import jalview.datamodel.PDBEntry.Type;
import jalview.util.MapList;
+import java.io.File;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
// change sequence, should trigger an update of cached result
sq.setSequence("ASDFASDFADSF");
assertTrue(sq.isProtein());
+ /*
+ * in situ change of sequence doesn't change hashcode :-O
+ * (sequence should not expose internal implementation)
+ */
+ for (int i = 0; i < sq.getSequence().length; i++)
+ {
+ sq.getSequence()[i] = "acgtu".charAt(i % 5);
+ }
+ assertTrue(sq.isProtein()); // but it isn't
}
+
@Test(groups = { "Functional" })
public void testGetAnnotation()
{
{
AlignmentAnnotation ann1 = addAnnotation("label1", "desc1", "calcId1",
1f);
- AlignmentAnnotation ann2 = addAnnotation("label2", "desc2", "calcId2",
- 1f);
+ addAnnotation("label2", "desc2", "calcId2", 1f);
AlignmentAnnotation ann3 = addAnnotation("label1", "desc3", "calcId3",
1f);
AlignmentAnnotation[] anns = seq.getAnnotation("label1");
@Test(groups = { "Functional" })
public void testGetAlignmentAnnotations_forCalcIdAndLabel()
{
- AlignmentAnnotation ann1 = addAnnotation("label1", "desc1", "calcId1",
- 1f);
+ addAnnotation("label1", "desc1", "calcId1", 1f);
AlignmentAnnotation ann2 = addAnnotation("label2", "desc2", "calcId2",
1f);
- AlignmentAnnotation ann3 = addAnnotation("label2", "desc3", "calcId3",
- 1f);
+ addAnnotation("label2", "desc3", "calcId3", 1f);
AlignmentAnnotation ann4 = addAnnotation("label2", "desc3", "calcId2",
1f);
- AlignmentAnnotation ann5 = addAnnotation("label5", "desc3", null, 1f);
- AlignmentAnnotation ann6 = addAnnotation(null, "desc3", "calcId3", 1f);
+ addAnnotation("label5", "desc3", null, 1f);
+ addAnnotation(null, "desc3", "calcId3", 1f);
+
List<AlignmentAnnotation> anns = seq.getAlignmentAnnotations("calcId2",
"label2");
assertEquals(2, anns.size());
sq.setDescription("Test sequence description..");
sq.setVamsasId("TestVamsasId");
- sq.setSourceDBRef(new DBRefEntry("PDB", "version0", "1TST"));
+ sq.addDBRef(new DBRefEntry("PDB", "version0", "1TST"));
- sq.addDBRef(new DBRefEntry("PDB", "version1", "1Tst"));
- sq.addDBRef(new DBRefEntry("PDB", "version2", "2Tst"));
- sq.addDBRef(new DBRefEntry("PDB", "version3", "3Tst"));
- sq.addDBRef(new DBRefEntry("PDB", "version4", "4Tst"));
+ sq.addDBRef(new DBRefEntry("PDB", "version1", "1PDB"));
+ sq.addDBRef(new DBRefEntry("PDB", "version2", "2PDB"));
+ sq.addDBRef(new DBRefEntry("PDB", "version3", "3PDB"));
+ sq.addDBRef(new DBRefEntry("PDB", "version4", "4PDB"));
sq.addPDBId(new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1"));
sq.addPDBId(new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1"));
sq.addPDBId(new PDBEntry("2PDB", "A", Type.MMCIF, "filePath/test2"));
sq.addPDBId(new PDBEntry("2PDB", "B", Type.MMCIF, "filePath/test2"));
+
+ DBRefEntry pdb1pdb = new DBRefEntry("PDB", "version1", "1PDB");
+ DBRefEntry pdb2pdb = new DBRefEntry("PDB", "version1", "2PDB");
+
+ List<DBRefEntry> primRefs = Arrays.asList(new DBRefEntry[] { pdb1pdb,
+ pdb2pdb });
+
+ sq.getDatasetSequence().addDBRef(pdb1pdb);
+ sq.getDatasetSequence().addDBRef(pdb2pdb);
sq.getDatasetSequence().addDBRef(
- new DBRefEntry("PDB", "version1", "1Tst"));
- sq.getDatasetSequence().addDBRef(
- new DBRefEntry("PDB", "version2", "2Tst"));
- sq.getDatasetSequence().addDBRef(
- new DBRefEntry("PDB", "version3", "3Tst"));
+ new DBRefEntry("PDB", "version3", "3PDB"));
sq.getDatasetSequence().addDBRef(
- new DBRefEntry("PDB", "version4", "4Tst"));
-
- sq.getDatasetSequence().addPDBId(
- new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1"));
- sq.getDatasetSequence().addPDBId(
- new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1"));
+ new DBRefEntry("PDB", "version4", "4PDB"));
+
+ PDBEntry pdbe1a=new PDBEntry("1PDB", "A", Type.PDB, "filePath/test1");
+ PDBEntry pdbe1b = new PDBEntry("1PDB", "B", Type.PDB, "filePath/test1");
+ PDBEntry pdbe2a=new PDBEntry("2PDB", "A", Type.MMCIF, "filePath/test2");
+ PDBEntry pdbe2b = new PDBEntry("2PDB", "B", Type.MMCIF, "filePath/test2");
sq.getDatasetSequence().addPDBId(
- new PDBEntry("2PDB", "A", Type.MMCIF, "filePath/test2"));
+ pdbe1a);
sq.getDatasetSequence().addPDBId(
- new PDBEntry("2PDB", "B", Type.MMCIF, "filePath/test2"));
+ pdbe1b);
+ sq.getDatasetSequence().addPDBId(pdbe2a);
+ sq.getDatasetSequence().addPDBId(pdbe2b);
+ /*
+ * test we added pdb entries to the dataset sequence
+ */
+ Assert.assertEquals(sq.getDatasetSequence().getAllPDBEntries(), Arrays
+ .asList(new PDBEntry[] { pdbe1a, pdbe1b, pdbe2a, pdbe2b }),
+ "PDB Entries were not found on dataset sequence.");
+
+ /*
+ * we should recover a pdb entry that is on the dataset sequence via PDBEntry
+ */
+ Assert.assertEquals(pdbe1a,
+ sq.getDatasetSequence().getPDBEntry("1PDB"),
+ "PDB Entry '1PDB' not found on dataset sequence via getPDBEntry.");
ArrayList<Annotation> annotsList = new ArrayList<Annotation>();
System.out.println(">>>>>> " + sq.getSequenceAsString().length());
annotsList.add(new Annotation("A", "A", 'X', 0.1f));
new AlignmentAnnotation("Test annot", "Test annot description",
annots));
Assert.assertEquals(sq.getDescription(), "Test sequence description..");
- Assert.assertEquals(sq.getDBRefs().length, 4);
+ Assert.assertEquals(sq.getDBRefs().length, 5);
Assert.assertEquals(sq.getAllPDBEntries().size(), 4);
Assert.assertNotNull(sq.getAnnotation());
Assert.assertEquals(sq.getAnnotation()[0].annotations.length, 2);
Assert.assertEquals(derived.getDescription(),
"Test sequence description..");
- Assert.assertEquals(derived.getDBRefs().length, 4);
+ Assert.assertEquals(derived.getDBRefs().length, 4); // come from dataset
Assert.assertEquals(derived.getAllPDBEntries().size(), 4);
Assert.assertNotNull(derived.getAnnotation());
Assert.assertEquals(derived.getAnnotation()[0].annotations.length, 2);
assertNotNull(sq.getSequenceFeatures());
assertArrayEquals(sq.getSequenceFeatures(),
derived.getSequenceFeatures());
+
+ /*
+ * verify we have primary db refs *just* for PDB IDs with associated
+ * PDBEntry objects
+ */
+
+ assertEquals(primRefs, sq.getPrimaryDBRefs());
+ assertEquals(primRefs, sq.getDatasetSequence().getPrimaryDBRefs());
+
+ assertEquals(sq.getPrimaryDBRefs(), derived.getPrimaryDBRefs());
+
}
/**
assertSame(dbref3, sq.getDBRefs()[2]);
assertEquals("3", dbref2.getVersion());
}
+
+ @Test(groups = { "Functional" })
+ public void testGetPrimaryDBRefs_peptide()
+ {
+ SequenceI sq = new Sequence("aseq", "ASDFKYLMQPRST", 10, 22);
+
+ // no dbrefs
+ List<DBRefEntry> primaryDBRefs = sq.getPrimaryDBRefs();
+ assertTrue(primaryDBRefs.isEmpty());
+
+ // empty dbrefs
+ sq.setDBRefs(new DBRefEntry[] {});
+ primaryDBRefs = sq.getPrimaryDBRefs();
+ assertTrue(primaryDBRefs.isEmpty());
+
+ // primary - uniprot
+ DBRefEntry upentry1 = new DBRefEntry("UNIPROT", "0", "Q04760");
+ sq.addDBRef(upentry1);
+
+ // primary - uniprot with congruent map
+ DBRefEntry upentry2 = new DBRefEntry("UNIPROT", "0", "Q04762");
+ upentry2.setMap(new Mapping(null, new MapList(new int[] { 10, 22 },
+ new int[] { 10, 22 }, 1, 1)));
+ sq.addDBRef(upentry2);
+
+ // primary - uniprot with map of enclosing sequence
+ DBRefEntry upentry3 = new DBRefEntry("UNIPROT", "0", "Q04763");
+ upentry3.setMap(new Mapping(null, new MapList(new int[] { 8, 24 },
+ new int[] { 8, 24 }, 1, 1)));
+ sq.addDBRef(upentry3);
+
+ // not primary - uniprot with map of sub-sequence (5')
+ DBRefEntry upentry4 = new DBRefEntry("UNIPROT", "0", "Q04764");
+ upentry4.setMap(new Mapping(null, new MapList(new int[] { 10, 18 },
+ new int[] { 10, 18 }, 1, 1)));
+ sq.addDBRef(upentry4);
+
+ // not primary - uniprot with map that overlaps 3'
+ DBRefEntry upentry5 = new DBRefEntry("UNIPROT", "0", "Q04765");
+ upentry5.setMap(new Mapping(null, new MapList(new int[] { 12, 22 },
+ new int[] { 12, 22 }, 1, 1)));
+ sq.addDBRef(upentry5);
+
+ // not primary - uniprot with map to different coordinates frame
+ DBRefEntry upentry6 = new DBRefEntry("UNIPROT", "0", "Q04766");
+ upentry6.setMap(new Mapping(null, new MapList(new int[] { 12, 18 },
+ new int[] { 112, 118 }, 1, 1)));
+ sq.addDBRef(upentry6);
+
+ // not primary - dbref to 'non-core' database
+ DBRefEntry upentry7 = new DBRefEntry("Pfam", "0", "PF00903");
+ sq.addDBRef(upentry7);
+
+ // primary - type is PDB
+ DBRefEntry pdbentry = new DBRefEntry("PDB", "0", "1qip");
+ sq.addDBRef(pdbentry);
+
+ // not primary - PDBEntry has no file
+ sq.addDBRef(new DBRefEntry("PDB", "0", "1AAA"));
+
+ // not primary - no PDBEntry
+ sq.addDBRef(new DBRefEntry("PDB", "0", "1DDD"));
+
+ // add corroborating PDB entry for primary DBref -
+ // needs to have a file as well as matching ID
+ // note PDB ID is not treated as case sensitive
+ sq.addPDBId(new PDBEntry("1QIP", null, Type.PDB, new File("/blah")
+ .toString()));
+
+ // not valid DBRef - no file..
+ sq.addPDBId(new PDBEntry("1AAA", null, null, null));
+
+ primaryDBRefs = sq.getPrimaryDBRefs();
+ assertEquals(4, primaryDBRefs.size());
+ assertTrue("Couldn't find simple primary reference (UNIPROT)",
+ primaryDBRefs.contains(upentry1));
+ assertTrue("Couldn't find mapped primary reference (UNIPROT)",
+ primaryDBRefs.contains(upentry2));
+ assertTrue("Couldn't find mapped context reference (UNIPROT)",
+ primaryDBRefs.contains(upentry3));
+ assertTrue("Couldn't find expected PDB primary reference",
+ primaryDBRefs.contains(pdbentry));
+ }
+
+ @Test(groups = { "Functional" })
+ public void testGetPrimaryDBRefs_nucleotide()
+ {
+ SequenceI sq = new Sequence("aseq", "TGATCACTCGACTAGCATCAGCATA", 10, 34);
+
+ // primary - Ensembl
+ DBRefEntry dbr1 = new DBRefEntry("ENSEMBL", "0", "ENSG1234");
+ sq.addDBRef(dbr1);
+
+ // not primary - Ensembl 'transcript' mapping of sub-sequence
+ DBRefEntry dbr2 = new DBRefEntry("ENSEMBL", "0", "ENST1234");
+ dbr2.setMap(new Mapping(null, new MapList(new int[] { 15, 25 },
+ new int[] { 1, 11 }, 1, 1)));
+ sq.addDBRef(dbr2);
+
+ // primary - EMBL with congruent map
+ DBRefEntry dbr3 = new DBRefEntry("EMBL", "0", "J1234");
+ dbr3.setMap(new Mapping(null, new MapList(new int[] { 10, 34 },
+ new int[] { 10, 34 }, 1, 1)));
+ sq.addDBRef(dbr3);
+
+ // not primary - to non-core database
+ DBRefEntry dbr4 = new DBRefEntry("CCDS", "0", "J1234");
+ sq.addDBRef(dbr4);
+
+ // not primary - to protein
+ DBRefEntry dbr5 = new DBRefEntry("UNIPROT", "0", "Q87654");
+ sq.addDBRef(dbr5);
+
+ List<DBRefEntry> primaryDBRefs = sq.getPrimaryDBRefs();
+ assertEquals(2, primaryDBRefs.size());
+ assertTrue(primaryDBRefs.contains(dbr1));
+ assertTrue(primaryDBRefs.contains(dbr3));
+ }
}