsequence
396 @Test(groups = { "Functional" })
397 public void testGetSubsequence()
399 SequenceI sq = new Sequence("TestSeq", "ABCDEFG");
400 sq.createDatasetSequence();
402 // positions are base 0, end position is exclusive
403 SequenceI subseq = sq.getSubSequence(2, 4);
405 assertEquals("CD", subseq.getSequenceAsString());
406 // start/end are base 1 positions
407 assertEquals(3, subseq.getStart());
408 assertEquals(4, subseq.getEnd());
409 // subsequence shares the full dataset sequence
410 assertSame(sq.getDatasetSequence(), subseq.getDatasetSequence());
414 * test createDatasetSequence behaves to doc
416 @Test(groups = { "Functional" })
417 public void testCreateDatasetSequence()
419 SequenceI sq = new Sequence("my","ASDASD");
420 assertNull(sq.getDatasetSequence());
421 SequenceI rds = sq.createDatasetSequence();
423 assertNull(rds.getDatasetSequence());
424 assertEquals(sq.getDatasetSequence(), rds);
428 * Test for deriveSequence applied to a sequence with a dataset
430 @Test(groups = { "Functional" })
431 public void testDeriveSequence_existingDataset()
433 Sequence sq = new Sequence("Seq1", "CD");
434 sq.setDatasetSequence(new Sequence("Seq1", "ABCDEF"));
435 sq.getDatasetSequence().addSequenceFeature(
436 new SequenceFeature("", "", 1, 2, 0f, null));
440 sq.setDescription("Test sequence description..");
441 sq.setVamsasId("TestVamsasId");
442 sq.addDBRef(new DBRefEntry("PDB", "version0", "1TST"));
444 sq.addDBRef(new DBRefEntry("PDB", "version1", "1PDB"));
445 sq.addDBRef(new DBRefEntry("PDB", "version2", "2PDB"));
446 sq.addDBRef(new DBRefEntry("PDB", "version3", "3PDB"));
447 sq.addDBRef(new DBRefEntry("PDB", "version4", "4PDB"));
449 sq.addPDBId(new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1"));
450 sq.addPDBId(new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1"));
451 sq.addPDBId(new PDBEntry("2PDB", "A", Type.MMCIF, "filePath/test2"));
452 sq.addPDBId(new PDBEntry("2PDB", "B", Type.MMCIF, "filePath/test2"));
454 DBRefEntry pdb1pdb = new DBRefEntry("PDB", "version1", "1PDB");
455 DBRefEntry pdb2pdb = new DBRefEntry("PDB", "version1", "2PDB");
458 List<DBRefEntry> primRefs = Arrays.asList(new DBRefEntry[] { pdb1pdb,
461 sq.getDatasetSequence().addDBRef(pdb1pdb);
462 sq.getDatasetSequence().addDBRef(pdb2pdb);
463 sq.getDatasetSequence().addDBRef(
464 new DBRefEntry("PDB", "version3", "3PDB"));
465 sq.getDatasetSequence().addDBRef(
466 new DBRefEntry("PDB", "version4", "4PDB"));
468 PDBEntry pdbe1a=new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1");
469 PDBEntry pdbe1b = new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1");
470 PDBEntry pdbe2a=new PDBEntry("2PDB", "A", Type.MMCIF, "filePath/test2");
471 PDBEntry pdbe2b = new PDBEntry("2PDB", "B", Type.MMCIF, "filePath/test2");
472 sq.getDatasetSequence().addPDBId(
474 sq.getDatasetSequence().addPDBId(
476 sq.getDatasetSequence().addPDBId(pdbe2a);
477 sq.getDatasetSequence().addPDBId(pdbe2b);
480 * test we added pdb entries to the dataset sequence
482 Assert.assertEquals(sq.getDatasetSequence().getAllPDBEntries(), Arrays
483 .asList(new PDBEntry[] { pdbe1a, pdbe1b, pdbe2a, pdbe2b }),
484 "PDB Entries were not found on dataset sequence.");
487 * we should recover a pdb entry that is on the dataset sequence via PDBEntry
489 Assert.assertEquals(pdbe1a,
490 sq.getDatasetSequence().getPDBEntry("1PDB"),
491 "PDB Entry '1PDB' not found on dataset sequence via getPDBEntry.");
492 ArrayList<Annotation> annotsList = new ArrayList<Annotation>();
493 System.out.println(">>>>>> " + sq.getSequenceAsString().length());
494 annotsList.add(new Annotation("A", "A", 'X', 0.1f));
495 annotsList.add(new Annotation("A", "A", 'X', 0.1f));
496 Annotation[] annots = annotsList.toArray(new Annotation[0]);
497 sq.addAlignmentAnnotation(new AlignmentAnnotation("Test annot",
498 "Test annot description", annots));
499 sq.getDatasetSequence().addAlignmentAnnotation(
500 new AlignmentAnnotation("Test annot", "Test annot description",
502 Assert.assertEquals(sq.getDescription(), "Test sequence description..");
503 Assert.assertEquals(sq.getDBRefs().length, 5);
504 Assert.assertEquals(sq.getAllPDBEntries().size(), 4);
505 Assert.assertNotNull(sq.getAnnotation());
506 Assert.assertEquals(sq.getAnnotation()[0].annotations.length, 2);
507 Assert.assertEquals(sq.getDatasetSequence().getDBRefs().length, 4);
508 Assert.assertEquals(sq.getDatasetSequence().getAllPDBEntries().size(),
510 Assert.assertNotNull(sq.getDatasetSequence().getAnnotation());
512 Sequence derived = (Sequence) sq.deriveSequence();
514 Assert.assertEquals(derived.getDescription(),
515 "Test sequence description..");
516 Assert.assertEquals(derived.getDBRefs().length, 4); // come from dataset
517 Assert.assertEquals(derived.getAllPDBEntries().size(), 4);
518 Assert.assertNotNull(derived.getAnnotation());
519 Assert.assertEquals(derived.getAnnotation()[0].annotations.length, 2);
520 Assert.assertEquals(derived.getDatasetSequence().getDBRefs().length, 4);
521 Assert.assertEquals(derived.getDatasetSequence().getAllPDBEntries()
523 Assert.assertNotNull(derived.getDatasetSequence().getAnnotation());
525 assertEquals("CD", derived.getSequenceAsString());
526 assertSame(sq.getDatasetSequence(), derived.getDatasetSequence());
528 assertNull(sq.sequenceFeatures);
529 assertNull(derived.sequenceFeatures);
530 // derived sequence should access dataset sequence features
531 assertNotNull(sq.getSequenceFeatures());
532 assertArrayEquals(sq.getSequenceFeatures(),
533 derived.getSequenceFeatures());
536 * verify we have primary db refs *just* for PDB IDs with associated
540 assertEquals(primRefs, sq.getPrimaryDBRefs());
541 assertEquals(primRefs, sq.getDatasetSequence().getPrimaryDBRefs());
543 assertEquals(sq.getPrimaryDBRefs(), derived.getPrimaryDBRefs());
548 * Test for deriveSequence applied to an ungapped sequence with no dataset
550 @Test(groups = { "Functional" })
551 public void testDeriveSequence_noDatasetUngapped()
553 SequenceI sq = new Sequence("Seq1", "ABCDEF");
554 assertEquals(1, sq.getStart());
555 assertEquals(6, sq.getEnd());
556 SequenceI derived = sq.deriveSequence();
557 assertEquals("ABCDEF", derived.getSequenceAsString());
558 assertEquals("ABCDEF", derived.getDatasetSequence()
559 .getSequenceAsString());
563 * Test for deriveSequence applied to a gapped sequence with no dataset
565 @Test(groups = { "Functional" })
566 public void testDeriveSequence_noDatasetGapped()
568 SequenceI sq = new Sequence("Seq1", "AB-C.D EF");
569 assertEquals(1, sq.getStart());
570 assertEquals(6, sq.getEnd());
571 assertNull(sq.getDatasetSequence());
572 SequenceI derived = sq.deriveSequence();
573 assertEquals("AB-C.D EF", derived.getSequenceAsString());
574 assertEquals("ABCDEF", derived.getDatasetSequence()
575 .getSequenceAsString());
578 @Test(groups = { "Functional" })
579 public void testCopyConstructor_noDataset()
581 SequenceI seq1 = new Sequence("Seq1", "AB-C.D EF");
582 seq1.setDescription("description");
583 seq1.addAlignmentAnnotation(new AlignmentAnnotation("label", "desc",
585 seq1.addSequenceFeature(new SequenceFeature("type", "desc", 22, 33,
587 seq1.addPDBId(new PDBEntry("1A70", "B", Type.PDB, "File"));
588 seq1.addDBRef(new DBRefEntry("EMBL", "1.2", "AZ12345"));
590 SequenceI copy = new Sequence(seq1);
592 assertNull(copy.getDatasetSequence());
594 verifyCopiedSequence(seq1, copy);
596 // copy has a copy of the DBRefEntry
597 // this is murky - DBrefs are only copied for dataset sequences
598 // where the test for 'dataset sequence' is 'dataset is null'
599 // but that doesn't distinguish it from an aligned sequence
600 // which has not yet generated a dataset sequence
601 // NB getDBRef looks inside dataset sequence if not null
602 DBRefEntry[] dbrefs = copy.getDBRefs();
603 assertEquals(1, dbrefs.length);
604 assertFalse(dbrefs[0] == seq1.getDBRefs()[0]);
605 assertTrue(dbrefs[0].equals(seq1.getDBRefs()[0]));
608 @Test(groups = { "Functional" })
609 public void testCopyConstructor_withDataset()
611 SequenceI seq1 = new Sequence("Seq1", "AB-C.D EF");
612 seq1.createDatasetSequence();
613 seq1.setDescription("description");
614 seq1.addAlignmentAnnotation(new AlignmentAnnotation("label", "desc",
616 // JAL-2046 - what is the contract for using a derived sequence's
617 // addSequenceFeature ?
618 seq1.addSequenceFeature(new SequenceFeature("type", "desc", 22, 33,
620 seq1.addPDBId(new PDBEntry("1A70", "B", Type.PDB, "File"));
621 // here we add DBRef to the dataset sequence:
622 seq1.getDatasetSequence().addDBRef(
623 new DBRefEntry("EMBL", "1.2", "AZ12345"));
625 SequenceI copy = new Sequence(seq1);
627 assertNotNull(copy.getDatasetSequence());
628 assertSame(copy.getDatasetSequence(), seq1.getDatasetSequence());
630 verifyCopiedSequence(seq1, copy);
632 // getDBRef looks inside dataset sequence and this is shared,
633 // so holds the same dbref objects
634 DBRefEntry[] dbrefs = copy.getDBRefs();
635 assertEquals(1, dbrefs.length);
636 assertSame(dbrefs[0], seq1.getDBRefs()[0]);
640 * Helper to make assertions about a copied sequence
645 protected void verifyCopiedSequence(SequenceI seq1, SequenceI copy)
647 // verify basic properties:
648 assertEquals(copy.getName(), seq1.getName());
649 assertEquals(copy.getDescription(), seq1.getDescription());
650 assertEquals(copy.getStart(), seq1.getStart());
651 assertEquals(copy.getEnd(), seq1.getEnd());
652 assertEquals(copy.getSequenceAsString(), seq1.getSequenceAsString());
654 // copy has a copy of the annotation:
655 AlignmentAnnotation[] anns = copy.getAnnotation();
656 assertEquals(1, anns.length);
657 assertFalse(anns[0] == seq1.getAnnotation()[0]);
658 assertEquals(anns[0].label, seq1.getAnnotation()[0].label);
659 assertEquals(anns[0].description, seq1.getAnnotation()[0].description);
660 assertEquals(anns[0].score, seq1.getAnnotation()[0].score);
662 // copy has a copy of the sequence feature:
663 SequenceFeature[] sfs = copy.getSequenceFeatures();
664 assertEquals(1, sfs.length);
665 if (seq1.getDatasetSequence()!=null && copy.getDatasetSequence()==seq1.getDatasetSequence()) {
666 assertTrue(sfs[0] == seq1.getSequenceFeatures()[0]);
668 assertFalse(sfs[0] == seq1.getSequenceFeatures()[0]);
670 assertTrue(sfs[0].equals(seq1.getSequenceFeatures()[0]));
672 // copy has a copy of the PDB entry
673 Vector<PDBEntry> pdbs = copy.getAllPDBEntries();
674 assertEquals(1, pdbs.size());
675 assertFalse(pdbs.get(0) == seq1.getAllPDBEntries().get(0));
676 assertTrue(pdbs.get(0).equals(seq1.getAllPDBEntries().get(0)));
679 @Test(groups = "Functional")
680 public void testGetCharAt()
682 SequenceI sq = new Sequence("", "abcde");
683 assertEquals('a', sq.getCharAt(0));
684 assertEquals('e', sq.getCharAt(4));
685 assertEquals(' ', sq.getCharAt(5));
686 assertEquals(' ', sq.getCharAt(-1));
690 * Tests for adding (or updating) dbrefs
692 * @see DBRefEntry#updateFrom(DBRefEntry)
694 @Test(groups = { "Functional" })
695 public void testAddDBRef()
697 SequenceI sq = new Sequence("", "abcde");
698 assertNull(sq.getDBRefs());
699 DBRefEntry dbref = new DBRefEntry("Uniprot", "1", "P00340");
701 assertEquals(1, sq.getDBRefs().length);
702 assertSame(dbref, sq.getDBRefs()[0]);
705 * change of version - new entry
707 DBRefEntry dbref2 = new DBRefEntry("Uniprot", "2", "P00340");
709 assertEquals(2, sq.getDBRefs().length);
710 assertSame(dbref, sq.getDBRefs()[0]);
711 assertSame(dbref2, sq.getDBRefs()[1]);
714 * matches existing entry - not added
716 sq.addDBRef(new DBRefEntry("UNIPROT", "1", "p00340"));
717 assertEquals(2, sq.getDBRefs().length);
720 * different source = new entry
722 DBRefEntry dbref3 = new DBRefEntry("UniRef", "1", "p00340");
724 assertEquals(3, sq.getDBRefs().length);
725 assertSame(dbref3, sq.getDBRefs()[2]);
728 * different ref = new entry
730 DBRefEntry dbref4 = new DBRefEntry("UniRef", "1", "p00341");
732 assertEquals(4, sq.getDBRefs().length);
733 assertSame(dbref4, sq.getDBRefs()[3]);
736 * matching ref with a mapping - map updated
738 DBRefEntry dbref5 = new DBRefEntry("UniRef", "1", "p00341");
739 Mapping map = new Mapping(new MapList(new int[] { 1, 3 }, new int[] {
743 assertEquals(4, sq.getDBRefs().length);
744 assertSame(dbref4, sq.getDBRefs()[3]);
745 assertSame(map, dbref4.getMap());
748 * 'real' version replaces "0" version
750 dbref2.setVersion("0");
751 DBRefEntry dbref6 = new DBRefEntry(dbref2.getSource(), "3",
752 dbref2.getAccessionId());
754 assertEquals(4, sq.getDBRefs().length);
755 assertSame(dbref2, sq.getDBRefs()[1]);
756 assertEquals("3", dbref2.getVersion());
759 * 'real' version replaces "source:0" version
761 dbref3.setVersion("Uniprot:0");
762 DBRefEntry dbref7 = new DBRefEntry(dbref3.getSource(), "3",
763 dbref3.getAccessionId());
765 assertEquals(4, sq.getDBRefs().length);
766 assertSame(dbref3, sq.getDBRefs()[2]);
767 assertEquals("3", dbref2.getVersion());
770 @Test(groups = { "Functional" })
771 public void testGetPrimaryDBRefs_peptide()
773 SequenceI sq = new Sequence("aseq", "ASDFKYLMQPRST", 10, 22);
776 List<DBRefEntry> primaryDBRefs = sq.getPrimaryDBRefs();
777 assertTrue(primaryDBRefs.isEmpty());
780 sq.setDBRefs(new DBRefEntry[] {});
781 primaryDBRefs = sq.getPrimaryDBRefs();
782 assertTrue(primaryDBRefs.isEmpty());
785 DBRefEntry upentry1 = new DBRefEntry("UNIPROT", "0", "Q04760");
786 sq.addDBRef(upentry1);
788 // primary - uniprot with congruent map
789 DBRefEntry upentry2 = new DBRefEntry("UNIPROT", "0", "Q04762");
790 upentry2.setMap(new Mapping(null, new MapList(new int[] { 10, 22 },
791 new int[] { 10, 22 }, 1, 1)));
792 sq.addDBRef(upentry2);
794 // primary - uniprot with map of enclosing sequence
795 DBRefEntry upentry3 = new DBRefEntry("UNIPROT", "0", "Q04763");
796 upentry3.setMap(new Mapping(null, new MapList(new int[] { 8, 24 },
797 new int[] { 8, 24 }, 1, 1)));
798 sq.addDBRef(upentry3);
800 // not primary - uniprot with map of sub-sequence (5')
801 DBRefEntry upentry4 = new DBRefEntry("UNIPROT", "0", "Q04764");
802 upentry4.setMap(new Mapping(null, new MapList(new int[] { 10, 18 },
803 new int[] { 10, 18 }, 1, 1)));
804 sq.addDBRef(upentry4);
806 // not primary - uniprot with map that overlaps 3'
807 DBRefEntry upentry5 = new DBRefEntry("UNIPROT", "0", "Q04765");
808 upentry5.setMap(new Mapping(null, new MapList(new int[] { 12, 22 },
809 new int[] { 12, 22 }, 1, 1)));
810 sq.addDBRef(upentry5);
812 // not primary - uniprot with map to different coordinates frame
813 DBRefEntry upentry6 = new DBRefEntry("UNIPROT", "0", "Q04766");
814 upentry6.setMap(new Mapping(null, new MapList(new int[] { 12, 18 },
815 new int[] { 112, 118 }, 1, 1)));
816 sq.addDBRef(upentry6);
818 // not primary - dbref to 'non-core' database
819 DBRefEntry upentry7 = new DBRefEntry("Pfam", "0", "PF00903");
820 sq.addDBRef(upentry7);
822 // primary - type is PDB
823 DBRefEntry pdbentry = new DBRefEntry("PDB", "0", "1qip");
824 sq.addDBRef(pdbentry);
826 // not primary - PDBEntry has no file
827 sq.addDBRef(new DBRefEntry("PDB", "0", "1AAA"));
829 // not primary - no PDBEntry
830 sq.addDBRef(new DBRefEntry("PDB", "0", "1DDD"));
832 // add corroborating PDB entry for primary DBref -
833 // needs to have a file as well as matching ID
834 // note PDB ID is not treated as case sensitive
835 sq.addPDBId(new PDBEntry("1QIP", null, Type.PDB, new File("/blah")
838 // not valid DBRef - no file..
839 sq.addPDBId(new PDBEntry("1AAA", null, null, null));
841 primaryDBRefs = sq.getPrimaryDBRefs();
842 assertEquals(4, primaryDBRefs.size());
843 assertTrue("Couldn't find simple primary reference (UNIPROT)",
844 primaryDBRefs.contains(upentry1));
845 assertTrue("Couldn't find mapped primary reference (UNIPROT)",
846 primaryDBRefs.contains(upentry2));
847 assertTrue("Couldn't find mapped context reference (UNIPROT)",
848 primaryDBRefs.contains(upentry3));
849 assertTrue("Couldn't find expected PDB primary reference",
850 primaryDBRefs.contains(pdbentry));
853 @Test(groups = { "Functional" })
854 public void testGetPrimaryDBRefs_nucleotide()
856 SequenceI sq = new Sequence("aseq", "TGATCACTCGACTAGCATCAGCATA", 10, 34);
859 DBRefEntry dbr1 = new DBRefEntry("ENSEMBL", "0", "ENSG1234");
862 // not primary - Ensembl 'transcript' mapping of sub-sequence
863 DBRefEntry dbr2 = new DBRefEntry("ENSEMBL", "0", "ENST1234");
864 dbr2.setMap(new Mapping(null, new MapList(new int[] { 15, 25 },
865 new int[] { 1, 11 }, 1, 1)));
868 // primary - EMBL with congruent map
869 DBRefEntry dbr3 = new DBRefEntry("EMBL", "0", "J1234");
870 dbr3.setMap(new Mapping(null, new MapList(new int[] { 10, 34 },
871 new int[] { 10, 34 }, 1, 1)));
874 // not primary - to non-core database
875 DBRefEntry dbr4 = new DBRefEntry("CCDS", "0", "J1234");
878 // not primary - to protein
879 DBRefEntry dbr5 = new DBRefEntry("UNIPROT", "0", "Q87654");
882 List<DBRefEntry> primaryDBRefs = sq.getPrimaryDBRefs();
883 assertEquals(2, primaryDBRefs.size());
884 assertTrue(primaryDBRefs.contains(dbr1));
885 assertTrue(primaryDBRefs.contains(dbr3));
889 * Test the method that updates the list of PDBEntry from any new DBRefEntry
892 @Test(groups = { "Functional" })
893 public void testUpdatePDBIds()
895 PDBEntry pdbe1 = new PDBEntry("3A6S", null, null, null);
897 seq.addDBRef(new DBRefEntry("Ensembl", "8", "ENST1234"));
898 seq.addDBRef(new DBRefEntry("PDB", "0", "1A70"));
899 seq.addDBRef(new DBRefEntry("PDB", "0", "4BQGa"));
900 seq.addDBRef(new DBRefEntry("PDB", "0", "3a6sB"));
901 // 7 is not a valid chain code:
902 seq.addDBRef(new DBRefEntry("PDB", "0", "2GIS7"));
905 List<PDBEntry> pdbIds = seq.getAllPDBEntries();
906 assertEquals(4, pdbIds.size());
907 assertSame(pdbe1, pdbIds.get(0));
908 // chain code got added to 3A6S:
909 assertEquals("B", pdbe1.getChainCode());
910 assertEquals("1A70", pdbIds.get(1).getId());
911 // 4BQGA is parsed into id + chain
912 assertEquals("4BQG", pdbIds.get(2).getId());
913 assertEquals("a", pdbIds.get(2).getChainCode());
914 assertEquals("2GIS7", pdbIds.get(3).getId());
915 assertNull(pdbIds.get(3).getChainCode());
919 * Test the method that either adds a pdbid or updates an existing one
921 @Test(groups = { "Functional" })
922 public void testAddPDBId()
924 PDBEntry pdbe = new PDBEntry("3A6S", null, null, null);
926 assertEquals(1, seq.getAllPDBEntries().size());
927 assertSame(pdbe, seq.getPDBEntry("3A6S"));
928 assertSame(pdbe, seq.getPDBEntry("3a6s")); // case-insensitive
930 // add the same entry
932 assertEquals(1, seq.getAllPDBEntries().size());
933 assertSame(pdbe, seq.getPDBEntry("3A6S"));
935 // add an identical entry
936 seq.addPDBId(new PDBEntry("3A6S", null, null, null));
937 assertEquals(1, seq.getAllPDBEntries().size());
938 assertSame(pdbe, seq.getPDBEntry("3A6S"));
940 // add a different entry
941 PDBEntry pdbe2 = new PDBEntry("1A70", null, null, null);
943 assertEquals(2, seq.getAllPDBEntries().size());
944 assertSame(pdbe, seq.getAllPDBEntries().get(0));
945 assertSame(pdbe2, seq.getAllPDBEntries().get(1));
947 // update pdbe with chain code, file, type
948 PDBEntry pdbe3 = new PDBEntry("3a6s", "A", Type.PDB, "filepath");
950 assertEquals(2, seq.getAllPDBEntries().size());
951 assertSame(pdbe, seq.getAllPDBEntries().get(0)); // updated in situ
952 assertEquals("3A6S", pdbe.getId()); // unchanged
953 assertEquals("A", pdbe.getChainCode()); // updated
954 assertEquals(Type.PDB.toString(), pdbe.getType()); // updated
955 assertEquals("filepath", pdbe.getFile()); // updated
956 assertSame(pdbe2, seq.getAllPDBEntries().get(1));
958 // add with a different file path
959 PDBEntry pdbe4 = new PDBEntry("3a6s", "A", Type.PDB, "filepath2");
961 assertEquals(3, seq.getAllPDBEntries().size());
962 assertSame(pdbe4, seq.getAllPDBEntries().get(2));
964 // add with a different chain code
965 PDBEntry pdbe5 = new PDBEntry("3a6s", "B", Type.PDB, "filepath");
967 assertEquals(4, seq.getAllPDBEntries().size());
968 assertSame(pdbe5, seq.getAllPDBEntries().get(3));