X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=test%2Fjalview%2Fanalysis%2FAlignmentUtilsTests.java;h=35196faaccb4e58d7ea4386716c3dc4df68d75c4;hb=07194be147ec7a652d1029c9460fb6426db13b7e;hp=bada3caab0b26c34685e1c37d13206e9ba2e17d8;hpb=483e7163b1fb8d4bcb9393014816c944befce328;p=jalview.git diff --git a/test/jalview/analysis/AlignmentUtilsTests.java b/test/jalview/analysis/AlignmentUtilsTests.java index bada3ca..35196fa 100644 --- a/test/jalview/analysis/AlignmentUtilsTests.java +++ b/test/jalview/analysis/AlignmentUtilsTests.java @@ -40,12 +40,14 @@ import jalview.datamodel.SearchResultsI; import jalview.datamodel.Sequence; import jalview.datamodel.SequenceFeature; import jalview.datamodel.SequenceI; +import jalview.datamodel.features.SequenceFeatures; import jalview.gui.JvOptionPane; import jalview.io.AppletFormatAdapter; import jalview.io.DataSourceType; import jalview.io.FileFormat; import jalview.io.FileFormatI; import jalview.io.FormatAdapter; +import jalview.io.gff.SequenceOntologyI; import jalview.util.MapList; import jalview.util.MappingUtils; @@ -262,14 +264,14 @@ public class AlignmentUtilsTests @Test(groups = { "Functional" }) public void testMapProteinAlignmentToCdna_noXrefs() throws IOException { - List protseqs = new ArrayList(); + List protseqs = new ArrayList<>(); protseqs.add(new Sequence("UNIPROT|V12345", "EIQ")); protseqs.add(new Sequence("UNIPROT|V12346", "EIQ")); protseqs.add(new Sequence("UNIPROT|V12347", "SAR")); AlignmentI protein = new Alignment(protseqs.toArray(new SequenceI[3])); protein.setDataset(null); - List dnaseqs = new ArrayList(); + List dnaseqs = new ArrayList<>(); dnaseqs.add(new Sequence("EMBL|A11111", "TCAGCACGC")); // = SAR dnaseqs.add(new Sequence("EMBL|A22222", "GAGATACAA")); // = EIQ dnaseqs.add(new Sequence("EMBL|A33333", "GAAATCCAG")); // = EIQ @@ -506,7 +508,7 @@ public class AlignmentUtilsTests acf.addMap(dna1.getDatasetSequence(), prot1.getDatasetSequence(), map); acf.addMap(dna2.getDatasetSequence(), prot2.getDatasetSequence(), map); acf.addMap(dna3.getDatasetSequence(), prot3.getDatasetSequence(), map); - ArrayList acfs = new ArrayList(); + ArrayList acfs = new ArrayList<>(); acfs.add(acf); protein.setCodonFrames(acfs); @@ -604,14 +606,14 @@ public class AlignmentUtilsTests public void testMapProteinAlignmentToCdna_withStartAndStopCodons() throws IOException { - List protseqs = new ArrayList(); + List protseqs = new ArrayList<>(); protseqs.add(new Sequence("UNIPROT|V12345", "EIQ")); protseqs.add(new Sequence("UNIPROT|V12346", "EIQ")); protseqs.add(new Sequence("UNIPROT|V12347", "SAR")); AlignmentI protein = new Alignment(protseqs.toArray(new SequenceI[3])); protein.setDataset(null); - List dnaseqs = new ArrayList(); + List dnaseqs = new ArrayList<>(); // start + SAR: dnaseqs.add(new Sequence("EMBL|A11111", "ATGTCAGCACGC")); // = EIQ + stop @@ -696,14 +698,14 @@ public class AlignmentUtilsTests @Test(groups = { "Functional" }) public void testMapProteinAlignmentToCdna_withXrefs() throws IOException { - List protseqs = new ArrayList(); + List protseqs = new ArrayList<>(); protseqs.add(new Sequence("UNIPROT|V12345", "EIQ")); protseqs.add(new Sequence("UNIPROT|V12346", "EIQ")); protseqs.add(new Sequence("UNIPROT|V12347", "SAR")); AlignmentI protein = new Alignment(protseqs.toArray(new SequenceI[3])); protein.setDataset(null); - List dnaseqs = new ArrayList(); + List dnaseqs = new ArrayList<>(); dnaseqs.add(new Sequence("EMBL|A11111", "TCAGCACGC")); // = SAR dnaseqs.add(new Sequence("EMBL|A22222", "ATGGAGATACAA")); // = start + EIQ dnaseqs.add(new Sequence("EMBL|A33333", "GAAATCCAG")); // = EIQ @@ -773,14 +775,14 @@ public class AlignmentUtilsTests public void testMapProteinAlignmentToCdna_prioritiseXrefs() throws IOException { - List protseqs = new ArrayList(); + List protseqs = new ArrayList<>(); protseqs.add(new Sequence("UNIPROT|V12345", "EIQ")); protseqs.add(new Sequence("UNIPROT|V12346", "EIQ")); AlignmentI protein = new Alignment( protseqs.toArray(new SequenceI[protseqs.size()])); protein.setDataset(null); - List dnaseqs = new ArrayList(); + List dnaseqs = new ArrayList<>(); dnaseqs.add(new Sequence("EMBL|A11111", "GAAATCCAG")); // = EIQ dnaseqs.add(new Sequence("EMBL|A22222", "GAAATTCAG")); // = EIQ AlignmentI cdna = new Alignment(dnaseqs.toArray(new SequenceI[dnaseqs @@ -847,8 +849,8 @@ public class AlignmentUtilsTests al.addAnnotation(ann4); // Temp for seq1 al.addAnnotation(ann5); // Temp for seq2 al.addAnnotation(ann6); // Temp for no sequence - List types = new ArrayList(); - List scope = new ArrayList(); + List types = new ArrayList<>(); + List scope = new ArrayList<>(); /* * Set all sequence related Structure to hidden (ann1, ann2) @@ -1179,12 +1181,12 @@ public class AlignmentUtilsTests /* * check cds2 acquired a variant feature in position 5 */ - SequenceFeature[] sfs = cds2Dss.getSequenceFeatures(); + List sfs = cds2Dss.getSequenceFeatures(); assertNotNull(sfs); - assertEquals(1, sfs.length); - assertEquals("variant", sfs[0].type); - assertEquals(5, sfs[0].begin); - assertEquals(5, sfs[0].end); + assertEquals(1, sfs.size()); + assertEquals("variant", sfs.get(0).type); + assertEquals(5, sfs.get(0).begin); + assertEquals(5, sfs.get(0).end); } /** @@ -1489,39 +1491,39 @@ public class AlignmentUtilsTests * that partially overlap 5' or 3' (start or end) of target sequence */ AlignmentUtils.transferFeatures(dna, cds, map, null); - SequenceFeature[] sfs = cds.getSequenceFeatures(); - assertEquals(6, sfs.length); + List sfs = cds.getSequenceFeatures(); + assertEquals(6, sfs.size()); - SequenceFeature sf = sfs[0]; + SequenceFeature sf = sfs.get(0); assertEquals("type2", sf.getType()); assertEquals("desc2", sf.getDescription()); assertEquals(2f, sf.getScore()); assertEquals(1, sf.getBegin()); assertEquals(1, sf.getEnd()); - sf = sfs[1]; + sf = sfs.get(1); assertEquals("type3", sf.getType()); assertEquals("desc3", sf.getDescription()); assertEquals(3f, sf.getScore()); assertEquals(1, sf.getBegin()); assertEquals(3, sf.getEnd()); - sf = sfs[2]; + sf = sfs.get(2); assertEquals("type4", sf.getType()); assertEquals(2, sf.getBegin()); assertEquals(5, sf.getEnd()); - sf = sfs[3]; + sf = sfs.get(3); assertEquals("type5", sf.getType()); assertEquals(1, sf.getBegin()); assertEquals(6, sf.getEnd()); - sf = sfs[4]; + sf = sfs.get(4); assertEquals("type8", sf.getType()); assertEquals(6, sf.getBegin()); assertEquals(6, sf.getEnd()); - sf = sfs[5]; + sf = sfs.get(5); assertEquals("type9", sf.getType()); assertEquals(6, sf.getBegin()); assertEquals(6, sf.getEnd()); @@ -1551,10 +1553,10 @@ public class AlignmentUtilsTests // desc4 and desc8 are the 'omit these' varargs AlignmentUtils.transferFeatures(dna, cds, map, null, "type4", "type8"); - SequenceFeature[] sfs = cds.getSequenceFeatures(); - assertEquals(1, sfs.length); + List sfs = cds.getSequenceFeatures(); + assertEquals(1, sfs.size()); - SequenceFeature sf = sfs[0]; + SequenceFeature sf = sfs.get(0); assertEquals("type5", sf.getType()); assertEquals(1, sf.getBegin()); assertEquals(6, sf.getEnd()); @@ -1584,10 +1586,10 @@ public class AlignmentUtilsTests // "type5" is the 'select this type' argument AlignmentUtils.transferFeatures(dna, cds, map, "type5"); - SequenceFeature[] sfs = cds.getSequenceFeatures(); - assertEquals(1, sfs.length); + List sfs = cds.getSequenceFeatures(); + assertEquals(1, sfs.size()); - SequenceFeature sf = sfs[0]; + SequenceFeature sf = sfs.get(0); assertEquals("type5", sf.getType()); assertEquals(1, sf.getBegin()); assertEquals(6, sf.getEnd()); @@ -1746,7 +1748,7 @@ public class AlignmentUtilsTests map = new MapList(new int[] { 9, 11 }, new int[] { 2, 2 }, 3, 1); acf.addMap(dna3.getDatasetSequence(), prot3.getDatasetSequence(), map); - ArrayList acfs = new ArrayList(); + ArrayList acfs = new ArrayList<>(); acfs.add(acf); protein.setCodonFrames(acfs); @@ -2029,9 +2031,9 @@ public class AlignmentUtilsTests sf6.setValue("ID", "var6"); sf6.setValue("clinical_significance", "Good"); - List codon1Variants = new ArrayList(); - List codon2Variants = new ArrayList(); - List codon3Variants = new ArrayList(); + List codon1Variants = new ArrayList<>(); + List codon2Variants = new ArrayList<>(); + List codon3Variants = new ArrayList<>(); List codonVariants[] = new ArrayList[3]; codonVariants[0] = codon1Variants; codonVariants[1] = codon2Variants; @@ -2078,24 +2080,29 @@ public class AlignmentUtilsTests * var6 P -> H COSMIC * var6 P -> R COSMIC */ - SequenceFeature[] sfs = peptide.getSequenceFeatures(); - assertEquals(5, sfs.length); + List sfs = peptide.getSequenceFeatures(); + SequenceFeatures.sortFeatures(sfs, true); + assertEquals(5, sfs.size()); - SequenceFeature sf = sfs[0]; + /* + * features are sorted by start position ascending, but in no + * particular order where start positions match; asserts here + * simply match the data returned (the order is not important) + */ + SequenceFeature sf = sfs.get(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("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()); - // link to variation is urlencoded assertEquals( - "p.Lys1Glu var1.125A>G|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var1.125A%3EG", + "p.Lys1Asn var4|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var4", sf.links.get(0)); assertEquals(ensembl, sf.getFeatureGroup()); - sf = sfs[1]; + sf = sfs.get(1); assertEquals(1, sf.getBegin()); assertEquals(1, sf.getEnd()); assertEquals("p.Lys1Gln", sf.getDescription()); @@ -2108,43 +2115,44 @@ public class AlignmentUtilsTests sf.links.get(0)); assertEquals(dbSnp, sf.getFeatureGroup()); - sf = sfs[2]; + sf = sfs.get(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("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.Lys1Asn var4|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var4", + "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()); - // var5 generates two distinct protein variant features - sf = sfs[3]; + sf = sfs.get(3); assertEquals(3, sf.getBegin()); assertEquals(3, sf.getEnd()); - assertEquals("p.Pro3His", sf.getDescription()); + 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.Pro3His var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6", + "p.Pro3Arg var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6", sf.links.get(0)); assertEquals(cosmic, sf.getFeatureGroup()); - sf = sfs[4]; + // var5 generates two distinct protein variant features + sf = sfs.get(4); assertEquals(3, sf.getBegin()); assertEquals(3, sf.getEnd()); - assertEquals("p.Pro3Arg", sf.getDescription()); + 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.Pro3Arg var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6", + "p.Pro3His var6|http://www.ensembl.org/Homo_sapiens/Variation/Summary?v=var6", sf.links.get(0)); assertEquals(cosmic, sf.getFeatureGroup()); } @@ -2265,7 +2273,7 @@ public class AlignmentUtilsTests seq1.createDatasetSequence(); Mapping mapping = new Mapping(seq1, new MapList( new int[] { 3, 6, 9, 10 }, new int[] { 1, 6 }, 1, 1)); - Map> map = new TreeMap>(); + Map> map = new TreeMap<>(); AlignmentUtils.addMappedPositions(seq1, from, mapping, map); /* @@ -2297,7 +2305,7 @@ public class AlignmentUtilsTests seq1.createDatasetSequence(); Mapping mapping = new Mapping(seq1, new MapList( new int[] { 3, 6, 9, 10 }, new int[] { 1, 6 }, 1, 1)); - Map> map = new TreeMap>(); + Map> map = new TreeMap<>(); AlignmentUtils.addMappedPositions(seq1, from, mapping, map); /* @@ -2526,4 +2534,243 @@ public class AlignmentUtilsTests assertEquals(s_as3, uas3.getSequenceAsString()); } + /** + * Tests for the method that maps nucleotide to protein based on CDS features + */ + @Test(groups = "Functional") + public void testMapCdsToProtein() + { + SequenceI peptide = new Sequence("pep", "KLQ"); + + /* + * Case 1: CDS 3 times length of peptide + * NB method only checks lengths match, not translation + */ + SequenceI dna = new Sequence("dna", "AACGacgtCTCCT"); + dna.createDatasetSequence(); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 1, 4, null)); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 9, 13, null)); + MapList ml = AlignmentUtils.mapCdsToProtein(dna, peptide); + assertEquals(3, ml.getFromRatio()); + assertEquals(1, ml.getToRatio()); + assertEquals("[[1, 3]]", + Arrays.deepToString(ml.getToRanges().toArray())); + assertEquals("[[1, 4], [9, 13]]", + Arrays.deepToString(ml.getFromRanges().toArray())); + + /* + * Case 2: CDS 3 times length of peptide + stop codon + * (note code does not currently check trailing codon is a stop codon) + */ + dna = new Sequence("dna", "AACGacgtCTCCTCCC"); + dna.createDatasetSequence(); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 1, 4, null)); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 9, 16, null)); + ml = AlignmentUtils.mapCdsToProtein(dna, peptide); + assertEquals(3, ml.getFromRatio()); + assertEquals(1, ml.getToRatio()); + assertEquals("[[1, 3]]", + Arrays.deepToString(ml.getToRanges().toArray())); + assertEquals("[[1, 4], [9, 13]]", + Arrays.deepToString(ml.getFromRanges().toArray())); + + /* + * Case 3: CDS longer than 3 * peptide + stop codon - no mapping is made + */ + dna = new Sequence("dna", "AACGacgtCTCCTTGATCA"); + dna.createDatasetSequence(); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 1, 4, null)); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 9, 19, null)); + ml = AlignmentUtils.mapCdsToProtein(dna, peptide); + assertNull(ml); + + /* + * Case 4: CDS shorter than 3 * peptide - no mapping is made + */ + dna = new Sequence("dna", "AACGacgtCTCC"); + dna.createDatasetSequence(); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 1, 4, null)); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 9, 12, null)); + ml = AlignmentUtils.mapCdsToProtein(dna, peptide); + assertNull(ml); + + /* + * Case 5: CDS 3 times length of peptide + part codon - mapping is truncated + */ + dna = new Sequence("dna", "AACGacgtCTCCTTG"); + dna.createDatasetSequence(); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 1, 4, null)); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 9, 15, null)); + ml = AlignmentUtils.mapCdsToProtein(dna, peptide); + assertEquals(3, ml.getFromRatio()); + assertEquals(1, ml.getToRatio()); + assertEquals("[[1, 3]]", + Arrays.deepToString(ml.getToRanges().toArray())); + assertEquals("[[1, 4], [9, 13]]", + Arrays.deepToString(ml.getFromRanges().toArray())); + + /* + * Case 6: incomplete start codon corresponding to X in peptide + */ + dna = new Sequence("dna", "ACGacgtCTCCTTGG"); + dna.createDatasetSequence(); + SequenceFeature sf = new SequenceFeature("CDS", "", 1, 3, null); + sf.setPhase("2"); // skip 2 positions (AC) to start of next codon (GCT) + dna.addSequenceFeature(sf); + dna.addSequenceFeature(new SequenceFeature("CDS", "", 8, 15, null)); + peptide = new Sequence("pep", "XLQ"); + ml = AlignmentUtils.mapCdsToProtein(dna, peptide); + assertEquals("[[2, 3]]", + Arrays.deepToString(ml.getToRanges().toArray())); + assertEquals("[[3, 3], [8, 12]]", + Arrays.deepToString(ml.getFromRanges().toArray())); + } + + /** + * Tests for the method that locates the CDS sequence that has a mapping to + * the given protein. That is, given a transcript-to-peptide mapping, find the + * cds-to-peptide mapping that relates to both, and return the CDS sequence. + */ + @Test + public void testFindCdsForProtein() + { + List mappings = new ArrayList<>(); + AlignedCodonFrame acf1 = new AlignedCodonFrame(); + mappings.add(acf1); + + SequenceI dna1 = new Sequence("dna1", "cgatATcgGCTATCTATGacg"); + dna1.createDatasetSequence(); + + // NB we currently exclude STOP codon from CDS sequences + // the test would need to change if this changes in future + SequenceI cds1 = new Sequence("cds1", "ATGCTATCT"); + cds1.createDatasetSequence(); + + SequenceI pep1 = new Sequence("pep1", "MLS"); + pep1.createDatasetSequence(); + List seqMappings = new ArrayList<>(); + MapList mapList = new MapList( + new int[] + { 5, 6, 9, 15 }, new int[] { 1, 3 }, 3, 1); + Mapping dnaToPeptide = new Mapping(pep1.getDatasetSequence(), mapList); + + // add dna to peptide mapping + seqMappings.add(acf1); + acf1.addMap(dna1.getDatasetSequence(), pep1.getDatasetSequence(), + mapList); + + /* + * first case - no dna-to-CDS mapping exists - search fails + */ + SequenceI seq = AlignmentUtils.findCdsForProtein(mappings, dna1, + seqMappings, dnaToPeptide); + assertNull(seq); + + /* + * second case - CDS-to-peptide mapping exists but no dna-to-CDS + * - search fails + */ + // todo this test fails if the mapping is added to acf1, not acf2 + // need to tidy up use of lists of mappings in AlignedCodonFrame + AlignedCodonFrame acf2 = new AlignedCodonFrame(); + mappings.add(acf2); + MapList cdsToPeptideMapping = new MapList(new int[] + { 1, 9 }, new int[] { 1, 3 }, 3, 1); + acf2.addMap(cds1.getDatasetSequence(), pep1.getDatasetSequence(), + cdsToPeptideMapping); + assertNull(AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings, + dnaToPeptide)); + + /* + * third case - add dna-to-CDS mapping - CDS is now found! + */ + MapList dnaToCdsMapping = new MapList(new int[] { 5, 6, 9, 15 }, + new int[] + { 1, 9 }, 1, 1); + acf1.addMap(dna1.getDatasetSequence(), cds1.getDatasetSequence(), + dnaToCdsMapping); + seq = AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings, + dnaToPeptide); + assertSame(seq, cds1.getDatasetSequence()); + } + + /** + * Tests for the method that locates the CDS sequence that has a mapping to + * the given protein. That is, given a transcript-to-peptide mapping, find the + * cds-to-peptide mapping that relates to both, and return the CDS sequence. + * This test is for the case where transcript and CDS are the same length. + */ + @Test + public void testFindCdsForProtein_noUTR() + { + List mappings = new ArrayList<>(); + AlignedCodonFrame acf1 = new AlignedCodonFrame(); + mappings.add(acf1); + + SequenceI dna1 = new Sequence("dna1", "ATGCTATCTTAA"); + dna1.createDatasetSequence(); + + // NB we currently exclude STOP codon from CDS sequences + // the test would need to change if this changes in future + SequenceI cds1 = new Sequence("cds1", "ATGCTATCT"); + cds1.createDatasetSequence(); + + SequenceI pep1 = new Sequence("pep1", "MLS"); + pep1.createDatasetSequence(); + List seqMappings = new ArrayList<>(); + MapList mapList = new MapList( + new int[] + { 1, 9 }, new int[] { 1, 3 }, 3, 1); + Mapping dnaToPeptide = new Mapping(pep1.getDatasetSequence(), mapList); + + // add dna to peptide mapping + seqMappings.add(acf1); + acf1.addMap(dna1.getDatasetSequence(), pep1.getDatasetSequence(), + mapList); + + /* + * first case - transcript lacks CDS features - it appears to be + * the CDS sequence and is returned + */ + SequenceI seq = AlignmentUtils.findCdsForProtein(mappings, dna1, + seqMappings, dnaToPeptide); + assertSame(seq, dna1.getDatasetSequence()); + + /* + * second case - transcript has CDS feature - this means it is + * not returned as a match for CDS (CDS sequences don't have CDS features) + */ + dna1.addSequenceFeature( + new SequenceFeature(SequenceOntologyI.CDS, "cds", 1, 12, null)); + seq = AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings, + dnaToPeptide); + assertNull(seq); + + /* + * third case - CDS-to-peptide mapping exists but no dna-to-CDS + * - search fails + */ + // todo this test fails if the mapping is added to acf1, not acf2 + // need to tidy up use of lists of mappings in AlignedCodonFrame + AlignedCodonFrame acf2 = new AlignedCodonFrame(); + mappings.add(acf2); + MapList cdsToPeptideMapping = new MapList(new int[] + { 1, 9 }, new int[] { 1, 3 }, 3, 1); + acf2.addMap(cds1.getDatasetSequence(), pep1.getDatasetSequence(), + cdsToPeptideMapping); + assertNull(AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings, + dnaToPeptide)); + + /* + * fourth case - add dna-to-CDS mapping - CDS is now found! + */ + MapList dnaToCdsMapping = new MapList(new int[] { 1, 9 }, + new int[] + { 1, 9 }, 1, 1); + acf1.addMap(dna1.getDatasetSequence(), cds1.getDatasetSequence(), + dnaToCdsMapping); + seq = AlignmentUtils.findCdsForProtein(mappings, dna1, seqMappings, + dnaToPeptide); + assertSame(seq, cds1.getDatasetSequence()); + } }