import jalview.datamodel.SearchResults;
import jalview.datamodel.SearchResults.Match;
import jalview.datamodel.Sequence;
+import jalview.datamodel.SequenceFeature;
import jalview.datamodel.SequenceI;
import jalview.io.AppletFormatAdapter;
import jalview.io.FormatAdapter;
}
/**
- * Test the method that extracts the exon-only part of a dna alignment.
+ * Test the method that extracts the cds-only part of a dna alignment.
*/
@Test(groups = { "Functional" })
- public void testMakeExonAlignment()
+ public void testMakeCdsAlignment()
{
SequenceI dna1 = new Sequence("dna1", "aaaGGGcccTTTaaa");
SequenceI dna2 = new Sequence("dna2", "GGGcccTTTaaaCCC");
acf.addMap(dna2.getDatasetSequence(), pep2.getDatasetSequence(), map);
mappings.add(acf);
- AlignmentI exons = AlignmentUtils.makeExonAlignment(new SequenceI[] {
+ AlignmentI cds = AlignmentUtils.makeCdsAlignment(new SequenceI[] {
dna1, dna2 }, mappings);
- assertEquals(2, exons.getSequences().size());
- assertEquals("GGGTTT", exons.getSequenceAt(0).getSequenceAsString());
- assertEquals("GGGTTTCCC", exons.getSequenceAt(1).getSequenceAsString());
+ assertEquals(2, cds.getSequences().size());
+ assertEquals("GGGTTT", cds.getSequenceAt(0).getSequenceAsString());
+ assertEquals("GGGTTTCCC", cds.getSequenceAt(1).getSequenceAsString());
/*
* Verify updated mappings
SearchResults sr = MappingUtils.buildSearchResults(pep1, 1, mappings);
assertEquals(1, sr.getResults().size());
Match m = sr.getResults().get(0);
- assertEquals(exons.getSequenceAt(0).getDatasetSequence(),
+ assertEquals(cds.getSequenceAt(0).getDatasetSequence(),
m.getSequence());
assertEquals(1, m.getStart());
assertEquals(3, m.getEnd());
// map F to TTT
sr = MappingUtils.buildSearchResults(pep1, 2, mappings);
m = sr.getResults().get(0);
- assertEquals(exons.getSequenceAt(0).getDatasetSequence(),
+ assertEquals(cds.getSequenceAt(0).getDatasetSequence(),
m.getSequence());
assertEquals(4, m.getStart());
assertEquals(6, m.getEnd());
sr = MappingUtils.buildSearchResults(pep2, 1, mappings);
assertEquals(1, sr.getResults().size());
m = sr.getResults().get(0);
- assertEquals(exons.getSequenceAt(1).getDatasetSequence(),
+ assertEquals(cds.getSequenceAt(1).getDatasetSequence(),
m.getSequence());
assertEquals(1, m.getStart());
assertEquals(3, m.getEnd());
// map F to TTT
sr = MappingUtils.buildSearchResults(pep2, 2, mappings);
m = sr.getResults().get(0);
- assertEquals(exons.getSequenceAt(1).getDatasetSequence(),
+ assertEquals(cds.getSequenceAt(1).getDatasetSequence(),
m.getSequence());
assertEquals(4, m.getStart());
assertEquals(6, m.getEnd());
// map P to CCC
sr = MappingUtils.buildSearchResults(pep2, 3, mappings);
m = sr.getResults().get(0);
- assertEquals(exons.getSequenceAt(1).getDatasetSequence(),
+ assertEquals(cds.getSequenceAt(1).getDatasetSequence(),
m.getSequence());
assertEquals(7, m.getStart());
assertEquals(9, m.getEnd());
}
/**
- * Test the method that makes an exon-only sequence from a DNA sequence and
- * its product mapping. Test includes the expected case that the DNA sequence
+ * Test the method that makes a cds-only sequence from a DNA sequence and its
+ * product mapping. Test includes the expected case that the DNA sequence
* already has a protein product (Uniprot translation) which in turn has an
* x-ref to the EMBLCDS record.
*/
@Test(groups = { "Functional" })
- public void testMakeExonSequences()
+ public void testMakeCdsSequences()
{
SequenceI dna1 = new Sequence("dna1", "aaaGGGcccTTTaaa");
SequenceI pep1 = new Sequence("pep1", "GF");
mappings.add(acf);
AlignedCodonFrame newMapping = new AlignedCodonFrame();
- List<SequenceI> exons = AlignmentUtils.makeExonSequences(dna1, acf,
+ List<SequenceI> cdsSeqs = AlignmentUtils.makeCdsSequences(dna1, acf,
newMapping);
- assertEquals(1, exons.size());
- SequenceI exon = exons.get(0);
+ assertEquals(1, cdsSeqs.size());
+ SequenceI cdsSeq = cdsSeqs.get(0);
- assertEquals("GGGTTT", exon.getSequenceAsString());
- assertEquals("dna1|A12345", exon.getName());
- assertEquals(1, exon.getDBRef().length);
- DBRefEntry cdsRef = exon.getDBRef()[0];
+ assertEquals("GGGTTT", cdsSeq.getSequenceAsString());
+ assertEquals("dna1|A12345", cdsSeq.getName());
+ assertEquals(1, cdsSeq.getDBRef().length);
+ DBRefEntry cdsRef = cdsSeq.getDBRef()[0];
assertEquals("EMBLCDS", cdsRef.getSource());
assertEquals("2", cdsRef.getVersion());
assertEquals("A12345", cdsRef.getAccessionId());
}
/**
- * Test the method that makes an exon-only alignment from a DNA sequence and
- * its product mappings, for the case where there are multiple exon mappings
- * to different protein products.
+ * Test the method that makes a cds-only alignment from a DNA sequence and its
+ * product mappings, for the case where there are multiple exon mappings to
+ * different protein products.
*/
@Test(groups = { "Functional" })
- public void testMakeExonAlignment_multipleProteins()
+ public void testMakeCdsAlignment_multipleProteins()
{
SequenceI dna1 = new Sequence("dna1", "aaaGGGcccTTTaaa");
SequenceI pep1 = new Sequence("pep1", "GF"); // GGGTTT
* Create the Exon alignment; also replaces the dna-to-protein mappings with
* exon-to-protein and exon-to-dna mappings
*/
- AlignmentI exal = AlignmentUtils.makeExonAlignment(
+ AlignmentI exal = AlignmentUtils.makeCdsAlignment(
new SequenceI[] { dna1 }, mappings);
/*
- * Verify we have 3 exon sequences, mapped to pep1/2/3 respectively
+ * Verify we have 3 cds sequences, mapped to pep1/2/3 respectively
*/
- List<SequenceI> exons = exal.getSequences();
- assertEquals(3, exons.size());
-
- SequenceI exon = exons.get(0);
- assertEquals("GGGTTT", exon.getSequenceAsString());
- assertEquals("dna1|A12345", exon.getName());
- assertEquals(1, exon.getDBRef().length);
- DBRefEntry cdsRef = exon.getDBRef()[0];
+ List<SequenceI> cds = exal.getSequences();
+ assertEquals(3, cds.size());
+
+ SequenceI cdsSeq = cds.get(0);
+ assertEquals("GGGTTT", cdsSeq.getSequenceAsString());
+ assertEquals("dna1|A12345", cdsSeq.getName());
+ assertEquals(1, cdsSeq.getDBRef().length);
+ DBRefEntry cdsRef = cdsSeq.getDBRef()[0];
assertEquals("EMBLCDS", cdsRef.getSource());
assertEquals("2", cdsRef.getVersion());
assertEquals("A12345", cdsRef.getAccessionId());
- exon = exons.get(1);
- assertEquals("aaaccc", exon.getSequenceAsString());
- assertEquals("dna1|A12346", exon.getName());
- assertEquals(1, exon.getDBRef().length);
- cdsRef = exon.getDBRef()[0];
+ cdsSeq = cds.get(1);
+ assertEquals("aaaccc", cdsSeq.getSequenceAsString());
+ assertEquals("dna1|A12346", cdsSeq.getName());
+ assertEquals(1, cdsSeq.getDBRef().length);
+ cdsRef = cdsSeq.getDBRef()[0];
assertEquals("EMBLCDS", cdsRef.getSource());
assertEquals("3", cdsRef.getVersion());
assertEquals("A12346", cdsRef.getAccessionId());
- exon = exons.get(2);
- assertEquals("aaaTTT", exon.getSequenceAsString());
- assertEquals("dna1|A12347", exon.getName());
- assertEquals(1, exon.getDBRef().length);
- cdsRef = exon.getDBRef()[0];
+ cdsSeq = cds.get(2);
+ assertEquals("aaaTTT", cdsSeq.getSequenceAsString());
+ assertEquals("dna1|A12347", cdsSeq.getName());
+ assertEquals(1, cdsSeq.getDBRef().length);
+ cdsRef = cdsSeq.getDBRef()[0];
assertEquals("EMBLCDS", cdsRef.getSource());
assertEquals("4", cdsRef.getVersion());
assertEquals("A12347", cdsRef.getAccessionId());
/*
- * Verify there are mappings from each exon sequence to its protein product
+ * Verify there are mappings from each cds sequence to its protein product
* and also to its dna source
*/
Iterator<AlignedCodonFrame> newMappingsIterator = mappings.iterator();
// mappings for dna1 - exon1 - pep1
- AlignedCodonFrame exonMapping = newMappingsIterator.next();
- List<Mapping> dnaMappings = exonMapping.getMappingsForSequence(dna1);
+ AlignedCodonFrame cdsMapping = newMappingsIterator.next();
+ List<Mapping> dnaMappings = cdsMapping.getMappingsForSequence(dna1);
assertEquals(1, dnaMappings.size());
- assertSame(exons.get(0).getDatasetSequence(), dnaMappings.get(0)
+ assertSame(cds.get(0).getDatasetSequence(), dnaMappings.get(0)
.getTo());
assertEquals("G(1) in CDS should map to G(4) in DNA", 4, dnaMappings
.get(0).getMap().getToPosition(1));
- List<Mapping> peptideMappings = exonMapping
+ List<Mapping> peptideMappings = cdsMapping
.getMappingsForSequence(pep1);
assertEquals(1, peptideMappings.size());
assertSame(pep1.getDatasetSequence(), peptideMappings.get(0).getTo());
- // mappings for dna1 - exon2 - pep2
- exonMapping = newMappingsIterator.next();
- dnaMappings = exonMapping.getMappingsForSequence(dna1);
+ // mappings for dna1 - cds2 - pep2
+ cdsMapping = newMappingsIterator.next();
+ dnaMappings = cdsMapping.getMappingsForSequence(dna1);
assertEquals(1, dnaMappings.size());
- assertSame(exons.get(1).getDatasetSequence(), dnaMappings.get(0)
+ assertSame(cds.get(1).getDatasetSequence(), dnaMappings.get(0)
.getTo());
assertEquals("c(4) in CDS should map to c(7) in DNA", 7, dnaMappings
.get(0).getMap().getToPosition(4));
- peptideMappings = exonMapping.getMappingsForSequence(pep2);
+ peptideMappings = cdsMapping.getMappingsForSequence(pep2);
assertEquals(1, peptideMappings.size());
assertSame(pep2.getDatasetSequence(), peptideMappings.get(0).getTo());
- // mappings for dna1 - exon3 - pep3
- exonMapping = newMappingsIterator.next();
- dnaMappings = exonMapping.getMappingsForSequence(dna1);
+ // mappings for dna1 - cds3 - pep3
+ cdsMapping = newMappingsIterator.next();
+ dnaMappings = cdsMapping.getMappingsForSequence(dna1);
assertEquals(1, dnaMappings.size());
- assertSame(exons.get(2).getDatasetSequence(), dnaMappings.get(0)
+ assertSame(cds.get(2).getDatasetSequence(), dnaMappings.get(0)
.getTo());
assertEquals("T(4) in CDS should map to T(10) in DNA", 10, dnaMappings
.get(0).getMap().getToPosition(4));
- peptideMappings = exonMapping.getMappingsForSequence(pep3);
+ peptideMappings = cdsMapping.getMappingsForSequence(pep3);
assertEquals(1, peptideMappings.size());
assertSame(pep3.getDatasetSequence(), peptideMappings.get(0).getTo());
}
checkAlignSequenceAs("AAACCCTTT", "K-PFG", true, true, map,
"AAA---CCCTTT---");
}
+
+ @Test(groups = { "Functional" })
+ public void testTransferFeatures()
+ {
+ SequenceI dna = new Sequence("dna/20-34", "acgTAGcaaGCCcgt");
+ SequenceI cds = new Sequence("cds/10-15", "TAGGCC");
+
+ // no overlap
+ dna.addSequenceFeature(new SequenceFeature("type1", "desc1", 1, 2, 1f,
+ null));
+ // partial overlap - to [1, 1]
+ dna.addSequenceFeature(new SequenceFeature("type2", "desc2", 3, 4, 2f,
+ null));
+ // exact overlap - to [1, 3]
+ dna.addSequenceFeature(new SequenceFeature("type3", "desc3", 4, 6, 3f,
+ null));
+ // spanning overlap - to [2, 5]
+ dna.addSequenceFeature(new SequenceFeature("type4", "desc4", 5, 11, 4f,
+ null));
+ // exactly overlaps whole mapped range [1, 6]
+ dna.addSequenceFeature(new SequenceFeature("type5", "desc5", 4, 12, 5f,
+ null));
+ // no overlap (internal)
+ dna.addSequenceFeature(new SequenceFeature("type6", "desc6", 7, 9, 6f,
+ null));
+ // no overlap (3' end)
+ dna.addSequenceFeature(new SequenceFeature("type7", "desc7", 13, 15,
+ 7f, null));
+ // overlap (3' end) - to [6, 6]
+ dna.addSequenceFeature(new SequenceFeature("type8", "desc8", 12, 12,
+ 8f, null));
+ // extended overlap - to [6, +]
+ dna.addSequenceFeature(new SequenceFeature("type9", "desc9", 12, 13,
+ 9f, null));
+
+ MapList map = new MapList(new int[] { 4, 6, 10, 12 },
+ new int[] { 1, 6 }, 1, 1);
+
+ /*
+ * behaviour of transferFeatures depends on MapList.locateInTo()
+ * if start and end positions are mapped, returns the mapped region
+ * if either is not mapped, does _not_ search for overlapped region
+ */
+ AlignmentUtils.transferFeatures(dna, cds, map);
+ SequenceFeature[] sfs = cds.getSequenceFeatures();
+ assertEquals(4, sfs.length);
+
+ SequenceFeature sf = sfs[0];
+ assertEquals("type3", sf.getType());
+ assertEquals("desc3", sf.getDescription());
+ assertEquals(3f, sf.getScore());
+ assertEquals(1, sf.getBegin());
+ assertEquals(3, sf.getEnd());
+
+ sf = sfs[1];
+ assertEquals("type4", sf.getType());
+ assertEquals(2, sf.getBegin());
+ assertEquals(5, sf.getEnd());
+
+ sf = sfs[2];
+ assertEquals("type5", sf.getType());
+ assertEquals(1, sf.getBegin());
+ assertEquals(6, sf.getEnd());
+
+ sf = sfs[3];
+ assertEquals("type8", sf.getType());
+ assertEquals(6, sf.getBegin());
+ assertEquals(6, sf.getEnd());
+ }
}