+ /*
+ * scenario: AAATTTCCC codes for KFP
+ * variants:
+ * GAA -> E source: Ensembl
+ * CAA -> Q source: dbSNP
+ * AAG synonymous source: COSMIC
+ * AAT -> N source: Ensembl
+ * ...TTC synonymous source: dbSNP
+ * ......CAC,CGC -> H,R source: COSMIC
+ * (one variant with two alleles)
+ */
+ SequenceI peptide = new Sequence("pep/10-12", "KFP");
+
+ /*
+ * two distinct variants for codon 1 position 1
+ * second one has clinical significance
+ */
+ String ensembl = "Ensembl";
+ String dbSnp = "dbSNP";
+ String cosmic = "COSMIC";
+ SequenceFeature sf1 = new SequenceFeature("sequence_variant", "", 1, 1,
+ 0f, ensembl);
+ sf1.setValue("alleles", "A,G"); // GAA -> E
+ sf1.setValue("ID", "var1.125A>G");
+ SequenceFeature sf2 = new SequenceFeature("sequence_variant", "", 1, 1,
+ 0f, dbSnp);
+ 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, cosmic);
+ sf3.setValue("alleles", "A,G"); // synonymous
+ sf3.setValue("ID", "var3");
+ sf3.setValue("clinical_significance", "None");
+ SequenceFeature sf4 = new SequenceFeature("sequence_variant", "", 3, 3,
+ 0f, ensembl);
+ 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, dbSnp);
+ sf5.setValue("alleles", "T,C"); // synonymous
+ sf5.setValue("ID", "var5");
+ sf5.setValue("clinical_significance", "Bad");
+ SequenceFeature sf6 = new SequenceFeature("sequence_variant", "", 8, 8,
+ 0f, cosmic);
+ 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
+ */
+ 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 Ensembl
+ * var2 K -> Q dbSNP
+ * var4 K -> N Ensembl
+ * var6 P -> H COSMIC
+ * var6 P -> R COSMIC
+ */
+ SequenceFeature[] sfs = peptide.getSequenceFeatures();
+ assertEquals(5, sfs.length);
+
+ SequenceFeature sf = sfs[0];
+ assertEquals(1, sf.getBegin());
+ assertEquals(1, sf.getEnd());
+ assertEquals("p.Lys1Glu", sf.getDescription());
+ assertEquals("var1.125A>G", sf.getValue("ID"));
+ assertNull(sf.getValue("clinical_significance"));
+ assertEquals("ID=var1.125A>G", sf.getAttributes());
+ assertEquals(1, sf.links.size());
+ // link to variation is urlencoded
+ assertEquals(
+ "p.Lys1Glu var1.125A>G|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var1.125A%3EG",
+ sf.links.get(0));
+ assertEquals(ensembl, sf.getFeatureGroup());
+
+ sf = sfs[1];
+ assertEquals(1, sf.getBegin());
+ assertEquals(1, sf.getEnd());
+ assertEquals("p.Lys1Gln", sf.getDescription());
+ assertEquals("var2", sf.getValue("ID"));
+ assertEquals("Dodgy", sf.getValue("clinical_significance"));
+ assertEquals("ID=var2;clinical_significance=Dodgy", sf.getAttributes());
+ assertEquals(1, sf.links.size());
+ assertEquals(
+ "p.Lys1Gln var2|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var2",
+ sf.links.get(0));
+ assertEquals(dbSnp, sf.getFeatureGroup());
+
+ sf = sfs[2];
+ assertEquals(1, sf.getBegin());
+ assertEquals(1, sf.getEnd());
+ assertEquals("p.Lys1Asn", sf.getDescription());
+ assertEquals("var4", sf.getValue("ID"));
+ assertEquals("Benign", sf.getValue("clinical_significance"));
+ assertEquals("ID=var4;clinical_significance=Benign", sf.getAttributes());
+ assertEquals(1, sf.links.size());
+ assertEquals(
+ "p.Lys1Asn var4|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var4",
+ sf.links.get(0));
+ assertEquals(ensembl, sf.getFeatureGroup());
+
+ // var5 generates two distinct protein variant features
+ sf = sfs[3];
+ assertEquals(3, sf.getBegin());
+ assertEquals(3, sf.getEnd());
+ assertEquals("p.Pro3His", sf.getDescription());
+ assertEquals("var6", sf.getValue("ID"));
+ assertEquals("Good", sf.getValue("clinical_significance"));
+ assertEquals("ID=var6;clinical_significance=Good", sf.getAttributes());
+ assertEquals(1, sf.links.size());
+ assertEquals(
+ "p.Pro3His var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6",
+ sf.links.get(0));
+ assertEquals(cosmic, sf.getFeatureGroup());
+
+ sf = sfs[4];
+ assertEquals(3, sf.getBegin());
+ assertEquals(3, sf.getEnd());
+ assertEquals("p.Pro3Arg", sf.getDescription());
+ assertEquals("var6", sf.getValue("ID"));
+ assertEquals("Good", sf.getValue("clinical_significance"));
+ assertEquals("ID=var6;clinical_significance=Good", sf.getAttributes());
+ assertEquals(1, sf.links.size());
+ assertEquals(
+ "p.Pro3Arg var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6",
+ sf.links.get(0));
+ assertEquals(cosmic, sf.getFeatureGroup());
+ }
+
+ /**
+ * 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();
+
+ // 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);
+ /*
+ * verify ranges { [12-10], [6-4] }
+ */
+ 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);
+
+ /*
+ * check the mapping starts with the first complete codon
+ * expect ranges [13, 13], [9, 5]
+ */
+ 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);
+
+ /*
+ * verify CDS alignment is as:
+ * cccGGGTTTaaa (cdna)
+ * CCCgggtttAAA (cdna)
+ *
+ * ---GGGTTT--- (cds)
+ * CCC------AAA (cds)
+ */
+ dna.addCodonFrame(acf);
+ AlignmentUtils.alignAs(cds, dna);
+ assertEquals("---GGGTTT", cds.getSequenceAt(0).getSequenceAsString());
+ assertEquals("CCC------AAA", cds.getSequenceAt(1).getSequenceAsString());