import static org.testng.AssertJUnit.assertSame;
import static org.testng.AssertJUnit.assertTrue;
+import jalview.analysis.AlignmentUtils.DnaVariant;
import jalview.datamodel.AlignedCodonFrame;
import jalview.datamodel.Alignment;
import jalview.datamodel.AlignmentAnnotation;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
-import java.util.HashSet;
import java.util.Iterator;
import java.util.LinkedHashMap;
import java.util.List;
import java.util.Map;
-import java.util.Set;
+import java.util.TreeMap;
import org.testng.annotations.Test;
public class AlignmentUtilsTests
{
- // @formatter:off
- private static final String TEST_DATA =
- "# STOCKHOLM 1.0\n" +
- "#=GS D.melanogaster.1 AC AY119185.1/838-902\n" +
- "#=GS D.melanogaster.2 AC AC092237.1/57223-57161\n" +
- "#=GS D.melanogaster.3 AC AY060611.1/560-627\n" +
- "D.melanogaster.1 G.AGCC.CU...AUGAUCGA\n" +
- "#=GR D.melanogaster.1 SS ................((((\n" +
- "D.melanogaster.2 C.AUUCAACU.UAUGAGGAU\n" +
- "#=GR D.melanogaster.2 SS ................((((\n" +
- "D.melanogaster.3 G.UGGCGCU..UAUGACGCA\n" +
- "#=GR D.melanogaster.3 SS (.(((...(....(((((((\n" +
- "//";
-
- private static final String AA_SEQS_1 =
- ">Seq1Name\n" +
- "K-QY--L\n" +
- ">Seq2Name\n" +
- "-R-FP-W-\n";
-
- private static final String CDNA_SEQS_1 =
- ">Seq1Name\n" +
- "AC-GG--CUC-CAA-CT\n" +
- ">Seq2Name\n" +
- "-CG-TTA--ACG---AAGT\n";
-
- private static final String CDNA_SEQS_2 =
- ">Seq1Name\n" +
- "GCTCGUCGTACT\n" +
- ">Seq2Name\n" +
- "GGGTCAGGCAGT\n";
- // @formatter:on
-
- // public static Sequence ts=new
- // Sequence("short","ASDASDASDASDASDASDASDASDASDASDASDASDASD");
public static Sequence ts = new Sequence("short",
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklm");
}
/**
- * Test for the method that generates an aligned translated sequence from one
- * mapping.
- */
- @Test(groups = { "Functional" })
- public void testGetAlignedTranslation_dnaLikeProtein()
- {
- // dna alignment will be replaced
- SequenceI dna = new Sequence("Seq1", "T-G-CC-A--T-TAC-CAG-");
- dna.createDatasetSequence();
- // protein alignment will be 'applied' to dna
- SequenceI protein = new Sequence("Seq1", "-CH-Y--Q-");
- protein.createDatasetSequence();
- MapList map = new MapList(new int[] { 1, 12 }, new int[] { 1, 4 }, 3, 1);
- AlignedCodonFrame acf = new AlignedCodonFrame();
- acf.addMap(dna.getDatasetSequence(), protein.getDatasetSequence(), map);
-
- final SequenceI aligned = AlignmentUtils.getAlignedTranslation(protein,
- '-', acf);
- assertEquals("---TGCCAT---TAC------CAG---",
- aligned.getSequenceAsString());
- assertSame(aligned.getDatasetSequence(), dna.getDatasetSequence());
- }
-
- /**
* Test the method that realigns protein to match mapped codon alignment.
*/
@Test(groups = { "Functional" })
acf.addMap(dna2.getDatasetSequence(), pep2.getDatasetSequence(), map);
mappings.add(acf);
+ /*
+ * execute method under test:
+ */
AlignmentI cds = AlignmentUtils.makeCdsAlignment(new SequenceI[] {
dna1, dna2 }, mappings, dna);
+
assertEquals(2, cds.getSequences().size());
- assertEquals("---GGG---TTT---", cds.getSequenceAt(0)
+ assertEquals("GGGTTT", cds.getSequenceAt(0)
.getSequenceAsString());
- assertEquals("GGG---TTT---CCC", cds.getSequenceAt(1)
+ assertEquals("GGGTTTCCC", cds.getSequenceAt(1)
.getSequenceAsString());
/*
.contains(cds.getSequenceAt(1).getDatasetSequence()));
/*
- * Verify updated mappings
+ * Verify mappings from CDS to peptide and cDNA to CDS
+ * the mappings are on the shared alignment dataset
*/
- assertEquals(2, mappings.size());
-
+ assertSame(dna.getCodonFrames(), cds.getCodonFrames());
+ List<AlignedCodonFrame> cdsMappings = cds.getCodonFrames();
+ assertEquals(2, cdsMappings.size());
+
/*
* Mapping from pep1 to GGGTTT in first new exon sequence
*/
List<AlignedCodonFrame> pep1Mapping = MappingUtils
- .findMappingsForSequence(pep1, mappings);
+ .findMappingsForSequence(pep1, cdsMappings);
assertEquals(1, pep1Mapping.size());
// map G to GGG
- SearchResults sr = MappingUtils.buildSearchResults(pep1, 1, mappings);
+ SearchResults sr = MappingUtils
+ .buildSearchResults(pep1, 1, cdsMappings);
assertEquals(1, sr.getResults().size());
Match m = sr.getResults().get(0);
assertSame(cds.getSequenceAt(0).getDatasetSequence(),
assertEquals(1, m.getStart());
assertEquals(3, m.getEnd());
// map F to TTT
- sr = MappingUtils.buildSearchResults(pep1, 2, mappings);
+ sr = MappingUtils.buildSearchResults(pep1, 2, cdsMappings);
m = sr.getResults().get(0);
assertSame(cds.getSequenceAt(0).getDatasetSequence(),
m.getSequence());
* Mapping from pep2 to GGGTTTCCC in second new exon sequence
*/
List<AlignedCodonFrame> pep2Mapping = MappingUtils
- .findMappingsForSequence(pep2, mappings);
+ .findMappingsForSequence(pep2, cdsMappings);
assertEquals(1, pep2Mapping.size());
// map G to GGG
- sr = MappingUtils.buildSearchResults(pep2, 1, mappings);
+ sr = MappingUtils.buildSearchResults(pep2, 1, cdsMappings);
assertEquals(1, sr.getResults().size());
m = sr.getResults().get(0);
assertSame(cds.getSequenceAt(1).getDatasetSequence(),
assertEquals(1, m.getStart());
assertEquals(3, m.getEnd());
// map F to TTT
- sr = MappingUtils.buildSearchResults(pep2, 2, mappings);
+ sr = MappingUtils.buildSearchResults(pep2, 2, cdsMappings);
m = sr.getResults().get(0);
assertSame(cds.getSequenceAt(1).getDatasetSequence(),
m.getSequence());
assertEquals(4, m.getStart());
assertEquals(6, m.getEnd());
// map P to CCC
- sr = MappingUtils.buildSearchResults(pep2, 3, mappings);
+ sr = MappingUtils.buildSearchResults(pep2, 3, cdsMappings);
m = sr.getResults().get(0);
assertSame(cds.getSequenceAt(1).getDatasetSequence(),
m.getSequence());
}
/**
- * 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 testMakeCdsSequences()
- {
- SequenceI dna1 = new Sequence("dna1", "aaaGGGcccTTTaaa");
- SequenceI pep1 = new Sequence("pep1", "GF");
- dna1.createDatasetSequence();
- pep1.createDatasetSequence();
- pep1.getDatasetSequence().addDBRef(
- new DBRefEntry("EMBLCDS", "2", "A12345"));
-
- /*
- * Make the mapping from dna to protein. The protein sequence has a DBRef to
- * EMBLCDS|A12345.
- */
- Set<AlignedCodonFrame> mappings = new HashSet<AlignedCodonFrame>();
- MapList map = new MapList(new int[] { 4, 6, 10, 12 },
- new int[] { 1, 2 }, 3, 1);
- AlignedCodonFrame acf = new AlignedCodonFrame();
- acf.addMap(dna1.getDatasetSequence(), pep1.getDatasetSequence(), map);
- mappings.add(acf);
-
- AlignedCodonFrame newMapping = new AlignedCodonFrame();
- List<int[]> ungappedColumns = new ArrayList<int[]>();
- ungappedColumns.add(new int[] { 4, 6 });
- ungappedColumns.add(new int[] { 10, 12 });
- List<SequenceI> cdsSeqs = AlignmentUtils.makeCdsSequences(dna1, acf,
- ungappedColumns,
- newMapping, '-');
- assertEquals(1, cdsSeqs.size());
- SequenceI cdsSeq = cdsSeqs.get(0);
-
- assertEquals("GGGTTT", cdsSeq.getSequenceAsString());
- assertEquals("dna1|A12345", cdsSeq.getName());
- assertEquals(1, cdsSeq.getDBRefs().length);
- DBRefEntry cdsRef = cdsSeq.getDBRefs()[0];
- assertEquals("EMBLCDS", cdsRef.getSource());
- assertEquals("2", cdsRef.getVersion());
- assertEquals("A12345", cdsRef.getAccessionId());
- }
-
- /**
* 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.
mappings.add(acf);
/*
- * Create the Exon alignment; also replaces the dna-to-protein mappings with
+ * Create the CDS alignment; also augments the dna-to-protein mappings with
* exon-to-protein and exon-to-dna mappings
*/
AlignmentI dna = new Alignment(new SequenceI[] { dna1 });
dna.setDataset(null);
- AlignmentI exal = AlignmentUtils.makeCdsAlignment(
+
+ /*
+ * execute method under test
+ */
+ AlignmentI cdsal = AlignmentUtils.makeCdsAlignment(
new SequenceI[] { dna1 }, mappings, dna);
/*
* Verify we have 3 cds sequences, mapped to pep1/2/3 respectively
*/
- List<SequenceI> cds = exal.getSequences();
+ List<SequenceI> cds = cdsal.getSequences();
assertEquals(3, cds.size());
/*
* verify shared, extended alignment dataset
*/
- assertSame(exal.getDataset(), dna.getDataset());
+ assertSame(cdsal.getDataset(), dna.getDataset());
assertTrue(dna.getDataset().getSequences()
.contains(cds.get(0).getDatasetSequence()));
assertTrue(dna.getDataset().getSequences()
* verify aligned cds sequences and their xrefs
*/
SequenceI cdsSeq = cds.get(0);
- assertEquals("---GGG---TTT", cdsSeq.getSequenceAsString());
- assertEquals("dna1|A12345", cdsSeq.getName());
- assertEquals(1, cdsSeq.getDBRefs().length);
- DBRefEntry cdsRef = cdsSeq.getDBRefs()[0];
- assertEquals("EMBLCDS", cdsRef.getSource());
- assertEquals("2", cdsRef.getVersion());
- assertEquals("A12345", cdsRef.getAccessionId());
+ assertEquals("GGGTTT", cdsSeq.getSequenceAsString());
+ // assertEquals("dna1|A12345", cdsSeq.getName());
+ assertEquals("dna1|pep1", cdsSeq.getName());
+ // assertEquals(1, cdsSeq.getDBRefs().length);
+ // DBRefEntry cdsRef = cdsSeq.getDBRefs()[0];
+ // assertEquals("EMBLCDS", cdsRef.getSource());
+ // assertEquals("2", cdsRef.getVersion());
+ // assertEquals("A12345", cdsRef.getAccessionId());
cdsSeq = cds.get(1);
- assertEquals("aaa---ccc---", cdsSeq.getSequenceAsString());
- assertEquals("dna1|A12346", cdsSeq.getName());
- assertEquals(1, cdsSeq.getDBRefs().length);
- cdsRef = cdsSeq.getDBRefs()[0];
- assertEquals("EMBLCDS", cdsRef.getSource());
- assertEquals("3", cdsRef.getVersion());
- assertEquals("A12346", cdsRef.getAccessionId());
+ assertEquals("aaaccc", cdsSeq.getSequenceAsString());
+ // assertEquals("dna1|A12346", cdsSeq.getName());
+ assertEquals("dna1|pep2", cdsSeq.getName());
+ // assertEquals(1, cdsSeq.getDBRefs().length);
+ // cdsRef = cdsSeq.getDBRefs()[0];
+ // assertEquals("EMBLCDS", cdsRef.getSource());
+ // assertEquals("3", cdsRef.getVersion());
+ // assertEquals("A12346", cdsRef.getAccessionId());
cdsSeq = cds.get(2);
- assertEquals("aaa------TTT", cdsSeq.getSequenceAsString());
- assertEquals("dna1|A12347", cdsSeq.getName());
- assertEquals(1, cdsSeq.getDBRefs().length);
- cdsRef = cdsSeq.getDBRefs()[0];
- assertEquals("EMBLCDS", cdsRef.getSource());
- assertEquals("4", cdsRef.getVersion());
- assertEquals("A12347", cdsRef.getAccessionId());
+ assertEquals("aaaTTT", cdsSeq.getSequenceAsString());
+ // assertEquals("dna1|A12347", cdsSeq.getName());
+ assertEquals("dna1|pep3", cdsSeq.getName());
+ // assertEquals(1, cdsSeq.getDBRefs().length);
+ // cdsRef = cdsSeq.getDBRefs()[0];
+ // assertEquals("EMBLCDS", cdsRef.getSource());
+ // assertEquals("4", cdsRef.getVersion());
+ // assertEquals("A12347", cdsRef.getAccessionId());
/*
* Verify there are mappings from each cds sequence to its protein product
* and also to its dna source
*/
- Iterator<AlignedCodonFrame> newMappingsIterator = mappings.iterator();
+ Iterator<AlignedCodonFrame> newMappingsIterator = cdsal
+ .getCodonFrames().iterator();
// mappings for dna1 - exon1 - pep1
AlignedCodonFrame cdsMapping = newMappingsIterator.next();
- List<Mapping> dnaMappings = cdsMapping.getMappingsForSequence(dna1);
- assertEquals(1, dnaMappings.size());
+ List<Mapping> dnaMappings = cdsMapping.getMappingsFromSequence(dna1);
+ assertEquals(3, dnaMappings.size());
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 = cdsMapping
- .getMappingsForSequence(pep1);
+ List<Mapping> peptideMappings = cdsMapping.getMappingsFromSequence(cds
+ .get(0).getDatasetSequence());
assertEquals(1, peptideMappings.size());
assertSame(pep1.getDatasetSequence(), peptideMappings.get(0).getTo());
// mappings for dna1 - cds2 - pep2
- cdsMapping = newMappingsIterator.next();
- dnaMappings = cdsMapping.getMappingsForSequence(dna1);
- assertEquals(1, dnaMappings.size());
- assertSame(cds.get(1).getDatasetSequence(), dnaMappings.get(0)
+ assertSame(cds.get(1).getDatasetSequence(), dnaMappings.get(1)
.getTo());
assertEquals("c(4) in CDS should map to c(7) in DNA", 7, dnaMappings
- .get(0).getMap().getToPosition(4));
- peptideMappings = cdsMapping.getMappingsForSequence(pep2);
+ .get(1).getMap().getToPosition(4));
+ peptideMappings = cdsMapping.getMappingsFromSequence(cds.get(1)
+ .getDatasetSequence());
assertEquals(1, peptideMappings.size());
assertSame(pep2.getDatasetSequence(), peptideMappings.get(0).getTo());
// mappings for dna1 - cds3 - pep3
- cdsMapping = newMappingsIterator.next();
- dnaMappings = cdsMapping.getMappingsForSequence(dna1);
- assertEquals(1, dnaMappings.size());
- assertSame(cds.get(2).getDatasetSequence(), dnaMappings.get(0)
+ assertSame(cds.get(2).getDatasetSequence(), dnaMappings.get(2)
.getTo());
assertEquals("T(4) in CDS should map to T(10) in DNA", 10, dnaMappings
- .get(0).getMap().getToPosition(4));
- peptideMappings = cdsMapping.getMappingsForSequence(pep3);
+ .get(2).getMap().getToPosition(4));
+ peptideMappings = cdsMapping.getMappingsFromSequence(cds.get(2)
+ .getDatasetSequence());
assertEquals(1, peptideMappings.size());
assertSame(pep3.getDatasetSequence(), peptideMappings.get(0).getTo());
}
List<SequenceI> cdsSeqs = cds.getSequences();
assertEquals(2, cdsSeqs.size());
assertEquals("GGGCCCTTTGGG", cdsSeqs.get(0).getSequenceAsString());
- assertEquals("GGGCC---TGGG", cdsSeqs.get(1).getSequenceAsString());
+ assertEquals("GGGCCTGGG", cdsSeqs.get(1).getSequenceAsString());
/*
* verify shared, extended alignment dataset
/*
* Verify updated mappings
*/
- assertEquals(2, mappings.size());
+ List<AlignedCodonFrame> cdsMappings = cds.getCodonFrames();
+ assertEquals(2, cdsMappings.size());
/*
* Mapping from pep1 to GGGTTT in first new CDS sequence
*/
List<AlignedCodonFrame> pep1Mapping = MappingUtils
- .findMappingsForSequence(pep1, mappings);
+ .findMappingsForSequence(pep1, cdsMappings);
assertEquals(1, pep1Mapping.size());
/*
* maps GPFG to 1-3,4-6,7-9,10-12
*/
- SearchResults sr = MappingUtils.buildSearchResults(pep1, 1, mappings);
+ SearchResults sr = MappingUtils
+ .buildSearchResults(pep1, 1, cdsMappings);
assertEquals(1, sr.getResults().size());
Match m = sr.getResults().get(0);
assertEquals(cds.getSequenceAt(0).getDatasetSequence(),
m.getSequence());
assertEquals(1, m.getStart());
assertEquals(3, m.getEnd());
- sr = MappingUtils.buildSearchResults(pep1, 2, mappings);
+ sr = MappingUtils.buildSearchResults(pep1, 2, cdsMappings);
m = sr.getResults().get(0);
assertEquals(4, m.getStart());
assertEquals(6, m.getEnd());
- sr = MappingUtils.buildSearchResults(pep1, 3, mappings);
+ sr = MappingUtils.buildSearchResults(pep1, 3, cdsMappings);
m = sr.getResults().get(0);
assertEquals(7, m.getStart());
assertEquals(9, m.getEnd());
- sr = MappingUtils.buildSearchResults(pep1, 4, mappings);
+ sr = MappingUtils.buildSearchResults(pep1, 4, cdsMappings);
m = sr.getResults().get(0);
assertEquals(10, m.getStart());
assertEquals(12, m.getEnd());
* GPG in pep2 map to 1-3,4-6,7-9 in second CDS sequence
*/
List<AlignedCodonFrame> pep2Mapping = MappingUtils
- .findMappingsForSequence(pep2, mappings);
+ .findMappingsForSequence(pep2, cdsMappings);
assertEquals(1, pep2Mapping.size());
- sr = MappingUtils.buildSearchResults(pep2, 1, mappings);
+ sr = MappingUtils.buildSearchResults(pep2, 1, cdsMappings);
assertEquals(1, sr.getResults().size());
m = sr.getResults().get(0);
assertEquals(cds.getSequenceAt(1).getDatasetSequence(),
m.getSequence());
assertEquals(1, m.getStart());
assertEquals(3, m.getEnd());
- sr = MappingUtils.buildSearchResults(pep2, 2, mappings);
+ sr = MappingUtils.buildSearchResults(pep2, 2, cdsMappings);
m = sr.getResults().get(0);
assertEquals(4, m.getStart());
assertEquals(6, m.getEnd());
- sr = MappingUtils.buildSearchResults(pep2, 3, mappings);
+ sr = MappingUtils.buildSearchResults(pep2, 3, cdsMappings);
m = sr.getResults().get(0);
assertEquals(7, m.getStart());
assertEquals(9, m.getEnd());
}
/**
- * Tests for gapped column in sequences
- */
- @Test(groups = { "Functional" })
- public void testIsGappedColumn()
- {
- SequenceI seq1 = new Sequence("Seq1", "a--c.tc-a-g");
- SequenceI seq2 = new Sequence("Seq2", "aa---t--a-g");
- SequenceI seq3 = new Sequence("Seq3", "ag-c t-g-");
- List<SequenceI> seqs = Arrays
- .asList(new SequenceI[] { seq1, seq2, seq3 });
- // the column number is base 1
- assertFalse(AlignmentUtils.isGappedColumn(seqs, 1));
- assertFalse(AlignmentUtils.isGappedColumn(seqs, 2));
- assertTrue(AlignmentUtils.isGappedColumn(seqs, 3));
- assertFalse(AlignmentUtils.isGappedColumn(seqs, 4));
- assertTrue(AlignmentUtils.isGappedColumn(seqs, 5));
- assertFalse(AlignmentUtils.isGappedColumn(seqs, 6));
- assertFalse(AlignmentUtils.isGappedColumn(seqs, 7));
- assertFalse(AlignmentUtils.isGappedColumn(seqs, 8));
- assertFalse(AlignmentUtils.isGappedColumn(seqs, 9));
- assertTrue(AlignmentUtils.isGappedColumn(seqs, 10));
- assertFalse(AlignmentUtils.isGappedColumn(seqs, 11));
- // out of bounds:
- assertTrue(AlignmentUtils.isGappedColumn(seqs, 0));
- assertTrue(AlignmentUtils.isGappedColumn(seqs, 100));
- assertTrue(AlignmentUtils.isGappedColumn(seqs, -100));
- assertTrue(AlignmentUtils.isGappedColumn(null, 0));
- }
-
- @Test(groups = { "Functional" })
- public void testFindCdsColumns()
- {
- // TODO target method belongs in a general-purpose alignment
- // analysis method to find columns for feature
-
- /*
- * NB this method assumes CDS ranges are contiguous (no introns)
- */
- SequenceI gene = new Sequence("gene", "aaacccgggtttaaacccgggttt");
- SequenceI seq1 = new Sequence("Seq1", "--ac-cgGG-GGaaACC--GGtt-");
- SequenceI seq2 = new Sequence("Seq2", "AA--CCGG--g-AAA--cG-GTTt");
- seq1.createDatasetSequence();
- seq2.createDatasetSequence();
- seq1.addSequenceFeature(new SequenceFeature("CDS", "cds", 5, 6, 0f,
- null));
- seq1.addSequenceFeature(new SequenceFeature("CDS", "cds", 7, 8, 0f,
- null));
- seq1.addSequenceFeature(new SequenceFeature("CDS", "cds", 11, 13, 0f,
- null));
- seq1.addSequenceFeature(new SequenceFeature("CDS", "cds", 14, 15, 0f,
- null));
- seq2.addSequenceFeature(new SequenceFeature("CDS", "cds", 1, 2, 0f,
- null));
- seq2.addSequenceFeature(new SequenceFeature("CDS", "cds", 3, 6, 0f,
- null));
- seq2.addSequenceFeature(new SequenceFeature("CDS", "cds", 8, 10, 0f,
- null));
- seq2.addSequenceFeature(new SequenceFeature("CDS", "cds", 12, 12, 0f,
- null));
- seq2.addSequenceFeature(new SequenceFeature("CDS", "cds", 13, 15, 0f,
- null));
-
- List<int[]> cdsColumns = AlignmentUtils.findCdsColumns(new SequenceI[] {
- seq1, seq2 });
- assertEquals(4, cdsColumns.size());
- assertEquals("[1, 2]", Arrays.toString(cdsColumns.get(0)));
- assertEquals("[5, 9]", Arrays.toString(cdsColumns.get(1)));
- assertEquals("[11, 17]", Arrays.toString(cdsColumns.get(2)));
- assertEquals("[19, 23]", Arrays.toString(cdsColumns.get(3)));
- }
-
- /**
* Test the method that realigns protein to match mapped codon alignment.
*/
@Test(groups = { "Functional" })
* (or subtype) feature - case where the start codon is incomplete.
*/
@Test(groups = "Functional")
- public void testGetCdsRanges_fivePrimeIncomplete()
+ public void testFindCdsPositions_fivePrimeIncomplete()
{
SequenceI dnaSeq = new Sequence("dna", "aaagGGCCCaaaTTTttt");
dnaSeq.createDatasetSequence();
* (or subtype) feature.
*/
@Test(groups = "Functional")
- public void testGetCdsRanges()
+ public void testFindCdsPositions()
{
SequenceI dnaSeq = new Sequence("dna", "aaaGGGcccAAATTTttt");
dnaSeq.createDatasetSequence();
SequenceI ds = dnaSeq.getDatasetSequence();
- // CDS for dna 3-6
- SequenceFeature sf = new SequenceFeature("CDS", "", 4, 6, 0f, null);
+ // CDS for dna 10-12
+ SequenceFeature sf = new SequenceFeature("CDS_predicted", "", 10, 12,
+ 0f, null);
+ sf.setStrand("+");
+ ds.addSequenceFeature(sf);
+ // CDS for dna 4-6
+ sf = new SequenceFeature("CDS", "", 4, 6, 0f, null);
+ sf.setStrand("+");
ds.addSequenceFeature(sf);
// exon feature should be ignored here
sf = new SequenceFeature("exon", "", 7, 9, 0f, null);
ds.addSequenceFeature(sf);
- // CDS for dna 10-12
- sf = new SequenceFeature("CDS_predicted", "", 10, 12, 0f, null);
- ds.addSequenceFeature(sf);
List<int[]> ranges = AlignmentUtils.findCdsPositions(dnaSeq);
+ /*
+ * verify ranges { [4-6], [12-10] }
+ * note CDS ranges are ordered ascending even if the CDS
+ * features are not
+ */
assertEquals(6, MappingUtils.getLength(ranges));
assertEquals(2, ranges.size());
assertEquals(4, ranges.get(0)[0]);
/*
* first with no variants on dna
*/
- LinkedHashMap<Integer, String[][]> variantsMap = AlignmentUtils
+ LinkedHashMap<Integer, List<DnaVariant>[]> variantsMap = AlignmentUtils
.buildDnaVariantsMap(dna, map);
assertTrue(variantsMap.isEmpty());
- // single allele codon 1, on base 1
- SequenceFeature sf = new SequenceFeature("sequence_variant", "", 1, 1,
+ /*
+ * single allele codon 1, on base 1
+ */
+ SequenceFeature sf1 = new SequenceFeature("sequence_variant", "", 1, 1,
0f, null);
- sf.setValue("alleles", "T");
- dna.addSequenceFeature(sf);
-
- // two alleles codon 2, on bases 2 and 3
- sf = new SequenceFeature("sequence_variant", "", 5, 5, 0f, null);
- sf.setValue("alleles", "T");
- dna.addSequenceFeature(sf);
- sf = new SequenceFeature("sequence_variant", "", 6, 6, 0f, null);
- sf.setValue("alleles", "G");
- dna.addSequenceFeature(sf);
-
- // two alleles codon 3, both on base 2
- sf = new SequenceFeature("sequence_variant", "", 8, 8, 0f, null);
- sf.setValue("alleles", "C, G");
- dna.addSequenceFeature(sf);
+ sf1.setValue("alleles", "T");
+ sf1.setValue("ID", "sequence_variant:rs758803211");
+ dna.addSequenceFeature(sf1);
+
+ /*
+ * two alleles codon 2, on bases 2 and 3 (distinct variants)
+ */
+ SequenceFeature sf2 = new SequenceFeature("sequence_variant", "", 5, 5,
+ 0f, null);
+ sf2.setValue("alleles", "T");
+ sf2.setValue("ID", "sequence_variant:rs758803212");
+ dna.addSequenceFeature(sf2);
+ SequenceFeature sf3 = new SequenceFeature("sequence_variant", "", 6, 6,
+ 0f, null);
+ sf3.setValue("alleles", "G");
+ sf3.setValue("ID", "sequence_variant:rs758803213");
+ dna.addSequenceFeature(sf3);
+
+ /*
+ * two alleles codon 3, both on base 2 (one variant)
+ */
+ SequenceFeature sf4 = new SequenceFeature("sequence_variant", "", 8, 8,
+ 0f, null);
+ sf4.setValue("alleles", "C, G");
+ sf4.setValue("ID", "sequence_variant:rs758803214");
+ dna.addSequenceFeature(sf4);
// no alleles on codon 4
- // alleles on codon 5 on all 3 bases
- sf = new SequenceFeature("sequence_variant", "", 13, 13, 0f, null);
- sf.setValue("alleles", "C, G"); // (C duplicates given base value)
- dna.addSequenceFeature(sf);
- sf = new SequenceFeature("sequence_variant", "", 14, 14, 0f, null);
- sf.setValue("alleles", "g, a"); // should force to upper-case
- dna.addSequenceFeature(sf);
- sf = new SequenceFeature("sequence_variant", "", 15, 15, 0f, null);
- sf.setValue("alleles", "A, T");
- dna.addSequenceFeature(sf);
+ /*
+ * alleles on codon 5 on all 3 bases (distinct variants)
+ */
+ SequenceFeature sf5 = new SequenceFeature("sequence_variant", "", 13,
+ 13, 0f, null);
+ sf5.setValue("alleles", "C, G"); // (C duplicates given base value)
+ sf5.setValue("ID", "sequence_variant:rs758803215");
+ dna.addSequenceFeature(sf5);
+ SequenceFeature sf6 = new SequenceFeature("sequence_variant", "", 14,
+ 14, 0f, null);
+ sf6.setValue("alleles", "g, a"); // should force to upper-case
+ sf6.setValue("ID", "sequence_variant:rs758803216");
+ dna.addSequenceFeature(sf6);
+ SequenceFeature sf7 = new SequenceFeature("sequence_variant", "", 15,
+ 15, 0f, null);
+ sf7.setValue("alleles", "A, T");
+ sf7.setValue("ID", "sequence_variant:rs758803217");
+ dna.addSequenceFeature(sf7);
+
+ /*
+ * build map - expect variants on positions 1, 2, 3, 5
+ */
variantsMap = AlignmentUtils.buildDnaVariantsMap(dna, map);
assertEquals(4, variantsMap.size());
- assertTrue(Arrays.deepEquals(new String[][] { { "A", "T" }, { "T" },
- { "G" } }, variantsMap.get(1)));
- assertTrue(Arrays.deepEquals(new String[][] { { "A" }, { "A", "T" },
- { "A", "G" } }, variantsMap.get(2)));
- assertTrue(Arrays.deepEquals(new String[][] { { "T" },
- { "T", "C", "G" }, { "T" } }, variantsMap.get(3)));
- // duplicated bases are not removed here, handled in computePeptideVariants
- assertTrue(Arrays.deepEquals(new String[][] { { "C", "C", "G" },
- { "C", "G", "A" }, { "C", "A", "T" } }, variantsMap.get(5)));
+
+ /*
+ * protein residue 1: variant on codon (ATG) base 1, not on 2 or 3
+ */
+ List<DnaVariant>[] pep1Variants = variantsMap.get(1);
+ assertEquals(3, pep1Variants.length);
+ assertEquals(1, pep1Variants[0].size());
+ assertEquals("A", pep1Variants[0].get(0).base); // codon[1] base
+ assertSame(sf1, pep1Variants[0].get(0).variant); // codon[1] variant
+ assertEquals(1, pep1Variants[1].size());
+ assertEquals("T", pep1Variants[1].get(0).base); // codon[2] base
+ assertNull(pep1Variants[1].get(0).variant); // no variant here
+ assertEquals(1, pep1Variants[2].size());
+ assertEquals("G", pep1Variants[2].get(0).base); // codon[3] base
+ assertNull(pep1Variants[2].get(0).variant); // no variant here
+
+ /*
+ * protein residue 2: variants on codon (AAA) bases 2 and 3
+ */
+ List<DnaVariant>[] pep2Variants = variantsMap.get(2);
+ assertEquals(3, pep2Variants.length);
+ assertEquals(1, pep2Variants[0].size());
+ // codon[1] base recorded while processing variant on codon[2]
+ assertEquals("A", pep2Variants[0].get(0).base);
+ assertNull(pep2Variants[0].get(0).variant); // no variant here
+ // codon[2] base and variant:
+ assertEquals(1, pep2Variants[1].size());
+ assertEquals("A", pep2Variants[1].get(0).base);
+ assertSame(sf2, pep2Variants[1].get(0).variant);
+ // codon[3] base was recorded when processing codon[2] variant
+ // and then the variant for codon[3] added to it
+ assertEquals(1, pep2Variants[2].size());
+ assertEquals("A", pep2Variants[2].get(0).base);
+ assertSame(sf3, pep2Variants[2].get(0).variant);
+
+ /*
+ * protein residue 3: variants on codon (TTT) base 2 only
+ */
+ List<DnaVariant>[] pep3Variants = variantsMap.get(3);
+ assertEquals(3, pep3Variants.length);
+ assertEquals(1, pep3Variants[0].size());
+ assertEquals("T", pep3Variants[0].get(0).base); // codon[1] base
+ assertNull(pep3Variants[0].get(0).variant); // no variant here
+ assertEquals(1, pep3Variants[1].size());
+ assertEquals("T", pep3Variants[1].get(0).base); // codon[2] base
+ assertSame(sf4, pep3Variants[1].get(0).variant); // codon[2] variant
+ assertEquals(1, pep3Variants[2].size());
+ assertEquals("T", pep3Variants[2].get(0).base); // codon[3] base
+ assertNull(pep3Variants[2].get(0).variant); // no variant here
+
+ /*
+ * three variants on protein position 5
+ */
+ List<DnaVariant>[] pep5Variants = variantsMap.get(5);
+ assertEquals(3, pep5Variants.length);
+ assertEquals(1, pep5Variants[0].size());
+ assertEquals("C", pep5Variants[0].get(0).base); // codon[1] base
+ assertSame(sf5, pep5Variants[0].get(0).variant); // codon[1] variant
+ assertEquals(1, pep5Variants[1].size());
+ assertEquals("C", pep5Variants[1].get(0).base); // codon[2] base
+ assertSame(sf6, pep5Variants[1].get(0).variant); // codon[2] variant
+ assertEquals(1, pep5Variants[2].size());
+ assertEquals("C", pep5Variants[2].get(0).base); // codon[3] base
+ assertSame(sf7, pep5Variants[2].get(0).variant); // codon[3] variant
}
/**
@Test(groups = "Functional")
public void testComputePeptideVariants()
{
- String[][] codonVariants = new String[][] { { "A" }, { "G" }, { "T" } };
-
/*
- * AGT codes for S - this is not included in the variants returned
+ * scenario: AAATTTCCC codes for KFP, with variants
+ * GAA -> E
+ * CAA -> Q
+ * AAG synonymous
+ * AAT -> N
+ * TTC synonymous
+ * CAC,CGC -> H,R (as one variant)
+ */
+ SequenceI peptide = new Sequence("pep/10-12", "KFP");
+
+ /*
+ * two distinct variants for codon 1 position 1
+ * second one has clinical significance
+ */
+ SequenceFeature sf1 = new SequenceFeature("sequence_variant", "", 1, 1,
+ 0f, null);
+ sf1.setValue("alleles", "A,G"); // GAA -> E
+ sf1.setValue("ID", "var1.125A>G");
+ SequenceFeature sf2 = new SequenceFeature("sequence_variant", "", 1, 1,
+ 0f, null);
+ sf2.setValue("alleles", "A,C"); // CAA -> Q
+ sf2.setValue("ID", "var2");
+ sf2.setValue("clinical_significance", "Dodgy");
+ SequenceFeature sf3 = new SequenceFeature("sequence_variant", "", 3, 3,
+ 0f, null);
+ sf3.setValue("alleles", "A,G"); // synonymous
+ sf3.setValue("ID", "var3");
+ sf3.setValue("clinical_significance", "None");
+ SequenceFeature sf4 = new SequenceFeature("sequence_variant", "", 3, 3,
+ 0f, null);
+ sf4.setValue("alleles", "A,T"); // AAT -> N
+ sf4.setValue("ID", "sequence_variant:var4"); // prefix gets stripped off
+ sf4.setValue("clinical_significance", "Benign");
+ SequenceFeature sf5 = new SequenceFeature("sequence_variant", "", 6, 6,
+ 0f, null);
+ sf5.setValue("alleles", "T,C"); // synonymous
+ sf5.setValue("ID", "var5");
+ sf5.setValue("clinical_significance", "Bad");
+ SequenceFeature sf6 = new SequenceFeature("sequence_variant", "", 8, 8,
+ 0f, null);
+ sf6.setValue("alleles", "C,A,G"); // CAC,CGC -> H,R
+ sf6.setValue("ID", "var6");
+ sf6.setValue("clinical_significance", "Good");
+
+ List<DnaVariant> codon1Variants = new ArrayList<DnaVariant>();
+ List<DnaVariant> codon2Variants = new ArrayList<DnaVariant>();
+ List<DnaVariant> codon3Variants = new ArrayList<DnaVariant>();
+ List<DnaVariant> codonVariants[] = new ArrayList[3];
+ codonVariants[0] = codon1Variants;
+ codonVariants[1] = codon2Variants;
+ codonVariants[2] = codon3Variants;
+
+ /*
+ * compute variants for protein position 1
+ */
+ codon1Variants.add(new DnaVariant("A", sf1));
+ codon1Variants.add(new DnaVariant("A", sf2));
+ codon2Variants.add(new DnaVariant("A"));
+ codon2Variants.add(new DnaVariant("A"));
+ codon3Variants.add(new DnaVariant("A", sf3));
+ codon3Variants.add(new DnaVariant("A", sf4));
+ AlignmentUtils.computePeptideVariants(peptide, 1, codonVariants);
+
+ /*
+ * compute variants for protein position 2
+ */
+ codon1Variants.clear();
+ codon2Variants.clear();
+ codon3Variants.clear();
+ codon1Variants.add(new DnaVariant("T"));
+ codon2Variants.add(new DnaVariant("T"));
+ codon3Variants.add(new DnaVariant("T", sf5));
+ AlignmentUtils.computePeptideVariants(peptide, 2, codonVariants);
+
+ /*
+ * compute variants for protein position 3
*/
- List<String> variants = AlignmentUtils.computePeptideVariants(codonVariants, "S");
- assertEquals("[]", variants.toString());
+ codon1Variants.clear();
+ codon2Variants.clear();
+ codon3Variants.clear();
+ codon1Variants.add(new DnaVariant("C"));
+ codon2Variants.add(new DnaVariant("C", sf6));
+ codon3Variants.add(new DnaVariant("C"));
+ AlignmentUtils.computePeptideVariants(peptide, 3, codonVariants);
+
+ /*
+ * verify added sequence features for
+ * var1 K -> E
+ * var2 K -> Q
+ * var4 K -> N
+ * var6 P -> H
+ * var6 P -> R
+ */
+ SequenceFeature[] sfs = peptide.getSequenceFeatures();
+ assertEquals(5, sfs.length);
+ SequenceFeature sf = sfs[0];
+ assertEquals(1, sf.getBegin());
+ assertEquals(1, sf.getEnd());
+ assertEquals("K->E", sf.getDescription());
+ assertEquals("var1.125A>G", sf.getValue("ID"));
+ assertNull(sf.getValue("clinical_significance"));
+ assertEquals(1, sf.links.size());
+ // link to variation is urlencoded
+ assertEquals(
+ "K->E var1.125A>G|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var1.125A%3EG",
+ sf.links.get(0));
+ sf = sfs[1];
+ assertEquals(1, sf.getBegin());
+ assertEquals(1, sf.getEnd());
+ assertEquals("K->Q", sf.getDescription());
+ assertEquals("var2", sf.getValue("ID"));
+ assertEquals("Dodgy", sf.getValue("clinical_significance"));
+ assertEquals(1, sf.links.size());
+ assertEquals(
+ "K->Q var2|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var2",
+ sf.links.get(0));
+ sf = sfs[2];
+ assertEquals(1, sf.getBegin());
+ assertEquals(1, sf.getEnd());
+ assertEquals("K->N", sf.getDescription());
+ assertEquals("var4", sf.getValue("ID"));
+ assertEquals("Benign", sf.getValue("clinical_significance"));
+ assertEquals(1, sf.links.size());
+ assertEquals(
+ "K->N var4|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var4",
+ sf.links.get(0));
+ sf = sfs[3];
+ assertEquals(3, sf.getBegin());
+ assertEquals(3, sf.getEnd());
+ assertEquals("P->H", sf.getDescription());
+ assertEquals("var6", sf.getValue("ID"));
+ assertEquals("Good", sf.getValue("clinical_significance"));
+ assertEquals(1, sf.links.size());
+ assertEquals(
+ "P->H var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6",
+ sf.links.get(0));
+ // var5 generates two distinct protein variant features
+ sf = sfs[4];
+ assertEquals(3, sf.getBegin());
+ assertEquals(3, sf.getEnd());
+ assertEquals("P->R", sf.getDescription());
+ assertEquals("var6", sf.getValue("ID"));
+ assertEquals("Good", sf.getValue("clinical_significance"));
+ assertEquals(1, sf.links.size());
+ assertEquals(
+ "P->R var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6",
+ sf.links.get(0));
+ }
+
+ /**
+ * Tests for the method that maps the subset of a dna sequence that has CDS
+ * (or subtype) feature, with CDS strand = '-' (reverse)
+ */
+ // test turned off as currently findCdsPositions is not strand-dependent
+ // left in case it comes around again...
+ @Test(groups = "Functional", enabled = false)
+ public void testFindCdsPositions_reverseStrand()
+ {
+ SequenceI dnaSeq = new Sequence("dna", "aaaGGGcccAAATTTttt");
+ dnaSeq.createDatasetSequence();
+ SequenceI ds = dnaSeq.getDatasetSequence();
- // S is reported if it differs from the current value (A):
- variants = AlignmentUtils.computePeptideVariants(codonVariants, "A");
- assertEquals("[S]", variants.toString());
+ // CDS for dna 4-6
+ SequenceFeature sf = new SequenceFeature("CDS", "", 4, 6, 0f, null);
+ sf.setStrand("-");
+ ds.addSequenceFeature(sf);
+ // exon feature should be ignored here
+ sf = new SequenceFeature("exon", "", 7, 9, 0f, null);
+ ds.addSequenceFeature(sf);
+ // CDS for dna 10-12
+ sf = new SequenceFeature("CDS_predicted", "", 10, 12, 0f, null);
+ sf.setStrand("-");
+ ds.addSequenceFeature(sf);
+ List<int[]> ranges = AlignmentUtils.findCdsPositions(dnaSeq);
/*
- * synonymous variant is not reported
+ * verify ranges { [12-10], [6-4] }
*/
- codonVariants = new String[][] { { "A" }, { "G" }, { "C", "T" } };
- // AGC and AGT both code for S
- variants = AlignmentUtils.computePeptideVariants(codonVariants, "s");
- assertEquals("[]", variants.toString());
+ assertEquals(6, MappingUtils.getLength(ranges));
+ assertEquals(2, ranges.size());
+ assertEquals(12, ranges.get(0)[0]);
+ assertEquals(10, ranges.get(0)[1]);
+ assertEquals(6, ranges.get(1)[0]);
+ assertEquals(4, ranges.get(1)[1]);
+ }
+
+ /**
+ * Tests for the method that maps the subset of a dna sequence that has CDS
+ * (or subtype) feature - reverse strand case where the start codon is
+ * incomplete.
+ */
+ @Test(groups = "Functional", enabled = false)
+ // test turned off as currently findCdsPositions is not strand-dependent
+ // left in case it comes around again...
+ public void testFindCdsPositions_reverseStrandThreePrimeIncomplete()
+ {
+ SequenceI dnaSeq = new Sequence("dna", "aaagGGCCCaaaTTTttt");
+ dnaSeq.createDatasetSequence();
+ SequenceI ds = dnaSeq.getDatasetSequence();
+
+ // CDS for dna 5-9
+ SequenceFeature sf = new SequenceFeature("CDS", "", 5, 9, 0f, null);
+ sf.setStrand("-");
+ ds.addSequenceFeature(sf);
+ // CDS for dna 13-15
+ sf = new SequenceFeature("CDS_predicted", "", 13, 15, 0f, null);
+ sf.setStrand("-");
+ sf.setPhase("2"); // skip 2 bases to start of next codon
+ ds.addSequenceFeature(sf);
+
+ List<int[]> ranges = AlignmentUtils.findCdsPositions(dnaSeq);
/*
- * equivalent variants are only reported once
+ * check the mapping starts with the first complete codon
+ * expect ranges [13, 13], [9, 5]
*/
- codonVariants = new String[][] { { "C" }, { "T" },
- { "A", "C", "G", "T" } };
- // CTA CTC CTG CTT all code for L
- variants = AlignmentUtils.computePeptideVariants(codonVariants, "S");
- assertEquals("[L]", variants.toString());
-
+ assertEquals(6, MappingUtils.getLength(ranges));
+ assertEquals(2, ranges.size());
+ assertEquals(13, ranges.get(0)[0]);
+ assertEquals(13, ranges.get(0)[1]);
+ assertEquals(9, ranges.get(1)[0]);
+ assertEquals(5, ranges.get(1)[1]);
+ }
+
+ @Test(groups = "Functional")
+ public void testAlignAs_alternateTranscriptsUngapped()
+ {
+ SequenceI dna1 = new Sequence("dna1", "cccGGGTTTaaa");
+ SequenceI dna2 = new Sequence("dna2", "CCCgggtttAAA");
+ AlignmentI dna = new Alignment(new SequenceI[] { dna1, dna2 });
+ ((Alignment) dna).createDatasetAlignment();
+ SequenceI cds1 = new Sequence("cds1", "GGGTTT");
+ SequenceI cds2 = new Sequence("cds2", "CCCAAA");
+ AlignmentI cds = new Alignment(new SequenceI[] { cds1, cds2 });
+ ((Alignment) cds).createDatasetAlignment();
+
+ AlignedCodonFrame acf = new AlignedCodonFrame();
+ MapList map = new MapList(new int[] { 4, 9 }, new int[] { 1, 6 }, 1, 1);
+ acf.addMap(dna1.getDatasetSequence(), cds1.getDatasetSequence(), map);
+ map = new MapList(new int[] { 1, 3, 10, 12 }, new int[] { 1, 6 }, 1, 1);
+ acf.addMap(dna2.getDatasetSequence(), cds2.getDatasetSequence(), map);
+
/*
- * vary codons 1 and 2; variant products are sorted and non-redundant
+ * verify CDS alignment is as:
+ * cccGGGTTTaaa (cdna)
+ * CCCgggtttAAA (cdna)
+ *
+ * ---GGGTTT--- (cds)
+ * CCC------AAA (cds)
*/
- codonVariants = new String[][] { { "a", "C" }, { "g", "T" }, { "A" } };
- // aga ata cga cta code for R, I, R, L
- variants = AlignmentUtils.computePeptideVariants(codonVariants, "S");
- assertEquals("[I, L, R]", variants.toString());
-
+ dna.addCodonFrame(acf);
+ AlignmentUtils.alignAs(cds, dna);
+ assertEquals("---GGGTTT", cds.getSequenceAt(0).getSequenceAsString());
+ assertEquals("CCC------AAA", cds.getSequenceAt(1).getSequenceAsString());
+ }
+
+ @Test(groups = { "Functional" })
+ public void testAddMappedPositions()
+ {
+ SequenceI from = new Sequence("dna", "ggAA-ATcc-TT-g");
+ SequenceI seq1 = new Sequence("cds", "AAATTT");
+ from.createDatasetSequence();
+ seq1.createDatasetSequence();
+ Mapping mapping = new Mapping(seq1, new MapList(
+ new int[] { 3, 6, 9, 10 },
+ new int[] { 1, 6 }, 1, 1));
+ Map<Integer, Map<SequenceI, Character>> map = new TreeMap<Integer, Map<SequenceI, Character>>();
+ AlignmentUtils.addMappedPositions(seq1, from, mapping, map);
+
/*
- * vary codons 2 and 3
+ * verify map has seq1 residues in columns 3,4,6,7,11,12
*/
- codonVariants = new String[][] { { "a" }, { "g", "T" }, { "A", "c" } };
- // aga agc ata atc code for R, S, I, I
- variants = AlignmentUtils.computePeptideVariants(codonVariants, "S");
- assertEquals("[I, R]", variants.toString());
-
+ assertEquals(6, map.size());
+ assertEquals('A', map.get(3).get(seq1).charValue());
+ assertEquals('A', map.get(4).get(seq1).charValue());
+ assertEquals('A', map.get(6).get(seq1).charValue());
+ assertEquals('T', map.get(7).get(seq1).charValue());
+ assertEquals('T', map.get(11).get(seq1).charValue());
+ assertEquals('T', map.get(12).get(seq1).charValue());
+
/*
- * vary codons 1 and 3
+ *
*/
- codonVariants = new String[][] { { "a", "t" }, { "a" }, { "t", "g" } };
- // aat aag tat tag code for N, K, Y, STOP - STOP sorted to end
- variants = AlignmentUtils.computePeptideVariants(codonVariants, "S");
- assertEquals("[K, N, Y, STOP]", variants.toString());
+ }
+
+ /**
+ * Test case where the mapping 'from' range includes a stop codon which is
+ * absent in the 'to' range
+ */
+ @Test(groups = { "Functional" })
+ public void testAddMappedPositions_withStopCodon()
+ {
+ SequenceI from = new Sequence("dna", "ggAA-ATcc-TT-g");
+ SequenceI seq1 = new Sequence("cds", "AAATTT");
+ from.createDatasetSequence();
+ seq1.createDatasetSequence();
+ Mapping mapping = new Mapping(seq1, new MapList(
+ new int[] { 3, 6, 9, 10 },
+ new int[] { 1, 6 }, 1, 1));
+ Map<Integer, Map<SequenceI, Character>> map = new TreeMap<Integer, Map<SequenceI, Character>>();
+ AlignmentUtils.addMappedPositions(seq1, from, mapping, map);
/*
- * vary codons 1, 2 and 3
+ * verify map has seq1 residues in columns 3,4,6,7,11,12
*/
- codonVariants = new String[][] { { "a", "t" }, { "G", "C" },
- { "t", "g" } };
- // agt agg act acg tgt tgg tct tcg code for S, R, T, T, C, W, S, S
- variants = AlignmentUtils.computePeptideVariants(codonVariants, "S");
- assertEquals("[C, R, T, W]", variants.toString());
+ assertEquals(6, map.size());
+ assertEquals('A', map.get(3).get(seq1).charValue());
+ assertEquals('A', map.get(4).get(seq1).charValue());
+ assertEquals('A', map.get(6).get(seq1).charValue());
+ assertEquals('T', map.get(7).get(seq1).charValue());
+ assertEquals('T', map.get(11).get(seq1).charValue());
+ assertEquals('T', map.get(12).get(seq1).charValue());
}
}