+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
+ *
+ * This file is part of Jalview.
+ *
+ * Jalview is free software: you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *
+ * Jalview is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
+ * PURPOSE. See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
package jalview.datamodel.xdb.embl;
import static org.testng.AssertJUnit.assertEquals;
+import static org.testng.AssertJUnit.assertNull;
import static org.testng.AssertJUnit.assertSame;
-import jalview.util.MappingUtils;
+import jalview.analysis.SequenceIdMatcher;
+import jalview.datamodel.DBRefEntry;
+import jalview.datamodel.DBRefSource;
+import jalview.datamodel.SequenceI;
+import jalview.util.MapList;
+import java.util.ArrayList;
import java.util.Arrays;
-import java.util.Vector;
+import java.util.List;
import org.testng.annotations.Test;
EmblEntry testee = new EmblEntry();
/*
- * Make a (CDS) Feature with 4 locations
+ * Make a (CDS) Feature with 5 locations
*/
EmblFeature cds = new EmblFeature();
- Vector<EmblFeatureLocations> locs = new Vector<EmblFeatureLocations>();
- cds.setLocations(locs);
-
- /*
- * single range [10-20]
- */
- EmblFeatureLocations loc = new EmblFeatureLocations();
- loc.setLocationType("single");
- loc.setLocationComplement(false);
- Vector<EmblFeatureLocElement> elements = new Vector<EmblFeatureLocElement>();
- EmblFeatureLocElement locElement = new EmblFeatureLocElement();
- BasePosition b1 = new BasePosition();
- b1.setPos("10");
- BasePosition b2 = new BasePosition();
- b2.setPos("20");
- locElement.setBasePositions(new BasePosition[] { b1, b2 });
- elements.add(locElement);
- loc.setLocElements(elements);
- locs.add(loc);
-
- /*
- * complement range [30-40]
- */
- loc = new EmblFeatureLocations();
- loc.setLocationType("single");
- loc.setLocationComplement(true);
- elements = new Vector<EmblFeatureLocElement>();
- locElement = new EmblFeatureLocElement();
- b1 = new BasePosition();
- b1.setPos("30");
- b2 = new BasePosition();
- b2.setPos("40");
- locElement.setBasePositions(new BasePosition[] { b1, b2 });
- elements.add(locElement);
- loc.setLocElements(elements);
- locs.add(loc);
-
- /*
- * join range [50-60], [70-80]
- */
- loc = new EmblFeatureLocations();
- loc.setLocationType("join");
- loc.setLocationComplement(false);
- elements = new Vector<EmblFeatureLocElement>();
- locElement = new EmblFeatureLocElement();
- b1 = new BasePosition();
- b1.setPos("50");
- b2 = new BasePosition();
- b2.setPos("60");
- locElement.setBasePositions(new BasePosition[] { b1, b2 });
- elements.add(locElement);
- locElement = new EmblFeatureLocElement();
- b1 = new BasePosition();
- b1.setPos("70");
- b2 = new BasePosition();
- b2.setPos("80");
- locElement.setBasePositions(new BasePosition[] { b1, b2 });
- elements.add(locElement);
- loc.setLocElements(elements);
- locs.add(loc);
-
- /*
- * complement range [90-100], [110-120]
- * this should be the same as complement(join(90..100,110.120))
- * which is "join 90-100 and 110-120, then complement"
- */
- loc = new EmblFeatureLocations();
- loc.setLocationType("join");
- loc.setLocationComplement(true);
- elements = new Vector<EmblFeatureLocElement>();
- locElement = new EmblFeatureLocElement();
- b1 = new BasePosition();
- b1.setPos("90");
- b2 = new BasePosition();
- b2.setPos("100");
- locElement.setBasePositions(new BasePosition[] { b1, b2 });
- elements.add(locElement);
- locElement = new EmblFeatureLocElement();
- b1 = new BasePosition();
- b1.setPos("110");
- b2 = new BasePosition();
- b2.setPos("120");
- locElement.setBasePositions(new BasePosition[] { b1, b2 });
- elements.add(locElement);
- loc.setLocElements(elements);
- locs.add(loc);
+ cds.setLocation("join(10..20,complement(30..40),50..60,70..80,complement(110..120))");
int[] exons = testee.getCdsRanges(cds);
- assertEquals("[10, 20, 40, 30, 50, 60, 70, 80, 120, 110, 100, 90]",
+ assertEquals("[10, 20, 40, 30, 50, 60, 70, 80, 120, 110]",
Arrays.toString(exons));
}
@Test(groups = "Functional")
- public void testGetCdsRanges_badData()
+ public void testParseCodingFeature()
{
- EmblEntry testee = new EmblEntry();
+ // not the whole sequence but enough for this test...
+ List<SequenceI> peptides = new ArrayList<SequenceI>();
+ SequenceIdMatcher matcher = new SequenceIdMatcher(peptides);
+ EmblFile ef = EmblTestHelper.getEmblFile();
+ assertEquals(1, ef.getEntries().size());
+ EmblEntry testee = ef.getEntries().get(0);
+ String sourceDb = "EMBL";
+ SequenceI dna = testee.makeSequence(sourceDb);
+
+ /*
+ * parse three CDS features, with two/one/no Uniprot cross-refs
+ */
+ for (EmblFeature feature : ef.getEntries().get(0).getFeatures())
+ {
+ if ("CDS".equals(feature.getName()))
+ {
+ testee.parseCodingFeature(feature, sourceDb, dna, peptides, matcher);
+ }
+ }
+
+ /*
+ * peptides should now have five entries:
+ * EMBL product and two Uniprot accessions for the first CDS / translation
+ * EMBL product and one Uniprot accession for the second CDS / "
+ * EMBL product only for the third
+ */
+ assertEquals(6, peptides.size());
+ assertEquals("CAA30420.1", peptides.get(0).getName());
+ assertEquals("MLCF", peptides.get(0).getSequenceAsString());
+ assertEquals("UNIPROT|B0BCM4", peptides.get(1).getName());
+ assertEquals("MLCF", peptides.get(1).getSequenceAsString());
+ assertEquals("UNIPROT|P0CE20", peptides.get(2).getName());
+ assertEquals("MLCF", peptides.get(2).getSequenceAsString());
+ assertEquals("CAA30421.1", peptides.get(3).getName());
+ assertEquals("MSSS", peptides.get(3).getSequenceAsString());
+ assertEquals("UNIPROT|B0BCM3", peptides.get(4).getName());
+ assertEquals("MSSS", peptides.get(4).getSequenceAsString());
+ assertEquals("CAA12345.6", peptides.get(5).getName());
+ assertEquals("MSS", peptides.get(5).getSequenceAsString());
+
+ /*
+ * verify dna sequence has dbrefs with CDS mappings to the peptide 'products'
+ */
+ MapList cds1Map = new MapList(new int[] { 57, 46 }, new int[] { 1, 4 },
+ 3, 1);
+ MapList cds2Map = new MapList(new int[] { 4, 15 }, new int[] { 1, 4 },
+ 3, 1);
+ MapList cds3Map = new MapList(new int[] { 4, 6, 10, 15 }, new int[] {
+ 1, 3 }, 3, 1);
+ DBRefEntry[] dbrefs = dna.getDBRefs();
+ assertEquals(4, dbrefs.length);
+ DBRefEntry dbRefEntry = dbrefs[0];
+ assertEquals("UNIPROT", dbRefEntry.getSource());
+ assertEquals("B0BCM4", dbRefEntry.getAccessionId());
+ assertSame(peptides.get(1), dbRefEntry.getMap().getTo());
+ assertEquals(cds1Map, dbRefEntry.getMap().getMap());
+
+ dbRefEntry = dbrefs[1];
+ assertEquals("UNIPROT", dbRefEntry.getSource());
+ assertEquals("P0CE20", dbRefEntry.getAccessionId());
+ assertSame(peptides.get(2), dbRefEntry.getMap().getTo());
+ assertEquals(cds1Map, dbRefEntry.getMap().getMap());
+
+ dbRefEntry = dbrefs[2];
+ assertEquals("UNIPROT", dbRefEntry.getSource());
+ assertEquals("B0BCM3", dbRefEntry.getAccessionId());
+ assertSame(peptides.get(4), dbRefEntry.getMap().getTo());
+ assertEquals(cds2Map, dbRefEntry.getMap().getMap());
+
+ dbRefEntry = dbrefs[3];
+ assertEquals("EMBLCDSPROTEIN", dbRefEntry.getSource());
+ assertEquals("CAA12345.6", dbRefEntry.getAccessionId());
+ assertSame(peptides.get(5), dbRefEntry.getMap().getTo());
+ assertEquals(cds3Map, dbRefEntry.getMap().getMap());
+
+ /*
+ * verify peptides have dbrefs
+ * - to EMBL sequence (with inverse 1:3 cds mapping)
+ * - to EMBLCDS (with 1:3 mapping)
+ * - direct (no mapping) to other protein accessions
+ */
+ MapList proteinToCdsMap1 = new MapList(new int[] { 1, 4 }, new int[] {
+ 1, 12 }, 1, 3);
+ MapList proteinToCdsMap2 = new MapList(new int[] { 1, 3 }, new int[] {
+ 1, 9 }, 1, 3);
+
+ // dbrefs for first CDS EMBL product CAA30420.1
+ dbrefs = peptides.get(0).getDBRefs();
+ assertEquals(5, dbrefs.length);
+ assertEquals(DBRefSource.EMBL, dbrefs[0].getSource());
+ assertEquals("CAA30420.1", dbrefs[0].getAccessionId());
+ // TODO: verify getPrimaryDBRefs() for peptide products
+ assertEquals(cds1Map.getInverse(), dbrefs[0].getMap().getMap());
+ assertEquals(DBRefSource.EMBLCDS, dbrefs[1].getSource());
+ assertEquals("CAA30420.1", dbrefs[1].getAccessionId());
+ assertEquals(proteinToCdsMap1, dbrefs[1].getMap().getMap());
+ assertEquals(DBRefSource.EMBLCDSProduct, dbrefs[2].getSource());
+ assertEquals("CAA30420.1", dbrefs[2].getAccessionId());
+ assertNull(dbrefs[2].getMap());
+ assertEquals(new DBRefEntry(DBRefSource.UNIPROT, "2.1", "B0BCM4"),
+ dbrefs[3]);
+ assertNull(dbrefs[3].getMap());
+ assertEquals(new DBRefEntry(DBRefSource.UNIPROT, "0", "P0CE20"),
+ dbrefs[4]);
+ assertNull(dbrefs[4].getMap());
+
+ // dbrefs for first CDS first Uniprot xref
+ dbrefs = peptides.get(1).getDBRefs();
+ assertEquals(2, dbrefs.length);
+ assertEquals(new DBRefEntry(DBRefSource.UNIPROT, "2.1", "B0BCM4"),
+ dbrefs[0]);
+ assertNull(dbrefs[0].getMap());
+ assertEquals(DBRefSource.EMBL, dbrefs[1].getSource());
+ assertEquals("X07547", dbrefs[1].getAccessionId());
+ assertEquals(cds1Map.getInverse(), dbrefs[1].getMap().getMap());
+
+ // dbrefs for first CDS second Uniprot xref
+ dbrefs = peptides.get(2).getDBRefs();
+ assertEquals(2, dbrefs.length);
+ assertEquals(new DBRefEntry(DBRefSource.UNIPROT, "0", "P0CE20"),
+ dbrefs[0]);
+ assertNull(dbrefs[0].getMap());
+ assertEquals(DBRefSource.EMBL, dbrefs[1].getSource());
+ assertEquals("X07547", dbrefs[1].getAccessionId());
+ assertEquals(cds1Map.getInverse(), dbrefs[1].getMap().getMap());
+
+ // dbrefs for second CDS EMBL product CAA30421.1
+ dbrefs = peptides.get(3).getDBRefs();
+ assertEquals(4, dbrefs.length);
+ assertEquals(DBRefSource.EMBL, dbrefs[0].getSource());
+ assertEquals("CAA30421.1", dbrefs[0].getAccessionId());
+ assertEquals(cds2Map.getInverse(), dbrefs[0].getMap().getMap());
+ assertEquals(DBRefSource.EMBLCDS, dbrefs[1].getSource());
+ assertEquals("CAA30421.1", dbrefs[1].getAccessionId());
+ assertEquals(proteinToCdsMap1, dbrefs[1].getMap().getMap());
+ assertEquals(DBRefSource.EMBLCDSProduct, dbrefs[2].getSource());
+ assertEquals("CAA30421.1", dbrefs[2].getAccessionId());
+ assertNull(dbrefs[2].getMap());
+ assertEquals(new DBRefEntry(DBRefSource.UNIPROT, "0", "B0BCM3"),
+ dbrefs[3]);
+ assertNull(dbrefs[3].getMap());
+
+ // dbrefs for second CDS second Uniprot xref
+ dbrefs = peptides.get(4).getDBRefs();
+ assertEquals(2, dbrefs.length);
+ assertEquals(new DBRefEntry(DBRefSource.UNIPROT, "0", "B0BCM3"),
+ dbrefs[0]);
+ assertNull(dbrefs[0].getMap());
+ assertEquals(DBRefSource.EMBL, dbrefs[1].getSource());
+ assertEquals("X07547", dbrefs[1].getAccessionId());
+ assertEquals(cds2Map.getInverse(), dbrefs[1].getMap().getMap());
+
+ // dbrefs for third CDS inferred EMBL product CAA12345.6
+ dbrefs = peptides.get(5).getDBRefs();
+ assertEquals(3, dbrefs.length);
+ assertEquals(DBRefSource.EMBL, dbrefs[0].getSource());
+ assertEquals("CAA12345.6", dbrefs[0].getAccessionId());
+ assertEquals(cds3Map.getInverse(), dbrefs[0].getMap().getMap());
+ assertEquals(DBRefSource.EMBLCDS, dbrefs[1].getSource());
+ assertEquals("CAA12345.6", dbrefs[1].getAccessionId());
+ assertEquals(proteinToCdsMap2, dbrefs[1].getMap().getMap());
+ assertEquals(DBRefSource.EMBLCDSProduct, dbrefs[2].getSource());
+ assertEquals("CAA12345.6", dbrefs[2].getAccessionId());
+ assertNull(dbrefs[2].getMap());
+ }
- /*
- * Make a (CDS) Feature with 4 locations
- */
- EmblFeature cds = new EmblFeature();
- Vector<EmblFeatureLocations> locs = new Vector<EmblFeatureLocations>();
- cds.setLocations(locs);
+ @Test(groups = "Functional")
+ public void testAdjustForProteinLength()
+ {
+ int[] exons = new int[] { 11, 15, 21, 25, 31, 38 }; // 18 bp
- /*
- * single range [10-20]
- */
- EmblFeatureLocations loc = new EmblFeatureLocations();
- loc.setLocationType("single");
- loc.setLocationComplement(false);
- Vector<EmblFeatureLocElement> elements = new Vector<EmblFeatureLocElement>();
- EmblFeatureLocElement locElement = new EmblFeatureLocElement();
- BasePosition b1 = new BasePosition();
- b1.setPos("10");
- BasePosition b2 = new BasePosition();
- b2.setPos("20");
- locElement.setBasePositions(new BasePosition[] { b1, b2 });
- elements.add(locElement);
- loc.setLocElements(elements);
- locs.add(loc);
+ // exact length match:
+ assertSame(exons, EmblEntry.adjustForProteinLength(6, exons));
- /*
- * single range with missing end position - should be skipped
- */
- loc = new EmblFeatureLocations();
- loc.setLocationType("single");
- loc.setLocationComplement(false);
- elements = new Vector<EmblFeatureLocElement>();
- locElement = new EmblFeatureLocElement();
- b1 = new BasePosition();
- b1.setPos("30");
- locElement.setBasePositions(new BasePosition[] { b1 });
- elements.add(locElement);
- loc.setLocElements(elements);
- locs.add(loc);
+ // match if we assume exons include stop codon not in protein:
+ assertSame(exons, EmblEntry.adjustForProteinLength(5, exons));
- /*
- * single range with extra base position - should be skipped
- */
- loc = new EmblFeatureLocations();
- loc.setLocationType("single");
- loc.setLocationComplement(false);
- elements = new Vector<EmblFeatureLocElement>();
- locElement = new EmblFeatureLocElement();
- b1 = new BasePosition();
- b1.setPos("30");
- locElement.setBasePositions(new BasePosition[] { b1, b1, b1 });
- elements.add(locElement);
- loc.setLocElements(elements);
- locs.add(loc);
+ // truncate last exon by 6bp
+ int[] truncated = EmblEntry.adjustForProteinLength(4, exons);
+ assertEquals("[11, 15, 21, 25, 31, 32]", Arrays.toString(truncated));
- /*
- * single valid range [50-60] to finish
- */
- loc = new EmblFeatureLocations();
- loc.setLocationType("single");
- loc.setLocationComplement(false);
- elements = new Vector<EmblFeatureLocElement>();
- locElement = new EmblFeatureLocElement();
- b1 = new BasePosition();
- b1.setPos("50");
- b2 = new BasePosition();
- b2.setPos("60");
- locElement.setBasePositions(new BasePosition[] { b1, b2 });
- elements.add(locElement);
- loc.setLocElements(elements);
- locs.add(loc);
+ // remove last exon and truncate preceding by 1bp
+ truncated = EmblEntry.adjustForProteinLength(3, exons);
+ assertEquals("[11, 15, 21, 24]", Arrays.toString(truncated));
- int[] exons = testee.getCdsRanges(cds);
- assertEquals("[10, 20, 50, 60]", Arrays.toString(exons));
- }
+ // exact removal of exon case:
+ exons = new int[] { 11, 15, 21, 27, 33, 38 }; // 18 bp
+ truncated = EmblEntry.adjustForProteinLength(4, exons);
+ assertEquals("[11, 15, 21, 27]", Arrays.toString(truncated));
- /**
- * Test retrieval of exon locations matching an accession id
- */
- @Test(groups = "Functional")
- public void testGetCdsRanges_forAccession()
- {
- EmblEntry testee = new EmblEntry();
- String accession = "A1234";
- testee.setAccession(accession);
- /*
- * Make a (CDS) Feature with 4 locations
- */
- EmblFeature cds = new EmblFeature();
- Vector<EmblFeatureLocations> locs = new Vector<EmblFeatureLocations>();
- cds.setLocations(locs);
-
- /*
- * single range [10-20] for 'this' accession
- */
- EmblFeatureLocations loc = new EmblFeatureLocations();
- loc.setLocationType("single");
- loc.setLocationComplement(false);
- Vector<EmblFeatureLocElement> elements = new Vector<EmblFeatureLocElement>();
- EmblFeatureLocElement locElement = new EmblFeatureLocElement();
- locElement.setAccession(accession);
- BasePosition b1 = new BasePosition();
- b1.setPos("10");
- BasePosition b2 = new BasePosition();
- b2.setPos("20");
- locElement.setBasePositions(new BasePosition[] { b1, b2 });
- elements.add(locElement);
- loc.setLocElements(elements);
- locs.add(loc);
-
- /*
- * complement range [30-40] - no accession
- */
- loc = new EmblFeatureLocations();
- loc.setLocationType("single");
- loc.setLocationComplement(true);
- elements = new Vector<EmblFeatureLocElement>();
- locElement = new EmblFeatureLocElement();
- b1 = new BasePosition();
- b1.setPos("30");
- b2 = new BasePosition();
- b2.setPos("40");
- locElement.setBasePositions(new BasePosition[] { b1, b2 });
- elements.add(locElement);
- loc.setLocElements(elements);
- locs.add(loc);
-
- /*
- * join range [50-60] this accession, [70-80] another
- */
- loc = new EmblFeatureLocations();
- loc.setLocationType("join");
- loc.setLocationComplement(false);
- elements = new Vector<EmblFeatureLocElement>();
- locElement = new EmblFeatureLocElement();
- locElement.setAccession(accession);
- b1 = new BasePosition();
- b1.setPos("50");
- b2 = new BasePosition();
- b2.setPos("60");
- locElement.setBasePositions(new BasePosition[] { b1, b2 });
- elements.add(locElement);
- locElement = new EmblFeatureLocElement();
- locElement.setAccession("notme");
- b1 = new BasePosition();
- b1.setPos("70");
- b2 = new BasePosition();
- b2.setPos("80");
- locElement.setBasePositions(new BasePosition[] { b1, b2 });
- elements.add(locElement);
- loc.setLocElements(elements);
- locs.add(loc);
-
- /*
- * complement range [90-100] wrong accession, [110-120] good
- * this should be the same as complement(join(90..100,110.120))
- * which is "join 90-100 and 110-120, then complement"
- */
- loc = new EmblFeatureLocations();
- loc.setLocationType("join");
- loc.setLocationComplement(true);
- elements = new Vector<EmblFeatureLocElement>();
- locElement = new EmblFeatureLocElement();
- locElement.setAccession("wrong");
- b1 = new BasePosition();
- b1.setPos("90");
- b2 = new BasePosition();
- b2.setPos("100");
- locElement.setBasePositions(new BasePosition[] { b1, b2 });
- elements.add(locElement);
- locElement = new EmblFeatureLocElement();
- locElement.setAccession(accession);
- b1 = new BasePosition();
- b1.setPos("110");
- b2 = new BasePosition();
- b2.setPos("120");
- locElement.setBasePositions(new BasePosition[] { b1, b2 });
- elements.add(locElement);
- loc.setLocElements(elements);
- locs.add(loc);
-
- /*
- * verify we pick out only ranges for A1234
- */
- int[] exons = testee.getCdsRanges(cds);
- assertEquals("[10, 20, 50, 60, 120, 110]",
- Arrays.toString(exons));
+ // what if exons are too short for protein?
+ truncated = EmblEntry.adjustForProteinLength(7, exons);
+ assertSame(exons, truncated);
}
}